Fakultät für Informatik
Refine
Year of publication
Document Type
- Conference Proceeding (90)
- Book (21)
- Article (peer reviewed) (11)
- Other (10)
- Contribution to a Periodical (9)
- Part of a Book (4)
- Doctoral Thesis (2)
- Working Paper (1)
Is part of the Bibliography
- no (148)
Keywords
- Speech Recognition (18)
- CFT (6)
- Software Development (6)
- Database (5)
- Microsoft (5)
- Sql server (5)
- Augmented Reality (AR) (4)
- Fault trees (4)
- Mobile Robot (4)
- Robotic Research (4)
Institute
Das Buch richtet sich an Studierende der Informatik oder verwandter Studiengänge und enthält Übungsaufgaben mit Lösungen aus Gebieten, die typischerweise in den ersten Semestern als Grundlagen behandelt werden. Ausgenommen ist der Bereich des Programmierens. Das Buch ergänzt den Grundkurs Informatik mit Übungen zu ausgewählten Kapiteln, ist aber auch in Kombination mit anderen Lehrbüchern verwendbar.
Das Buch bietet eine umfassende und praxisorientierte Einführung in die wesentlichen Grundlagen und Konzepte der Informatik. Es umfasst den Stoff, der typischerweise in den ersten Semestern eines Informatikstudiums vermittelt wird, vertieft Zusammenhänge, die darüber hinausgehen und macht sie verständlich. Die Themenauswahl orientiert sich an der langfristigen Relevanz für die praktische Anwendung. Praxisnah und aktuell werden die Inhalte für Studierende der Informatik und verwandter Studiengänge sowie für im Beruf stehende Praktiker vermittelt.
Fault and anomaly detection in district heating substations: A survey on methodology and data sets
(2023)
District heating systems are essential building blocks for affordable, low-carbon heat supply. Early detection and elimination of faults is crucial for the efficiency of these systems and necessary to achieve the low temperatures targeted for 4th generation district heating systems. Especially methods for fault and anomaly detection in district heating substations are currently of high interest, as faults in substations can be repaired quickly and inexpensively, and smart meter data are becoming widely available. In this paper, we review recent scientific publications presenting data-driven approaches for fault and anomaly detection in district heating substations with a focus on methods and data sets. Our review indicates that researchers use a wide variety of methods, mostly focusing on unsupervised anomaly detection rather than fault detection. This is due to a lack of labeled data sets, preventing the use of supervised learning methods and quantitative analysis. Together with the lack of publicly available data sets, this impedes the accurate comparison of individual methods. To overcome this impediment, increase the comparability of different methods and foster competition, future research should focus on establishing publicly available data sets, and industry-relevant metrics as benchmarks.
Mobility management is a key feature of mobile edge computing. We present an edge cloud infrastructure testbed to explore various mobility scenarios. The design objection of this testbed has been a flexible open platform based on commodity hardware that can easily be scaled with more edge devices and compute resources to perform various edge cloud experiments. As first experiments on our testbed, we have investigated the feasibility of task migration among edge devices caused by edge device overload and unpredictable user movements. We describe the migration process and present some measurements to demonstrate the feasibility.
Parameter free Non-intrusive Load Monitoring (NILM) algorithms are a major step toward real-world NILM scenarios. The identification of appliances is the key element in NILM. The task consists of identification of the appliance category and its current state. In this paper, we present a param- eter free appliance identification algorithm for NILM using a 2D representation of time series known as unthresholded Recurrence Plots (RP) for appliance category identification. One cycle of voltage and current (V-I trajectory) are transformed into a RP and classified using a Spacial Pyramid Pooling Convolutional Neural Network architecture. The performance of our approach is evaluated on the three public datasets COOLL, PLAID and WHITEDv1.1 and compared to previous publications. We show that compared to other approaches using our architecture no initial parameters have to be manually tuned for each specific dataset.
Stuttering is a complex speech disorder identified by repetitions, prolongations of sounds, syllables or words and blockswhile speaking. Specific stuttering behaviour differs strongly,thus needing personalized therapy. Therapy sessions requirea high level of concentration by the therapist. We introduce STAN, a system to aid speech therapists in stuttering therapysessions. Such an automated feedback system can lower the cognitive load on the therapist and thereby enable a more consistent therapy as well as allowing analysis of stuttering over the span of multiple therapy sessions.
Real-world domestic electricity demand datasets are the key enabler for developing and evaluating machine learning algorithms that facilitate the analysis of demand attribution and usage behavior. Breaking down the electricity demand of domestic households is seen as the key technology for intelligent smart-grid management systems that seek an equilibrium of electricity supply and demand. For the purpose of comparable research, we publish DEDDIAG, a domestic electricity demand dataset of individual appliances in Germany. The dataset contains recordings of 15 homes over a period of up to 3.5 years, wherein total 50 appliances have been recorded at a frequency of 1 Hz. Recorded appliances are of significance for load-shifting purposes such as dishwashers, washing machines and refrigerators. One home also includes three-phase mains readings that can be used for disaggregation tasks. Additionally, DEDDIAG contains manual ground truth event annotations for 14 appliances, that provide precise start and stop timestamps. Such annotations have not been published for any long-term electricity dataset we are aware of.
Mobile-access edge clouds provide distributed com-pute capacities for low-latency applications. 5G technology willpave the way for such mobile deployment scenarios. In thispaper, we propose an edge cloud infrastructure that supportslow-latency video analysis connected with bandwidth reductionfor a moving group of persons. As example, we consider a mobilebody camera scenario that monitors the situation in a certain areaand transmits it to an operations center. Our discussion focuseson three aspects: mobility support, low-latency video processing,and bandwidth reduction. For this, we propose a mobile edgecloud infrastructure with a central cloud. In order to optimizevideo processing we optimize the edge cloud device assignmentof the cameras depending on their movement by reassigning itto another cloud device. This requires live migration of ongoingvideo analysis between edge devices. Finally we discuss the useof a mobile central cloud.
The classical results of the binomial and negative binomial probability distribution are generalized by means of homogeneous Discrete Time Markov Chains to series of stochastically independent random trials. These have not only two possible outcomes but two groups of them -- different kinds of successes and failures with occurrence probabilities depending on the outcome of the previous trial. This generalization allows a uniform view of occupation time, first passage time and recurrence time. Our results are consequently derived and presented in matrix form, the probabilities as well as the moments. They can be applied to all Discrete Time Markov Chains, especially in computer capacity planning, performability and economics.
Zahlensysteme und binäre Arithmetik – Nachricht und Information – Codierung und Datenkompression – Verschlüsselung – Schaltalgebra, Schaltnetze und Elemente der Computerhardware – Rechnerarchitekturen – Rechnernetze – Betriebssysteme – prozedurale und objektorientierte Programmierung (C und Java) – Automatentheorie und formale Sprachen – Berechenbarkeit und Komplexität – Suchen und Sortieren – Bäume und Graphen – Software-Engineering – Datenbanken – Anwendungsprogrammierung im Internet (HTML, CSS, JavaScript und PHP) – Deep Learning mit neuronalen Netzen
Generating a more detailed understanding of domestic electricity demand is a major topic for energy suppliers and householders in times of climate change.
Over the years there have been many studies on consumption feedback systems to inform householders, disaggregation algorithms for Non-Intrusive-Load-Monitoring (NILM), Real-Time-Pricing (RTP) to promote supply aware behavior through monetary incentives and appliance usage prediction algorithms. While these studies are vital steps towards energy awareness, one of the most fundamental challenges has not yet been tackled: Automated detection of start and stop of usage cycles of household appliances. We argue that most research efforts in this area will benefit from a reliable segmentation method to provide accurate usage information.
We propose a SVM-based segmentation method for home appliances such as dishwashers and washing machines. The method is evaluated using manually annotated electricity measurements of five different appliances recorded over two years in multiple households.
Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrence Plots. In order to utilize the research done in the area of image classification, where Deep Neural Networks have achieved very good results, we use a Residual Neural Networks architecture known as ResNet. As preprocessing of time series is a major part of every time series classification pipeline, the method proposed simplifies this step and requires only few parameters. For the first time we propose a method for multi time series classification: Training a single network to classify all datasets in the archive with one network. We are among the first to evaluate the method on the latest 2018 release of the UCR archive, a well established time series classification benchmarking dataset.
An apparatus and method for analyzing availability of a system including subsystems each having at least one failure mode with a corresponding failure effect on the system are provided. The apparatus includes a degraded mode tree generation unit configured to automatically generate a degraded mode tree. The degraded mode tree includes at least one degraded mode element representing a degraded system state of the system that deviates from a normal operation state of the system based on a predetermined generic system meta model stored in a database including Failure Mode and Effects Analysis elements representing subsystems, failure modes, failure effects, and diagnostic measures. The apparatus also includes a processor configured to evaluate the generated degraded mode tree for calculation of the availability of the system.
A method for automated qualification of a safety critical system including a plurality of components is provided. A functional safety behavior of each component is represented by an associated component fault tree element. The method includes automatically performing a failure port mapping of output failure modes to input failure modes of component fault tree elements based on a predetermined generic fault type data model stored in a database.
A method for automated recertification of a safety critical system with at least one altered functionality is provided. The method includes providing a failure propagation model of the safety critical system. The method also includes updating the failure propagation model of the safety critical system according to the at least one altered functionality using inner port dependency traces between inports and outports of a failure propagation model element representing the at least one altered functionality. The method includes calculating top events of the updated failure propagation model, and comparing the calculated top events with predetermined system requirements to recertify the safety critical system.
A method for integrated model-based safety analysis includes integrating a safety analysis model into a system development model of a safety-critical system. The system development model includes model components. The safety analysis model models a failure logic separately for each of the model components. The method includes representing dependencies among the model components with a design structure matrix. The design structure matrix represents each of the model components with a row and a column and shows dependencies between model components with corresponding entries. The method also includes sequencing the design structure matrix, and identifying at least one dependency loop and loop components in the sequenced design structure matrix. The loop components are part of the at least one dependency loop.
Skriptum Geschäftsprozesse
(2012)
The present paper examines which benefit an automated documentation of the IT infrastructure can have for the configuration management process of ITIL, and whether it is possible to fully automate documentation. The result is the conclusion that the documentation process can be fully automated. It follows from this analysis that the automated documentation can “only” supply information for the ITIL configuration management, respectively for the CMDB.
The strong technical orientation of the previous multimedia evolution shows a lack of theoretical foundation. Both during the evolution and application of multimedia technology, well-founded theoretical concepts are missing. The intention of this paper is to show categories of different information representations and interaction types and their strengths in representing contents. A classification of multimedia information and interaction types is given also as an
overview of the problem fields of multimedia, especially in the field of learning theory. This classification is used to give some guidelines for using and combining multimedia contents in multimedia systems.
This paper is an interdisciplinary synopsis about multimedia learning systems and mass information systems, and presents an action model for construction of these systems and the embedding of this model in an existing concept of system planning.
First step in the paper is the containment and definition of the term ‘multimedia’ on the basis of general criterions of the human-machine-human communication. Result is a taxonomy to classify scientific research areas in this field.
The second part follows an examination of different concepts of learning theories by means of a five dimensional raster. Output of this examination are two models fitting for computer based learning in general.
The third part discusses information presentation and interaction possibilities at the human - machine - interface. Therefore a consistent raster is acquired, where psychological perception parameters and technical parameters of information presentations and interaction possibilities are examined. This results in the so-called storyboarding, which is the description of a process adapted from theater, film and TV for developing a multimedia script.
The combination of learntheoretical concepts with the process of storyboarding of multimedia applications and the embedding in a system planning action model is described in the fourth part. The result of this last part shows a phase concept for system planning of multimedia learning systems and mass information systems.
Die Arbeit ist eine Anleitung zur Planung und Erstellung von IT-Systemen, die auch Filme, Sprache, Musik, Animationen und virtuelle Welten – also die gesamte Palette multimedialer Darstellungen – beinhalten. Solche Programme werden hauptsächlich in drei Bereichen eingesetzt: Im Spielebereich (z.B. Autorennen, Erlebnisspiele), im Aus- und Weiterbildungsbereich (z.B. multimediale Lernprogramme) und im Bereich von elektronisch unterstützten Informationssystemen (z.B. Präsentationen, Produktvorstellungen und Produktkataloge u.a. auch auf CD-ROM oder Kiosksysteme wie etwa Informationsterminals auf Messen u.ä.).
Die Arbeit beschäftigt sich vorwiegend mit Lernsystemen. Das Schwierige an der Verwendung multimedialer Darstellungen wie Film, Musik usw. ist, dass in die "trockene" Programmierung Aspekte wie Regie, Dramaturgie, psychologische und didaktische Aspekte einfließen. Daher ist die interdisziplinäre Sichtweise bei der Entwicklung multimedialer Systeme besonders wichtig. Die Arbeit betrachtet die Problematik also nicht techniklastig (obwohl natürlich die technischen Aspekte nicht außer Acht gelassen werden), sondern nutzerorientiert.
Die Arbeit ist für drei Bereiche bedeutend: erstens für den Bereich der Wissenschaft(stheorie), zweitens für den Aus- und Weiterbildungssektor und drittens für die Entwickler von multimedialen Systemen.
Aus der Sicht der Wissenschaft liefert die Arbeit eine klare Einteilung für multimediale Arbeitsbereiche. Mögliche künftige Forschungsbereiche werden aufgezeigt und begriffliche Unklarheiten offengelegt und ausgeräumt. Weiters wird die interdisziplinäre Bandbreite der Thematik geschildert und damit eine umfassende Darstellung der Problematik vorgenommen. In diesem Sinn kann die Arbeit fast als Lexikon gesehen werden.
Aus der Sicht des Aus- und Weiterbildungssektors dient diese Arbeit als Zusammenfassung bestehender Lernkonzepte, in der ein eigenständiger, einfacher Raster in Hinblick auf multimediale Systeme entwickelt wird. Dabei werden Erfahrungen aus mehreren multimedialen Programmen eingearbeitet, die vom Autor am Institut für Wirtschaftsinformatik (mit)entwickelt und evaluiert worden sind. Eine Erkenntnis ist, dass der Wissensstand des Benutzers auf dem Lerngebiet eine entscheidende Rolle spielt. Lernsysteme für Anfänger müssen anders gestaltet werden als für Fortgeschrittene. Das wie wird in der Arbeit beschrieben.
Aus der Sicht der Entwickler von multimedialen Systemen ist die Arbeit von Bedeutung, da sie die Unterschiede bei der Entwicklung im Vergleich zu traditionellen Programmen herausarbeitet und dafür eine Vorgangsweise anbietet. Die Vorgangsweise ist eine Art multimediales Drehbuch, das als Storyboard bezeichnet wird. In der Arbeit wird beschrieben wie die einzelnen dramaturgischen, didaktischen und psychologischen Aspekte in das Storyboard eingearbeitet werden und letztlich das System in einem entsprechenden Umfeld eingesetzt werden kann.
The use of multimedia can significantly improve the quality of case studies, especially with regard to their presentation of reality. The development of multimedia case studies poses a challenge of both a creative and a technical nature. This paper describes the various stages of the development of the case study itself as well as an action model which supports the application of didactical aims in a multimedia case study. This paper then describes experiences with a multimedia case study used at the Department of Information Systems for training students in data processing for business purposes. The report includes a description of how the case study was integrated as a didactic element in a university course, with special emphasis being given to theoretical aspects of presentation and learning. Additionally, a description of the case study and its development rounds off the article. The experiences were gained within the framework of an explorational, empirical study whose results are presented at the end of this paper and form the basis of suggestions for how the case study could be developed further.
This contribution describes experiences with a multimedia case study used at the Department of Information Systems for training students in data processing for business purposes. The report includes a description of how the case study was integrated as a didactic element in a university course, with special emphasis being given to theoretical aspects of presentation and learning. Additionally, a description of the case study and its development rounds off the article. The experiences were gained within the framework of an explorational, empirical study whose results are presented at the end of this paper and form the basis of suggestions for how the case study could be developed further.
The use of multimedia can significantly improve the quality of case studies, especially with regard to their presentation of reality. The development of multimedia case studies poses a challenge of both a creative and a technical nature. This paper describes the various stages of the development of the case study itself as well as an action model which supports the application of didactical aims in a multimedia case study.
Ergebnis der Arbeit ist eine interdisziplinäre Zusammenschau zum Erkenntnisobjekt "multimediale Lern- und Masseninformationssysteme" und darauf aufbauend die Vorstellung eines Vorgehensmodell zur Konstruktion dieser Systeme und die Einbettung dieses Modells in ein bestehendes Systemplanungskonzept.
Dazu wird in der Arbeit zunächst der Begriff Multimedia anhand von allgemeinen Kriterien der Mensch-Maschine-Mensch - Kommunikation eingegrenzt und definiert. Ergebnis ist eine Systematik zur Einordnung von wissenschaftlichen Forschungsgebieten in diesem Bereich. Im zweiten Schritt erfolgt eine Untersuchung lerntheoretischer Konzepte anhand eines fünfdimensionalen Rasters. Ergebnis sind zwei Modelle, die sich zur elektronisch unterstützten Wissensvermittlung im allgemeinen eignen. Im dritten Schritt erfolgt eine Auseinandersetzung mit Informationsdarstellungen und Interaktionsmöglichkeiten an der Mensch-Maschine-Schnittstelle. Dazu wird ein konsistentes Raster erarbeitet, anhand dessen wahrnehmungspsychologische und technische Parameter von Informationsdarstellungen und Interaktionsmöglichkeiten untersucht werden. Ergebnis ist die Beschreibung von einem aus der Theater-, Film- und Fernsehbranche adaptierten Prozeß zur Erstellung eines multimedialen Drehbuchs, dem Storyboard. Der vierte Schritt beschreibt die Kombination der lerntheoretischen Konzepte mit dem Prozeß des Storyboardings multimedialer Anwendungen und die Einbettung in ein systemplanerisches Vorgehen dazu. Ergebnis ist ein Phasenkonzept zur Systemplanung multimedialer Lern- und Masseninformationssysteme.
The growing size and complexity of software in embedded systems poses new challenges to the safety assessment of embedded control systems. In industrial practice, the control software is mostly treated as a black box during the system's safety analysis. The appropriate representation of the failure propagation of the software is a pressing need in order to increase the accuracy of safety analyses. However, it also increase the effort for creating and maintaining the safety analysis models (such as fault trees) significantly. In this work, we present a method to automatically generate Component Fault Trees from Continuous Function Charts. This method aims at generating the failure propagation model of the detailed software specification. Hence, control software can be included into safety analyses without additional manual effort required to construct the safety analysis models of the software. Moreover, safety analyses created during early system specification phases can be verified by comparing it with the automatically generated one in the detailed specification phased.
INSiDER: Incorporation of system and safety analysis models using a dedicated reference model
(2016)
In order to enable model-based, iterative design of safety-relevant systems, an efficient incorporation of safety and system engineering is a pressing need. Our approach interconnects system design and safety analysis models efficiently using a dedicated reference model. Since all information are available in a structured way, traceability between the model elements and consistency checks enable automated synchronization to guarantee that information within both kind of models are consistent during the development life-cycle.
Safety assurance is a major challenge in the design of today's complex embedded systems and future Cyber-physical systems. Especially changes in a system's architectural design invalidate former safety analyses and require an adaptation of related safety analysis models in order to restore consistency. In this work, we present an approach for automatically generating mappings between failure ports in compositional safety analysis models. This way, automatic and system-wide safety analyses are enabled that can be easily repeated after making modifications to the system's architecture. We demonstrate the feasibility of our approach using a case study from the automotive domain.
Automating compositional safety analysis using a failure type taxonomy for component fault trees
(2016)
Safety assurance is a major challenge in the design of today’s complex embedded systems and future Cyber-physical systems. Changes in a system’s architectural design invalidate former safety analyses and require a manual adaptation of related safety analysis models in order to restore consistency. In this work, we present an approach for automating the compositional assembly of Component Fault Trees by automatically generating mappings between their input and output failure modes. Therefore, we propose a taxonomy of failure types for annotating model elements and deriving a model of the failure propagation. This way, automatic and system-wide safety analyses can be executed and easily repeated after making modifications to the system’s architecture. We demonstrate the feasibility of our approach using an example ethylene vaporization unit from an industrial domain.
Safety assurance is a major challenge in the design of modern embedded systems that has become increasingly difficult in recent years. Growing system sizes and the rise of Cyber-Physical systems confront safety engineers with large sets of configurations to be analyzed. Current approaches are usually carried out at design time and do not address the need for automated assessments in the field. With Component Fault Trees (CFTs) there exists a component-based methodology that enables an efficient modular composition of safety artifacts. The combined model is a system-level CFT that can be analyzed by means of popular Fault Tree Analysis techniques that are widely accepted in the industry. However, when composing models, their interfacing elements must be connected manually which impedes the automation of the procedure. In this work, we introduce the notion of flow types that represent a particular kind of component interaction and define a taxonomy of related failure behavior. By annotating CFTs with types, a machine-readable vocabulary is provided that allows for an automated interconnection of their interfaces. This way, the automatic composition of models according to system architecture is enabled, allowing for automated safety assessments on system-level. We demonstrate the feasibility of our approach using an example ethylene vaporization unit.
In safety analysis for safety-critical embedded systems, methods such as FMEA and fault trees (FT) are strongly established in practice. However, the current shift towards model-based development has resulted in various new safety analysis methods, such as Component Integrated Fault Trees (CFT). Industry demands to know the benefits of these new methods. To compare CFT to FT, we conducted a controlled experiment in which 18 participants from industry and academia had to apply each method to safety modeling tasks from the avionics domain.
Although the analysis of the solutions showed that the use of CFT did not yield a significantly different number of correct or incorrect solutions, the participants subjectively rated the modeling capacities of CFT significantly higher in terms of model consistency, clarity, and maintainability. The results are promising for the potential of CFT as a model-based approach.
(Background) Empirical Software Engineering (SE) strives to provide empirical evidence about the pros and cons of SE approaches. This kind of knowledge becomes relevant when the issue is whether to change from a currently employed approach to a new one or not. An informed decision is required and is particularly important in the development of safety-critical systems. For example, for the safety analysis of safety-critical embedded systems, methods such as Failure Mode and Effect Analysis (FMEA) and Fault Tree Analysis (FTA) are used. With the advent of model-based systems and software development, the question arises whether safety engineering methods should also be adopted. New technologies such as Component Integrated Fault Trees (CFT) come into play. Industry demands to know the benefits of these new methods over established ones such as Fault Trees (FT). (Methods) For the purpose of comparing CFT and FT with regard to the capabilities of the safety analysis methods (such as quality of the results) and to the participants' rating of the consistency, clarity, and maintainability of the methods, we designed a comparative study as a controlled experiment using a within-subject design. The experiment was run with seven academic staff members working towards their PhD. The study was replicated with eleven domain experts from industry. (Results) Although the analysis of the tasks' solutions showed that the use of CFT did not yield a significantly different number of correct or incorrect solutions, the participants rated the modeling capacities of CFT higher in terms of model consistency, clarity, and maintainability. (Conclusion) From this first evidence, we conclude that CFT have the potential of being beneficial for companies looking for a safety analysis approachfor projects using model-based development.
Safety assurance is a major challenge in the design of complex embedded and Cyber-physical Systems. Especially, changes and adoptions during the design or run-time of an embedded system invalidate former safety analyses and require an adaptation of the system's safety analysis models. In this paper, we present a methodology to fill up empty safety analysis artifacts in component fault trees using so-called inner port dependency traces to describe failure propagation. Thus, enabling a imprecise but rapid safety analysis of an entire system at early development stages or during system run-time for the automated certification of Cyber-physical Systems. We evaluate our approach using case study from the automotive domain.
Identifying drawbacks or insufficiencies in terms of safety is important also in early development stages of safety critical systems. In industry, development artefacts such as components or units, are often reused from existing artefacts to save time and costs. When development artefacts are reused, their existing safety analysis models are an important input for an early safety assessment for the new system, since they already provide a valid model. Component fault trees support such reuse strategies by a compositional horizontal approach. But current development strategies do not only divide systems horizontally, e.g., By encapsulating different functionality into separate components and hierarchies of components, but also vertically, e.g. Into software and hardware architecture layers. Current safety analysis methodologies, such as component fault trees, do not support such vertical layers. Therefore, we present here a methodology that is able to divide safety analysis models into different layers of a systems architecture. We use so called Architecture Layer Failure Dependencies to enable component fault trees on different layers of an architecture. These dependencies are then used to generate safety evidence for the entire system and over all different architecture layers. A case study applies the approach to hardware and software layers.
The growing complexity of safety-critical embedded systems is leading to an increased complexity of safety analysis models. Often used fault tolerance mechanisms have complex failure behavior and produce overhead compared to systems without such mechanisms. The question arises whether the overhead for fault tolerance is acceptable for the increased safety of a system. Manually modeling the timing behavior is cost intensive and error prone. Current approaches of safety analysis and execution time analysis are not able to reflect the timing behavior of complex mechanisms according to failures. In this paper, we describe an approach that combines safety analysis models with execution times to extract different execution times for different failure conditions. This provides a detailed view on the safety behavior in combination with the produced overhead and allows to find and certify appropriate fault tolerance mechanisms.
Embedded real-time systems are growing in complexity, which goes far beyond simplistic closedloop functionality. Current approaches of worst-case execution time (WCET) analysis are used to verify deadlines of such systems, especially when they are safety critical. These approaches calculate or measure WCET as a single value that is expected as an upper bound for a system's execution time. Overestimations are taken into account to make this upper bound a safe bound, but modern processor architectures with caches, multi-threading, and instruction pipelines often expand those overestimations for safe upper bounds into unrealistic areas. Some approaches try to overcome this problem by calculating multiple upper bounds and argue that each single upper bound will hold for a certain probability (probabilistic worst-case execution time). Even though some of them tackle the problem of obtaining reliable probabilistic values for such upper bounds, more effort is required. Therefore, we present in this paper how probabilities of safety analysis models can be combined with elements of system development models to calculate a probabilistic worst-case execution time. This approach can be applied to systems that use mechanisms belonging to the area of fault tolerance, since such mechanisms are usually quantified in safety analyses to certify the system as being highly reliable or safe.
Embedded real-time systems are growing in complexity, which goes far beyond simplistic closed-loop functionality. Current approaches for worst-case execution time (WCET) analysis are used to verify the deadlines of such systems. These approaches calculate or measure the WCET as a single value that is expected as an upper bound for a system’s execution time. Overestimations are taken into account to make this upper bound a safe bound, but modern processor architectures expand those overestimations into unrealistic areas. Therefore, we present in this paper how of safety analysis model probabilities can be combined with elements of system development models to calculate a probabilistic WCET. This approach can be applied to systems that use mechanisms belonging to the area of fault tolerance, since such mechanisms are usually quantified using safety analyses to certify the system as being highly reliable or safe. A tool prototype implementing this approach is also presented which provides reliable safe upper bounds by performing a static WCET analysis and which overcomes the frequently encountered problem of dependence structures by using a fault injection approach.
The number of embedded systems in our daily lives that are distributed, hidden, and ubiquitous continues to increase. Many of them are safety-critical. To provide additional or better functionalities, they are becoming more and more complex, which makes it difficult to guarantee safety. It is undisputed that safety must be considered before the start of development, continue until decommissioning, and is particularly important during the design of the system and software architecture. An architecture must be able to avoid, detect, or mitigate all dangerous failures to a sufficient degree. For this purpose, the architectural design must be guided and verified by safety analyses. However, state-of-the-art component-oriented or model-based architectural design approaches use different levels of abstraction to handle complexity. So, safety analyses must also be applied on different levels of abstraction, and it must be checked and guaranteed that they are consistent with each other, which is not supported by standard safety analyses. In this paper, we present a consistency check for CFTs that automatically detects commonalities and inconsistencies between fault trees of different levels of abstraction. This facilitates the application of safety analyses in top-down architectural designs and reduces effort.
The open and cooperative nature of Cyber-Physical Systems (CPS) poses new challenges in assuring dependability. The DEIS project (Dependability Engineering Innovation for automotive CPS. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732242, see http://www.deis-project.eu) addresses these challenges by developing technologies that form a science of dependable system integration. In the core of these technologies lies the concept of a Digital Dependability Identity (DDI) of a component or system. DDIs are modular, composable, and executable in the field facilitating (a) efficient synthesis of component and system dependability information over the supply chain and (b) effective evaluation of this information in-the-field for safe and secure composition of highly distributed and autonomous CPS. The paper outlines the DDI concept and opportunities for application in four industrial use cases.
Efficient safety analyses of complex software intensive embedded systems are still a challenging task. This article illustrates how model-driven development principles can be used in safety engineering to reduce cost and effort. To this end, the article shows how well accepted safety engineering approaches can be shifted to the level of model-driven development by integrating safety models into functional development models. Namely, we illustrate how UML profiles, model transformations, and techniques for multi language development can be used to seamlessly integrate component fault trees into the UML.
This paper shows the experiences made with a multimedia based case study in academic education. The case study has been used within three courses of business process engineering. It was compared to a case study based solely on text. 13 assumptions have been evaluated. The main conclusion is that the multimedia based case study is much more practice oriented than a text based case study. Also the solutions of the students, which did the multimedia based case study, have been of higher quality. But on the other hand the expectations of the students to a multimedia based system are hard to meet. Based on these experiences some hints in further developing of multimedia based case studies are formulated.
Get up and running on Microsoft SQL Server 2016 in no time with help from this thoroughly revised, practical resource. The book offers thorough coverage of SQL management and development and features full details on the newest business intelligence, reporting, and security features.
Filled with new real-world examples and hands-on exercises, Microsoft SQL Server 2016: A Beginner's Guide, Sixth Edition, starts by explaining fundamental relational database system concepts.
From there, you will learn how to write Transact-SQL statements, execute simple and complex database queries, handle system administration and security, and use the powerful analysis and BI tools. XML, spatial data, and full-text search are also covered in this step-by-step tutorial.
· Revised from the ground up to cover the latest version of SQL Server
· Ideal both as a self-study guide and a classroom textbook
· Written by a prominent professor and best-selling author
Get Started on Microsoft SQL Server 2012 in No TimeLearn to use all of the powerful features available in SQL Server 2012 quickly and easily.
Microsoft SQL Server 2012: A Beginner's Guide explains the fundamentals of each topic alongside examples and tutorials that walk you through real-world database tasks.
Install SQL Server 2012, construct high-performance databases, use powerful Transact-SQL statements, create stored procedures and triggers, and execute simple and complex database queries.
Performance tuning, Database Engine security, Business Intelligence, and XML are also covered.
Set up, configure, and maintain SQL Server 20012 Build and manage database objects using Transact-SQL statements Create stored procedures and user-defined functionsOptimize database performance, availability, and reliabilityImplement solid security using authentication, encryption, and authorization
Automate tasks using SQL Server AgentCreate reliable data backups and perform flawless system restoresUse all-new SQL Server 2012 Business Intelligence, development, and administration toolsLearn in detail the SQL Server XML technology (SQLXML)
Get Started on Microsoft SQL Server 2008 in No TimeLearn to use all of the powerful features available in SQL Server 2008 quickly and easily.
Microsoft SQL Server 2008: A Beginner's Guide explains the fundamentals of each topic alongside examples and tutorials that walk you through real-world database tasks.
Install SQL Server 2008, construct high-performance databases, use powerful Transact-SQL statements, create stored procedures and triggers, and execute simple and complex database queries. Performance tuning, Database Engine security, Business Intelligence, and XML are also covered.
Set up, configure, and maintain SQL Server 2008
Build and manage database objects using Transact-SQL statements Create stored procedures and user-defined functionsOptimize database performance, availability, and reliability
Implement solid security using authentication, encryption, and authorization Automate tasks using SQL Server Agent
Create reliable data backups and perform flawless system restores
Use all-new SQL Server 2008 Business Intelligence, development, and administration toolsLearn in detail the SQL Server XML technology (SQLXML)
Deploy and manage SQL Server 2005 with easeLearn to use all the powerful features available in SQL Server 2005 from this straightforward, hands-on guide.
Set up SQL Server 2005, automate system administration tasks, execute simple and complex database queries, and use the robust analysis, business intelligence, and reporting tools. Troubleshooting, data partitioning, replication, and query optimization are also covered.
With SQL Server 2005: A Beginner's Guide, you'll be able to set up a secure, reliable, and productive data management platform in no time.
Essential Skills for Database Professionals
- Install and customize SQL Server 2005
- Create, alter, and remove database objects with Transact-SQL statements
- Use SQL Server as a native XML database system - Tune your database system for optimal performance
- Use the new SQL Server Management Studio tool for executing and analyzing ad hoc queries
- Retrieve data from more than one source using join operations and SELECT statements
- Secure your database using two different authentication modes--Windows and mixed
- Restore databases using transaction logs and backup and recovery methods
- Streamline system administration tasks using the SQL Server Agent service tool
- Analyze and manage information stored in a data warehouse with Microsoft Analysis Services
Create, query, and manage high-performance SQL Server 7 databases with the hot new release of this scalable database management system.
SQL Server 7: A Beginner's Guide explains enterprise database fundamentals and shows you how to take advantage of the new features of SQL Server 7, such as improved space management, new data transformation services, and data warehousing.
From installation to query optimization to security to data warehousing, this hands-on guide provides everything you need to know to get up and running smoothly on SQL Server 7.
We present an approach for indoor mapping and localization with a mobile robot using sparse range data, without the need for solving the SLAM problem.
The paper consists of two main parts. First, a split and merge based method for dividing a given metric map into distinct regions is presented, thus creating a topological map in a metric framework.
Spatial information extracted from this map is then used for self-localization. The robot computes local confidence maps for two simple localization strategies based on distance and relative orientation of regions.
The local confidence maps are then fused using an approach adapted from computer vision to produce overall confidence maps. Experiments on data acquired by mobile robots equipped with sonar sensors are presented.
We present a novel split and merge based method for dividing a given metric map into distinct regions, thus effectively creating a topological map on top of a metric one. The initial metric map is obtained from range data that are converted to a geometric map consisting of linear approximations of the indoor environment.
The splitting is done using an objective function that computes the quality of a region, based on criteria such as the average region width (to distinguish big rooms from corridors) and overall direction (which accounts for sharp bends).
A regularization term is used in order to avoid the formation of very small regions, which may originate from missing or unreliable sensor data. Experiments based on data acquired by a mobile robot equipped with sonar sensors are presented, which demonstrate the capabilities of the proposed method.
This paper presents a novel algorithm for computing absolute space representations (ASRs) in Yeap, W.K. and Jefferies, M. (1988) for mobile robots equipped with sonar sensors and an odometer. The robot is allowed to wander freely (i.e. without following any fixed path) along the corridors in an office environment from a given start point to an end point. It then wanders from the end point back to the start point. The resulting ASRs computed in both directions are shown
This paper shows how a mobile robot equipped with sonar sensors and an odometer is used to test ideas about cognitive mapping. The robot first explores an office environment and computes a "cognitive map" which is a network of ASRs [1]. The robot generates two networks, one for the outward journey and the other for the journey home.
It is shown that both networks are different. The two networks, however, are not merged to form a single network. Instead, the robot attempts to use distance information implicit in the shape of each ASR to find its way home. At random positions in the homeward journey, the robot calculates its orientation towards home. The robot's performances for both problems are evaluated and found to be surprisingly accurate.
OBJECTIVES:
To generate a fast and robust 3-D visualization of the operation site during minimal invasive surgery.
METHODS:
Light fields are used to model and visualize the 3-D operation site during minimal invasive surgery. An endoscope positioning robot provides the position and orientation of the endoscope. The a priori un-known transformation from the endoscope plug to the endoscope tip (hand-eye transformation) can either be determined by a three-step algorithm, which includes measuring the endoscope length by hand or by using an automatic hand-eye calibration algorithm. Both methods are described in this paper and their respective computation times and accuracies are compared.
RESULTS:
Light fields were generated during real operations and in the laboratory. The comparison of the two methods to determine the unknown hand-eye transformation was done in the laboratory. The results which are being presented in this paper are: rendered images from the generated light fields, the calculated extrinsic camera parameters and their accuracies with respect to the applied hand-eye calibration method, and computation times.
CONCLUSION:
Using an endoscope positioning robot and knowing the hand-eye transformation, the fast and robust generation of light fields for minimal invasive surgery is possible.
This paper describes using a mobile robot, equipped with some sonar sensors and an odometer, to test navigation through the use of a cognitive map. The robot explores an office environment, computes a cognitive map, which is a network of ASRs [36, 35], and attempts to find its way home.
Ten trials were conducted and the robot found its way home each time. From four random positions in two trials, the robot estimated the home position relative to its current position reasonably accurately.
Our robot does not solve the simultaneous localization and mapping problem and the map computed is fuzzy and inaccurate with much of the details missing.
In each homeward journey, it computes a new cognitive map of the same part of the environment, as seen from the perspective of the homeward journey. We show how the robot uses distance information from both maps to find its way home.
When animals (including humans) first explore a new environment, what they remember is fragmentary knowledge about the places visited. Yet, they have to use such fragmentary knowledge to find their way home.
Humans naturally use more powerful heuristics while lower animals have shown to develop a variety of methods that tend to utilize two key pieces of information, namely distance and orientation information.
Their methods differ depending on how they sense their environment. Could a mobile robot be used to investigate the nature of such a process, commonly referred to in the psychological literature as cognitive mapping? What might be computed in the initial explorations and how is the resulting “cognitive map” be used for localization?
In this paper, we present an approach using a mobile robot to generate a “cognitive map”, the main focus being on experiments conducted in large spaces that the robot cannot apprehend at once due to the very limited range of its sensors. The robot computes a “cognitive map” and uses distance and orientation information for localization.
We present an approach for indoor mapping and localisation using sparse range data, acquired by a mobile robot equipped with sonar sensors.
The chapter consists of two main parts. First, a split and merge based method for dividing a given metric map into distinct regions is presented, thus creating a topological map in a metric framework. Spatial information extracted from this map is then used for self-localisation on the return home journey.
The robot computes local confidence maps for two simple localisation strategies based on distance and relative orientation of regions. These local maps are then fused to produce overall confidence maps.
When animals (including humans) first explore a new environment, what they remember is fragmentary knowledge about the places visited. Yet, they have to use such fragmentary knowledge to find their way home. Humans naturally use more powerful heuristics while lower animals have shown to developa varietyof methodsthat tend to utilize two key pieces of information,namely distance and orientation information.
Their methods differ depending on how they sense their environment.
Could a mobile robot be used to investigate the nature of such a process, commonly referred to in the psychological literature as cognitive mapping? What might be computed in the initial explorations and how is the resulting “cognitive map” be used to return home?
In this paper, we presented a novel approach using a mobile robot to do cognitive mapping. Our robot computes a “cognitive map” and uses distance and orientation information to find its way home.
The process developed provides interesting insights into the nature of cognitive mapping and encourages us to use a mobile robot to do cognitive mapping in the future, as opposed to its popular use in robot mapping.
The main focus of this work is the development of new methods for the self-calibration of a rigid stereo camera system. However, many of the algorithms introduced here have a wider impact, particularly in robot hand-eye calibration with all its different areas of application. Stereo self-calibration refers to the computation of the intrinsic and extrinsic parameters of a stereo rig using neither a priori knowledge on the movement of the rig nor on the geometry of the observed scene.
The stereo parameters obtained by self-calibration, namely rotation and translation from left to right camera, are used for computing depth maps for both images, which are applied for rendering correctly occluded virtual objects into a real scene (Augmented Reality).
The proposed methods were evaluated on real and synthetic data and compared to algorithms from the literature. In addition to a stereo rig, an optical tracking system with a camera mounted on an endoscope was calibrated without a calibration pattern using the proposed extended hand-eye calibration algorithm.
The self-calibration methods developed in this work have a number of features, which make them easily applicable in practice: They rely on temporal feature tracking only, as this monocular tracking in a continuous image sequence is much easier than left-to-right tracking when the camera parameters are still unknown.
Intrinsic and extrinsic camera parameters are computed during the self-calibration process, i.e., no calibration pattern is required. The proposed stereo self-calibration approach can also be used for extended hand-eye calibration, where the eye poses are obtained by structure-from-motion rather than from a calibration pattern.
An inherent problem to hand-eye calibration is that it requires at least two general movements of the cameras in order to compute the rigid transformation.
If the motion is not general enough, only a part of the parameters can be obtained, which would not be sufficient for computing depth maps. Therefore, a main part of this work discusses methods for data selection that increase the robustness of hand-eye calibration. Different new approaches are shown, the most successful ones being based on vector quantization.
The data selection algorithms developed in this work can not only be used for stereo self-calibration, but also for classic robot hand-eye calibration, and they are independent of the actually used hand-eye calibration algorithm.
In this paper, we present our experience in designing and teaching of our first robotics course for students at primary school level.
The course was carried out over a comparatively short period of time, namely 6 weeks, 2 hours per week. In contrast to many other projects, we use robots that researchers used to conduct their research and discuss problems faced by these researchers. Thus, this is not a behavioural study but a hands-on learning experience for the students.
The aim is to highlight the development of autonomous robots and artificial intelligence as well as to promote science and robotics in schools.
C/C++ GE-PACKT
(2007)
Previously we have shown that ASR technology can be used to objectively evaluate pathologic speech. Here we report on progress for routine clinical use: 1) We introduce an easy-to-use recording and evaluation environment. 2) We confirm our previous results for a larger group of patients. 3) We show that telephone speech can be analyzed with the same methods with only a small loss of agreement with human experts. 4) We show that prosodic information leads to more robust results. 5) We show that text reference instead of transliteration can be used for evaluation. Using word accuracy of a speech recognizer and prosodic features as features for SVM regression, we achieve a correlation of .90 between the automatic analysis and human experts.
In früheren Arbeiten wurde gezeigt, dass automatische Spracherkennungsverfahren verwendet werden können, um die Verständlichkeit von Sprechern mit tracheoösophagealer Ersatzstimme (TE-Stimme) automatisch zu bewerten [1,2]. In diesem Beitrag wird eine automatische Version des Postlaryngektomie-Telefontests (PLTT, [3]) vorgestellt, der einen eingeführten Standardtest für die Verständlichkeit über das Telefon darstellt.
The tracheoesophageal (TE) substitute voice is currently state–of–the–art treatment to restore the ability to speak after laryngectomy. The intelligibility while talking over a telephone is an important clinical factor, as it is a crucial part of the patients’ social life. An objective way to rate the intelligibility of substitute voices when talking over a telephone is desirable to improve the post–laryngectomy speech therapy. An automatic speech recognition (ASR) system was applied to 41 high quality recordings of post–laryngectomy patients. The ASR system was trained with normal, non–pathologic speech. It yielded a word accuracy (WA) of 36.9%±18.0%; compared to the intelligibility rating of a group of human experts the ASR system had a correlation coefficient of -.88. After downsampling the 41 recordings to telephone quality, the ASR system reached a WA of 26.4%±13.9% leading to a correlation coefficient of -.80. These results confirm that an ASR system can be used for objective intelligibility rating over the telephone.
Die tracheoösophageale Ersatzstimme: Automatische Verständlichkeitsbewertung über das Telefon
(2006)
Die tracheoösophageale Ersatzstimme TE ist heute "state of the art" der Stimmrehabilitation nach einer Laryngektomie. In dieser Studie, einem Teilprojekt eines von der Deutschen Krebshilfe geförderten Forschungsvorhabens, ging es um die objektive Bewertung des Behandlungsfortschritts. Untersucht wurden 41 Laryngektomierte mit einer TE (Provox-Stimmventilprothese) durchgeführt. Ziel der Studie war es, die Verständlichkeit im Gespräch und am Telefon objektiv zu beurteilen und zu vergleichen, um den Patienten in der Zukunft die telefonische Evaluation von zuhause aus zu ermöglichen. Zur Bewertung diente ein für Marktzwecke professionalisiertes automatisches Spracherkennungssystem. Es wurden zunächst Nahbesprechungsaufnahmen des "Nordwind und Sonne"-Textes von fünf Experten hinsichtlich ihrer Verständlichkeit beurteilt. Aus diesen Aufnahmen entstanden durch Abspielen über ein Telefon simulierte Telefonaufnahmen. Zielkriterium der automatischen Analyse war die Wortakkuratheit WA, die mit der an Schulnoten orientierten Stimmbewertung durch die Experten korreliert wurde. Die Studie ergab eine Korrelation von -0,82 für die Nahbesprechungs- und -0,69 für die Telefonaufnahmen. Die Ergebnisse zeigen, dass die automatische Verständlichkeitsbewertung von Ersatzstimmen auch per Telefon prinzipiell möglich ist. Möglichkeiten, die Qualitätsverluste durch die Telefonübertragung und die somit niedrigere Korrelation zu kompensieren, werden aufgezeigt.
Folks that have been here last winter prior to ASRU might be familiar with the title of that talk. But don't be misled, I'll have something new for you. In this talk, I will give an overview over the FAU Lecture Browser which I developed in the context of my thesis. I will start out with the description of a novel data set: The LME Lectures are a corpus of two series of graduate level computer science lectures with 18 recordings each. The courses cover topics in medical image processing and pattern analysis/machine learning. The roughly 40 hours of speech were manually transcribed, and one particular lecture was annotated with key phrases by five human raters. Using this data set, I trained three different speech recognizers using regular continuous, multi-codebook semi-continuous and subspace Gaussian mixture models, that show an error rate of about 10% WER. I will then briefly describe the key phrase extraction and automatic ranking, which was then compared against five raters on one lecture recording. Finally, I will talk about a little usability study where 10 students were asked to perform a certain task-- with and without the proposed lecture browser. Although the number of contestants is limited, the numbers are interesting: the users that had the interface could complete the tasks about 30% faster than the control group, while maintaining about the same accuracy.
Tracheoesophageal (TE) speech is a possibility to restore the ability to speak after total laryngectomy, i.e. the removal of the larynx. The quality of the substitute voice has to be evaluated during therapy. For the intelligibility evaluation of German speakers over telephone, the Post-Laryngectomy Telephone Test (PLTT) was defined. Each patient reads out 20 of 400 different monosyllabic words and 5 out of 100 sentences. A human listener writes down the words and sentences understood and computes an overall score. This paper presents a means of objective and automatic evaluation that can replace the subjective method. The scores of 11 naïve raters for a set of 31 test speakers were compared to the word recognition rate of speech recognizers. Correlation values of about 0.9 were reached.
Remeeting is a tool that helps you get more out of in-person
meetings. Calendar integration and a special email address allow
users to email agenda items prior to a certain meeting. A
discrete notification at the time of the meeting reminds the user
to start the recording. During the meeting, the user focuses on the conversation, or can add notes and photos if desired. After the meeting, every participant gets notified by an automated email that lists the participants along with automatically extracted keywords, notes and photos. This stimulates collaboration, and keeps follow-up contributions at a central place: Just reply to add further notes to the meeting. The resulting meeting “document” can be shared with others and reviewed using a web app that acts as a visual index to the meeting. This makes Remeeting the perfect tool for regular group meetings, standups and interviews, where people typically track progress and follow up on. Remeeting is leveraging, promoting and contributing to open source projects including kaldi and docker.
This paper presents an unsupervised, graph based approach for extractive summarization of meetings. Graph based methods such as TextRank have been used for sentence extraction from news articles. These methods model text as a graph with sentences as nodes and edges based on word overlap. A sentence node is then ranked according to its similarity with other nodes. The spontaneous speech in meetings leads to incomplete, informed sentences with high redundancy and calls for additional measures to extract relevant sentences. We propose an extension of the TextRank algorithm that clusters the meeting utterances and uses these clusters to construct the graph. We evaluate this method on the AM I meeting corpus and show a significant improvement over TextRank and other baseline methods.
We introduce a model for extractive meeting summarization based on the hypothesis that utterances convey bits of information, or concepts. Using keyphrases as concepts weighted by frequency, and an integer linear program to determine the best set of utterances, that is, covering as many concepts as possible while satisfying a length constraint, we achieve ROUGE scores at least as good as a ROUGE-based oracle derived from human summaries. This brings us to a critical discussion of ROUGE and the future of extractive meeting summarization.
Rooted in multi-document summarization, maximum marginal relevance (MMR) is a widely used algorithm for meeting summarization (MS). A major problem in extractive MS using MMR is finding a proper query: the centroid based query which is commonly used in the absence of a manually specified query, can not significantly outperform a simple baseline system. We introduce a simple yet robust algorithm to automatically extract keyphrases (KP) from a meeting which can then be used as a query in the MMR algorithm. We show that the KP based system significantly outperforms both baseline and centroid based systems. As human refined KPs show even better summarization performance, we outline how to integrate the KP approach into a graphical user interface allowing interactive summarization to match the user's needs in terms of summary length and topic focus.
The CALO meeting assistant provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper summarizes the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, question-answer pair identification, action item recognition, decision extraction, and summarization.
Despite considerable work in automatic meeting summarization over the last few years, comparing results remains difficult due to varied task conditions and evaluations. To address this issue, we present a method for determining the best possible extractive summary given an evaluation metric like ROUGE. Our oracle system is based on a knapsack-packing framework, and though NP-Hard, can be solved nearly optimally by a genetic algorithm. To frame new research results in a meaningful context, we suggest presenting our oracle results alongside two simple baselines. We show oracle and baseline results for a variety of evaluation scenarios that have recently appeared in this field.
For many aspects of speech therapy an objective evaluation of the intelligibility of a patient's speech is needed. We investigate the evaluation of the intelligibility of speech by means of automatic speech recognition. Previous studies have shown that measures like word accuracy are consistent with human experts' ratings. To ease the patient's burden, it is highly desirable to conduct the assessment via phone. However, the telephone channel influences the quality of the speech signal which negatively affects the results. To reduce inaccuracies, we propose a combination of two speech recognizers. Experiments on two sets of pathological speech show that the combination results in consistent improvements in the correlation between the automatic evaluation and the ratings by human experts. Furthermore, the approach leads to reductions of 10% and 25% of the maximum error of the intelligibility measure.
Towards a Language-independent Intelligibility Assessment of Children with Cleft Lip and Palate
(2009)
We describe a novel evaluation system for the intelligibility assessment of children with CLP on standardized tests. The system is solely based on standard cepstral features in form of MFCCs. No other information like word alignments is used. So the system can be easily adapted to other languages. For each child one GMM is created by adaptation of a UBM to the speaker-specific MFCCs. The components of this GMM are concatenated in order to create a so-called GMM supervector. These GMM supervectors are then used as meta features for an SVR. We evaluated our language-independent system on two different datasets of children suffering from CLP. One dataset contains recordings of 35 German children, where the children named different pictograms. The other dataset contains recordings of 14 Italian speaking children, who repeated standardized sentences. On both datasets we achieved high correlations: up to 0.81 for the German dataset and 0.83 for the Italian dataset.
We present a novel lecture browser that utilizes ranked key phrases displayed on a stream graph to overcome the shortcomings of traditional extractive (query-based) summaries. The system extracts key phrases from the ASR transcripts, performs an unsupervised ranking, and displays an initial number of phrases on the stream graph. This graph gives an intuition of when which key phrase is spoken, and how dominant it is throughout the lecture. The user can select the phrases to be displayed and furthermore adjust the ranking of the all phrases. All user interactions are logged to a server to improve the ranking algorithms and provide user specific rankings.
A growing number of universities offer recordings of lectures, seminars and talks in an online e-learning portal. However, the user is often not interested in the entire recording, but is looking for parts covering a certain topic. Usually, the user has to either watch the whole video or “zap” through the lecture and risk missing important details. We present an integrated web-based platform to help users find relevant sections within recorded lecture videos by providing them with a ranked list of key phrases. For a user-defined subset of these, a StreamGraph visualizes when important key phrases occur and how prominent they are at the given time. To come up with the best key phrase rankings, we evaluate three different key phrase ranking methods using lectures of different topics by comparing automatic with human rankings, and show that human and automatic rankings yield similar scores using Normalized Discounted Cumulative Gain (NDCG).
In this paper, we describe a new Java framework for an easy and efficient way of developing new GUI based speech processing applications. Standard components are provided to display the speech signal, the power plot, and the spectrogram. Furthermore, a component to create a new transcription and to display and manipulate an existing transcription is provided, as well as a component to display and manually correct external pitch values. These Swing components can be easily embedded into own Java programs. They can be synchronized to display the same region of the speech file. The object-oriented design provides base classes for rapid development of own components.
This paper focuses on the automatic detection of a person's blood level alcohol based on automatic speech processing approaches. We compare 5 different feature types with different ways of modeling. Experiments are based on the ALC corpus of IS2011 Speaker State Challenge. The classification task is restricted to the detection of a blood alcohol level above 0.5‰. Three feature sets are based on spectral observations: MFCCs, PLPs, TRAPS. These are modeled by GMMs. Classification is either done by a Gaussian classifier or by SVMs. In the later case classification is based on GMM-based supervectors, i.e. concatenation of GMM mean vectors. A prosodic system extracts a 292-dimensional feature vector based on a voiced-unvoiced decision. A transcription-based system makes use of text transcriptions related to phoneme durations and textual structure. We compare the stand-alone performances of these systems and combine them on score level by logistic regression. The best stand-alone performance is the transcriptionbased system which outperforms the baseline by 4.8% on the development set. A Combination on score level gave a huge boost when the spectral-based systems were added (73.6%). This is a relative improvement of 12.7% to the baseline. On the test-set we achieved an UA of 68.6% which is a significant improvement of 4.1% to the baseline system.
In this work we focus on speaker verification on channels of varying quality, namely Skype and high frequency (HF) radio. In our setup, we assume to have telephone recordings of speakers for training, but recordings of different channels for testing with varying (lower) signal quality. Starting from a Gaussian mixture / support vector machine (GMM/SVM) baseline, we evaluate multi-condition training (MCT), an ideal channel classification approach (ICC), and nuisance attribute projection (NAP) to compensate for the loss of information due to the transmission. In an evaluation on Switchboard-2 data using Skype and HF channel simulators, we show that, for good signal quality, NAP improves the baseline system performance from 5% EER to 3.33% EER (for both Skype and HF). For strongly distorted data, MCT or, if adequate, ICC turn out to be the method of choice.
Online Identification of Learner Problem Solving Strategies Using Pattern Recognition Methods
(2010)
Learning and programming environments used in computer science education give feedback to the users by system messages. These are triggered by programming errors and give only "technical" hints without regard to the learners' problem solving process. To adapt the messages not only to the factual but also to the procedural knowledge of the learners, their problem solving strategies have to be identified automatically and in process. This article describes a way to achieve this with the help of pattern recognition methods. Using data from a study with 65 learners aged 12 to 13 using a learning environment for programming, a classification system based on hidden Markov models is trained and integrated in the very same environment. We discuss findings in that data and the performance of the automatic online identification, and present first results using the developed software in class.
Reverberation effects as observed by room microphones severely degrade the performance of automatic speech recognition systems. We investigate the use of dereverberation by spectral subtraction as proposed by Lebart and Boucher and introduce a simple approach to estimate the required decay parameter by clapping hands. Experiments on small vocabulary continuous speech recognition task on read speech show that using the calibrated dereverberation improves WER from 73.2 to 54.7 for the best microphone. In combination with system adaptation, the WER could be reduced to 28.2, which is only a 16% relative loss of performance comparison to using a headset instead of a room microphone.
We describe a lattice generation method that is exact, i.e. it satisfies all the natural properties we would want from a lattice of alternative transcriptions of an utterance. This method does not introduce substantial overhead above one-best decoding. Our method is most directly applicable when using WFST decoders where the WFST is “fully expanded”, i.e. where the arcs correspond to HMM transitions. It outputs lattices that include HMM-state-level alignments as well as word labels. The general idea is to create a state-level lattice during decoding, and to do a special form of determinization that retains only the best-scoring path for each word sequence. This special determinization algorithm is a solution to the following problem: Given a WFST A, compute a WFST B that, for each input-symbol-sequence of A, contains just the lowest-cost path through A.
In the past decade, semi-continuous hidden Markov models (SCHMMs) have not attracted much attention in the speech recognition community. Growing amounts of training data and increasing sophistication of model estimation led to the impression that continuous HMMs are the best choice of acoustic model. However, recent work on recognition of under-resourced languages faces the same old problem of estimating a large number of parameters from limited amounts of transcribed speech. This has led to a renewed interest in methods of reducing the number of parameters while maintaining or extending the modeling capabilities of continuous models. In this work, we compare classic and multiple-codebook semi-continuous models using diagonal and full covariance matrices with continuous HMMs and subspace Gaussian mixture models. Experiments on the RM and WSJ corpora show that while a classical semicontinuous system does not perform as well as a continuous one, multiple-codebook semi-continuous systems can perform better, particular when using full-covariance Gaussians.
In this paper we describe Erlangen-CLP, a large speech database of children with Cleft Lip and Palate. More than 800 German children with CLP (most of them between 4 and 18 years old) and 380 age matched control speakers spoke the semi-standardized PLAKSS test that consists of words with all German phonemes in different positions. So far 250 CLP speakers were manually transcribed, 120 of these were analyzed by a speech therapist and 27 of them by four additional therapists. The tharapists marked 6 different processes/criteria like pharyngeal backing and hypernasality which typically occur in speech of people with CLP. We present detailed statistics about the the marked processes and the inter-rater agreement.
In this paper we apply diagnostic analysis to gain a deeper understanding of the performance of the the keyword search system that we have developed for conversational telephone speech in the IARPA Babel program. We summarize the Babel task, its primary performance metric, “actual term weighted value” (ATWV), and our recognition and keyword search systems. Our analysis uses two new oracle ATWV measures, a bootstrap-based ATWV confidence interval, and includes a study of the underpinnings of the large ATWV gains due to system combination. This analysis quantifies the potential ATWV gains from improving the number of true hits and the overall quality of the detection scores in our system's posting lists. It also shows that system combination improves our systems' ATWV via a small increase in the number of true hits in the posting lists.
This paper describes the acquisition, transcription and annotation of a multi-media corpus of academic spoken English, the LMELectures. It consists of two lecture se-ries that were read in the summer term 2009 at the com-puter science department of the University of Erlangen-Nuremberg, covering topics in pattern analysis, machine learning and interventional medical image processing. In total, about 40 hours of high-definition audio and video of a single speaker was acquired in a constant recording en-vironment. In addition to the recordings, the presentation slides are available in machine readable (PDF) format. The manual annotations include a suggested segmenta-tion into speech turns and a complete manual transcrip-tion that was done using BLITZSCRIBE2, a new tool for the rapid transcription. For one lecture series, the lecturer assigned key words to each recordings; one recording of that series was further annotated with a list of ranked key phrases by five human annotators each. The corpus is available for non-commercial purpose upon request.
We describe a state-of-the-art large vocabulary continuous speech recognition (LVCSR) and keyword search (KWS) system trained on roughly 70 hours of conversational telephone speech. Using the Kaldi speech recognition toolkit, we investigate several aspects: for the acoustic front-end, we analyze the use of mel-frequency cepstral coefficients (MFCC), pitch and probability-of-voicing (PoV), and deep neural network (DNN) bottleneck (BN) features, as well as their feature-level combination ("tandem"). For the acousticphonetic decision tree, we explore different hidden Markov model (HMM) topologies for the glottalization phoneme /?/ to model its typically short duration. For the acoustic model, we compare regular continuous HMM with a sort of multi-codebook subspace Gaussian mixture model (SGMM) that lead to an overall best word error rate (WER) of 58.7% and 56.3%, respectively. The KWS is implemented as a word lattice search, and is augmented by a syllable lattice back-up search to capture out-of-vocabulary keywords as well as misrecognized lexical surface forms due to ambiguous prefix and hyphenation rules.
Cleft Lip and Palate (CLP) is among the most frequent congenital abnormalities. The impaired facial development affects the articulation, with different phonemes being impacted inhomogeneously among different patients. This work focuses on automatic phoneme analysis of children with CLP for a detailed diagnosis and therapy control. In clinical routine, the state-of-the-art evaluation is based on perceptual evaluations. Perceptual ratings act as ground-truth throughout this work, with the goal to build an automatic system that is as reliable as humans. We propose two different automatic systems focusing on modeling the articulatory space of a speaker: one system models a speaker by a GMM, the other system employs a speech recognition system and estimates fMLLR matrices for each speaker. SVR is then used to predict the perceptual ratings. We show that the fMLLR-based system is able to achieve automatic phoneme evaluation results that are in the same range as perceptual inter-rater-agreements.
A growing number of universities and other educational institutions provide recordings of lectures and seminars as an additional resource to the students. In contrast to educational films that are scripted, directed and often shot by film professionals, these plain recordings are typically not post-processed in an editorial sense. Thus, the videos often contain longer periods of inactivity or silence, unnecessary repetitions, or corrections of prior mistakes. This paper describes the FAU Video Lecture Browser system, a web-based platform for the interactive assessment of video lectures, that helps to close the gap between a plain recording and a useful e-learning resource by displaying automatically extracted and ranked key phrases on an augmented time line based on stream graphs. In a pilot study, users of the interface were able to complete a topic localization task about 29 % faster than users provided with the video only while achieving about the same accuracy. The user interactions can be logged on the server to collect data to evaluate the quality of the phrases and rankings, and to train systems that produce customized phrase rankings.
In earlier studies, we assessed the degree of non-nativeness employing prosodic information. In this paper, we combine prosodic information with (1) features derived from a Gaussian Mixture Model used as Universal Background Model (GMM-UBM), a powerful approach used in speaker identification, and (2) openSMILE, a standard open-source toolkit for extracting acoustic features. We evaluate our approach with English speech from 94 non-native speakers. GMM-UBM or openSMILE modelling alone yields lower performance than our prosodic feature vector; however, adding information from the GMM-UBM modelling or openSMILE by late fusion improves results.
Voice scrambling is widely used to add privacy to the radio communication of various authorities - but is also used by criminals to evade prosecution. In this article, we consider various analog voice scrambling techniques such as fixed frequency inversion, splitband inversion and rolling code scramblers. We explain how to break them using automatically extracted measures and scoring algorithms, and evaluate the proposed system using simulated data. While the simple inversion can be easily broken, the more advanced techniques require additional work prior to unsupervised automatization; the presented user interface allows the user to refine the automatic results to obtain a high quality solution.
In this paper we present an algorithm that produces pitch and probability-of-voicing estimates for use as features in automatic speech recognition systems. These features give large performance improvements on tonal languages for ASR systems, and even substantial improvements for non-tonal languages. Our method, which we are calling the Kaldi pitch tracker (because we are adding it to the Kaldi ASR toolkit), is a highly modified version of the getf0 (RAPT) algorithm. Unlike the original getf0 we do not make a hard decision whether any given frame is voiced or unvoiced; instead, we assign a pitch even to unvoiced frames while constraining the pitch trajectory to be continuous. Our algorithm also produces a quantity that can be used as a probability of voicing measure; it is based on the normalized autocorrelation measure that our pitch extractor uses. We present results on data from various languages in the BABEL project, and show a large improvement over systems without tonal features and systems where pitch and POV information was obtained from SAcC or getf0.