Institut für Medizintechnologie
Refine
Year of publication
Document Type
Way of publication
- Open Access (6)
Keywords
- Nystagmus (2)
- Vertigo (2)
- Acute stroke (1)
- Acute unilateral vestibulopathy (1)
- Adaptation (1)
- Atrial fibrillation (1)
- Catheter ablation, AVNRT, Complications, Registry, Long-term follow-up (1)
- Catheter ablation, Atrial fibrillation, Elderly, Repeat ablation (1)
- Computer Science Applications (1)
- Computer vision (1)
- Convolutional neural networks (1)
- DTW (1)
- Digital medicine (1)
- Distant learning (1)
- Dizziness (1)
- Education (1)
- Educational technology (1)
- Eye movement disorders (1)
- Gait analysis (1)
- Head Impulse (1)
- Head Impulse Testing (1)
- Head Velocity (1)
- Head impulse test (1)
- Html5 app development (1)
- Human-Computer Interaction (1)
- IMS QTI transformation (1)
- Inertial sensors (1)
- Interface (1)
- Intraoperative microwave ablation (1)
- LMS assessment (1)
- Mobile-assessment (1)
- Moodle (1)
- Moodle Plugin (1)
- Motion sickness (1)
- Online Self-Assessment Tools (1)
- Parkinson (1)
- Parkinson’s disease (1)
- Precision medicine (1)
- Question Exchange (1)
- Rotational Chair (1)
- Skew deviation (1)
- Stop-and-go car ride (1)
- Stride detection (1)
- Telemedicine (1)
- Test of skew (1)
- Time up and go test (1)
- VOG (1)
- Validation Dynamic time warping (1)
- Vestibular Function Test (1)
- Vestibulo-ocular reflex (1)
- Video head impulse test (1)
- Video-oculography (1)
- Videooculography (1)
- abduction (1)
- adduction (1)
- automatic formative assessment (1)
- binocular video head impulse test (1)
- clustering (1)
- computer science (1)
- conjugate gaze (1)
- databases (1)
- downbeat nystagmus (1)
- ductional VOR asymmetry index (1)
- dysconjugacy ratio (1)
- education (1)
- handwriting (1)
- higher education (1)
- mathematics (1)
- metadata (1)
- monocular VOR asymmetry index (1)
- on-line handwriting features (1)
- online strokes (1)
- oscillopsia (1)
- parkinson disease (1)
- password identification (1)
- plugins (1)
- reduction feature (1)
- resting (1)
- symptom relief (1)
- time series (1)
- vestibuloocular reflex (1)
- video-oculographic measurement (VOG) (1)
- writer verification (1)
Institute
We investigated whether a passive brain–computer interface that was trained to distinguish low and high mental workload in the electroencephalogram (EEG) can be used to identify (1) texts of different readability difficulties and (2) texts read at different presentation speeds. For twelve subjects we calibrated a subject-dependent, but task-independent predictive model classifying mental workload. We then recorded EEG data from each subject, while twelve texts in blocks of three were presented to them word by word. Half of the texts were easy, and the other half were difficult texts according to classic reading formulas. From each text category three texts were read at a self-adjusted comfortable presentation speed and the other three at an increased speed. For each subject we applied the predictive model to EEG data of each word of the twelve texts. We found that the resulting predictive values for mental workload were higher for difficult texts than for easy texts. Predictive values from texts presented at an increased speed were also higher than for those presented at a normal self-adjusted speed. The results suggest that the task-independent predictive model can be used on single-subject level to build a highly predictive user model of the reader over time. Such a model could be employed in a system which continuously monitors brain activity related to mental workload and adapts to specific reader’s abilities and characteristics by adjusting the difficulty of text materials and the way it is presented to the reader in real time. A neuroadaptive system like this could foster efficient reading and text-based learning by keeping readers’ mental workload levels at an individually optimal level.
Objective
Skew deviation results from a dysfunction of the graviceptive pathways in patients with an acute vestibular syndrome (AVS) leading to vertical diplopia due to vertical ocular misalignment. It is considered as a central sign, however, the prevalence of skew and the accuracy of its test is not well known .
Methods
We performed a prospective study from February 2015 until September 2020 of all patients presenting at our emergency department (ED) with signs of AVS. All patients underwent clinical HINTS and video test of skew (vTS) followed by a delayed MRI, which served as a gold standard for vestibular stroke confirmation.
Results
We assessed 58 healthy subjects, 53 acute unilateral vestibulopathy patients (AUVP) and 24 stroke patients. Skew deviation prevalence was 24% in AUVP and 29% in strokes. For a positive clinical test of skew, the cut-off of vertical misalignment was 3 deg with a very low sensitivity of 15% and specificity of 98.2%. The sensitivity of vTS was 29.2% with a specificity of 75.5%.
Conclusions
Contrary to prior knowledge, skew deviation proved to be more prevalent in patients with AVS and occurred in every forth patient with AUVP. Large skew deviations (> 3.3 deg), were pointing toward a central lesion. Clinical and video test of skew offered little additional diagnostic value compared to other diagnostic tests such as the head impulse test and nystagmus test. Video test of skew could aid to quantify skew in the ED setting in which neurotological expertise is not always readily available.
Resting in an upright position during daytime decreases downbeat nystagmus (DBN). When measured in brightness only, that is, without intermitting exposure to darkness, it does not make a significant difference whether patients have previously rested in brightness or in darkness. In real-world scenarios, people are often exposed to brightness and darkness intermittently. The aim of this study was to analyze whether resting in brightness or resting in darkness was associated with a lower post-resting DBN after intermitting exposures to brightness and darkness. Eight patients were recorded with three-dimensional video-oculography in brightness and darkness conditions, each following two 2-h resting intervals under either brightness or darkness resting conditions. The dependent variable was DBN intensity, measured in mean slow phase velocity. A repeated measures ANOVA with the factors measurement condition (brightness vs. darkness), resting condition (brightness vs. darkness), and time (after first vs. second resting interval) showed a significant effect for the factor resting condition, where previous resting in darkness was associated with a significantly lower DBN relative to previous resting in brightness (P < 0.01). The clinical relevance is to advise patients with DBN to rest in darkness.
Motion sickness is a physiological condition that negatively impacts a person's comfort and will be an emerging condition in autonomous vehicles without proper countermeasures. The vestibular system plays a key role in the origin of motion sickness. Understanding the susceptibility and (mal) adaptive mechanisms of the highly integrated vestibular system is a prerequisite for the development of countermeasures. We hypothesize a differential association between motion sickness and vestibular function in healthy individuals with and without susceptibility for motion sickness. We quantified vestibular function by measuring the high-frequency vestibulo-ocular reflex (VOR) using video head impulse testing (vHIT) in 17 healthy volunteers before and after a 11 min motion sickness-inducing naturalistic stop-and-go car ride on a test track (Dekra Test Oval, Klettwitz, Germany). The cohort was classified as motion sickness susceptible (n = 11) and non-susceptible (n = 6). Six (out of 11) susceptible participants developed nausea symptoms, while a total of nine participants were free of these symptoms. The VOR gain (1) did not differ significantly between participant groups with (n = 8) and without motion sickness symptoms (n = 9), (2) did not differ significantly in the factor time before and after the car ride, and showed no interaction between symptom groups and time, as indicated by a repeated measures ANOVA (F(1,15) = 2.19, p = 0.16. Bayesian inference confirmed that there was “anecdotal evidence” for equality of gain rather than difference across groups and time (BF10 < 0.77). Our results suggest that individual differences in VOR measures or adaptation to motion sickness provocative stimuli during naturalistic stop-and-go driving cannot predict motion sickness susceptibility or the likelihood of developing motion sickness.
Eye movement abnormalities are commonplace in neurological disorders. However, unaided eye movement assessments lack granularity. Although videooculography (VOG) improves diagnostic accuracy, resource intensiveness precludes its broad use. To bridge this care gap, we here validate a framework for smartphone video-based nystagmography capitalizing on recent computer vision advances.
Methods
A convolutional neural network was fine-tuned for pupil tracking using > 550 annotated frames: ConVNG. In a cross-sectional approach, slow-phase velocity of optokinetic nystagmus was calculated in 10 subjects using ConVNG and VOG. Equivalence of accuracy and precision was assessed using the “two one-sample t-test” (TOST) and Bayesian interval-null approaches. ConVNG was systematically compared to OpenFace and MediaPipe as computer vision (CV) benchmarks for gaze estimation.
Results
ConVNG tracking accuracy reached 9–15% of an average pupil diameter. In a fully independent clinical video dataset, ConVNG robustly detected pupil keypoints (median prediction confidence 0.85). SPV measurement accuracy was equivalent to VOG (TOST p < 0.017; Bayes factors (BF) > 24). ConVNG, but not MediaPipe, achieved equivalence to VOG in all SPV calculations. Median precision was 0.30°/s for ConVNG, 0.7°/s for MediaPipe and 0.12°/s for VOG. ConVNG precision was significantly higher than MediaPipe in vertical planes, but both algorithms’ precision was inferior to VOG.
Conclusions
ConVNG enables offline smartphone video nystagmography with an accuracy comparable to VOG and significantly higher precision than MediaPipe, a benchmark computer vision application for gaze estimation. This serves as a blueprint for highly accessible tools with potential to accelerate progress toward precise and personalized Medicine.
Objective measurement of HINTS (Head Impulse, Nystagmus, Test of Skew) in peripheral vestibulopathy
(2022)
ABSTRACT
Objective
To evaluate how often the positive sign of HINTS (Head-Impulse, Gaze Evoked Nystagmus, Test of Skew) appears in patients with acute peripheral vestibular lesion, HINTS findings were quantitatively measured and analyzed in patients with peripheral vestibulopathy accompanying spontaneous nystagmus.
Methods
HINTS was evaluated in 14 vertigo patients with spontaneous nystagmus. Horizontal vestibulo-ocular reflex (VOR) gain was measured using the video head impulse test (vHIT). To evaluate gaze-evoked nystagmus (GEN), slow-phase velocities at different points of lateral gaze were measured and plotted, then the slope and its inverse value, the neural integrator time constant, were calculated. Skew deviation was tested using anaglyph filters to simulate the alternate cover test, and the degree and latency of vertical eyeball deviation were measured. The ABCD2 score was calculated to evaluate the risk of stroke.
Results
Among 13 patients of peripheral vestibulopathy, 7 showed positive signs in HINTS (normal vHIT: 5, direction-changing GEN: 0, skew deviation: 3). One patient with a cerebellopontine angle tumor presented with both a peripheral and central pattern and showed positive HINTS findings (presence of direction-changing GEN). The mean VOR gain of patients with abnormal vHIT was 0.58±0.29 and 1.10±0.11 in the affected and contralateral side, respectively, while those in patients with normal vHIT were 1.04±0.21 and 1.13±0.12, respectively. The neural integrator time constant calculated from the mean slope of horizontal slow-phase velocity according to horizontal eye position was 42.9 s. The mean vertical eyeball deviation of patients with positive skew was 2.14±1.18° while uncovering the eye on the affected side, and -1.97±1.59° while uncovering the eye on the unaffected side. The median ABCD2 score of 14 patients was 2 (range, 1-3).
Conclusions
HINTS findings were objectively measured in vertigo patients with spontaneous nystagmus. Although positive findings of HINTS have been recognized as a central sign, 54% (7/13) of cases with peripheral vestibulopathy showed positive HINTS signs. HINTS results should be interpreted carefully considering that a substantial proportion of peripheral vestibulopathy shows a positive HINTS sign.
Introduction
The video head impulse test (vHIT) evaluates the vestibulo-ocular reflex (VOR). It’s usually recorded from only one eye. Newer vHIT devices allow a binocular quantification of the VOR.
Purpose (Aim)
To investigate the advantages of simultaneously recorded binocular vHIT (bvHIT) to detect the differences between the VOR gains of the adducting and the abducting eye, to define the most precise VOR measure, and to assess gaze dys/conjugacy. We aimed to establish normative values for bvHIT adducting/abducting eye VOR gains and to introduce the VOR dysconjugacy ratio (vorDR) between adducting and abducting eyes for bvHIT.
Methods
We enrolled 44 healthy adult participants in a cross-sectional, prospective study using a repeated-measures design to assess test–retest reliability. A binocular EyeSeeCam Sci 2 device was used to simultaneously record bvHIT from both eyes during impulsive head stimulation in the horizontal plane.
Results
Pooled bvHIT retest gains of the adducting eye significantly exceeded those of the abducting eye (mean (SD): 1.08 (SD = 0.06), 0.95 (SD = 0.06), respectively). Both adduction and abduction gains showed similar variability, suggesting comparable precision and therefore equal suitability for VOR asymmetry assessment. The pooled vorDR here introduced to bvHIT was 1.13 (SD = 0.05). The test–retest repeatability coefficient was 0.06.
Conclusion
Our study provides normative values reflecting the conjugacy of eye movement responses to horizontal bvHIT in healthy participants. The results were similar to a previous study using the gold-standard scleral search coil, which also reported greater VOR gains in the adducting than in the abducting eye. In analogy to the analysis of saccade conjugacy, we propose the use of a novel bvHIT dysconjugacy ratio to assess dys/conjugacy of VOR-induced eye movements. In addition, to accurately assess VOR asymmetry, and to avoid directional gain preponderance between adduction and abduction VOR-induced eye movements leading to monocular vHIT bias, we recommend using a binocular ductional VOR asymmetry index that compares the VOR gains of only the abduction or only the adduction movements of both eyes.
Portal for generating cross university didactic self-assessment apps without programming skills
(2021)
Based on the didactic concept of a school mathematics app, a portal for the automatic creation of interdisciplinary learning apps without programming knowledge is being developed at the Brandenburg University of Technology Cottbus – Senftenberg (BTU). The aim was to develop the conception and implementation of a portal for the creation of universal learning apps as a mobile (online) assessment for the study entry phase on the one hand and the publication of the apps on the other. This article presents the basic concept of the app portal, the structure of the app portal, and initial tests of the prototype with faculty and students at BTU.
In the ESF project "StudiPortal Brandenburg", eight Brandenburg universities, colleges and the Brandenburg Study Orientation Network are working together on the development of a portal for study orientation, preparation and support. An important part of the project is to store questions from different systems in a question exchange database and make it accessible for all project partners. Since there is currently no well-functioning option for this, we decided to develop an extension for integration into our question exchange platform. For this purpose, a new Moodle plugin was developed at BTU Cottbus - Senftenberg that converts questions from the QTI 2.1 standard into Moodle XML and vice versa. The aim was to convert as many question types as possible free of loss. For this purpose, questions from various systems that work with the QTI standard were made available and tested for the possibility of lossless conversion. The result is the prototype of a plugin that can convert eight different question types. In this article we present the first prototype of the plugin.
Interaction with the visual world critically depends on when and how we move our eyes. Eye movements, in turn, alter our experience of the world by selecting objects to foveate and tracking objects over time. The interaction between vision and eye movements continues indefinitely, one process modulating the strength and timing of the other. Despite this tight linkage, vision is often studied outside the context of eye movements, during stable fixation. Likewise, eye movements are often studied with sparse visual stimuli and under ideal viewing conditions. A more accurate understanding of vision requires studying perception in the context of eye movements.
Different types of eye movements reveal different aspects of how the brain works. The continuous nature of tracking smooth pursuit eye movements, combined with its ubiquitous presence in natural vision, makes it an excellent system in which to analyze perception at fine spatial and temporal resolutions. For example, how does vision change during the transition from fixation to pursuit, and when does the brain allocate resources to account for these changes? In contrast, the ballistic nature of saccades requires analysis divided into discrete epochs, including well before the saccade during the planning stage, during saccade execution, and after the movement. At the neuronal level, how do heterogeneous populations of visual- and saccade-related cells come to represent a single saccade vector during these different epochs? What are the effects on visual perception when saccades and pursuit interact? This symposium will reveal how research incorporating both types of eye movements and visual perception can provide a more ecologically valid account of visual-motor integration and the intervening cognitive processes.
This symposium will review innovative approaches and recent advances in understanding the interplay of eye movements and vision. We will take a multifaceted approach to understanding the effects of both exploratory (saccades) and tracking (smooth pursuit) eye movements on vision by using a range of methodologies and animal models (data-driven modeling, clinical populations, and simultaneous recordings of neuronal populations; humans, macaques, and marmosets). This symposium will appeal to vision scientists interested in selective attention, motion processing, neuronal modeling, motor control, neural circuits, and related topics. Our collective goal is to uncover the dynamics of visual perception and the candidate neuronal mechanisms that support eye movements.
Methods: Body sway was analyzed by measuring the center of pressure (CoP) in 10 healthy participants on a pressure-sensitive treadmill during standing and walking at 0.4 or 0.8 m/s. Continuous SVS (0–25 Hz; peak amplitude at±4.5 mA) was delivered by a bipolar binaural electrode configuration over the mastoid processes to evoke postural responses in the roll plane. Time-dependent coherence between SVS and medio-lateral body sway was analyzed to examine the dynamic impact of vestibular cues during locomotion. HMP was estimated using a previously established model (MacNeilage and Glasauer, 2017).
Results: SVS-CoP coherence decreased from standing to slow walking and further decreased with increasing locomotor speed (p< 0.001). Correspondingly, HMP increased with faster locomotion (p= 0.001). SVS-CoP coherence depended on the gait cycle phase with two distinct peaks occurring at 25 …
In the European Social Fund (ESF)project "Profilgebundene-Wissenschecks 2.0", seven Brandenburg Universities and Colleges are working together on the implementation and further development of online tools for study orientation, study preparation and support. The work packages include the development of online subject quizzes(online self-assessments), in order to support prospective students to compare their individual knowledge levels with the knowledge required at the beginning of their studies. Depending on the results achieved, e-learning units are provided with the necessary subject-related knowledge.These unitscan be refreshed independently and the attendance of preliminary courses is recommended. The basis for the online assessments is a cross-university question exchange platform on which the affiliated universities sharethe developed questions and thereby establish a nationwide quality standard for self-assessments. The project partners at Brandenburg University of TechnologyCottbus -Senftenberg (BTU)are responsible fordeveloping the question exchange platform and for making the platform available to all partner universities. For this purpose, a concept was developed, whereinMoodle Learning Management Systems (LMS)is used as a basis and expandedto include functions for storing questions with associated metadata and search functions to search for questions with specific metadata. The concept of the cross-university question exchange platform is presented in this paper.
Objective: Uni- or bilateral vestibular hypofunction (VH) impairs balance and mobility, and may specifically lead to injury from falls and to disability. The extent of this problem in the general population is still unknown and most likely to be underestimated. Objective of this study was to determine the prevalence, determinants, and consequences of VH in the general population.
Methods: Data originates from the cross-sectional second follow-up (FF4) in 2013/14 of the KORA (Cooperative Health Research in the Region of Augsburg)-S4 study (1999–2001) from Southern Germany. This was a random sample of the target population consisting of all residents of the region aged 25–74 years in 1999. We included all participants who reported moderate or severe vertigo or dizziness during the last 12 months and a random sub-sample of participants representative for the general population without vertigo or dizziness during the last 12 months were tested. VH was assessed with the Video-Head Impulse Test (vHIT). Trained examiners applied high-acceleration, small-amplitude passive head rotations (“head impulses”) to the left and right in the plane of the horizontal semicircular canals while participants fixated a target straight ahead. During head impulses, head movements were measured with inertial sensors, eye movements with video-oculography (EyeSeeCam vHIT).
Results: A total of 2,279 participants were included (mean age 60.8 years, 51.6% female), 570 (25.0%) with moderate or severe vertigo or dizziness during the last 12 months. Of these, 450 were assessed with vHIT where 26 (5.8%) had unilateral VH, and 16 (3.6%) had bilateral VH. Likewise, 190 asymptomatic participants were tested. Of these 5 (2.6%) had unilateral VH, and 2 (1.1%) had bilateral VH. Prevalence of uni- or bilateral VH among tested symptomatic participants was 2.4% in those < 48 years, and 32.1% in individuals aged 79 and over. Age-adjusted prevalence was 6.7% (95% CI 4.8%; 8.6%). VH was associated with worse health, falls, hearing loss, hearing impairment, and ear pressure.
Conclusion: VH may affect between 53 and 95 million adults in Europe and the US. While not all affected persons will experience the full spectrum of symptoms and consequences, adequate diagnostic and therapeutic measures should become standard of care to decrease the burden of disease.
Objective To investigate long-term recovery of allocentric and egocentric spatial orientation as a sensitive marker for hippocampal and extrahippocampal network function in transient global amnesia (TGA).
Methods A group of 18 patients with TGA performed an established real-space navigation paradigm, requiring allo- and egocentric spatial orientation abilities, 3 days (postacute stage) and 3 months (follow-up) after symptom onset. Visual exploration behavior and navigation strategy were documented by a gaze-controlled, head-fixed camera. Allo- and egocentric spatial orientation performance was compared to that of 12 age-matched healthy controls. Navigation-induced brain activations were measured using [18F]-fluorodeoxyglucose-PET in a subgroup of 8 patients in the postacute stage and compared to those of the controls.
Results In the postacute stage, the patients navigated worse and had higher error rates than controls in allocentric (p = 0.002), but not in egocentric, route planning (p = 0.30), despite complete recovery of verbal (p = 0.58) and figural memory (p = 0.11). Until follow-up, allocentric navigation deficits improved, but higher error rates and reduced use of shortcuts persisted (p < 0.0001). Patients still exhibited relatively more fixations of unique landmarks during follow-up (p = 0.05). PET measurements during the postacute stage showed increased navigation-induced brain activations in the right hippocampus, bilateral retrosplenial, parietal, and mesiofrontal cortices, and cerebellar dentate nucleus in patients compared to controls (p < 0.005).
Conclusions Patients with TGA show selective and prolonged deficits of allocentric spatial orientation. Activations in right hippocampal and extrahippocampal hubs of the cerebral navigation network functionally substitute for the deficit in creating and updating the internal cognitive map in TGA.
Secondary Stroke Prevention With Ximelagatran Versus Warfarin in Patients With Atrial Fibrillation
(2007)
Concomitant microwave ablation for curative treatment of atrial fibrillation (AF) was performed in 18 patients with history of chronic atrial fibrillation and indication for open heart surgery, 11 patients with mitral valve replacement and 7 patients with coronary artery bypass grafting. There were no perioperative complications. During the postoperative period most of the patients had intermittent AF, they received low dose Sotalol therapy and electric cardio-versions. Up to now seven patients have reached follow-up day 90. One patient has persistent AF. Two patients had typical atrial flutter that was electrically converted to sinus rhythm (SR), isthmus ablation is planned. The other four patients have SR, one patient without cardioversions. These four patients show recovered atrial function with observed A-wave for transmitral flow. Under visual guidance the continuous atrial lesion lines could be induced effectively and safely by the intraoperative device Lynx.
Objectives: To determine the incidence of gentamicin vestibulotoxicity with current dosing regimens, and to evaluate the feasibility of routine video-oculography on all patients given gentamicin. Materials and methods: In this prospective incidence study serial horizontal vestibulo-ocular reflex (HVOR) gain measurements were recorded using video-oculography on adult inpatients receiving intravenous gentamicin. The primary outcome was the proportion of patients developing impairment of their HVOR gain. Results: After exclusions, 42 patients were included in the analysis. Three patients (7.1%) developed asymptomatic vestibulotoxicity, exact 95% confidence interval 1.5-19.5%. In two of these patients the deficit resolved within several hours. No patients developed symptomatic vestibulotoxicity. There was no evidence for a generalised reduction in group HVOR gain with time. HVOR gain was not associated with total gentamicin dose, dynamic visual acuity or subjective imbalance. Conclusions and significance: Gentamicin may cause reversible, asymptomatic vestibulotoxicity. Video-oculography may be useful to monitor for vestibulotoxicity in patients treated with gentamcin; however, testing all patients routinely may be challenging.
Treatment of Atrial Fibrillation in Open Heart Surgery. The Potential Role of Microwave Energy
(1999)
Sensor-based systems for diagnosis or therapy support of motor dysfunctions need methodologies of automatically stride detection from movement sequences. In this proposal, we developed a stride detection system for daily life use. We compared mostly used algorithms min–max patterns, dynamic time warping, convolutional neural networks (CNN), and automatic framing using two data sets of 32 healthy and 28 Parkinson’s disease (PD) persons. We developed an insole with force and IMU sensors to record the gait data. The PD patients carried out the standardized time up and go test, and the healthy persons a daily life activities test (walking, sitting, standing, ascending and descending stairs). As an automatically stride detection process for daily life use, we propose a first stride detection using automatic framing, and after normalization and resampling data a CNN is used. A F1-score of 0.938 (recall 0.968, precision 0.910) for time up and go test and of 0.944 (recall 0.992, precision 0.901) for daily life activities test were obtained for CNN. Compared to the other detection methods, up to 6% F-measure improvement was shown.
One of the biometric methods in authentication systems is the writer verification/identification using password handwriting. The main objective of this paper is to present a robust writer verification system by using cursive texts as well as block letter words. To evaluate the system, two datasets have been used. One of them is called Secure Password DB 150, which is composed of 150 users with 18 samples of single character words per user. Another dataset is public and called IAM online handwriting database, and it is composed of 220 users of cursive text samples. Each sample has been defined by a set of features, composed of 67 geometrical, statistical, and temporal features. In order to get more discriminative information, two feature reduction methods have been applied, Fisher Score and Info Gain Attribute Evaluation. Finally, the classification system has been implemented by hold-out cross validation and k-folds cross validation strategies for three different classifiers, K-NN, Naïve Bayes and Bayes Net classifiers. Besides, it has been applied for verification and identification approaches. The best results of 95.38% correct classification are achieved by using the k-nearest neighbor classifier for single character DB. A feature reduction by Info Gain Attribute Evaluation improves the results for Naïve Bayes Classifier to 98.34% for IAM online handwriting DB. It is concluded that the set of features and its reduction are a strong selection for the based-password handwritten writer identification in comparison with the state-of-the-art.
Programming is not complicated and yet many students do not pass the first hurdles. Software is logical, follows clear rules and mathematical laws. Any healthy person with basic literacy, numeracy and writing skills can learn it. Writing a book, painting pictures or other creative challenges are much harder. And yet many fail at
comparable competences. Teaching programming skills by listening and reading is not enough. Students need the process of trial and error in order to acquire the skills needed and should be able to learn by them. However, students should be able to work independently on a computer. The problem that the beginners are overwhelmed and the advanced are bored. This is the case especially in computer science. Despite the use of a comfortable Learning Management System (LMS), many tasks have been submitted to paper and PDF at our university so
far. Since the available question-types could not cover all possible complex tasks, it was difficult to inspire the lecturers for a complete digitization of their tasks. To be able to automatically evaluate even tasks in mathematics, computer science and related scientific disciplines two modules have been successfully evaluated
at our university. This paper presents the use of these Moodle modules STACK and VPL in selected courses in mathematics and computer science and how to randomize tasks. In these modules complex tasks are prepared in such a way that they are still solvable for the students and automatically evaluated by the system, thus could considerably facilitate the work of the lecturers and academic staff. On concrete examples possible solutions are shown.
We present a new method for detecting gait disorders according to their stadium using cluster methods for sensor data. 21 healthy and 18 Parkinson subjects performed the Time Up and Go test. The time series were segmented into separate steps. For the analysis the horizontal acceleration measured by a mobile sensor system was considered. We used Dynamic Time Warping and Hierarchical Custering to distinguish the stadiums. A specificity of 92% was achieved.