@article{WenningerMaierSchmidt2021, author = {Wenninger, Marc and Maier, Andreas and Schmidt, Jochen}, title = {DEDDIAG, a domestic electricity demand dataset of individual appliances in Germany}, series = {Scientific Data}, volume = {8}, journal = {Scientific Data}, number = {176}, pages = {15}, year = {2021}, abstract = {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.}, language = {en} } @inproceedings{BayerlWenningerSchmidtetal.2021, author = {Bayerl, Sebastian P. and Wenninger, Marc and Schmidt, Jochen and Wolff von Gudenberg, Alexander and Riedhammer, Korbinian}, title = {STAN: A stuttering therapy analysis helper}, series = {2021 IEEE Spoken Language Technology Workshop (SLT)}, booktitle = {2021 IEEE Spoken Language Technology Workshop (SLT)}, pages = {2}, year = {2021}, abstract = {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.}, language = {en} } @inproceedings{WenningerBayerlMaieretal.2021, author = {Wenninger, Marc and Bayerl, Sebastian P. and Maier, Andreas and Schmidt, Jochen}, title = {Recurrence Plot Spacial Pyramid Pooling Network for Appliance Identification in Non-Intrusive Load Monitoring}, series = {2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)}, booktitle = {2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)}, pages = {108 -- 115}, year = {2021}, abstract = {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.}, language = {en} } @article{NeumayerStecherGrimmetal.2023, author = {Neumayer, Martin and Stecher, Dominik and Grimm, Sebastian and Maier, Andreas and B{\"u}cker, Dominikus and Schmidt, Jochen}, title = {Fault and anomaly detection in district heating substations: A survey on methodology and data sets}, series = {Energy}, volume = {276}, journal = {Energy}, doi = {10.1016/j.energy.2023.127569}, pages = {127569}, year = {2023}, abstract = {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.}, language = {en} } @book{ErnstSchmidtBeneken2023, author = {Ernst, Hartmut and Schmidt, Jochen and Beneken, Gerd}, title = {Grundkurs Informatik: Grundlagen und Konzepte f{\"u}r die erfolgreiche IT-Praxis - Eine umfassende, praxisorientierte Einf{\"u}hrung}, edition = {8}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {9783658417789}, doi = {10.1007/978-3-658-41779-6}, publisher = {Technische Hochschule Rosenheim}, pages = {915}, year = {2023}, abstract = {Das Buch bietet eine umfassende und praxisorientierte Einf{\"u}hrung in die wesentlichen Grundlagen und Konzepte der Informatik. Es umfasst den Stoff, der typischerweise in den ersten Semestern eines Informatikstudiums vermittelt wird, vertieft Zusammenh{\"a}nge, die dar{\"u}ber hinausgehen und macht sie verst{\"a}ndlich. Die Themenauswahl orientiert sich an der langfristigen Relevanz f{\"u}r die praktische Anwendung. Praxisnah und aktuell werden die Inhalte f{\"u}r Studierende der Informatik und verwandter Studieng{\"a}nge sowie f{\"u}r im Beruf stehende Praktiker vermittelt.}, language = {de} } @book{Schmidt2023, author = {Schmidt, Jochen}, title = {Grundkurs Informatik - Das {\"U}bungsbuch: 163 Aufgaben mit L{\"o}sungen}, edition = {3}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3658434427}, doi = {10.1007/978-3-658-43443-4}, publisher = {Technische Hochschule Rosenheim}, pages = {216}, year = {2023}, abstract = {Das Buch richtet sich an Studierende der Informatik oder verwandter Studieng{\"a}nge und enth{\"a}lt {\"U}bungsaufgaben mit L{\"o}sungen aus Gebieten, die typischerweise in den ersten Semestern als Grundlagen behandelt werden. Ausgenommen ist der Bereich des Programmierens. Das Buch erg{\"a}nzt den Grundkurs Informatik mit {\"U}bungen zu ausgew{\"a}hlten Kapiteln, ist aber auch in Kombination mit anderen Lehrb{\"u}chern verwendbar.}, language = {de} } @article{StecherNeumayerRamachandranetal.2024, author = {Stecher, Dominik and Neumayer, Martin and Ramachandran, Adithya and Hort, Anastasia and Maier, Andreas and B{\"u}cker, Dominikus and Schmidt, Jochen}, title = {Creating a labelled district heating data set: From anomaly detection towards fault detection}, series = {Energy}, volume = {313}, journal = {Energy}, publisher = {Elsevier}, doi = {10.1016/j.energy.2024.134016}, pages = {134016}, year = {2024}, abstract = {For an efficient operation of district heating systems, being able to detect anomalies and faults at an early stage is highly desirable. Here, data-driven machine learning methods can be a cornerstone, particularly for fault detection in district heating substations, where the availability of heat meter data keeps increasing. However, the creation of data sets suitable for training such machine learning models poses challenges to researchers and practitioners alike. To address this problem, we propose a systematic and domain-specific process for data set creation for fault detection in the form of practical guidelines. This process concretizes the data science and data mining cross-industry standard CRISP-DM for the district heating domain and focuses on the process steps of goal definition, data acquisition and understanding, and data curation. We aim to enable researchers and practitioners to create data sets for fault detection in the district heating domain and therefore also enable the creation or improvement of machine learning models in this domain. In addition, we propose a minimum viable feature set for fault detection in district heating networks with the goal of enabling better cooperation between researchers and easier transfer of the resulting machine learning models, to better proliferate new progress in the field.}, language = {en} } @inproceedings{HambergerMurgulSchmidtetal.2025, author = {Hamberger, Anna and Murgul, Sebastian and Schmidt, Jochen and Heizmann, Michael}, title = {Fretting-Transformer: Encoder-Decoder Model for MIDI to Tablature Transcription}, series = {Proceedings of the 50th International Computer Music Conference 2025}, booktitle = {Proceedings of the 50th International Computer Music Conference 2025}, publisher = {The International Computer Music Association}, pages = {438 -- 445}, year = {2025}, abstract = {Music transcription plays a pivotal role in Music Information Retrieval (MIR), particularly for stringed instruments like the guitar, where symbolic music notations such as MIDI lack crucial playability information. This contribution introduces the Fretting-Transformer, an encoderdecoder model that utilizes a T5 transformer architecture to automate the transcription of MIDI sequences into guitar tablature. By framing the task as a symbolic translation problem, the model addresses key challenges, including string-fret ambiguity and physical playability. The proposed system leverages diverse datasets, including DadaGP, GuitarToday, and Leduc, with novel data pre-processing and tokenization strategies. We have developed metrics for tablature accuracy and playability to quantitatively evaluate the performance. The experimental results demonstrate that the Fretting-Transformer surpasses baseline methods like A* and commercial applications like Guitar Pro. The integration of context-sensitive processing and tuning/capo conditioning further enhances the model's performance, laying a robust foundation for future developments in automated guitar transcription.}, language = {en} } @article{StecherZiegltrumReiprichetal.2025, author = {Stecher, Dominik and Ziegltrum, Lukas and Reiprich, Paul and Fuchs, Christian and Maier, Andreas and Schmidt, Jochen}, title = {Neural network synthetic dataset generation for fault detection in district heating substations}, series = {Smart Energy}, volume = {20}, journal = {Smart Energy}, publisher = {Elsevier}, doi = {10.1016/j.segy.2025.100206}, pages = {100206}, year = {2025}, abstract = {District heating systems (DHS) play a vital role in sustainable heating solutions and the decarbonization of the energy sector. However, inefficiencies due to undetected faults in substations result in high return temperatures, increasing heat losses, and limiting the integration of renewable energy sources. The lack of publicly available labeled datasets poses a significant challenge for fault detection using supervised learning models. To address this issue, this study explores three machine learning-based synthetic data generation techniques - time series forecasting, generative adversarial networks (GANs), and fault signature transfer. These methods aim to increase publicly available data either by sharing the generating model or a synthetic dataset. The novelty lies in the combination of advanced supervised machine learning methods being applied to a large, fully labeled data set to create new, equally labeled data for publication, as, to our knowledge, no such dataset has been compiled before. We evaluate our methods on the first-of-its-kind ILSE dataset, which includes real-world smart meter data from 547 substations and 1,162 reviewed faults from a German DHS network, including detailed root cause information. Overall, time series forecasting achieves an MAPE of 3\% to 10\% for inlet and outlet temperature and 25\% to 40\% for heat load and flow rate, both of which are within year-to-year variance. For GANs, specifically TimeGAN, we found a discriminative score of about 0.10 compared to 0.24 in the original publication when tested on Energy benchmark data. Fault signature transfer has yet to yield usable results, most likely due to the high variance in the fault signatures, fault duration, and overlapping or multiple root causes. Finally, fault data in the synthetic data is not yet good enough for practical use, e.g. training a fault detector.}, language = {en} }