@article{KappattanavarHeckerMoontahaetal.2023, author = {Kappattanavar, Arpita Mallikarjuna and Hecker, Pascal and Moontaha, Sidratul and Steckhan, Nico and Arnrich, Bert}, title = {Food choices after cognitive load}, series = {Sensors}, volume = {23}, journal = {Sensors}, number = {14}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s23146597}, pages = {22}, year = {2023}, abstract = {Psychology and nutritional science research has highlighted the impact of negative emotions and cognitive load on calorie consumption behaviour using subjective questionnaires. Isolated studies in other domains objectively assess cognitive load without considering its effects on eating behaviour. This study aims to explore the potential for developing an integrated eating behaviour assistant system that incorporates cognitive load factors. Two experimental sessions were conducted using custom-developed experimentation software to induce different stimuli. During these sessions, we collected 30 h of physiological, food consumption, and affective states questionnaires data to automatically detect cognitive load and analyse its effect on food choice. Utilising grid search optimisation and leave-one-subject-out cross-validation, a support vector machine model achieved a mean classification accuracy of 85.12\% for the two cognitive load tasks using eight relevant features. Statistical analysis was performed on calorie consumption and questionnaire data. Furthermore, 75\% of the subjects with higher negative affect significantly increased consumption of specific foods after high-cognitive-load tasks. These findings offer insights into the intricate relationship between cognitive load, affective states, and food choice, paving the way for an eating behaviour assistant system to manage food choices during cognitive load. Future research should enhance system capabilities and explore real-world applications.}, language = {en} } @article{HollensteinTrondlePlomeckaetal.2023, author = {Hollenstein, Nora and Trondle, Marius and Plomecka, Martyna and Kiegeland, Samuel and Ozyurt, Yilmazcan and J{\"a}ger, Lena Ann and Langer, Nicolas}, title = {The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data}, series = {Frontiers in psychology}, volume = {13}, journal = {Frontiers in psychology}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {1664-1078}, doi = {10.3389/fpsyg.2022.1028824}, pages = {20}, year = {2023}, abstract = {We present a new machine learning benchmark for reading task classification with the goal of advancing EEG and eye-tracking research at the intersection between computational language processing and cognitive neuroscience. The benchmark task consists of a cross-subject classification to distinguish between two reading paradigms: normal reading and task-specific reading. The data for the benchmark is based on the Zurich Cognitive Language Processing Corpus (ZuCo 2.0), which provides simultaneous eye-tracking and EEG signals from natural reading of English sentences. The training dataset is publicly available, and we present a newly recorded hidden testset. We provide multiple solid baseline methods for this task and discuss future improvements. We release our code and provide an easy-to-use interface to evaluate new approaches with an accompanying public leaderboard: .}, language = {en} } @article{RossoNendelGilardietal.2022, author = {Rosso, Pablo and Nendel, Claas and Gilardi, Nicolas and Udroiu, Cosmin and Chlebowski, Florent}, title = {Processing of remote sensing information to retrieve leaf area index in barley}, series = {Precision agriculture}, volume = {23}, journal = {Precision agriculture}, number = {4}, publisher = {Springer}, address = {Dordrecht}, issn = {1385-2256}, doi = {10.1007/s11119-022-09893-4}, pages = {1449 -- 1472}, year = {2022}, abstract = {Leaf area index (LAI) is a key variable in understanding and modeling crop-environment interactions. With the advent of increasingly higher spatial resolution satellites and sensors mounted on remotely piloted aircrafts (RPAs), the use of remote sensing in precision agriculture is becoming more common. Since also the availability of methods to retrieve LAI from image data have also drastically expanded, it is necessary to test simultaneously as many methods as possible to understand the advantages and disadvantages of each approach. Ground-based LAI data from three years of barley experiments were related to remote sensing information using vegetation indices (VI), machine learning (ML) and radiative transfer models (RTM), to assess the relative accuracy and efficacy of these methods. The optimized soil adjusted vegetation index and a modified version of the Weighted Difference Vegetation Index performed slightly better than any other retrieval method. However, all methods yielded coefficients of determination of around 0.7 to 0.9. The best performing machine learning algorithms achieved higher accuracies when four Sentinel-2 bands instead of 12 were used. Also, the good performance of VIs and the satisfactory performance of the 4-band RTM, strongly support the synergistic use of satellites and RPAs in precision agriculture. One of the methods used, Sen2-Agri, an open source ML-RTM-based operational system, was also able to accurately retrieve LAI, although it is restricted to Sentinel-2 and Landsat data. This study shows the benefits of testing simultaneously a broad range of retrieval methods to monitor crops for precision agriculture.}, language = {en} } @article{BaumgartBoosEckstein2023, author = {Baumgart, Lene and Boos, Pauline and Eckstein, Bernd}, title = {Datafication and algorithmic contingency}, series = {Work organisation, labour \& globalisation}, volume = {17}, journal = {Work organisation, labour \& globalisation}, number = {1}, publisher = {Pluto Journals}, address = {London}, issn = {1745-641X}, doi = {10.13169/workorgalaboglob.17.1.0061}, pages = {61 -- 73}, year = {2023}, abstract = {In the context of persistent images of self-perpetuated technologies, we discuss the interplay of digital technologies and organisational dynamics against the backdrop of systems theory. Building on the case of an international corporation that, during an agile reorganisation, introduced an AI-based personnel management platform, we show how technical systems produce a form of algorithmic contingency that subsequently leads to the emergence of formal and informal interaction systems. Using the concept of datafication, we explain how these interactions are barriers to the self-perpetuation of data-based decision-making, making it possible to take into consideration further decision factors and complementing the output of the platform. The research was carried out within the scope of the research project 'Organisational Implications of Digitalisation: The Development of (Post-)Bureaucratic Organisational Structures in the Context of Digital Transformation' funded by the German Research Foundation (DFG).}, language = {en} } @techreport{AndresBruttel2024, type = {Working Paper}, author = {Andres, Maximilian and Bruttel, Lisa}, title = {Communicating Cartel Intentions}, series = {CEPA Discussion Papers}, journal = {CEPA Discussion Papers}, number = {77}, issn = {2628-653X}, doi = {10.25932/publishup-63846}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-638469}, pages = {36}, year = {2024}, abstract = {While the economic harm of cartels is caused by their price-increasing effect, sanctioning by courts rather targets at the underlying process of firms reaching a price-fixing agreement. This paper provides experimental evidence on the question whether such sanctioning meets the economic target, i.e., whether evidence of a collusive meeting of the firms and of the content of their communication reliably predicts subsequent prices. We find that already the mere mutual agreement to meet predicts a strong increase in prices. Conversely, express distancing from communication completely nullifies its otherwise price-increasing effect. Using machine learning, we show that communication only increases prices if it is very explicit about how the cartel plans to behave.}, language = {en} } @misc{PanzerBenderGronau2021, author = {Panzer, Marcel and Bender, Benedict and Gronau, Norbert}, title = {Deep reinforcement learning in production planning and control}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, issn = {2701-6277}, doi = {10.25932/publishup-60572}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-605722}, pages = {13}, year = {2021}, abstract = {Increasingly fast development cycles and individualized products pose major challenges for today's smart production systems in times of industry 4.0. The systems must be flexible and continuously adapt to changing conditions while still guaranteeing high throughputs and robustness against external disruptions. Deep reinforcement learning (RL) algorithms, which already reached impressive success with Google DeepMind's AlphaGo, are increasingly transferred to production systems to meet related requirements. Unlike supervised and unsupervised machine learning techniques, deep RL algorithms learn based on recently collected sensorand process-data in direct interaction with the environment and are able to perform decisions in real-time. As such, deep RL algorithms seem promising given their potential to provide decision support in complex environments, as production systems, and simultaneously adapt to changing circumstances. While different use-cases for deep RL emerged, a structured overview and integration of findings on their application are missing. To address this gap, this contribution provides a systematic literature review of existing deep RL applications in the field of production planning and control as well as production logistics. From a performance perspective, it became evident that deep RL can beat heuristics significantly in their overall performance and provides superior solutions to various industrial use-cases. Nevertheless, safety and reliability concerns must be overcome before the widespread use of deep RL is possible which presumes more intensive testing of deep RL in real world applications besides the already ongoing intensive simulations.}, language = {en} } @misc{PanzerBenderGronau2022, author = {Panzer, Marcel and Bender, Benedict and Gronau, Norbert}, title = {Neural agent-based production planning and control}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe}, issn = {1867-5808}, doi = {10.25932/publishup-60477}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604777}, pages = {26}, year = {2022}, abstract = {Nowadays, production planning and control must cope with mass customization, increased fluctuations in demand, and high competition pressures. Despite prevailing market risks, planning accuracy and increased adaptability in the event of disruptions or failures must be ensured, while simultaneously optimizing key process indicators. To manage that complex task, neural networks that can process large quantities of high-dimensional data in real time have been widely adopted in recent years. Although these are already extensively deployed in production systems, a systematic review of applications and implemented agent embeddings and architectures has not yet been conducted. The main contribution of this paper is to provide researchers and practitioners with an overview of applications and applied embeddings and to motivate further research in neural agent-based production. Findings indicate that neural agents are not only deployed in diverse applications, but are also increasingly implemented in multi-agent environments or in combination with conventional methods — leveraging performances compared to benchmarks and reducing dependence on human experience. This not only implies a more sophisticated focus on distributed production resources, but also broadening the perspective from a local to a global scale. Nevertheless, future research must further increase scalability and reproducibility to guarantee a simplified transfer of results to reality.}, language = {en} } @article{PanzerBenderGronau2022, author = {Panzer, Marcel and Bender, Benedict and Gronau, Norbert}, title = {Neural agent-based production planning and control}, series = {Journal of Manufacturing Systems}, volume = {65}, journal = {Journal of Manufacturing Systems}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0278-6125}, doi = {10.1016/j.jmsy.2022.10.019}, pages = {743 -- 766}, year = {2022}, abstract = {Nowadays, production planning and control must cope with mass customization, increased fluctuations in demand, and high competition pressures. Despite prevailing market risks, planning accuracy and increased adaptability in the event of disruptions or failures must be ensured, while simultaneously optimizing key process indicators. To manage that complex task, neural networks that can process large quantities of high-dimensional data in real time have been widely adopted in recent years. Although these are already extensively deployed in production systems, a systematic review of applications and implemented agent embeddings and architectures has not yet been conducted. The main contribution of this paper is to provide researchers and practitioners with an overview of applications and applied embeddings and to motivate further research in neural agent-based production. Findings indicate that neural agents are not only deployed in diverse applications, but are also increasingly implemented in multi-agent environments or in combination with conventional methods — leveraging performances compared to benchmarks and reducing dependence on human experience. This not only implies a more sophisticated focus on distributed production resources, but also broadening the perspective from a local to a global scale. Nevertheless, future research must further increase scalability and reproducibility to guarantee a simplified transfer of results to reality.}, language = {en} } @phdthesis{Lilienkamp2024, author = {Lilienkamp, Henning}, title = {Enhanced computational approaches for data-driven characterization of earthquake ground motion and rapid earthquake impact assessment}, doi = {10.25932/publishup-63195}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-631954}, school = {Universit{\"a}t Potsdam}, pages = {x, 145}, year = {2024}, abstract = {Rapidly growing seismic and macroseismic databases and simplified access to advanced machine learning methods have in recent years opened up vast opportunities to address challenges in engineering and strong motion seismology from novel, datacentric perspectives. In this thesis, I explore the opportunities of such perspectives for the tasks of ground motion modeling and rapid earthquake impact assessment, tasks with major implications for long-term earthquake disaster mitigation. In my first study, I utilize the rich strong motion database from the Kanto basin, Japan, and apply the U-Net artificial neural network architecture to develop a deep learning based ground motion model. The operational prototype provides statistical estimates of expected ground shaking, given descriptions of a specific earthquake source, wave propagation paths, and geophysical site conditions. The U-Net interprets ground motion data in its spatial context, potentially taking into account, for example, the geological properties in the vicinity of observation sites. Predictions of ground motion intensity are thereby calibrated to individual observation sites and earthquake locations. The second study addresses the explicit incorporation of rupture forward directivity into ground motion modeling. Incorporation of this phenomenon, causing strong, pulse like ground shaking in the vicinity of earthquake sources, is usually associated with an intolerable increase in computational demand during probabilistic seismic hazard analysis (PSHA) calculations. I suggest an approach in which I utilize an artificial neural network to efficiently approximate the average, directivity-related adjustment to ground motion predictions for earthquake ruptures from the 2022 New Zealand National Seismic Hazard Model. The practical implementation in an actual PSHA calculation demonstrates the efficiency and operational readiness of my model. In a follow-up study, I present a proof of concept for an alternative strategy in which I target the generalizing applicability to ruptures other than those from the New Zealand National Seismic Hazard Model. In the third study, I address the usability of pseudo-intensity reports obtained from macroseismic observations by non-expert citizens for rapid impact assessment. I demonstrate that the statistical properties of pseudo-intensity collections describing the intensity of shaking are correlated with the societal impact of earthquakes. In a second step, I develop a probabilistic model that, within minutes of an event, quantifies the probability of an earthquake to cause considerable societal impact. Under certain conditions, such a quick and preliminary method might be useful to support decision makers in their efforts to organize auxiliary measures for earthquake disaster response while results from more elaborate impact assessment frameworks are not yet available. The application of machine learning methods to datasets that only partially reveal characteristics of Big Data, qualify the majority of results obtained in this thesis as explorative insights rather than ready-to-use solutions to real world problems. The practical usefulness of this work will be better assessed in the future by applying the approaches developed to growing and increasingly complex data sets.}, language = {en} } @article{HampfNendelStreyetal.2021, author = {Hampf, Anna and Nendel, Claas and Strey, Simone and Strey, Robert}, title = {Biotic yield losses in the Southern Amazon, Brazil}, series = {Frontiers in plant science : FPLS}, volume = {12}, journal = {Frontiers in plant science : FPLS}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {1664-462X}, doi = {10.3389/fpls.2021.621168}, pages = {16}, year = {2021}, abstract = {Pathogens and animal pests (P\&A) are a major threat to global food security as they directly affect the quantity and quality of food. The Southern Amazon, Brazil's largest domestic region for soybean, maize and cotton production, is particularly vulnerable to the outbreak of P\&A due to its (sub)tropical climate and intensive farming systems. However, little is known about the spatial distribution of P\&A and the related yield losses. Machine learning approaches for the automated recognition of plant diseases can help to overcome this research gap. The main objectives of this study are to (1) evaluate the performance of Convolutional Neural Networks (ConvNets) in classifying P\&A, (2) map the spatial distribution of P\&A in the Southern Amazon, and (3) quantify perceived yield and economic losses for the main soybean and maize P\&A. The objectives were addressed by making use of data collected with the smartphone application Plantix. The core of the app's functioning is the automated recognition of plant diseases via ConvNets. Data on expected yield losses were gathered through a short survey included in an "expert" version of the application, which was distributed among agronomists. Between 2016 and 2020, Plantix users collected approximately 78,000 georeferenced P\&A images in the Southern Amazon. The study results indicate a high performance of the trained ConvNets in classifying 420 different crop-disease combinations. Spatial distribution maps and expert-based yield loss estimates indicate that maize rust, bacterial stalk rot and the fall armyworm are among the most severe maize P\&A, whereas soybean is mainly affected by P\&A like anthracnose, downy mildew, frogeye leaf spot, stink bugs and brown spot. Perceived soybean and maize yield losses amount to 12 and 16\%, respectively, resulting in annual yield losses of approximately 3.75 million tonnes for each crop and economic losses of US\$2 billion for both crops together. The high level of accuracy of the trained ConvNets, when paired with widespread use from following a citizen-science approach, results in a data source that will shed new light on yield loss estimates, e.g., for the analysis of yield gaps and the development of measures to minimise them.}, language = {en} } @article{AndresBruttelFriedrichsen2022, author = {Andres, Maximilian and Bruttel, Lisa and Friedrichsen, Jana}, title = {How communication makes the difference between a cartel and tacit collusion}, series = {European economic review}, volume = {152}, journal = {European economic review}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0014-2921}, doi = {10.1016/j.euroecorev.2022.104331}, pages = {1 -- 18}, year = {2022}, abstract = {This paper sheds new light on the role of communication for cartel formation. Using machine learning to evaluate free-form chat communication among firms in a laboratory experiment, we identify typical communication patterns for both explicit cartel formation and indirect attempts to collude tacitly. We document that firms are less likely to communicate explicitly about price fixing and more likely to use indirect messages when sanctioning institutions are present. This effect of sanctions on communication reinforces the direct cartel-deterring effect of sanctions as collusion is more difficult to reach and sustain without an explicit agreement. Indirect messages have no, or even a negative, effect on prices.}, language = {en} } @article{ChenLangeAndjelkovicetal.2022, author = {Chen, Junchao and Lange, Thomas and Andjelkovic, Marko and Simevski, Aleksandar and Lu, Li and Krstić, Miloš}, title = {Solar particle event and single event upset prediction from SRAM-based monitor and supervised machine learning}, series = {IEEE transactions on emerging topics in computing / IEEE Computer Society, Institute of Electrical and Electronics Engineers}, volume = {10}, journal = {IEEE transactions on emerging topics in computing / IEEE Computer Society, Institute of Electrical and Electronics Engineers}, number = {2}, publisher = {Institute of Electrical and Electronics Engineers}, address = {[New York, NY]}, issn = {2168-6750}, doi = {10.1109/TETC.2022.3147376}, pages = {564 -- 580}, year = {2022}, abstract = {The intensity of cosmic radiation may differ over five orders of magnitude within a few hours or days during the Solar Particle Events (SPEs), thus increasing for several orders of magnitude the probability of Single Event Upsets (SEUs) in space-borne electronic systems. Therefore, it is vital to enable the early detection of the SEU rate changes in order to ensure timely activation of dynamic radiation hardening measures. In this paper, an embedded approach for the prediction of SPEs and SRAM SEU rate is presented. The proposed solution combines the real-time SRAM-based SEU monitor, the offline-trained machine learning model and online learning algorithm for the prediction. With respect to the state-of-the-art, our solution brings the following benefits: (1) Use of existing on-chip data storage SRAM as a particle detector, thus minimizing the hardware and power overhead, (2) Prediction of SRAM SEU rate one hour in advance, with the fine-grained hourly tracking of SEU variations during SPEs as well as under normal conditions, (3) Online optimization of the prediction model for enhancing the prediction accuracy during run-time, (4) Negligible cost of hardware accelerator design for the implementation of selected machine learning model and online learning algorithm. The proposed design is intended for a highly dependable and self-adaptive multiprocessing system employed in space applications, allowing to trigger the radiation mitigation mechanisms before the onset of high radiation levels.}, language = {en} } @article{GhafarianWielandLuettschwageretal.2022, author = {Ghafarian, Fatemeh and Wieland, Ralf and L{\"u}ttschwager, Dietmar and Nendel, Claas}, title = {Application of extreme gradient boosting and Shapley Additive explanations to predict temperature regimes inside forests from standard open-field meteorological data}, series = {Environmental modelling \& software with environment data news}, volume = {156}, journal = {Environmental modelling \& software with environment data news}, publisher = {Elsevier}, address = {Oxford}, issn = {1364-8152}, doi = {10.1016/j.envsoft.2022.105466}, pages = {11}, year = {2022}, abstract = {Forest microclimate can buffer biotic responses to summer heat waves, which are expected to become more extreme under climate warming. Prediction of forest microclimate is limited because meteorological observation standards seldom include situations inside forests. We use eXtreme Gradient Boosting - a Machine Learning technique - to predict the microclimate of forest sites in Brandenburg, Germany, using seasonal data comprising weather features. The analysis was amended by applying a SHapley Additive explanation to show the interaction effect of variables and individualised feature attributions. We evaluate model performance in comparison to artificial neural networks, random forest, support vector machine, and multi-linear regression. After implementing a feature selection, an ensemble approach was applied to combine individual models for each forest and improve robustness over a given single prediction model. The resulting model can be applied to translate climate change scenarios into temperatures inside forests to assess temperature-related ecosystem services provided by forests.}, language = {en} } @techreport{Andres2024, type = {Working Paper}, author = {Andres, Maximilian}, title = {Equilibrium selection in infinitely repeated games with communication}, series = {CEPA Discussion Papers}, journal = {CEPA Discussion Papers}, number = {75}, issn = {2628-653X}, doi = {10.25932/publishup-63180}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-631800}, pages = {38}, year = {2024}, abstract = {The present paper proposes a novel approach for equilibrium selection in the infinitely repeated prisoner's dilemma where players can communicate before choosing their strategies. This approach yields a critical discount factor that makes different predictions for cooperation than the usually considered sub-game perfect or risk dominance critical discount factors. In laboratory experiments, we find that our factor is useful for predicting cooperation. For payoff changes where the usually considered factors and our factor make different predictions, the observed cooperation is consistent with the predictions based on our factor.}, language = {en} } @article{KuehnHainzlDahmetal.2022, author = {K{\"u}hn, Daniela and Hainzl, Sebastian and Dahm, Torsten and Richter, Gudrun and Vera Rodriguez, Ismael}, title = {A review of source models to further the understanding of the seismicity of the Groningen field}, series = {Netherlands journal of geosciences : NJG}, volume = {101}, journal = {Netherlands journal of geosciences : NJG}, publisher = {Cambridge Univ. Press}, address = {Cambridge}, issn = {0016-7746}, doi = {10.1017/njg.2022.7}, pages = {12}, year = {2022}, abstract = {The occurrence of felt earthquakes due to gas production in Groningen has initiated numerous studies and model attempts to understand and quantify induced seismicity in this region. The whole bandwidth of available models spans the range from fully deterministic models to purely empirical and stochastic models. In this article, we summarise the most important model approaches, describing their main achievements and limitations. In addition, we discuss remaining open questions and potential future directions of development.}, language = {en} } @article{WilkschAbramova2023, author = {Wilksch, Moritz and Abramova, Olga}, title = {PyFin-sentiment}, series = {International journal of information management data insights}, volume = {3}, journal = {International journal of information management data insights}, number = {1}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2667-0968}, doi = {10.1016/j.jjimei.2023.100171}, pages = {10}, year = {2023}, abstract = {Responding to the poor performance of generic automated sentiment analysis solutions on domain-specific texts, we collect a dataset of 10,000 tweets discussing the topics of finance and investing. We manually assign each tweet its market sentiment, i.e., the investor's anticipation of a stock's future return. Using this data, we show that all existing sentiment models trained on adjacent domains struggle with accurate market sentiment analysis due to the task's specialized vocabulary. Consequently, we design, train, and deploy our own sentiment model. It outperforms all previous models (VADER, NTUSD-Fin, FinBERT, TwitterRoBERTa) when evaluated on Twitter posts. On posts from a different platform, our model performs on par with BERT-based large language models. We achieve this result at a fraction of the training and inference costs due to the model's simple design. We publish the artifact as a python library to facilitate its use by future researchers and practitioners.}, language = {en} } @article{BrandesSicksBerger2021, author = {Brandes, Stefanie and Sicks, Florian and Berger, Anne}, title = {Behaviour classification on giraffes (Giraffa camelopardalis) using machine learning algorithms on triaxial acceleration data of two commonly used GPS devices and its possible application for their management and conservation}, series = {Sensors}, volume = {21}, journal = {Sensors}, number = {6}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s21062229}, pages = {22}, year = {2021}, abstract = {Averting today's loss of biodiversity and ecosystem services can be achieved through conservation efforts, especially of keystone species. Giraffes (Giraffa camelopardalis) play an important role in sustaining Africa's ecosystems, but are 'vulnerable' according to the IUCN Red List since 2016. Monitoring an animal's behavior in the wild helps to develop and assess their conservation management. One mechanism for remote tracking of wildlife behavior is to attach accelerometers to animals to record their body movement. We tested two different commercially available high-resolution accelerometers, e-obs and Africa Wildlife Tracking (AWT), attached to the top of the heads of three captive giraffes and analyzed the accuracy of automatic behavior classifications, focused on the Random Forests algorithm. For both accelerometers, behaviors of lower variety in head and neck movements could be better predicted (i.e., feeding above eye level, mean prediction accuracy e-obs/AWT: 97.6\%/99.7\%; drinking: 96.7\%/97.0\%) than those with a higher variety of body postures (such as standing: 90.7-91.0\%/75.2-76.7\%; rumination: 89.6-91.6\%/53.5-86.5\%). Nonetheless both devices come with limitations and especially the AWT needs technological adaptations before applying it on animals in the wild. Nevertheless, looking at the prediction results, both are promising accelerometers for behavioral classification of giraffes. Therefore, these devices when applied to free-ranging animals, in combination with GPS tracking, can contribute greatly to the conservation of giraffes.}, language = {en} } @article{AdnanSrsicVenticichetal.2020, author = {Adnan, Hassan Sami and Srsic, Amanda and Venticich, Pete Milos and Townend, David M.R.}, title = {Using AI for mental health analysis and prediction in school surveys}, series = {European journal of public health}, volume = {30}, journal = {European journal of public health}, publisher = {Oxford Univ. Press}, address = {Oxford [u.a.]}, issn = {1101-1262}, doi = {10.1093/eurpub/ckaa165.336}, pages = {V125 -- V125}, year = {2020}, abstract = {Background: Childhood and adolescence are critical stages of life for mental health and well-being. Schools are a key setting for mental health promotion and illness prevention. One in five children and adolescents have a mental disorder, about half of mental disorders beginning before the age of 14. Beneficial and explainable artificial intelligence can replace current paper- based and online approaches to school mental health surveys. This can enhance data acquisition, interoperability, data driven analysis, trust and compliance. This paper presents a model for using chatbots for non-obtrusive data collection and supervised machine learning models for data analysis; and discusses ethical considerations pertaining to the use of these models. Methods: For data acquisition, the proposed model uses chatbots which interact with students. The conversation log acts as the source of raw data for the machine learning. Pre-processing of the data is automated by filtering for keywords and phrases. Existing survey results, obtained through current paper-based data collection methods, are evaluated by domain experts (health professionals). These can be used to create a test dataset to validate the machine learning models. Supervised learning can then be deployed to classify specific behaviour and mental health patterns. Results: We present a model that can be used to improve upon current paper-based data collection and manual data analysis methods. An open-source GitHub repository contains necessary tools and components of this model. Privacy is respected through rigorous observance of confidentiality and data protection requirements. Critical reflection on these ethics and law aspects is included in the project. Conclusions: This model strengthens mental health surveillance in schools. The same tools and components could be applied to other public health data. Future extensions of this model could also incorporate unsupervised learning to find clusters and patterns of unknown effects.}, language = {en} } @article{WulffMientusNowaketal.2023, author = {Wulff, Peter and Mientus, Lukas and Nowak, Anna and Borowski, Andreas}, title = {KI-basierte Auswertung von schriftlichen Unterrichtsreflexionen im Fach Physik und automatisierte R{\"u}ckmeldung}, series = {PSI-Potsdam: Ergebnisbericht zu den Aktivit{\"a}ten im Rahmen der Qualit{\"a}tsoffensive Lehrerbildung (2019-2023) (Potsdamer Beitr{\"a}ge zur Lehrerbildung und Bildungsforschung ; 3)}, journal = {PSI-Potsdam: Ergebnisbericht zu den Aktivit{\"a}ten im Rahmen der Qualit{\"a}tsoffensive Lehrerbildung (2019-2023) (Potsdamer Beitr{\"a}ge zur Lehrerbildung und Bildungsforschung ; 3)}, number = {3}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-568-2}, issn = {2626-3556}, doi = {10.25932/publishup-61636}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-616363}, pages = {103 -- 115}, year = {2023}, abstract = {F{\"u}r die Entwicklung professioneller Handlungskompetenzen angehender Lehrkr{\"a}fte stellt die Unterrichtsreflexion ein wichtiges Instrument dar, um Theoriewissen und Praxiserfahrungen in Beziehung zu setzen. Die Auswertung von Unterrichtsreflexionen und eine entsprechende R{\"u}ckmeldung stellt Forschende und Dozierende allerdings vor praktische wie theoretische Herausforderungen. Im Kontext der Forschung zu K{\"u}nstlicher Intelligenz (KI) entwickelte Methoden bieten hier neue Potenziale. Der Beitrag stellt {\"u}berblicksartig zwei Teilstudien vor, die mit Hilfe von KI-Methoden wie dem maschinellen Lernen untersuchen, inwieweit eine Auswertung von Unterrichtsreflexionen angehender Physiklehrkr{\"a}fte auf Basis eines theoretisch abgeleiteten Reflexionsmodells und die automatisierte R{\"u}ckmeldung hierzu m{\"o}glich sind. Dabei wurden unterschiedliche Ans{\"a}tze des maschinellen Lernens verwendet, um modellbasierte Klassifikation und Exploration von Themen in Unterrichtsreflexionen umzusetzen. Die Genauigkeit der Ergebnisse wurde vor allem durch sog. Große Sprachmodelle gesteigert, die auch den Transfer auf andere Standorte und F{\"a}cher erm{\"o}glichen. F{\"u}r die fachdidaktische Forschung bedeuten sie jedoch wiederum neue Herausforderungen, wie etwa systematische Verzerrungen und Intransparenz von Entscheidungen. Dennoch empfehlen wir, die Potenziale der KI-basierten Methoden gr{\"u}ndlicher zu erforschen und konsequent in der Praxis (etwa in Form von Webanwendungen) zu implementieren.}, language = {de} } @phdthesis{Najafi2023, author = {Najafi, Pejman}, title = {Leveraging data science \& engineering for advanced security operations}, doi = {10.25932/publishup-61225}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-612257}, school = {Universit{\"a}t Potsdam}, pages = {xix, 180}, year = {2023}, abstract = {The Security Operations Center (SOC) represents a specialized unit responsible for managing security within enterprises. To aid in its responsibilities, the SOC relies heavily on a Security Information and Event Management (SIEM) system that functions as a centralized repository for all security-related data, providing a comprehensive view of the organization's security posture. Due to the ability to offer such insights, SIEMS are considered indispensable tools facilitating SOC functions, such as monitoring, threat detection, and incident response. Despite advancements in big data architectures and analytics, most SIEMs fall short of keeping pace. Architecturally, they function merely as log search engines, lacking the support for distributed large-scale analytics. Analytically, they rely on rule-based correlation, neglecting the adoption of more advanced data science and machine learning techniques. This thesis first proposes a blueprint for next-generation SIEM systems that emphasize distributed processing and multi-layered storage to enable data mining at a big data scale. Next, with the architectural support, it introduces two data mining approaches for advanced threat detection as part of SOC operations. First, a novel graph mining technique that formulates threat detection within the SIEM system as a large-scale graph mining and inference problem, built on the principles of guilt-by-association and exempt-by-reputation. The approach entails the construction of a Heterogeneous Information Network (HIN) that models shared characteristics and associations among entities extracted from SIEM-related events/logs. Thereon, a novel graph-based inference algorithm is used to infer a node's maliciousness score based on its associations with other entities in the HIN. Second, an innovative outlier detection technique that imitates a SOC analyst's reasoning process to find anomalies/outliers. The approach emphasizes explainability and simplicity, achieved by combining the output of simple context-aware univariate submodels that calculate an outlier score for each entry. Both approaches were tested in academic and real-world settings, demonstrating high performance when compared to other algorithms as well as practicality alongside a large enterprise's SIEM system. This thesis establishes the foundation for next-generation SIEM systems that can enhance today's SOCs and facilitate the transition from human-centric to data-driven security operations.}, language = {en} }