Description:

The aim of this seminar is to identify and categorize challenges when developing systems of systems for the smart city.

• You perform a literature survey into further relevant works (beyond the literature provided)
• You identify what typifies a System of Systems in the context of a smart city according to the literature
• You distill the challenges described in the literature and categorize them in a logical structure

Literatur : (will be provided by supervisor)

Betreuer: Sarah Brandt

Description :

The world's population is growing steadily - in contrast to the arable land available for agriculture. Farmers face the challenge of having to increase their yields while personnel are in short supply. Digitalization promises to assist farmers in this endeavor.

Robotics, in particular, can help automate physically demanding tasks and increase productivity. The goal of this seminar paper is to provide an overview of field robots already in use or currently being researched. As part of a literature search, these are to be surveyed, classified and an overview created.

Literatur : (will be provided by supervisor)

Betreuer: Felix Möhrle

Description :

The world's population is growing steadily - in contrast to the arable land available for agriculture. Farmers face the challenge of having to increase their yields while maintaining quality. At the same time, calls for sustainability and the preservation of biodiversity are growing louder. Digitalization offers the potential to support farmers in this endeavor.

The digital twin paradigm is a promising enabling technology characterized by seamless integration between the real and digital worlds. The goal of this seminar paper is to explore applications of the digital twin paradigm in agriculture. In the context of a literature review, different use cases are to be collected, classified and an overview is to be created.

Literature :

1. Angin, Pelin, et al. "AgriLoRa: a digital twin framework for smart agriculture." J. Wirel. Mob. Networks Ubiquitous Comput. Dependable Appl. 11.4 (2020): 77-96.
2. Alves, Rafael Gomes, et al. "A digital twin for smart farming." 2019 IEEE Global Humanitarian Technology Conference (GHTC). IEEE, 2019.
3. Pylianidis, Christos, Sjoukje Osinga, and Ioannis N. Athanasiadis. "Introducing digital twins to agriculture." Computers and Electronics in Agriculture 184 (2021): 105942.Angin, Pelin, et al. "AgriLoRa: a digital twin framework for smart agriculture." J. Wirel. Mob. Networks Ubiquitous Comput. Dependable Appl. 11.4 (2020): 77-96.

Supervisor: Felix Möhrle

Description :

Causal Structure Learning and Causal Inference

Causal inference methods (e.g., do-calculus (Pearl 2019)) can be used first to determine whether a causal effect can be calculated from observational data (identification), and then to estimate treatment effects. These methods are based on a graphical model (Bayesian Causal Networks) describing a potential cause-and-effect network that must either be derived from domain knowledge, or automatically extracted from data (causal structure learning).

Application in Software Engineering.

Improving the quality of software components requires to understand causal relationships. In this seminar the students should present an overview of application of causal inference techniques to software engineering.

Literature :

1. Pearl, J. 2019. The seven tools of causal inference, with reflections on machine learning. In Commun. ACM 62 (3), pp. 54–60. DOI: 10.1145/3241036.
2. Kucuk, Y., Henderson, T.A.D., Podgurski, A. 2021. Improving fault localization by integrating value and predicate based causal inference techniques. Proceedings - International Conference on Software Engineering, pp. 649-660. DOI: 10.1109/ICSE43902.2021.00066
3. Gössler, G., Stefani, J.-B. 2020. Causality analysis and fault ascription in component-based systemsTheoretical Computer Science, 837, pp. 158-180. DOI: 10.1016/j.tcs.2020.06.010.
4. Hira, A., Boehm, B., Stoddard, R., Konrad, M. 2018. Preliminary causal discovery results with software effort estimation data. ACM International Conference Proceeding Series, art. no. a6. DOI: 10.1145/3172871.3172876.
5. Kazman, R., Stoddard, R., Danks, D., Cai, Y. 2017. Causal modeling, discovery, & inference for software engineering. Proceedings - 2017 IEEE/ACM 39th International Conference on Software Engineering Companion, ICSE-C 2017, art. no. 7965293, pp. 172-174. DOI: 10.1109/ICSE-C.2017.138.
6. Lehtinen, T.O.A., Mäntylä, M.V., Vanhanen, J., Itkonen, J., Lassenius, C. 2014. Perceived causes of software project failures - An analysis of their relationships. Information and Software Technology, 56 (6), pp. 623-643. DOI: 10.1016/j.infsof.2014.01.015.

Supervisor: Dr. Julien Siebert

Description :

The use of digital technologies in farming offers many benefits. Farm management information systems (FMIS) are a digital technology that helps farmers to collect, manage, and interpret their data. However, the low number of FMIS users does not reflect this. Therefore, it is important to evaluate the reasons of the low adoption rate and to find out the factors which influence the acceptance of farmers. The first step is to provide an overview of the general functionalities of an FMIS and the benefits for farmers who use it. In a second step, a literature review is to be conducted to provide an overview of studies on the factors that influence the adoption and acceptance of FMIS. Afterwards, recommendations for actions to increase the acceptance should be derived.

Research Questions:

• What is an FMIS and how does it work?
• What are the benefits for farmers using an FMIS?
• What factors influence farmer adoption of FMIS?
• What recommendations for actions can be provided in order to increase the acceptance among farmers?

Literature :

1. S. Fountas et al. (2015): Farm management information systems: Current situation and future perspectives
2. D. Schulze Schwering, D. Lemken (2020): Totally Digital? Adoption of Digital Farm Management Information Systems
3. Z. Tsiropoulos, G. Carli, E. Pignatti, S. Fountas (2017): Future Perspectives of Farm Management Information Systems
4. U. Knuth, T.S. Amjath-Babu, A. Knierim (2018): Adoption of Farm Management Systems for Cross Compliance - An empirical case in Germany
5. M. Carrer et al. (2017): Factors influencing the adoption of Farm Management Information Systems (FMIS) by Brazilian citrus farmers
6. J. Alvarez, P. Nuthall (2006): Adoption of computer based information systems. The case of dairy farmers in Canterbury, NZ, and Florida, Uruguay
7. R. Nikkilä, I. Seilonen, K. Koskinen (2010): Software architecture for farm management information systems in precision agriculture
8. J. Ammann, A. Walter, N. El Benni (2022): Adoption and perception of farm management information systems by future Swiss farm managers – An online study

Supervisor: Kira Willems

Description :

In order to improve the usability of applications, it is important to identify user acceptance and problems during use. As a first step, an overview of the topic of usability is to be given. What is usability and which models and methods are common to evaluate usability? Afterwards the models should be compared and the advantages and disadvantages of the methods should be highlighted. The third step is to conduct a literature review to provide an overview of models and methods used to evaluate the usability of digital farming solutions. Furthermore, it should be discussed why the evaluation of the usability of digital farming solutions is important.

Research Questions:

• What is usability?
• Which models and methods are common to evaluate the usability in general?
• What are the differences between the models?
• What are the advantages and disadvantages of the methods?
• Which models and methods are used to evaluate the usability of digital farming solutions?
• Why is it important to evaluate the usability of digital farming solutions?

Literature :

1. DIN EN ISO 9241-110
2. DIN EN ISO 9241-11
3. M. Jaspers (2009): A comparison of usability methods for testing interactive health technologies: Methodological aspects and empirical evidence
4. Nielsen (1993): Usability engineering. AP Professional 
5. K. Raikar, S. Gawade (2018): Usability Analysis and Improvements with Agricultural Services
6. H. Haapala, L. Personen, P. Nurkka (2006): Usability as a Challenge in Precision Agriculture – Case Study: an ISOBUS VT
7. K. Demestichas, C. Costopoulou (2020): Usability Assessment of agricultural mobile applications in the Greek market
8. G. Adamides et al. (2017): HRI usability evaluation of interaction modes for a teleoperated agricultural robotic sprayer
9. Simorangkir et al. (2018): Usability Testing of Corn Diseases and Pests Detection on a Mobile Application

Supervisor: Kira Willems

Description :

Since autonomous vehicles (AV) operate in safety-critical scenarios, they must be capable of continuously monitoring their components to be aware of their functional state. This awareness allows the vehicle to trigger safety measures should the components deviate from the expected behavior that may cause a safety-critical event. Monitoring requires creating knowledge about the vehicle and its functions and to this end, ontologies have proved to be an asset. Ontologies provide a formal structure to objects, their relations and attributes, and allow their logic reasoning. This seminar aims at surveying and documenting how ontologies create and represent knowledge of the vehicle and its functions.

Literature :

• An Intelligent Driver Assistance System (I-DAS) for Vehicle Safety Modelling using Ontology Approach
• Ontology-based test generation for automated and autonomous driving functions
• Concept of an ontology for automated vehicle behavior in the context of human-centered research on automated driving styles
• Using Ontologies for Test Suites Generation for Automated and Autonomous Driving Functions
• Knowledge-based risk assessment for intelligent vehicles

Supervisor: Nikita Bhardwaj Haupt

Description :

Ontologies not only allow a formal way of knowledge-representation but logic reasoning on the represented knowledge. From representing the operational context to modeling the traffic scene, to situation description for advanced driver assistance systems, multiple researches in the domain of autonomous vehicles (AV) employ ontologies for multiple purposes. The aim of this seminar is to explore and document the research on how ontologies are used to model the operational context of an autonomous vehicle, what parts of context are modeled, and how does this aid decision making of the AV.

Literature :

• Ontology based Scene Creation for the Development of Automated Vehicles
• Ontology-based driving decision making: A feasibility study at uncontrolled intersections
• Traffic intersection situation description ontology for advanced driver assistance
• Fast decision making using ontology-based knowledge base
• Ontology-based context awareness for driving assistance systems
• Ontology-based traffic scene modeling, traffic regulations dependent situational awareness and decision-making for automated vehicles

Supervisor: Nikita Bhardwaj Haupt

Description :

As an autonomous vehicle (AV) operates in safety-critical scenarios, it must be capable of handling its failures and malfunctions in a way that ensures safety at all times. This implies that the vehicle must continuously observe its own performance at runtime and should reach a safety state in the event of failures. One way the vehicle can achieve this is by monitoring its components such that is it aware of their functional state along its capabilities and trigger safety measures should they deviate from the expected behavior that may cause a safety-critical event. This seminar aims to perform a systematic literature review on different monitoring mechanisms or monitors used to monitor sensors of an AV, documenting their similarities and differences, and advantages and disadvantages.

Literature :

• Supporting Safe Decision Making Through Holistic System-Level Representations & Monitoring -- A Summary and Taxonomy of Self-Representation Concepts for Automated Vehicles.
• A Knowledge-based Approach for the Automatic Construction of Skill Graphs for Online Monitoring
• A surveillance and safety system based on performance criteria and functional degradation for an autonomous vehicle.
• Model-Based Distributed On-line Safety Monitoring Model-Based Distributed On-line Safety Monitoring.
• Event-based multi-level service monitoring.
• Runtime Monitoring for Safety-Critical Embedded Systems – PhD thesis
• ReMinds: A flexible runtime monitoring framework for systems of systems
• From Safety Requirements to Safety Monitors-Automatic Synthesis in Compliance with ISO 26262

Supervisor: Nikita Bhardwaj Haupt

Description :

Continuous engineering aims at orchestrating engineering knowledge from various disciplines to deal with the rapid changes within the ecosystems of which software-based systems are part of. The literature claims different means to ensure these prompt responses to be incorporated as early as possible in the development process, such that requirements and architecture decisions are verified early and continuously by means of simulations. Despite the maturity of practices for designing and assessing architectures, as well as for virtual prototyping, there are still challenges to jointly consider the practices from these disciplines within development processes, in order to address the dynamics imposed by continuous software engineering. In this regard, this seminar topic aims at investigating how to orchestrate architecture drivers and design specification techniques with virtual engineering techniques, to address the demands of continuous software engineering in development processes.

Literatur : (will be provided by Supervisor)

Supervisor: Dr. Pablo Antonino

Description :

Process knowledge is usually taught with seminars classes and handbooks. This seminar aims to identify attractive (hands-on, game-based) knowledge transfer concepts to learn process knowledge. The seminar should provide an overview over existing experiences, especially informing what parts of software development processes were taught, and which formats were used.

Literature :

• Teaching ISO/IEC 12207 software lifecycle processes: A serious game approach
• Towards a Serious Game to Teach ISO/IEC 12207 Software Lifecycle Process: An Interactive Learning Approach
• Coverage of ISO/IEC 12207 Software Lifecycle Process by a Simulation-Based Serious Game
• An experimental card game for teaching software engineering Processes
• SimulES-W: A Collaborative Game to Improve Software Engineering Teaching

Supervisor: Sven Theobald

Description :

There are distinct features used for the adaptation procedure. Your task is to find out what are these features used for context-based dynamic adaptations.

Literature :

1. Musil, A., Musil, J., Weyns, D., & Biffl, S. (2019, September). Continuous Adaptation Management in Collective Intelligence Systems. In European Conference on Software Architecture (pp. 109-125). Springer, Cham.
2. Acher, M., Collet, P., Fleurey, F., Lahire, P., Moisan, S., & Rigault, J. P. (2009, October). Modeling context and dynamic adaptations with feature models.
3. Flammini, F., Marrone, S., Nardone, R., Caporuscio, M., & D’Angelo, M. (2020). Safety integrity through self-adaptation for multi-sensor event detection: Methodology and case-study. Future Generation Computer Systems, 112, 965-981.
4. Jamshidi, P., Cámara, J., Schmerl, B., Käestner, C., & Garlan, D. (2019, May). Machine learning meets quantitative planning: Enabling self-adaptation in autonomous robots. In 2019 IEEE/ACM 14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) (pp. 39-50). IEEE.

Supervisor: Anil Patel

Description :

In order to optimize the adaptation space in self-adaptive systems, your task is to find out what are the available approaches and how we can optimize adaptation space for self-adaptive systems.

Literature :

1. Quin, F. (2019): Efficient Analysis of Large Adaptation Spaces in Self-Adaptive Systems using Machine Learning. In IEEE/ACM 14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS), pp. 1-12. DOI: 10.1109/SEAMS.2019.00011.
2. Adler, R. (2013): A model-based approach for exploring the space of adaptation behaviors of safety-related embedded systems. Doctoral. Technischen Universität Kaiserslautern, Fachbereich Informatik. Fraunhofer IESE.
3. Buttar, S. S. (2019): Applying Artificial Neural Networks to Reduce the Adaptation Space in Self-Adaptive Systems - an exploratory work. Master Thesis. Linnaeus University.

Supervisor: Anil Patel

Description :

Your task is to find out state-of-the-art dynamic safety management approaches used in automotive domain.

Literature :

1. Kimm, H. (2009): Failure management development for integrated automotive safety-critical software systems. In ACM symposium on Applied Computing, pp. 517-521. DOI: 10.1145/1529282.1529390.
2. Panagopoulos, I. (2018): Safety Management and the Concept of Dynamic Risk Management Dashboards. In AUP Advances 1 (1), pp. 58-74. DOI: 10.5117/ADV2018.1.004.PANA
3. Trapp, Mario; Schneider, Daniel; Weiss, Gereon (2018): Towards Safety-Awareness and Dynamic Safety Management. In Proc. - 2018 14th Eur. Dependable Comput. Conf. EDCC 2018, pp. 107-111. DOI: 10.1109/EDCC.2018.00027.
4. Leveson, N. (2015): A systems approach to risk management through leading safety indicators. In Reliability Engineering & System Safety 136, pp. 17-34. DOI: 10.1016/j.ress.2014.10.008.

Supervisor: Anil Patel

Description :

To collect all accidents caused by AI-based algorithm and summarized all into your paper scientifically.

Literature :

1. Brief, C. P. (2021). AI Accidents: An Emerging Threat.
2. Maas, M. M. (2018, December). Regulating for 'Normal AI Accidents' Operational Lessons for the Responsible Governance of Artificial Intelligence Deployment. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society (pp. 223-228).
3. Dietterich, T. G., & Horvitz, E. J. (2015). Rise of concerns about AI: reflections and directions. Communications of the ACM, 58(10), 38-40.
4. Williams, R., & Yampolskiy, R. (2021). Understanding and Avoiding AI Failures: A Practical Guide. Philosophies, 6(3), 53.
5. Barrett, A. M. (2014). Analyzing current and future catastrophic risks from emerging-threat technologies.

Supervisor: Anil Patel

Description :

To find out the approaches used for risk assessment using LSTM method for autonomous vehicles and explain them scientifically in your paper.

Literature :

1. Wang, H., Lu, B., Li, J., Liu, T., Xing, Y., Lv, C., ... & Hashemi, E. (2021). Risk Assessment and Mitigation in Local Path Planning for Autonomous Vehicles With LSTM Based Predictive Model. IEEE Transactions on Automation Science and Engineering.
2. Khan, I. A., Moustafa, N., Pi, D., Haider, W., Li, B., & Jolfaei, A. (2021). An enhanced multi-stage deep learning framework for detecting malicious activities from autonomous vehicles. IEEE Transactions on Intelligent Transportation Systems.
3. Jasour, A., Huang, X., Wang, A., & Williams, B. C. (2022). Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures. Autonomous Robots, 46(1), 269-282

Supervisor: Anil Patel

Description :

To find out the approaches used for risk assessment using Random Forest method for autonomous vehicles and explain them scientifically in your paper.

Literature :

1. Kruber, F., Wurst, J., Morales, E. S., Chakraborty, S., & Botsch, M. (2019, June). Unsupervised and supervised learning with the random forest algorithm for traffic scenario clustering and classification. In 2019 IEEE Intelligent Vehicles Symposium (IV) (pp. 2463-2470). IEEE.
2. Nahata, R., Omeiza, D., Howard, R., & Kunze, L. (2021, September). Assessing and explaining collision risk in dynamic environments for autonomous driving safety. In 2021 IEEE International Intelligent Transportation Systems Conference (ITSC) (pp. 223-230). IEEE.
3. Yu, R., & Li, S. (2022). Exploring the associations between driving volatility and autonomous vehicle hazardous scenarios: insights from field operational test data. Accident Analysis & Prevention, 166, 106537.
4. Zhu, J., Ma, Y., & Lou, Y. (2022). Multi-vehicle interaction safety of connected automated vehicles in merging area: A real-time risk assessment approach. Accident Analysis & Prevention, 166, 106546.
5. Omeiza, D. (2021). Assessing and Explaining Collision Risk in Dynamic Environments for Autonomous Driving Safety.

Supervisor: Anil Patel

Description :

The goal is to investigate how Artificial intelligence can enable a more sustainable agriculture. You should research what AI systems exist to make agriculture more sustainable and how they work.

Literature : (will be provided by supervisor)

Supervisor: Marc Favier

Description :

Ontologies are used in many fields as representations that formalize concepts and their relations. Software development processes can also be represented as ontologies, e.g. describing the agile method Scrum or certain project management practices from the PMBOK. The focus of this seminar is the combination/matching/alignment of different ontologies related to agile and classical software development processes.

In detail, the aim of this seminar is to identify further literature based on the proposed initial papers to investigate:

• What research has been conducted to integrate/combine/map/align classical and agile development approaches with the help of ontologies?
• What are the concrete approaches?
• What do the ontologies look like? What tools are used, etc.
• How is the alignment/matching/integration of two ontologies solved?

Literature :

• An ontology for the harmonization of multiple standards and models
• Integration of classical and agile project management methodologies based on ontological models
• Towards a Hybrid Approach for Software Project Management using Ontology Alignment
• (can be provided by the supervisor)

Supervisor: Sven Theobald