A5042430316- Autonomous Vehicle Technology and Safety
- Astrophysics and Cosmic Phenomena
- Neutrino Physics Research
- Gaussian Processes and Bayesian Inference
- Dark Matter and Cosmic Phenomena
- Human-Automation Interaction and Safety
- Vehicle emissions and performance
- Fault Detection and Control Systems
- Traffic Prediction and Management Techniques
- Traffic and Road Safety
- Advanced Battery Technologies Research
- Anomaly Detection Techniques and Applications
- Reinforcement Learning in Robotics
- Gaze Tracking and Assistive Technology
- Machine Learning and Data Classification
- Evolutionary Algorithms and Applications
- Particle physics theoretical and experimental studies
- Machine Fault Diagnosis Techniques
University of Duisburg-Essen
2020-2023
Research in understanding human behavior is a growing field within the development of Advanced Driving Assistance Systems (ADASs). In this contribution, state machine approach proposed to develop driving recognition model. The model based on current and given set inputs. Transitions different states occur or we remain same producing outputs. transition between depends environmental variables. Based heuristic situations modeled as states, well one related actions modeling state, using an...
Developing driving behavior prediction and recognition models play a crucial role in Advanced Driving Assistance Systems (ADAS). these generally requires the use of Machine Learning approaches. Often, approaches are difficult to interpret. In this contribution, an Artificial Neural Network (ANN)-based state machine model is developed estimate three lane changing behaviors. A topology defining relationship between states (driving behaviors) developed. The transitions another or remains same...
In recent years, the development of advanced driving assistance systems (ADAS) has grown significantly within transportation industry to assist drivers for making safe maneuvers. A major component in developing these are behavior prediction and recognition models. These models aim infer behaviors based on different sources parameters using complex mathematical Machine learning algorithms being used increasingly develop this contribution, two formerly developed trainable models, which an...
Driving behavior estimations play a significant role in the development of Advanced Assistance Systems (ADASs). The are often developed using ma- chine learning-based approaches, which influenced by different factors, such as input variables and design methods. However, developing suitable configuration can be complicated. In this contribution, an improved Hidden Markov Model (HMM)-based state machine model is introduced for recognition lane changing behaviors. Adapting previously HMM model,...
The prediction and recognition models of driving behaviors are often based on ma- chine learning approaches. These required for the growth advanced assistance systems. performance model depends optimal parameters, hy- perparameters, structure. In present study, hyperparameters a previously developed (neural network-based state machine model) optimized lane changing recognition. Two methods considered hyperparameter optimization: Bayesian optimization Genetic algorithm (GA). Three estimated....
The use of Lithium-Ion Batteries (LIBs) have increased in recent years many applications such as hybrid electrical vehicles (HEV), consumer electronic equipment, and electricity grid. batteries undergo degradation during usage due to material aging electrochemical processes, leading efficiency reduction battery-powered systems well catastrophic events. Several stress factors battery temperature, ambient C-rate the loading profiles influence degradation. Therefore, predicting health has...
Driving intention recognition is an important aspect of Advanced Assistance Systems (ADAS) for giving drivers suggestions to maneuver safely. The algorithms in ADAS are often developed using Machine Learning-based models. model's input, such as environmental (ENV) and eye-tracking (ET) features affect the performance. In this contribution, Artificial Neural Network-based state machine used lane changing recognition. Three behaviors considered, left/right change keeping. Here, data consisting...