Due to connectivity and automation trends, the medical device industry is experiencing increased demand for safety and security mechanisms. Anomaly detection has proven to be a valuable approach for ensuring safety and security in other industries, such as automotive or IT. Medical devices must operate across a wide range of values due to variations in patient anthropometric data, making anomaly detection based on a simple threshold for signal deviations impractical. For example, surgical robots directly contacting the patient’s tissue require precise sensor data. However, since the deformation of the patient’s body during interaction or movement is highly dependent on body mass, it is impossible to define a single threshold for implausible sensor data that applies to all patients. This also involves statistical methods, such as Z-score, that consider standard deviation. Even pure machine learning algorithms cannot be expected to provide the required accuracy simply due to the lack of available training data. This paper proposes using hybrid filters by combining dynamic system models based on expert knowledge and data-based models for anomaly detection in an operating room scenario. This approach can improve detection performance and explainability while reducing the computing resources needed on embedded devices, enabling a distributed approach to anomaly detection.

Vehicle diagnostic systems are crucial for the normal operation of vehicles and their propulsion-related systems. Undetected unusual behaviour of such systems makes the vehicle diagnostic system unreliable. Current diagnostic systems, such as On-Board Diagnostics (OBD), are limited to monitoring only specific systems in order to make fault decision. However, various anomalies, including drastic performance drops, vehicle tampering, and changes in the driving environment, often go undetected during OBD system testing, validation, and inspection. This research presents a novel explainable OBD anomaly detection pipeline that is able to detect anomalies based only on OBD data snapshots during processes of OBD validation and inspection. The novel approach is implemented using combined dimension reduction and data clustering methodologies. First, the data is transformed into a latent space using t-distributed Stochastic Neighbor Embedding (t-SNE), where the general structure of the anomaly in the data can be exploited. Subsequently, clustering using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is applied to group similar normal data and identify anomalous patterns. The novelty of the solution is further extended with a feedback loop that suggests the root cause of OBD signals for individual anomalies using explainable AI (XAI) methodology, in this case Shapley additive explanations (SHAP). The proposed concept was verified and evaluated using real OBD snapshots with synthetically generated anomalies in two scenarios with different engine status, engine off and on, with an achieved accuracy of 92.89% and 96.45% for anomaly detection, respectively. The majority of anomaly causes in the form of specific OBD signals from propulsion- and emission-related systems were successfully explained using SHAP.

The operational reliability of electric buses depends heavily on the thermal stability and longevity of their battery packs. In urban public transit, highly dynamic driving cycles characterized by severe current surges during regenerative braking and prolonged constant-current charging phases induce massive localized thermal stress. Traditional battery management systems often fail to dynamically balance energy recovery with the physical constraints of cell matrices, leading to accelerated degradation and potential safety hazards. This paper proposes an integrated cyber–physical framework that merges intelligent control with advanced prognostic monitoring and predictive thermal management. The core of the control layer is a deep Q-network (DQN) agent designed for real-time smart charging and dynamic regenerative braking current limitation (smart derating). This control loop is tightly integrated with a long short-term memory (LSTM) network-based digital twin (DT) operating at the edge level to mirror complex electro-thermal dynamics and track the battery state of health (SOH). To ensure transparency and proactive thermal control, a nonlinear model predictive control (NMPC) strategy is implemented, utilizing SHapley Additive exPlanations (SHAP) to map core heat generation and dynamically adjust for internal thermal lag. The predictive NMPC-xAI loop maintained cell temperatures within a tight, optimal envelope, preventing delayed under-cooling and reducing peak temperature fluctuations.