Arianna+: Scalable Human Activity Recognition by Reasoning with a Network of Ontologies
Aging population ratios are rising significantly. Meanwhile, smart home based health monitoring services are evolving rapidly to become a viable alternative to traditional healthcare solutions. Such services can augment qualitative analyses done by gerontologists with quantitative data. Hence, the recognition of Activities of Daily Living (ADL) has become an active domain of research in recent times. For a system to perform human activity recognition in a real-world environment, multiple requirements exist, such as scalability, robustness, ability to deal with uncertainty (e.g., missing sensor data), to operate with multi-occupants and to take into account their privacy and security. This paper attempts to address the requirements of scalability and robustness, by describing a reasoning mechanism based on modular spatial and/or temporal context models as a network of ontologies. The reasoning mechanism has been implemented in a smart home system referred to as Arianna+. The paper presents and discusses a use case, and experiments are performed on a simulated dataset, to showcase Arianna+'s modularity feature, internal working, and computational performance. Results indicate scalability and robustness for human activity recognition processes.
Code (0)
등록된 구현이 없습니다.
Tasks
Activity RecognitionHuman Activity RecognitionSimilar Papers 제목 키워드 기반
Human Activity Recognition Models in Ontology Networks
We present Arianna+, a framework to design networks of ontologies for representing knowledge enabling smart homes to perform human activity recognition online. In the network, nodes are ontologies allowing for various da…
Activity RecognitionHuman Activity RecognitionARIANNA: pAth Recognition for Indoor Assisted NavigatioN with Augmented perception
ARIANNA stands for pAth Recognition for Indoor Assisted Navigation with Augmented perception. It is a flexible and low cost navigation system for vi- sually impaired people. Arianna permits to navigate colored paths pain…
NavigateFew-shot Vision-based Human Activity Recognition with MLLM-based Visual Reinforcement Learning
Reinforcement learning in large reasoning models enables learning from feedback on their outputs, making it particularly valuable in scenarios where fine-tuning data is limited. However, its application in multi-modal hu…
Human Activity RecognitionReinforcement LearningOn-device Large Multi-modal Agent for Human Activity Recognition
Human Activity Recognition (HAR) has been an active area of research, with applications ranging from healthcare to smart environments. The recent advancements in Large Language Models (LLMs) have opened new possibilities…
Human Activity RecognitionA Unified XAI-LLM Approach for EndotrachealSuctioning Activity Recognition
Endotracheal suctioning (ES) is an invasive yet essential clinical procedure that requires a high degree of skill to minimize patient risk - particularly in home care and educational settings, where consistent supervisio…
Activity RecognitionAnomaly Detection