Sökning: L773:2169 3536 >
Entropy and Memory ...
Entropy and Memory Aware Active Transfer Learning in Smart Sensing Systems
-
- Alam, Umair (författare)
- Natl Univ Comp & Emerging Sci, FAST Sch Comp, Lahore 54770, Pakistan.
-
- Farhan, Asma Ahmad (författare)
- Natl Univ Comp & Emerging Sci, FAST Sch Comp, Lahore 54770, Pakistan.
-
- Kanwal, Summrina (författare)
- KTH,Teoretisk datalogi, TCS
-
visa fler...
-
- Allheeib, Nasser (författare)
- King Saud Univ, Coll Comp & Informat Sci, Dept Informat Syst, Riyadh 11451, Saudi Arabia.
-
visa färre...
-
Natl Univ Comp & Emerging Sci, FAST Sch Comp, Lahore 54770, Pakistan Teoretisk datalogi, TCS (creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2024
- 2024
- Engelska.
-
Ingår i: IEEE Access. - : Institute of Electrical and Electronics Engineers (IEEE). - 2169-3536. ; 12, s. 88841-88861
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Automated Human Activity Recognition (HAR) stems from the requirement to seamlessly integrate technology into daily life, to enhance user experience, improve healthcare, provide improved operations, ensure safety, deliver data-driven insights, and address various real-world challenges. However, unscripted Human activity faces challenges that must be understood, and require advances in sensor technology and machine learning models. This paper presents an Active Transfer Learning (ATL) approach for real-time HAR using mobile sensor data. Unlike traditional methods, our approach accounts for both the physical and habitual constraints of individuals. Existing works make an unrealistic assumption of an omniscient oracle while using the same datasets for both training and testing of the models, which makes them impractical for industry requirements. Our proposed approach addresses challenges in existing HAR algorithms, proposing a methodology to adapt models to the real-world datasets while training and testing on cross datasets. We have tailored an existing Entropy and Memory Maximization algorithm to work in a real-time environment while considering user constraints. Primarily trained in a well-labeled controlled environment dataset, we introduce noise injection to prevent the model from overfitting and enhance its generalization for scarcely labeled real-world datasets. Evaluations on publicly available datasets demonstrate our approach achieves 80% - 90% accuracy, outperforming the base algorithm accuracy of 12% - 14%. Importantly, our proposed technique outperforms with limited labeled data, making it valuable for real-time scenarios where labeling is sparse. This research advances HAR in real-world settings, offering improved accuracy and adaptability.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Human activity recognition
- Real-time systems
- Adaptation models
- Entropy
- Training
- Transfer learning
- Support vector machines
- Machine learning
- Internet of Things
- Wearable sensors
- Active transfer learning (ATL)
- Human activity recognition (HAR)
- Internet of Things (IoT)
- Machine learning (ML)
- Ubiquitous computing
- Wearable sensor devices
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas