A Close Look into Human Activity Recognition Models using Deep Learning

Tee, Wei Zhong; Dave, Rushit; Seliya, Naeem; Vanamala, Mounika

doi:10.48550/arxiv.2204.13589

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional machine learning methods in HAR relied heavily on manual feature extraction, limiting generalization. Deep learning has revolutionized HAR by enabling automatic feature extraction, overcoming the limitations of traditional manual methods [1,2].…”

Section: Related Workmentioning

confidence: 99%

“…Wang et al's survey on deep learning for sensor-based activity recognition encapsulates this transition, highlighting deep learning's capability to enhance generalization performance and its adaptability to unsupervised and incremental learning tasks [1], while Tee et al surveyed deep learning models, highlighting the success of hybrid systems that combine CNN and LSTM layers for activity recognition [2].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Human Activity Recognition with Siamese Networks: A Comparative Study of Contrastive and Triplet Learning Approaches

Cha,

Vaidya

2024

Electronics

View full text Add to dashboard Cite

This paper delves into the realm of human activity recognition (HAR) by leveraging the capabilities of Siamese neural networks (SNNs), focusing on the comparative effectiveness of contrastive and triplet learning approaches. Against the backdrop of HAR’s growing importance in healthcare, sports, and smart environments, the need for advanced models capable of accurately recognizing and classifying complex human activities has become paramount. Addressing this, we have introduced a Siamese network architecture integrated with convolutional neural networks (CNNs) for spatial feature extraction, bidirectional LSTM (Bi-LSTM) for temporal dependency capture, and attention mechanisms to prioritize salient features. Employing both contrastive and triplet loss functions, we meticulously analyze the impact of these learning approaches on the network’s ability to generate discriminative embeddings for HAR tasks. Through extensive experimentation, the study reveals that Siamese networks, particularly those utilizing triplet loss functions, demonstrate superior performance in activity recognition accuracy and F1 scores compared with baseline deep learning models. The inclusion of a stacking meta-classifier further amplifies classification efficacy, showcasing the robustness and adaptability of our proposed model. Conclusively, our findings underscore the potential of Siamese networks with advanced learning paradigms in enhancing HAR systems, paving the way for future research in model optimization and application expansion.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%