Multisource Data Fusion Using MLP for Human Activity Recognition
Source abstract
Abstract
This research investigates the application of multisource data fusion using a Multi-Layer Perceptron (MLP) for Human Activity Recognition (HAR). The study integrates four distinct open-source datasets—WISDM, DaLiAc, MotionS... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Context-Aware Activity Recognition Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (43)
Show source-provided references
1. Deep learning in human activity recognition with wearable sensors: a review on advances10.3390/s22041476 ↗
2. Wearable multi-sensor data fusion approach for human activity recognition using machine learning algorithms10.1016/j.sna.2022.113557 ↗
3. A survey on wearable sensor modality centred human activity recognition in health care10.1016/j.eswa.2019.04.057 ↗
4. A smart healthcare monitoring system for heart disease prediction based on ensemble deep learning and feature fusion10.1016/j.inffus.2020.06.008 ↗
5. Human activity classification using multilayer perceptron10.3390/s21186207 ↗
6. A study of accelerometer and gyroscope measurements in physical life-log activities detection systems10.3390/s20226670 ↗
7. Comparative analysis of HAR datasets using classification algorithms10.2298/CSIS201221043N ↗
8. Assessing the state of self-supervised human activity recognition using wearables10.1145/3550299 ↗
9. An overview of human activity recognition based on smartphone10.1108/SR-11-2017-0245 ↗
10. Saha U, Saha S, Kabir T, Fattah SA, Saquib M. Decoding human activities: analyzing wearable accelerometer and gyroscope data for activity recognition. arXiv:2310.02011. 2024. doi:10.48550/arXiv.2310.02011.10.1109/LSENS.2024.3423340 ↗
11. Deep learning models for real-time human activity recognition with smartphones10.1007/s11036-019-01445-x ↗
12. Smart healthcare activity recognition using statistical regression and intelligent learning10.32604/cmc.2023.034815 ↗
13. Multi-sensor fusion based on multiple classifier systems for human activity identification10.1186/s13673-019-0194-5 ↗
14. Adaimi R, Bedri A, Gong J, Kang R, Arreaza-Taylor J, Pascual G-M, et al. Advancing location-invariant and device-agnostic motion activity recognition on wearable devices. arXiv:2402.03714. 2024. doi:10.48550/arXiv.2402.03714.
15. Coupling analysis of multiple machine learning models for human activity recognition10.32604/cmc.2024.050376 ↗
16. EAR: an energy efficient human activity recognition from wearable devices
17. Impedance sensing-centered pervasive and wearable activity recognition on edge devices
18. Human activity recognition based on wearable devices and feedforward neural networks
19. Towards highly compressed CNN models for human activity recognition in wearable devices
20. Wearable sensor-based human activity recognition with transformer model10.3390/s22051911 ↗
21. Action transformer: a self-attention model for short-time pose-based human action recognition10.1016/j.patcog.2021.108487 ↗
22. Human activity recognition based on single sensor square HV acceleration images and convolutional neural networks10.1109/JSEN.2018.2882943 ↗
23. A novel approach for human activity recognition using vision based method
24. Browne · Proceedings for the 27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science, ser. CEUR Workshop Proceedings · 2019 Dec · 2563 · 76
25. Human activity recognition using ensemble of CNN-based transfer learning models
26. An intelligent implementation of multi-sensing data fusion with neuromorphic computing for human activity recognition10.1109/JIOT.2022.3204581 ↗
27. DAMUN: a domain adaptive human activity recognition network based on multimodal feature fusion10.1109/JSEN.2023.3300357 ↗
28. Sample fusion network: an end-to-end data augmentation network for skeleton-based human action recognition10.1109/TIP.2019.2913544 ↗
29. Improving the performance and explainability of indoor human activity recognition in the internet of things environment10.3390/sym14102022 ↗
30. Deep residual network with a CBAM mechanism for the recognition of symmetric and asymmetric human activity using wearable sensors10.3390/sym16050554 ↗
31. The state-of-the-art sensing techniques in human activity recognition: a survey10.3390/s22124596 ↗
32. Design considerations for the WISDM smart phone-based sensor mining architecture
33. Mobile sensor data anonymization
34. Hierarchical, multi-sensor based classification of daily life activities: comparison with state-of-the-art algorithms using a benchmark dataset10.1371/journal.pone.0075196 ↗
35. Creating and benchmarking a new dataset for physical activity monitoring
36. Heydarian M, Doyle TE. rWISDM: repaired WISDM, a public dataset for human activity recognition. arXiv:2305.10222v1. 2023.
37. Human activity recognition from multiple sensors data using deep CNNs10.1007/s11042-023-15830-y ↗
38. Gaud · Proceedings of Data Analytics and Management. ICDAM 2023. Lecture Notes in Networks and Systems · 2024 Jan · 785
39. A lean and performant hierarchical model for human activity recognition using body-mounted sensors10.3390/s20113090 ↗
40. Feature selection in recognizing daily living activities based on metabolic equivalent10.30534/ijatcse/2020/125922020 ↗
41. Deep wavelet convolutional neural networks for multimodal human activity recognition using wearable inertial sensors10.3390/s23249721 ↗
42. Multi attributes recognition from human gait analysis using MotionSense dataset
43. Enhanced human activity recognition through deep multi-layer perceptron on the UCI-HAR dataset10.11591/ijaas.v13.i2.pp429-438 ↗