Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data
Open accessThe DOI matches its Crossref record; 77 of the 77 references it cites were found in a registry or an index.
Abstract
Sensor-based human activity recognition (S-HAR) has become an important and high-impact topic of research within human-centered computing. In the last decade, successful applications of S-HAR have been presented through fruitful academic research and industrial applications, including for healthcare monitoring, smart home controlling, and daily sport tracking. However, the growing requirements of many current applications for recognizing complex human activities (CHA) have begun to attract the attention of the HAR research field when compared with simple human activities (SHA). S-HAR has shown that deep learning (DL), a type of machine learning based on complicated artificial neural networks, has a significant degree of recognition efficiency. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are two different types of DL methods that have been successfully applied to the S-HAR challenge in recent years. In this paper, we focused on four RNN-based DL models (LSTMs, BiLSTMs, GRUs, and BiGRUs) that performed complex activity recognition tasks. The efficiency of four hybrid DL models that combine convolutional layers with the efficient RNN-based models was also studied. Experimental studies on the UTwente dataset demonstrated that the suggested hybrid RNN-based models achieved a high level of recognition performance along with a variety of performance indicators, including accuracy, F1-score, and confusion matrix. The experimental results show that the hybrid DL model called CNN-BiGRU outperformed the other DL models with a high accuracy of 98.89% when using only complex activity data. Moreover, the CNN-BiGRU model also achieved the highest recognition performance in other scenarios (99.44% by using only simple activity data and 98.78% with a combination of simple and complex activities).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Previous studies, including [10, 18, 23, 24], have amalgamated convolutional neural networks (CNN), recurrent neural networks (RNN), and attention mechanisms;”
From Adaptive temporal attention mechanism and hybrid deep CNN model for wearable sensor-based human activity recognition (2025) · cites this paper as [10]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“This leads to more reduced error rates in the confusion matrix (Fig. 8) when compared to CNN-BiGRU [10] and CNN-LSTM [24].”
From Adaptive temporal attention mechanism and hybrid deep CNN model for wearable sensor-based human activity recognition (2025) · cites this paper as [10]
In the citing paper
“Furthermore, employing data standardization or normalization methods can enhance input quality and expedite model training [10, 31].”
From Adaptive temporal attention mechanism and hybrid deep CNN model for wearable sensor-based human activity recognition (2025) · cites this paper as [10]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“However, the RNNs suffered from the vanishing gradient problem [45] that made them hard to train with acceptable performance.”
BackgroundThe Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008 · cited 2×
“The GRU is a basic version of the LSTM that does not have a separate memory cell in its structure [52].”
BackgroundBidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · cited 1×
“The BiLSTM was introduced in 1997 by Schuster and Paliwal to increase the amount of knowledge available in the LSTM network [49].”
MethodOn the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014) · Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation · doi:10.3115/v1/w14-4012 · Cited by 7,099 · cited 1×
“[51] introduced the gate recurrent unit (GRU) network, a novel RNN-based model, in 2014.”
BackgroundA survey of cross-validation procedures for model selection
Arlot, S., & Célisse, A. (2010) · LillOA (Université de Lille (University Of Lille)) · Cited by 3,669
A survey of cross-validation procedures for model selection
Arlot, S., & Celisse, A. (2010) · Statistics Surveys · doi:10.1214/09-ss054 · Cited by 3,522 · cited 1×
“To split the data for training and testing, several techniques can be utilized, such as k-fold cross validation [68].”
MethodThe Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions
Hochreiter, S. (1998) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488598000094 · Cited by 2,939 · cited 1×
“LSTMs are very popular in the natural language processing domain where they are used for word prediction, language translation, etc., including in the HAR domain [46,47].”
BackgroundDeep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761
Factorizing personalized Markov chains for next-basket recommendation
Rendle, S., Freudenthaler, C., & Schmidt-Thieme, L. (2010) · Proceedings of the 19th international conference on World wide web · doi:10.1145/1772690.1772773 · Cited by 2,692
Cited by
A Comprehensive Overview and Comparative Analysis on Deep Learning Models
Perumal, T., Mustapha, N., Mohamed, R., & Shiri, F. M. (2024) · Journal on artificial intelligence · doi:10.32604/jai.2024.054314 · Cited by 667
“Unlike traditional methods, CNNs automatically learn and recognize features from the data without the need for manual feature extraction by humans [13].”
MethodDeep Learning for Time Series Classification and Extrinsic Regression: A Current Survey
Mohammadi Foumani, N., Miller, L., Tan, C. W., Webb, G. I., Forestier, G., & Salehi, M. (2024) · ACM Computing Surveys · doi:10.1145/3649448 · Cited by 268
“In addition to the subsequence-based methods, other models employ instance-based sampling [21, 143, 147–150], treating each sample individually to generate positive and negative”
BackgroundMethodHuman Activity Recognition via Hybrid Deep Learning Based Model
Khan, I. U., Afzal, S., & Lee, J. W. (2022) · Sensors · doi:10.3390/s22010323 · Cited by 256
“…recognition [39,40], person re-identification [41], Energy forecasting [42–45], machine translation [46], and activity recognition from sensor data [47] used a special kind of neural network called Recurrent Neural Network (RNN) specifically designed for sequential data analysis having the ability…”
MethodHuman Activity Recognition Based on Residual Network and BiLSTM
Li, Y., & Wang, L. (2022) · Sensors · doi:10.3390/s22020635 · Cited by 156
“In [27], four deep learning hybrid models composed of CNN and RNN were studied to recognize complex activities.”
MethodMekruksavanich, S., & Jitpattanakul, A. (2021) · Sensors · doi:10.3390/s21227519 · Cited by 109
“The human gait is passively visible, inconspicuous, implicit, continuous, and concurrent and can be readily assessed while users are carrying their phones [21].”
BackgroundSelf-citationMachine Learning Methods in Smart Lighting Toward Achieving User Comfort: A Survey
Putrada, A. G., Abdurohman, M., Perdana, D., & Nuha, H. H. (2022) · IEEE Access · doi:10.1109/access.2022.3169765 · Cited by 101
“Complex activities are washing dishes, watching TV, eating, and cooking, as classified by [335].”
BackgroundDiraco, G., Rescio, G., Caroppo, A., Manni, A., & Leone, A. (2023) · Sensors · doi:10.3390/s23136040 · Cited by 81
“Mekruksavanich et al.’s research involves the application of RNN-based deep learning models in recognizing complex human activities using sensor-based HAR [87].”
BackgroundMethodMekruksavanich, S., & Jitpattanakul, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-39080-y · Cited by 75
Self-citationConnecting the indispensable roles of IoT and artificial intelligence in smart cities: A survey
Nguyen, H., Nawara, D., & Kashef, R. F. (2024) · Journal of Information and Intelligence · doi:10.1016/j.jiixd.2024.01.003 · Cited by 95
Kim, Y.-W., Joa, K.-L., Jeong, H.-Y., & Lee, S. (2021) · Sensors · doi:10.3390/s21227628 · Cited by 67
“Mekruksa-Vanich’s study [24] demonstrated a CNN-bidirectional gated recurrent unit (GRU) model that showed better classification performance than a machine-learning model, including a CNN with a GRU, against several IMU-based HAR open datasets.”
MethodZhang, L., Yu, J., Gao, Z., & Ni, Q. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.01.030 · Cited by 61
Issa, M., Helmi, A. M., Al‐qaness, M. A. A., Dahou, A., Elaziz, M. A., & Damaševičius, R. (2022) · Healthcare · doi:10.3390/healthcare10061084 · Cited by 64
“In [50], the authors studied the applications of several deep learning methods.”
BackgroundMekruksavanich, S., & Jitpattanakul, A. (2022) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2022265 · Cited by 59
Self-citationAn ensemble deep learning model for human activity analysis using wearable sensory data
Batool, S., Khan, M. H., & Farid, M. S. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111599 · Cited by 55
Mekruksavanich, S., Hnoohom, N., & Jitpattanakul, A. (2022) · Applied Sciences · doi:10.3390/app12104988 · Cited by 56
“This research investigated S-HARs that are based on DL and use deep residual networks to extract the relevant abstract characteristics from raw sensor data.”
BackgroundSelf-citationHuman Activity Recognition Data Analysis: History, Evolutions, and New Trends
Ariza-Colpas, P. P., Vicario, E., Oviedo-Carrascal, A. I., Butt Aziz, S., Piñeres-Melo, M. A., Quintero-Linero, A., & Patara, F. (2022) · Sensors · doi:10.3390/s22093401 · Cited by 52
“Mekruksavanich [158], uses the Utwente Dataset and PAMAP2, applying the Naive Bayes, SVM, Deep Stacked Autoencoder, CNN-BiGRu techniques, showing better results with this last technique described.”
Mekruksavanich, S., & Jitpattanakul, A. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-19-0898-9_42 · Cited by 84
Self-citationLiang, W., Wang, F., Fan, A., Zhao, W., Yao, W., & Yang, P. (2023) · Sensors · doi:10.3390/s23094229 · Cited by 59
“…Zhong, Zhang, Sun, and Zhao, 2016; Haresamudram et al., 2020; Ignatov, 2018; Liu, Y., Zhao, Shao, and Luo, 2016; Ma, Li, Zhang, Gao, and Lu, 2019; Mekruksavanich and Jitpattanakul, 2021; Pei et al., 2013; Reyes-Ortiz, Oneto, Samà, Parra, and Anguita, 2016; Yao, S., Hu, Zhao, Zhang, and…”
BackgroundInfluentialAn Efficient ResNetSE Architecture for Smoking Activity Recognition from Smartwatch
Hnoohom, N., Mekruksavanich, S., & Jitpattanakul, A. (2022) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.028290 · Cited by 46
Self-citationHuman activity recognition: suitability of a neuromorphic approach for on-edge AIoT applications
Fra, V., Forno, E., Pignari, R., Stewart, T. C., Macii, E., & Urgese, G. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac4c38 · Cited by 58
“An example of benchmarking for network architectures on various datasets can be found in [71], where an extensive analysis is carried out involving different techniques and data.”
BackgroundMekruksavanich, S., & Jitpattanakul, A. (2023) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.033542 · Cited by 45
Self-citationMuhoza, A. C., Bergeret, E., Brdys, C., & Gary, F. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100930 · Cited by 52
Govea, J., Gutierrez, R., & Villegas-Ch, W. E. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1410790 · Cited by 43
“The data exploration methodology stands out for its use of statistical analysis and visualizations that allow us to decipher trends, identify patterns, and understand the distribution of user interactions (Mekruksavanich and Jitpattanakul, 2021).”
Recognition of Real-life Activities with Smartphone Sensors using Deep Learning Approaches
Mekruksavanich, S., & Jitpattanakul, A. (2021) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess52187.2021.9522231 · Cited by 42
“The existing smartphone-based HAR has recently been improved using deep learning approaches [27], [28].”
MethodSelf-citationMekruksavanich, S., Jantawong, P., Charoenphol, A., & Jitpattanakul, A. (2021) · International Computer Science and Engineering Conference · doi:10.1109/icsec53205.2021.9684626 · Cited by 42
“The most frequently utilized deep learning models for fall detection are convolutional and recurrent neural networks (CNNs and RNNs, respectively) [16]–[19].”
BackgroundSelf-citationHnoohom, N., Jitpattanakul, A., You, I., & Mekruksavanich, S. (2021) · Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C) · doi:10.1109/ri2c51727.2021.9559773 · Cited by 41
Self-citationGovea, J., Navarro, A. M., Sánchez-Viteri, S., & Villegas-Ch, W. E. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1458230 · Cited by 38
Bearing Fault Diagnosis Based on Multi-Scale CNN and Bidirectional GRU
Saghi, T., Bustan, D., & Aphale, S. S. (2022) · Vibration · doi:10.3390/vibration6010002 · Cited by 38
A Close Look into Human Activity Recognition Models using Deep Learning
Tee, W. Z., Dave, R., Seliya, J., & Vanamala, M. (2022) · International Conference on Computing, Networks and Internet of Things (CNIOT) · doi:10.1109/cniot55862.2022.00043 · Cited by 42
Jantawong, P., Jitpattanakul, A., & Mekruksavanich, S. (2021) · International Conference on Big Data Analytics and Practices (IBDAP) · doi:10.1109/ibdap52511.2021.9552133 · Cited by 31
Self-citationEffectiveness of an Adaptive Deep Learning-Based Intrusion Detection System
Villegas-Ch, W. E., Govea, J., Gutierrez, R., Navarro, A. M., & Mera-Navarrete, A. (2024) · IEEE Access · doi:10.1109/access.2024.3512363 · Cited by 30
In-depth analysis of design & development for sensor-based human activity recognition system
Choudhury, N. A., & Soni, B. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16423-5 · Cited by 30
Mekruksavanich, S., Jantawong, P., Hnoohom, N., & Jitpattanakul, A. (2022) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess54813.2022.9930147 · Cited by 28
Self-citationTransforming healthcare and fitness with AI powered next-generation smart clothing
Yadav, A., & Yadav, K. (2025) · Discover Electrochemistry. · doi:10.1007/s44373-025-00015-z · Cited by 28
“They have also shown excellent performance in signal processing, enabling precise motion analysis in sports and posture correction in healthcare settings [65].”
Multimodal AI techniques for pain detection: integrating facial gesture and paralanguage analysis
Gutierrez, R., García-Ortiz, J., & Villegas-Ch, W. E. (2024) · Frontiers in Computer Science · doi:10.3389/fcomp.2024.1424935 · Cited by 23
Li, H., Wu, Q., Xing, B., & Wang, W. (2023) · PLoS ONE · doi:10.1371/journal.pone.0282158 · Cited by 28
“In the deep learning model, multi-layer sensors can simulate heterogeneous logic in neural networks [25, 26] and have great potential for neural network applications in speech recognition, image processing, automobile driving, and other fields.”
BackgroundRetractedMekruksavanich, S., & Jitpattanakul, A. (2024) · Applied System Innovation · doi:10.3390/asi7040059 · Cited by 22
“Hybrid networks that combine CNNs and LSTMs have demonstrated remarkable accuracy in various domains, such as recognizing postures and detecting gestures, mainly when applied to multimodal data collected from wearable devices [14].”
BackgroundMethodSelf-citationShenoy, M. A., & Thillaiarasu, N. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-233919 · Cited by 21
“Recurrent Neural Networks (RNNs), designed explicitly for sequential data analysis, prove valuable for addressing issues demanding sequential analysis, such as sensor-based activity recognition [68].”
Ortiz-Garcés, I., Villegas-Ch, W. E., & Luján‐Mora, S. (2025) · Discover Internet of Things · doi:10.1007/s43926-025-00196-4 · Cited by 19
“Energy infrastructure, comprising uninterruptible power supplies (UPS) and solar panels, ensures system reliability and sustainability [21].”
Mekruksavanich, S., & Jitpattanakul, A. (2024) · Symmetry · doi:10.3390/sym16050554 · Cited by 19
Self-citationMekruksavanich, S., & Jitpattanakul, A. (2025) · Applied System Innovation · doi:10.3390/asi8030057 · Cited by 18
“Recurrent neural networks (RNNs), especially LSTM networks, effectively capture temporal dependencies in activity sequences [13].”
Self-citationSupervised machine learning aided behavior classification in pigeons
Wittek, N., Wittek, K., Keibel, C., & Güntürkün, O. (2022) · Behavior Research Methods · doi:10.3758/s13428-022-01881-w · Cited by 19
“…(LSTM) (Chen et al., 2016; Singh et al., 2017; Pienaar & Malekian, 2019) and convolutional neural networks (CNN) (Wang et al., 2019; Lee et al., 2017; Gholamrezaii & Taghi Almodarresi, 2019; Naqvi et al., 2020; Cruciani et al., 2020; Mehmood et al., 2021; Mekruksavanich & Jitpattanakul, 2021).”
BackgroundVillegas-Ch, W. E., Jaramillo-Alcázar, Á., Navarro, A. M., & Mera-Navarrete, A. (2025) · IEEE Access · doi:10.1109/access.2025.3541979 · Cited by 18
Mekruksavanich, S., & Jitpattanakul, A. (2021) · International Conference on Open Source Systems and Technologies (ICOSST) · doi:10.1109/icosst53930.2021.9683890 · Cited by 17
Self-citationVillegas-Ch, W. E., Gaibor-Naranjo, W., & Sánchez-Viteri, S. (2024) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-024-00596-4 · Cited by 16
“This study addresses this gap, exploring how integrating spatial and temporal data can offer a deeper understanding of industrial processes, facilitating more informed and accurate decision-making [4].”
Human Behavior Analysis Using Radar Data: A Survey
Miazek, P., Żmudzińska, A., Karczmarek, P., & Kiersztyn, A. (2024) · IEEE Access · doi:10.1109/access.2024.3474100 · Cited by 15
Deeptha, R., Ramkumar, K., Venkateswaran, S., Hassan, M. M., Hassan, M. R., Noori, F. M., & Uddin, M. Z. (2024) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2024.1454583 · Cited by 16
Jantawong, P., Hnoohom, N., Jitpattanakul, A., & Mekruksavanich, S. (2021) · International Computer Science and Engineering Conference · doi:10.1109/icsec53205.2021.9684631 · Cited by 15
Self-citationLSTM-XGB: A New Deep Learning Model for Human Activity Recognition based on LSTM and XGBoost
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2022) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon53731.2022.9720409 · Cited by 18
Self-citationMLPs Are All You Need for Human Activity Recognition
Ojiako, K., & Farrahi, K. (2023) · Applied Sciences · doi:10.3390/app132011154 · Cited by 12
Bollampally, A., Kavitha, J., Sumanya, P., Rajesh, D., Jaffar, A. Y., Eid, W. N., Albarakati, H. M., Aldosari, F. M., & Alharbi, A. A. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.8861 · Cited by 12
“In this setup, the BiLSTM network's ability to learn from past and future contexts resulted in high performance, showcasing its strength and efficiency in real-world HAR scenarios [26].”
Alshardan, A., Mahgoub, H., Alahmari, S., Alonazi, M., Marzouk, R., & Mohamed, A. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2539 · Cited by 11
“Mekruksavanich & Jitpattanakul (2021) suggested deep learning (DL), a sub fi eld of machine learning that relies on complex arti fi cial neural networks, has shown to be quite effective in recognition tasks according to S-HAR.”
Chatterjee, K., Raju, M., Selvamuthukumaran, N., Pramod, M. J. P., Kumar, B. K., Bandyopadhyay, A., & Mallik, S. (2024) · Information · doi:10.3390/info15020085 · Cited by 11
“Furthermore, to model inter-channel relationships and long-term dependencies within sensory signals, researchers designed 2D convolution with RNNs and LSTM neural networks to capture the long-term sequential correlations [5–7].”
VCHAR: A Variance-Driven Framework for Complex Human Activity Recognition With Vague Label
Sun, Y., Pargoo, N. S., & Ortiz, J. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3631794 · Cited by 11
“Mekruk-savanich and Jitpattanakul [33] introduced a CNN-BiGRU model that effectively recognizes complex activities from wrist-worn sensors, while Tahvilian et al. [46] compared the efficacy of CNN-LSTM and CNN-BiLSTM models for varying complexities of activities.”
Parameter-Tuned Deep Learning-Enabled Activity Recognition for Disabled People
Duhayyim, M. A. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.033045 · Cited by 11
Xie, Y., Yao, Y., & Li, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-96462-0 · Cited by 12
Barua, A., Fuller, D., Musa, S. B., & Jiang, X. (2022) · Biosensors · doi:10.3390/bios12070549 · Cited by 9
“Another study [53], using a dataset called “Complex human activities using smartphones and smartwatch sensors”, explored the performance of divergent deep neural networks including LSTM, bidirectional LSTM, GRU, bidirectional GRU, CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU for five different window lengths (in secon…”
BackgroundAn Optimal Feature Selection Method for Human Activity Recognition Using Multimodal Sensory Data
Haider, T., Khan, M. H., & Farid, M. S. (2024) · Information · doi:10.3390/info15100593 · Cited by 9
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2022) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon53731.2022.9720358 · Cited by 9
“They aim to identify the current actions/activities undertaken by a person or group based on sensory observation data to extract information about the context where the movement took place [16], HAR solutions are developed to do so in particular.”
BackgroundSelf-citationKnowledge Distillation for Efficient Human Activity Recognition on Resource-Constrained Smartwatches
Fan, Y., Phaphan, W., Jitpattanakul, A., & Mekruksavanich, S. (2026) · IEEE Access · doi:10.1109/access.2026.3664977 · Cited by 8
Self-citationWearable gesture control design for unmanned aerial vehicle based on multi-sensor fusion
Liu, G., Liu, Y., Fan, S., Cui, W., Xia, K., & Wang, L. (2025) · Robotica · doi:10.1017/s0263574724002194 · Cited by 8
“…it using 2D-FFT and importing it into CNN to complete classification Meanwhile recurrent neural networks (RNNs) are widely used for time series processing and many studies have been done to achieve recognition of dynamic gestures based on its variant Long Short Time Memory network (LSTM) [31–33].”
Malisetty, S., Rastegari, E., Siu, K., & Ali, H. (2024) · Journal of Clinical Medicine · doi:10.3390/jcm13041150 · Cited by 8
“Network Models have emerged as a promising approach for analyzing and visualizing complex data [14,15].”
BackgroundMekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2021) · International Conference on Big Data Analytics and Practices (IBDAP) · doi:10.1109/ibdap52511.2021.9552111 · Cited by 8
Self-citationMa, W. (2025) · Advances in Continuous and Discrete Models · doi:10.1186/s13662-025-03871-6 · Cited by 7
RetractedMulti-Position Human Activity Recognition using a Multi-Modal Deep Convolutional Neural Network
Muhoza, A. C., Bergeret, E., Brdys, C., & Gary, F. (2023) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech58164.2023.10193600 · Cited by 7
“Despite the success of single-position and sensor-fusion HAR systems, [1]–[4] the variability of datasets and the complexity of human activities require multi-position HAR systems for better recognition accuracy.”
BackgroundMethodEnhancing Sensor-Based Human Activity Recognition using Efficient Channel Attention
Jitpattanakul, A., & Mekruksavanich, S. (2023) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/sensors56945.2023.10325157 · Cited by 7
“This is primarily achieved through two prominent neural network architectures: convolutional neural networks (CNNs) [22], [23] and long short-term memory networks (LSTMs) [24], [25].”
Self-citationArtificial Intelligence-based System for Detecting Attention Levels in Students
Márquez-Carpintero, L., Pina-Navarro, M., Suescun-Ferrandiz, S., Escalona, F., Gomez‐Donoso, F., Roig-Vila, R., & Cazorla, M. (2023) · Journal of Visualized Experiments · doi:10.3791/65931 · Cited by 7
Gym Exercise Recognition Using Deep Convolutional and LSTM Neural Network Based on IMU Sensor Data
Mekruksavanich, S., Tancharoen, D., & Jitpattanakul, A. (2024) · International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) · doi:10.1109/itc-cscc62988.2024.10628426 · Cited by 7
“Recently, deep learning meth-ods using CNN and RNN structures have shown substantial advancements by directly learning feature representations from unprocessed sensor data tuned for the specific job at hand [28], [29].”
Self-citationComprehensive investigation on Deep learning models: Applications, Advantages, and Challenges
Avacharmal, R., Pamulaparthyvenkata, S., Pandiya, D. K., Prakash, R. K., Ranjan, P., Balakrishnan, A. V., & Maheswaran, S. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10723970 · Cited by 7
“When it comes to tasks like object detection, image recognition, and other visual data processing [6], CNNs are especially useful.”
MethodMoola, R., Hossain, A., & Prasad, C. R. (2025) · International Journal of Information Technology · doi:10.1007/s41870-025-02474-4 · Cited by 7
“The use of the sensors used to record these activities affects how HAR is implemented in various ways [6, 7].”
A multi-sensor deep learning approach for complex daily living activity recognition
Woodward, K., Kanjo, E., Taylor, K., & Hunt, J. A. (2022) · Proceedings of the 2022 Workshop on Emerging Devices for Digital Biomarkers · doi:10.1145/3539494.3542753 · Cited by 8
“By limiting each sample it ensures a more balanced dataset was produced helping to reduce bias within the classification models [10].”
MethodLeveraging a Smartwatch for Activity Recognition in Salat
Eliza, I. J., Al-Nabhan, N., Noor, J., Rahaman, M., & Islam, A. B. M. A. A. (2023) · IEEE Access · doi:10.1109/access.2023.3311261 · Cited by 9
“of other existing studies [60], [168], [169], [170], [171], the recognition of activities or methodologies under consideration are either not applicable for Salat [168] or are muchmore complex compared to ours one [16], [44].”
ResultMekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2023) · Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C) · doi:10.1109/ri2c60382.2023.10356022 · Cited by 7
“Wearable devices have gained immense popularity today, offering precise detection of everyday human motions like walking, running, sitting, and stair climbing [13]–[19].”
BackgroundSelf-citationHi-OSCAR: Hierarchical Open-set Classifier for Human Activity Recognition
McCarthy, C., Quirijnen, L., van Zandwijk, J. P., Geradts, Z., & Worring, M. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3770681 · Cited by 6
“Examples are CNN layers combined with LSTMs, BiLSTMs, GRUs, and BiGRUs [51, 60] which are effective for classification, as well as other variations incorporating residual modules [32] and unique combinations of CNNs based on modality before combination and being fed into an LSTM [18].”
Driving Activity Classification Using Deep Residual Networks Based on Smart Glasses Sensors
Hnoohom, N., Mekruksavanich, S., & Jitpattanakul, A. (2023) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.033940 · Cited by 6
Self-citationMekruksavanich, S., Hnoohom, N., Phaphan, W., & Jitpattanakul, A. (2025) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon64748.2025.10962074 · Cited by 6
“In particular, deep learning architec-tures—such as convolutional neural networks (CNNs) [12] and various forms of recurrent neural networks (RNNs) [13]—have exhibited outstanding performance in autonomously extracting hierarchical features from unprocessed sensor inputs [14]– [16].”
Self-citationSensor-Based Activity Recognition Using Frequency Band Enhancement Filters and Model Ensembles
Tsutsumi, H., Kondo, K., Takenaka, K., & Hasegawa, T. (2023) · Sensors · doi:10.3390/s23031465 · Cited by 6
“Others have proposed models that combine CNNs and BiGRUs, and have shown to significantly outperform the recognition accuracy of other RNN models [15].”
MethodWang, Z., & Kang, K. (2025) · Scientific Reports · doi:10.1038/s41598-025-18444-6 · Cited by 5
“The confusion matrix illustrates a classifier’s performance by presenting the correlation between real and anticipated classes in a tabular format [7, 10].”
InfluentialMekruksavanich, S., Tancharoen, D., & Jitpattanakul, A. (2025) · International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) · doi:10.1109/itc-cscc66376.2025.11137755 · Cited by 5
“Nevertheless, they may not adequately focus on extracting localized spatial features, which are equally crucial for precise activity identification [9].”
Self-citationEnhancing Sensor-based Human Activity Recognition Using Hybrid Deep Learning and Data Augmentation
Mekruksavanich, S., Phaphan, W., & Jitpattanakul, A. (2024) · Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C) · doi:10.1109/ri2c64012.2024.10784365 · Cited by 5
Self-citationComparative Analysis of CNN-based Deep Learning Approaches on Complex Activity Recognition
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2022) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon53731.2022.9720320 · Cited by 5
“Additionally, convolution neural networks (CNNs) have been designed to exploit their dominance over feature extraction and provide the state-of-the-art performance of the classifier for HAR [13], [14].”
BackgroundSelf-citationMekruksavanich, S., Jantawong, P., Phaphan, W., & Jitpattanakul, A. (2024) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon60518.2024.10480100 · Cited by 5
“However, past research has predominantly focused on basic household tasks, neglecting the more intricate procedures involved in sanitation work [7].”
BackgroundSelf-citationA Method of Precise Auto-Calibration in a Micro-Electro-Mechanical System Accelerometer
Łuczak, S., Ekwińska, M. A., & Tomaszewski, D. (2024) · Sensors · doi:10.3390/s24124018 · Cited by 4
“A simple calibration of the accelerometer without using laboratory equipment is very advantageous, especially for applications that are related to research fields other than mechanical engineering, e.g., human activity recognition for computational [20], sporting [21], or medical [22,23] purposes.”
BackgroundMekruksavanich, S., Tancharoen, D., & Jitpattanakul, A. (2024) · International Symposium on Communications and Information Technologies · doi:10.1109/iscit63075.2024.10793590 · Cited by 4
“Convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) have revolutionized the analysis of activities based on inertial sensors [21]–[23].”
Self-citationDeep Learning Models for Daily Living Activity Recognition based on Wearable Inertial Sensors
Mekruksavanich, S., Jantawong, P., Hnoohom, N., & Jitpattanakul, A. (2022) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse54890.2022.9836239 · Cited by 4
Self-citationRecognition of Shoulder Exercise Activity Based on EfficientNet Using Smartwatch Inertial Sensors
Hnoohom, N., Chotivatunyu, P., Mekruksavanich, S., & Jitpattanakul, A. (2022) · International Conference on Big Data Analytics and Practices (IBDAP) · doi:10.1109/ibdap55587.2022.9907217 · Cited by 4
“Hence, inertial measurement units (IMUs) are integrated into numerous commercially available products, such as smartphones [3] and smartwatches [4-6].”
BackgroundSelf-citationEnhancement of Sensor-based User Identification using Data Augmentation Techniques
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2022) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon53731.2022.9720293 · Cited by 4
Self-citationZhang, N., & Wang, H. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/9144656 · Cited by 4
“-is article focuses on constructing a constructive English teaching model with a multimodal neural network algorithm for teaching practice [9].”
BackgroundAssiri, M., & Selim, M. M. (2025) · Journal of Disability Research · doi:10.57197/jdr-2025-0657 · Cited by 3
Brery, A. F., Gallardo-Antolín, A., Fakhry, M., & González‐Carrasco, I. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132415 · Cited by 5
Evaluation of the Informativeness of Features in Datasets for Continuous Verification
Davydenko, S., Kostyuchenko, E. Y., & Novikov, S. (2024) · Informatics and Automation · doi:10.15622/ia.23.1.3 · Cited by 3
Comparison of Different Deep Learning Networks to Classify Epilepsy Seizure Based on EEG Signals
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2024) · International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) · doi:10.1109/ecti-con60892.2024.10594957 · Cited by 3
“Recurrent neural networks (RNNs), such as long short-term memory (LSTM) and gated recurrent units (GRUs), are capable of accurately representing long-term temporal relationships in sequential data [11].”
BackgroundSelf-citationMekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2022) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon53731.2022.9720389 · Cited by 3
Self-citationDeep Learning Networks for Complex Activity Recognition Based on Wrist-Worn Sensor
Mekruksavanich, S., & Jitpattanakul, A. (2023) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon58879.2023.10322430 · Cited by 3
“For instance, monitoring an individual’s eating-related activities has been recognized as a potentially valuable factor in treating various illnesses, including cancer, diabetes, obesity, and heart attacks [5], [6].”
BackgroundSelf-citationVillegas-Ch, W. E., Gutierrez, R., Navarro, A. M., & Mera-Navarrete, A. (2024) · IEEE Access · doi:10.1109/access.2024.3486188 · Cited by 3
“To overcome this limitation, LSTMs are employed, which introduce input and forget gates to handle long-term memory efficiently [36].”
MethodPRESENCIA Y REALIDAD DE LA PSICOLOGÍA POLÍTICA FRANCESA
Dorna, A. (1998) · Psicología Política · Cited by 7
Construction Labor Activity Recognition via an IMU-Implemented Wristband
Alipouri, Y., Bokharaeian, A., & Monfared, E. (2025) · Journal of Construction Engineering and Management · doi:10.1061/jcemd4.coeng-16728 · Cited by 2
Efficient Human Activity Recognition on Smartwatch Sensors Using Knowledge Distillation
Hnoohom, N., Mekruksavanich, S., & Jitpattanakul, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-07986-2_42 · Cited by 2
Self-citationOn-Site Construction Worker Activity Monitoring Using Deep Learning
Monfared, E., & Alipouri, Y. (2026) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-7234 · Cited by 2
Accuracy Improvement of Complex Sensor-based Activity Recognition Using Hybrid CNN
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2022) · doi:10.1109/incit56086.2022.10067453 · Cited by 2
“Complex activities continue longer and comprise many simple actions [4], often including high-level semantics, such as eating, writing, and working.”
BackgroundSelf-citation
Metadata
- Authors
- Mekruksavanich, S., & Jitpattanakul, A.
- Affiliations
- University of Phayao (TH)
- King Mongkut's University of Technology North Bangkok (TH)
- Corresponding author
- Jitpattanakul, Anuchit
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2021-07-14
- Volume
- 10
- Issue
- 14
- Pages
- 1685
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W3182319652
- Cited by
- 138
- References
- 76
- Citations by year
- 2026: 12 · 2025: 27 · 2024: 36 · 2023: 22 · 2022: 30 · 2021: 10
- FWCI
- 8.78
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- University of Phayao (FF64-UoE008)
- King Mongkut's University of Technology North Bangkok (KMUTNB-BasicR-64-33-2)
- Thailand Science Research and Innovation Fund (-)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Keywords
- wearable sensors, wrist-worn sensors, recurrent neural networks, long short-term memory, bidirectional LSTM, gated recurrent unit, bidirectional GRU, hybrid CNN-RNN model, CNN-BiGRU
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.