Deep Recurrent Neural Networks for Human Activity Recognition
Open accessThe DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index; 5 of the 23 sources its claims cite were checked for support.
Abstract
Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs) address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM) DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM) and k-nearest neighbors (KNN). Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs.
Overview
CoChat Summary
TL;DR
The paper proposes LSTM-based deep recurrent neural network (DRNN) architectures—unidirectional, bidirectional, and cascaded—for human activity recognition from wearable sensor sequences, including variable-length windows. Across benchmark datasets, the proposed models reportedly outperform conventional machine learning and other deep learning baselines.
Key findings
- On UCI-HAD, the unidirectional DRNN with four layers achieved 96.7% overall accuracy, outperforming CNNs, SVM, and sequential ELM.
- On Skoda, the cascaded DRNN with one bidirectional layer and two upper unidirectional layers achieved 92.6% overall accuracy, outperforming HMMs, DBNs, and CNNs.
- On Opportunity, the bidirectional DRNN with three layers outperformed DBNs, SVM, CNNs, and a CNN + unidirectional RNN state-of-the-art method, using F1 score because the dataset is imbalanced.
- On Daphnet FOG, the cascaded DRNN outperformed KNN and CNNs in F1 score; on USC-HAD, the unidirectional four-layer model performed best versus CNNs, LS-SVM, and random forest, though no exact accuracy is given in the text.
Methods
- Three LSTM-based DRNN architectures were developed: unidirectional, bidirectional, and cascaded (bidirectional first layer plus unidirectional upper layers), with late fusion using the sum rule over per-timestep scores.
- Models were evaluated on five public HAR datasets: UCI-HAD, USC-HAD, Opportunity, Daphnet FOG, and Skoda; training used 80% of data and testing used 20%, raw data without further preprocessing, Adam optimization, mean cross entropy, dropout, and a GPU-based TensorFlow framework.
- Performance metrics were precision, recall, accuracy, and F1-score.
Limitations
- Stated: future work includes large-scale and complex human activities, transfer learning between diverse datasets, and resource-efficient DRNN implementation for low-power devices.
- Stated: USC-HAD elevator up/down classes were combined because the model could not differentiate them using only a single IMU; barometer readings would be needed. Daphnet FOG had low recall and precision for the “Freeze” class due to dominance of the “Normal” class, and Opportunity is imbalanced due to the Null class.
- Evident: several dataset-specific results are reported only through figures/confusion matrices without exact accuracy or F1 values in the text, and the paper inconsistently refers to four datasets in the Discussion/Conclusions while the experimental setup describes five.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures












Verification
Claims the paper makes
3 Valid · 0 Not valid · 10 Not checked · 27 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The proposed method outperforms other methods, such as those based on deep believe networks (DBNs) [10], SVM [10], and CNNs [13].”
§ Deep Recurrent Neural Networks for Human Activity Recognition > 6. Results > 6.3. Opportunity
What the sources say
- Not checked yetcites [10] Yang, J.B., Nguyen, M.N., San, P.P., Li, X.L., and Krishnaswamy, S. (2015, January 25–31). Deep convolutional neural networks on multichannel time series for human activity recognition. Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI), Buenos Aires, Argentina.
- Partly supportedcites [13] Ordóñez, F.J., and Roggen, D. (2016). Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors, 16. sourceExperimental — accuracy not yet measured
Our copy supports the SVM and CNN parts: Table 4 (§5.1) shows DeepConvLSTM beating the OPPORTUNITY challenge submissions including SStar (described in Table 3 as a support-vector-machine submission), and §5.1 states it improves by 6% over the CNN results previously reported by Yang et al. and by 5% on average over the baseline CNN. However, the paper makes no head-to-head comparison with deep belief networks on OPPORTUNITY: DBNs appear only in the State of the Art (§2.3) as related work whose feature-extraction applicability is credited to references [31] and [32], with no DBN entry in Tables 3 or 4. The DBN half of the attributed claim is therefore not supported by this source. (LLM, conf=0.80)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Every source the paper cites for this claim was checked and supports it.
In the paper
“It also outperformed the state-of-the-art method, which is a combination of CNNS and unidirectional RNNs [13], for the opportunity dataset.”
§ Deep Recurrent Neural Networks for Human Activity Recognition > 6. Results > 6.3. Opportunity
What the sources say
- Supportedcites [13] Ordóñez, F.J., and Roggen, D. (2016). Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors, 16. source
The citation is attached to the characterisation of the state-of-the-art method on OPPORTUNITY as a combination of CNNs and unidirectional RNNs, and our copy of Ordóñez & Roggen (2016) is exactly that method: Section 3.1 (Architecture) describes DeepConvLSTM as four convolutional layers feeding two stacked recurrent LSTM layers, C(64)-C(64)-C(64)-C(64)-R(128)-R(128)-Sm, with the recurrent layers processing the time axis forward only (no bidirectional component). Section 5.1 (Performance Comparison) reports it outperforming the best OPPORTUNITY-challenge submissions by 6% on average (>9% on gesture recognition without the Null class) and Yang et al.'s CNN by 6%, i.e. it is the top-reported result on that dataset. So the source both is the CNN+unidirectional-RNN architecture and holds the state of the art on OPPORTUNITY that the citing method claims to beat. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We demonstrate the effectiveness of using unidirectional and bidirectional DRNNs for HAR tasks without any additional data-preprocessing or merging with other deep learning methods.”
§ Deep Recurrent Neural Networks for Human Activity Recognition > 1. Introduction
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For the UCI-HAD dataset, we found that the unidirectional DRNN model with four layers yields best performance results in terms of per-class precision and recall, as shown in Figure 8a.”
§ Deep Recurrent Neural Networks for Human Activity Recognition > 6. Results > 6.1. UCI-HAD
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The proposed method results in an overall accuracy of 92.6%, outperforming other methods such as HMMs [23], DBNs [6], and CNNs [11], as shown in Figure 12b.”
§ Deep Recurrent Neural Networks for Human Activity Recognition > 6. Results > 6.5. Skoda
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
23 more claims
Create a free account to see all 40 claims and to verify the 18 references still open.
- Probably not a substantial claim. 4
- It may state two separate claims as one. 7
- The quote only partly states this claim. 2
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
“We have applied this network because RvNN can be used to learn distributed, structured data. Therefore, it is ideal for our proposed multimodal IoT-based locomotion prediction system.”
From A Multimodal IoT-Based Locomotion Classification System Using Features Engineering and Recursive Neural Network (2023) · cites this paper as [32]
Experimental — accuracy not yet measuredIn the citing paper
“Papers [33,34] also compared deep-learning methods for HAR, and verified that variants of the LSTM architecture lead to flexible and robust results in several sensor-based HAR datasets.”
From Sensor Data Acquisition and Multimodal Sensor Fusion for Human Activity Recognition Using Deep Learning (2019) · cites this paper as [33]
In the citing paper
“Previous studies have shown that LSTMs have high performance in wearable HAR [199,202,203].”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [202]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Deep Recurrent Neural Networks for Human Activity Recognition > 8. Conclusions
“Additionally, we empirically evaluated our models by conducting experiments on four miscellaneous benchmark datasets.”
§ Deep Recurrent Neural Networks for Human Activity Recognition > 5. Experimental Setup > 5.1. Datasets of Human Activities
“In order to train and evaluate the proposed models, we considered five public benchmark datasets for HAR.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Deep Recurrent Neural Networks for Human Activity Recognition > 5. Experimental Setup > 5.3. Performance Metrics
“Overall Accuraccy=TP+TNTP+TN+FP+FN, where TP=∑c=1Ctpc is the overall true positive rate for a classifier on all classes, TN=∑c=1Ctnc is the overall true negative rate, FP =∑c=1Cfpc is the overall false positive rate, and FN=∑c=1Cfnc is the overall false negative rate.”
§ Deep Recurrent Neural Networks for Human Activity Recognition > 5. Experimental Setup > 5.3. Performance Metrics
“Accuracy: Measures the proportion of correctly predicted labels over all predictions:”
Citations
Cites
Bidirectional 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×
“It includes two parallel LSTM tracks: forward and backward loops for exploiting context from the past and future of a specific time step in order to predict its label [17].”
BackgroundTensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408 · cited 1×
“Training was conducted on a GPU-based TensorFlow framework in order to utilize the parallel computation power of a GPU [25].”
MethodSpeech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 3×
“Using sufficient number of DRNN layers can result in a very powerful model for transforming raw data into a more abstract representation, as well as for learning the temporal dependencies in time series data [1].”
BackgroundMethodA systematic analysis of performance measures for classification tasks
Sokolova, M., & Lapalme, G. (2009) · Information Processing & Management · doi:10.1016/j.ipm.2009.03.002 · Cited by 7,515
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319 · cited 1×
“The third model architecture, shown in Figure 6, is motivated by [18].”
BackgroundSupervised Sequence Labelling with Recurrent Neural Networks
Graves, A. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-24797-2 · Cited by 3,120
Deep 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
Phoneme recognition using time-delay neural networks
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. J. (1989) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/29.21701 · Cited by 2,643 · cited 1×
“To capture local dependencies, CNNs use parameter sharing across time—applying the same convolutional kernel at each time segment—and local connectivity—neurons receiving inputs from small groups of input samples—between adjacent layers [12].”
MethodLSTM neural networks for language modeling
Sundermeyer, M., Schlüter, R., & Ney, H. (2012) · Interspeech 2012 · doi:10.21437/interspeech.2012-65 · Cited by 1,963 · cited 1×
“They have achieved promising performance enhancements in many technical applications, such as speech recognition [1], language modeling [2], video processing [3], and many other sequence labeling tasks [4].”
Background(2013) · RECERCAT (Consorci de Serveis Universitaris de Catalunya) · Cited by 1,959
Research works printed but not linked: 1
- Goodfellow, I., Bengio, Y., and Courville, A. (2016). Optimization for Training Deep Models. Deep Learning, The MIT Press.
Cited by
Items 401–500 of 545
Basic Activity Recognition from Wearable Sensors Using a Lightweight Deep Neural Network
Benhaili, Z., Abouqora, Y., Balouki, Y., & Moumoun, L. (2022) · Journal of ICT Standardization · doi:10.13052/jicts2245-800x.1028 · Cited by 4
“Each node also has an activation function F connected with it [17].”
BackgroundMixing temporal experts for Human Activity Recognition
Roy, D., & Girdzijauskas, Š. (2022) · Swedish Artificial Intelligence Society Workshop (SAIS) · doi:10.1109/sais55783.2022.9833028 · Cited by 2
Unsupervised Representation Learning Method In Sensor Based Human Activity Recognition
Takenaka, K., & Hasegawa, T. (2022) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc56445.2022.9941334 · Cited by 2
Analysis of Machine Learning-based Human Activity Prediction Model for Assistive Exoskeleton
Sahoo, S., Sharma, M., Yadish, A., & Kumar, S. (2024) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa59508.2024.10467895 · Cited by 2
“In the literature [10], authors have used deep recurrent neural networks (DRNNs).”
BackgroundA Deep Ensemble model to Recognize Human Activities using inertial sensors on smartphones
Imanzadeh, S., Tanha, J., Razzaghi-Asl, N., Mostafaei, S. H., Samadi, N., & Tarhib, S. (2024) · CSI International Symposium on Artificial Intelligence and Signal Processing · doi:10.1109/aisp61396.2024.10475271 · Cited by 2
Sansano‐Sansano, E. (2020) · Tesis Doctorals en Xarxa (Consorci de Serveis Universitaris de Catalunya) · doi:10.6035/14101.2020.180044 · Cited by 4
Abnormal Activity Recognition in Private Places Using Deep Learning: A Survey
Suthar, A. (2023) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2023.53958 · Cited by 1
Vision-Based Human Activity Recognition Using CNN and LSTM Architecture
Gupta, N., Malik, P., Dubey, A. K., Jain, A., Yadav, S., & Verma, D. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-56700-1_10 · Cited by 2
Zhou, Z., Fang, S., Fang, W., Xu, Y., Zhu, B., Li, L., Ji, H., & Tu, W. (2024) · Water · doi:10.3390/w16202880 · Cited by 1
Bayesian and Genetic Optimization for Human Activity Recognition with CNN and LSTM
Sultana, S., Rahman, T., Khatun, H., Sultana, N., Islam, M. R., & Ahmed, N. (2024) · International Conference on Intelligent & Innovative Practices in Engineering & Management (IIPEM) · doi:10.1109/iipem62726.2024.10925732 · Cited by 1
“In 2017, A. Murad et al. [14] advocated for construction of identification models in deep recurrent neural networks.”
Elsi, Z. R. S., Stiawan, D., Suprapto, B. Y., Arifin, M. A. S., Idris, M. Y., & Budiarto, R. (2025) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v21i05.53485 · Cited by 1
Dual-Stream Sparse Transformer for Gait Recognition Based on Inertial Signals
Xia, Y., & Wang, H. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3620838 · Cited by 2
“Murad and Pyun [21] proposed to utilize LSTM networks to capture temporal relationships within the input sequences.”
(2025) · Computer Science Engineering and Technology · doi:10.46632/cset/3/4/3 · Cited by 1
Passive Localization Utilizing Wireless RSSI: A Review
Jabbar, M. W., Shoaib, U., Zahoor, S., Chaudhry, S. A., & Bhutta, M. N. M. (2025) · Cybernetics and Information Technologies · doi:10.2478/cait-2025-0031 · Cited by 1
A systematic review of deep learning-based models for elderly and human activity recognition
Dalal, M., & Mittal, P. (2025) · Computer Science Review · doi:10.1016/j.cosrev.2025.100879 · Cited by 1
Askhatova, A., Sharipov, U., Kasenov, S., Kassenov, K., Kenzhin, Z., Kuangaliyeva, T. K., Turzhanova, D., & Jamwal, P. K. (2026) · MethodsX · doi:10.1016/j.mex.2026.103845 · Cited by 1
“Prior studies have employed machine learning models for the gait symmetry evaluation [6], gait-based biometric authentication [7], and activity recognition [8 – 10].”
Fine-grained rehabilitation motion analysis: A knowledge-enhanced multi-branch network approach
Xue, J., Li, J., & Li, J. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109983 · Cited by 1
Human Activity Recognition via a Categorical Kalman Filter Using Inertial Sensors
Pitombeira-Neto, A. R., de França, D. S., Cruz, L. A., & de Macêdo, J. A. D. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3678199
“Noteworthy models have been proposed in the literature, including multilayer perceptrons (MLPs) [23], [24], convolutional NNs (CNNs) [25], [26], [27], deep recurrent NNs (RNNs) [28], [29], NN with attention mechanism [30], and ResNet [31].”
Deep Learning‐Based Passive Localization System Using Radio Tomography Images and Wi‐Fi RSSI
Jabbar, M., Shoaib, U., & Zakaria, K. A. I. (2026) · International Journal of Distributed Sensor Networks · doi:10.1155/dsn/1877891 · Cited by 1
Parveen, T., Khan, R., Saeed, U., & Koo, I. (2026) · Sensors · doi:10.3390/s26123821 · Cited by 1
“Early efforts relied on handcrafted features and classical ML classifiers, but these methods were typically environment-specific and exhibited limited generalization [9,10].”
The clinical effectiveness of joint protection education and exercises in hand osteoarthritis (OA)
Dziedzic, K., Nicholls, E. E., Hill, S., Hammond, A., Jowett, S. M., Oppong, R., & Hay, E. M. (2012) · Osteoarthritis and Cartilage · doi:10.1016/j.joca.2012.02.255 · Cited by 1
Overlapped State Hidden Semi-Markov Model for Grouped Multiple Sequences
Narimatsu, H., & Kasai, H. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054136 · Cited by 1
“Deep neural networks such as RNN [20, 21, 22] are widespread and are known to be effective for this purpose.”
BackgroundYıldırım, M., & Çınar, A. (2021) · Turkish Journal of Science and Technology · Cited by 2
Kim, H., & Lee, D. (2021) · ACM Symposium on Applied Computing · doi:10.1145/3412841.3441924 · Cited by 2
“[19] employ deep LSTM for capturing long dependencies between contexts and achieves better performance than a CNN-based approach.”
BackgroundMethodDeep Representation Learning in Computer Vision and Its Applications
Wu, F. (2021) · University of Liverpool · doi:10.17638/03108705 · Cited by 1
Human Activity Recognition based on Smartphone Sensors- A Comparative Study
Dhammi, L., & Tewari, P. (2021) · International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) · doi:10.1109/icrito51393.2021.9596305 · Cited by 1
Inertial measurement unit based human action recognition for soft-robotic exoskeletons
Kuschan, J., Burgdorff, M., Filaretov, H., & Krüger, J. (2021) · Proceedings of the Estonian Academy of Sciences · doi:10.3176/proc.2021.4.16 · Cited by 1
The pro-business effects of paramilitary terror in Colombia
Maher, D. (2021) · Routledge eBooks · doi:10.4324/9780429279430-4 · Cited by 1
Prediction of Human Physical Activities With Consumer Smartphone Sensor Data
Kumar, T., & Prasad, B. (2021) · IEEE Bombay Section Signature Conference (IBSSC) · doi:10.1109/ibssc53889.2021.9673366 · Cited by 1
Human Intention Recognition for Safe Robot Action Planning Using Head Pose
Orsag, L., Stipanĉić, T., Koren, L., & Posavec, K. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17618-0_23 · Cited by 1
Fruit Picker Activity Recognition with Wearable Sensors and Machine Learning
Dabrowski, J. J., & Rahman, A. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191571 · Cited by 2
“Like the CNN, the RNN has been also applied to several HAR problems [28]–[30].”
MethodMekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2023) · Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C) · doi:10.1109/ri2c60382.2023.10356026 · Cited by 1
Clasificación de actividades humanas aplicando Inteligencia Computacional
Reynaga, B. A. L., Acevedo, E., Acevedo, A., & Gomez-Coronel, S. L. (2024) · Ingeniería Investigación y Tecnología · doi:10.22201/fi.25940732e.2024.25.2.009
“Murad & Pyun (2017) aplican sus algoritmos a cinco conjuntos de datos: UCI-HAD, USC-87 HAD, Opportu-nity, Daphnet FOG y Skoda.”
BackgroundSuspicious Activity Monitoring System Using YOLOv5
Kushwaha, P., & Murmu, M. K. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10724525 · Cited by 1
“Murad and Pyun (2017) demonstrated the efficacy of deep recurrent neural networks (RNNs) in HAR, showcasing the superior performance of RNNs in processing sequential data [11].”
BackgroundGreeting Gesture Analysis Using Boosting Algorithms and SHAP
Wibowo, A. W., Sato-Shimokawara, E., & Kurnianingsih, K. (2024) · Joint International Conference on Soft Computing and Intelligent Systems and International Symposium on Advanced Intelligent Systems (SCIS&ISIS) · doi:10.1109/scisisis61014.2024.10759915 · Cited by 1
Kumar, P., Bhushan, S., & Suresh, S. (2024) · National Academy Science Letters · doi:10.1007/s40009-024-01585-z · Cited by 1
“This restriction could be addressed by using LSTM, a variant of RNN. Due to its unique memory cells, LSTM has a noteworthy advantage over convolutional neural networks regarding feature extraction from sequence data [15].”
Fahad, M. S., Ranjan, A., & Sharma, S. K. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11068-x · Cited by 3
“Murad et al. [20], for example, recommended that deep recurrent neural networks (deep RNN) are used to create a human activity recognition model.”
Zohrevand, A., Mirzaei, S., & Sajedi, H. (2025) · International Computer Conference, Computer Society of Iran (CSICC) · doi:10.1109/csicc65765.2025.10967410 · Cited by 1
“These methods were effective in structured environments but struggled with complex real-world data [13].”
Human Activity Recognition Algorithm Based on One-Dimensional Convolutional Neural Network
Tang, D., Jin, M., Wang, Q., Wei, Z., & Zhang, J. (2020) · Revue d intelligence artificielle · doi:10.18280/ria.340110 · Cited by 1
“[17] proposed the use of the deep recurrent neural network (DRNN) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences.”
BackgroundSystematic Evaluation of Deep Learning Models for Human Activity Recognition Using Accelerometer
Le, T.-H., Tran, Q.-H., & Le, T. (2020) · NAFOSTED Conference on Information and Computer Science (NICS) · doi:10.1109/nics51282.2020.9335853 · Cited by 2
“In fact, HAR has been widely applied to several areas such as sport training, remote health monitoring, health self-management, military applications, gaming, home behavior analysis, gait analysis and gesture recognition [4], [5].”
BackgroundHospital ratings rise, but ambulance ratings fall
Kmietowicz, Z. (2003) · BMJ · doi:10.1136/bmj.327.7407.119 · Cited by 1
A Sensor-fusion Framework for Queue-less Check-out in RetailPreprint
Gayen, T., & Shukla, A. (2019) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/d9xg6 · Cited by 1
Hybrid deep neural network models for boosting Human Activity Recognition using IoT wearablesPreprint
Sowmiya, S., & Dharmaraj, M. (2022) · Research Square · doi:10.21203/rs.3.rs-2035081/v1 · Cited by 1
Human Activity Recognition Using Deep Neural NetworksPreprint
Lodha, L. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4808220 · Cited by 1
AUTOMATED HUMAN ACTIVITY RECOGNITION FROM CONTROLLED ENVIRONMENT VIDEOS
Mandadapu, P. (2023) · UWM Digital Commons (University of Wisconsin–Milwaukee) · Cited by 1
Dine, K. B. E. (2022) · theses.fr (ABES) · doi:10.70675/cc19d401z0a39z4290za63ezbbbaa251cf69 · Cited by 2
British Asian Muslim women, multiple spatialities and cosmopolitanism
Held, N. (2014) · Journal of Tourism and Cultural Change · doi:10.1080/14766825.2014.892699
AB1119 Is Pain Disabling Adults with Musculoskeletal Conditions?
Prior, Y., Hammond, A., & Tyson, S. F. (2014) · Annals of the Rheumatic Diseases · doi:10.1136/annrheumdis-2014-eular.3399
Rowlett, P. (2003) · Journal of French Language Studies · doi:10.1017/s0959269503311056
Frade, C. (2006) · European Journal of Sociology · doi:10.1017/s0003975606000063
Properties of federated averaging on highly distributed data
Desai, N. V., & Verma, D. C. (2019) · Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications · doi:10.1117/12.2518941
“7 The results are compared with the baseline accuracy achieved with centralized training.”
ResultDeep Neural Networks for Human Behavior Understanding
Singh, R. K., & Nigam, S. (2019) · Springer eBooks · doi:10.1007/978-3-030-15887-3_32 · Cited by 1
Optimized Sequence Prediction of Risk Data for Financial Institutions
Wong, K. Y., Wong, R. K., & Huang, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29911-8_28
Low-Cost Method for Recognizing Table Tennis Activity
Lim, S.-M., Park, J., & Oh, H.-C. (2019) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2019edl8017
“Using the preprocessed data, the accuracy of all three methods increased, although only a small change was observed for the LSTM RNN; as it was noted in [5], the model captured a relatively long-range dependencies in the input sequence.”
BackgroundMethodInfluentialDownsampling wearable sensor data packets by measuring their information value
Belmonte, M., Casson, A. J., & Peek, N. B. (2019) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/sensors43011.2019.8956721 · Cited by 1
“Application of deep learning to the problem of HAR classification using wearable sensor measurements yields impressive recognition accuracies [1]–[4].”
BackgroundStory Generation from Smart Phone Data : A script approach
Nguyen, T. K. (2019) · theses.fr (ABES) · doi:10.70675/5bc6bff8z9eb7z406bz9d6ezc5643d7ae2d7
Cobal -A Novel Design of CNN Basedgait Feature Extraction Using Bat-Elm for Human Tracking System
Harish, R., & Kumar, P. R. (2020) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/993/1/012094
“To prove superior performance of the proposed algorithm, we have compared the performance with the hybrid models such as CNN+RNN[36], DR+NN[38],3DCNN[35] and other non-hybrid models such as Multi layer perceptron’s [37] , Support vector machines(SVM)[34] and Extreme Learning Machines(ELM).”
MethodVision-Based Activity Recognition System with a Deep Neural Network for Surveillance
Sherif, S., Ooi, C., Haw, T. W., & Fei, T. Y. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-33-4069-5_33
Zhong, Z., Lin, C., Kanai‐Pak, M., Maeda, J., Kitajima, Y., Nakamura, M., Kuwahara, N., Ogata, T., & Ota, J. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3075477 · Cited by 1
Mohammed hashim, B. A., & Amutha, R. (2021) · Research Square · doi:10.21203/rs.3.rs-766724/v1
Workload Management System for Cricketers
Ekanayaka, E. M. S. B., Gunawardhana, A. A. S., Mihirani, M. B., Silva, P., & Prins, N. W. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9631106
An Advanced Attention-Enhanced Hybrid Deep Learning Model for WBSNs’ Gait Pattern RecognitionPreprint
Wu, J., Tan, Q., & Wu, X. (2022) · Research Square · doi:10.21203/rs.3.rs-1251973/v1
“These algorithms mainly include convolutional neural network (CNN), dilated convolutional neural network (DCNN), recurrent neural network (RNN) and long short-term memory(LSTM) [12-15].”
BackgroundRecurrent Variational Open-Set Recognition
Diamond, N., Jordan, S., Norman, A., Buquicchio, L., & Rundensteiner, E. A. (2021) · IEEE MIT Undergraduate Research Technology Conference (URTC) · doi:10.1109/urtc54388.2021.9701621
Human Activity Recognition System Using Artificial Neural Networks
Almeida, V. F. D., & Andreão, R. V. (2022) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-030-70601-2_192
Hashim, B. A. M., & Amutha, R. (2021) · Research Square · doi:10.21203/rs.3.rs-766724/v2
Kumble, L., & Patil, K. K. (2022) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit228230
Human Activity Recognition System Using Smartphone Data Sensors with Python and Machine Learning
Gade, P. S., Lokare, S., Gadekar, T., & Khoje, K. (2022) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2022.41211
A survey on human behavior analysis and actions recognition from videos
Jaouedi, N., Boujnah, N., & Bouhlel, M. S. (2022) · International Conference on Sciences of Electronics, Technologies of Information and Telecommunications · doi:10.1109/setit54465.2022.9875464
“Murad and Ryun 2017 [8] and Qin et al. [9] applied body-worn sensors for human motion description.”
BackgroundGesture Analysis Using Image Processing: For Detection of Suspicious Human Actions
Bhagat, P. H., & Bhalchandra, A. S. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-19-9225-4_38
Recognizing Human Activity Using Hybrid Models of CNN and LSTM in Deep Learning
(2023) · International Journal of Food and Nutritional Sciences · doi:10.48047/ijfans/v11/i12/178
Comparison of Machine Learning Methods for Human Activity Recognition Using Pseudo Free-Living Data
Alkhoshi, E. E., Rasheed, K., Arabnia, H. R., Maier, F. W., & Gay, J. L. (2022) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci58124.2022.00029
Deep Learning Models to Estimate and Predict the Solar Irradiation in Brazil
de Souza, W. A., Alonso, A. M. S., Bernardino, L. G. R., Castoldi, M. F., do Nascimento, C. F., & Marafão, F. P. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-48652-4_5
DEEP LEARNING FRAMEWORK FOR HUMAN ACTIVITY DETECTION BASED ON WIRELESS SENSORS.
Anandharaj, G. (2023) · Journal of Propulsion Technology · doi:10.52783/tjjpt.v44.i5.2493
“Many sound sub-activity cuts are used to isolate the full movement test in specific [6].”
BackgroundA Survey on Different Deep Learning Model for Human Activity Recognition based on Application
Bhaidasna, E. A. H. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i10.8700
AI for technological innovations and practices in engineering education
Rzhevska, N., Dobroskok, I., & Михайлович, Г. Р. (2023) · AIP conference proceedings · doi:10.1063/5.0173117
Human activity recognition of surveillance videos using multilayer perceptron
Su, J., & Lina, L. (2023) · AIP conference proceedings · doi:10.1063/5.0127838
An Efficient Service-based System for Hierarchical Human Activity Sensing
Pawar, B. R., Bhattacharya, S., Sharma, V., Bhavsar, K., & Ghose, A. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc40787.2023.10340230
Li, H., & Xu, W. (2023) · International Conference on Computers, Information Processing and Advanced Education (CIPAE) · doi:10.1109/cipae60493.2023.00074
“…Markov Models (Hmm) in talk taking care of moves the analyst for action affirmation in accounts since records can be considered as a social event of progress outlines like state progress in Hmm. Shan et al. [7] proposed a slicing portrayal based method for dealing with see human action in accounts.”
MethodRetractedMODEL KLASYFIKACJI AKTYWNOŚCI NA BAZIE CZUJNIKÓW DLA SYSTEMÓW VR
Bernaś, M., & MARTSENYUK, V. (2023) · doi:10.53052/9788367652124.02
MONITOROWANIE I KLASYFIKACJA RUCHÓW UŻYTKOWNIKA W ŚRODOWISKU VR
Krawczyk, J., & Bernaś, M. (2023) · doi:10.53052/9788367652124.16
Abbas, M. (2021) · theses.fr (ABES) · doi:10.70675/0e24f440za090z4f9czae50z84bcb653fb1b · Cited by 1
Enhancing Class Monitoring Through Video Analytics and Deep Learning Models
Kushwaha, R., Rawat, H., Bando, S., Dass, A. K., Panwar, L., Srivastava, D., & Singal, G. (2023) · International Conference on Modeling, Simulation & Intelligent Computing (MoSICom) · doi:10.1109/mosicom59118.2023.10458742
“The suggested technique enhances radar data-cube-based human activity recognition [11], [12].”
MethodMethodology for Smartwatch-Based Complex Human Activity Recognition in Production SystemsPreprint
Mishchuk, M., Pavliuk, O., & Cupek, R. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4779157
Human activity recognition with a multibranch network based on CNN and LSTM
Yuan, R., Zhang, Y., Wang, L., & Li, S. (2024) · International Conference on Computer Technology, Information Engineering, and Electron Materials (CTIEEM) · doi:10.1117/12.3023366
“Murad [8] proposed a deep recurrent network architecture based on LSTM for classifying six different Activities of Daily Living (ADL).”
BackgroundBrain-Computer Interface Technology in Stroke Rehabilitation
Zhao, C. (2024) · MedScien · doi:10.61173/4y3cdc08
Contribution to Methodologies for Human Activity Recognition: Focusing on the Visually Impaired
Jaén-Vargas, M. (2024) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.82209
A Survey on Deep Learning Based Human Activity Recognition System
Thomas, A. L., & Judith, J. E. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-73065-8_10
Analysis of human action recognition using CNN algorithm in comparison with ANN algorithm
Basha, S. N., & Dass, P. (2024) · AIP conference proceedings · doi:10.1063/5.0233121
Sensing and Communication Integration Based Fall Detection with Commercial WiFi
Chen, Y., Sun, Z., Wang, Z., Yu, Z., & Guo, B. (2024) · International Conference on Artificial Intelligence of Things and Systems (AIoTSys) · doi:10.1109/aiotsys63104.2024.10780526
OneTrack-M: A Multitask Approach for Transformer-Based MOT Models
Filho, L. C. S. D. A., & Figueiredo, C. M. S. (2026) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2026.4636
“The strategy adopted by the model involves using the Vision Transformer encoder pre-trained on ImageNet [Murad and Pyun, 2017] to extract attention maps, converting each image patch into an input sequence element.”
Peng, Z., & Zeng, W. (2024) · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · doi:10.1109/csis-iac63491.2024.10919440
Solution Architecture & Design Roswell, G., & Kundu, S. (2022) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem17141
Human Activity Recognition Using Transformer Model
Ghafoor, H. Y., Izhar, M., Zubair, M., Abid, M. N., & Jahangir, R. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-77620-5_12
Salimi, M., Alves, C. M. A., Cardoso, A., Bicho, E. G., Louro, L., Colim, A., Machado, J. J. M., Tavares, J. M. R. S., & Fernandes, D. (2025) · International Conference on Automation, Robotics and Applications · doi:10.1109/icara64554.2025.10977610
“The other model that we applied to the novel dataset was RNN. RNN is a specific neural network type well known for the possibility of keeping a memory of the inputs from long before using their internal states, which is their ability to do [10].”
InfluentialGong, F., & Yang, F. (2025) · Research Square · doi:10.21203/rs.3.rs-6309936/v1
AI-Driven Gait Classification Using Portable Wearable Sensors: Advances and Case Study
Nahar, S., Sojitra, P., & Vashista, V. (2025) · Studies in systems, decision and control · doi:10.1007/978-3-031-86977-8_9
Broad Fractional Order Fuzzy System for Time Series ClassificationPreprint
Zhang, D., Zhang, T., Zhang, T., Cheng, L., Chen, C. L. P., & Li, G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5372221
On the Utilization of Sensor-Based Machine Learning Approaches for Human Activity Recognition
Hamid, S., Javed, T., Khan, A., & Iqbal, S. (2025) · Journal of Engineering and Applied Sciences , University of Engineering and Technology, Peshawar · doi:10.17582/journal.jeas/44.13.26
Metadata
- Authors
- Murad, A., & Pyun, J.-Y.
- Affiliations
- Chosun University (KR)
- Corresponding author
- Pyun, Jae-Young
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2017-11-06
- Volume
- 17
- Issue
- 11
- Pages
- 2556
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC5712979
- OpenAlex
- W2767979715
- Cited by
- 524
- References
- 33
- Citations by year
- 2026: 27 · 2025: 45 · 2024: 57 · 2023: 60 · 2022: 81 · 2021: 82 · 2020: 80 · 2019: 45 · 2018: 19 · 2017: 2
- FWCI
- 16.57
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- 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 › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Keywords
- human activity recognition, deep recurrent neural networks, long short-term memory, wearable sensors, temporal dependencies, bidirectional LSTM, wearable sensor data
- MeSH terms
- Machine Learning, Algorithms, Humans, Human Activities, Neural Networks, Computer
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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.