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 101–200 of 545
Energy-aware human activity recognition for wearable devices: A comprehensive review
Contoli, C., Freschi, V., & Lattanzi, E. (2024) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2024.101976 · Cited by 55
A Semi-Automatic Annotation Approach for Human Activity Recognition
Bota, P. J., da Silva, J. K. A., Folgado, D., & Gamboa, H. F. S. (2019) · Sensors · doi:10.3390/s19030501 · Cited by 48
“On this account, many on-body sensor-based machine learning classification techniques have surged applied in the context of HAR with increasing improved results [2,4,5,9], namely, SL [9–13], Unsupervised Learning (UL) [9,14,15] and more recently, deep learning techniques [16–18].”
MethodHuman Activity Recognition Using CNN & LSTM
Shiranthika, C., Premakumara, N., Chiu, H., Samani, H. A., Shyalika, C., & Yang, C. (2020) · International Conference on Information Technology Research (ICITR) · doi:10.1109/icitr51448.2020.9310792 · Cited by 53
“In [4] researchers have implemented and improved a stacked LSTM architecture for the feature-free classification of activities using both accelerometer and gyroscope signals as the raw data input.”
Knowledge discovery in temporal databases
Saraee, M. H. (1995) · doi:10.1049/ic:19950112 · Cited by 46
Prediction of Human Activities Based on a New Structure of Skeleton Features and Deep Learning Model
Jaouedi, N., Perales, F. J., Rubio, J. M. B., Boujnah, N., & Bouhlel, M. S. (2020) · Sensors · doi:10.3390/s20174944 · Cited by 45
“Murad and Ryun 2017 [15] and Qin et al. [16] applied body-worn sensors and Long Short Term Memory (LSTM) Recurrent Neural Networks for human motion description.”
BackgroundGeomagnetic Field Based Indoor Landmark Classification Using Deep Learning
Bhattarai, B., Yadav, R. K., Gang, H.-S., & Pyun, J.-Y. (2019) · IEEE Access · doi:10.1109/access.2019.2902573 · Cited by 44
“We introduce the implementation of bidirectional DRNNs for magnetic landmark classification.”
BackgroundMethodSelf-citationA Comprehensive Methodological Survey of Human Activity Recognition Across Diverse Data Modalities
Shin, J., Hassan, N., Miah, A. S. M., & Nishimura, S. (2025) · Sensors · doi:10.3390/s25134028 · Cited by 58
Music genre recognition using convolutional recurrent neural network architecture
Bisharad, D., & Laskar, R. H. (2019) · Expert Systems · doi:10.1111/exsy.12429 · Cited by 42
“CNNs can capture spatial dependencies of data in the feature space, whereas RNNs can capture the temporal dependency among the input sequences (Murad & Pyun, 2017).”
Wearable Antennas for Cross-Body Communication and Human Activity Recognition
Su, W., Zhu, J., Liao, H., & Tentzeris, M. M. (2020) · IEEE Access · doi:10.1109/access.2020.2982965 · Cited by 43
“in various kinds of HAR applications such as [38]–[40], due to its effectiveness in capturing useful patterns of previous observations, providing longer-range context for the current classification, and processing time series when there can be long time lags of unknown size between important events.”
BackgroundHybrid deep learning approaches for smartphone sensor-based human activity recognition
Ghate, V., & Sweetlin Hemalatha, C. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10478-4 · Cited by 42
Synthetic Sensor Data for Human Activity Recognition
Alharbi, F., Ouarbya, L., & Ward, J. A. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206624 · Cited by 40
“Since LSTMs in [10] and [11] and 1-D CNN in [12] and [13] have been successful in recognizing activity from raw sensor data and were implemented in both [14] and [15] for sensor data generation, we adopted them for this study.”
MethodUpper Body Posture Recognition Using Inertial Sensors and Recurrent Neural Networks
Tang, H.-Y., Tan, S.-H., Su, T.-Y., Chiang, C.-J., & Chen, H.-H. (2021) · Applied Sciences · doi:10.3390/app112412101 · Cited by 46
“Therefore, HAR research that uses DL models, such as the Convolutional Neural Network (CNN) [21–23], the Long Short-Term Memory Network (LSTM) [24–26], and the Recurrent Neural Network (RNN) [27,28], has recently increased in popularity.”
BackgroundMethodEssahraui, S., Lamaakal, I., Maleh, Y., Makkaoui, K. E., Bouami, M. F., Ouahbi, I., El‐Latif, A. A. A., Almousa, M., & Rodrigues, J. J. P. C. (2025) · IEEE Access · doi:10.1109/access.2025.3589938 · Cited by 44
“Studies such as [237], [238], [239], [240], [241], [242], and [243] have leveraged LSTMs for detecting a variety of human activities, including daily tasks, locomotion, and health-related actions.”
An active semi-supervised deep learning model for human activity recognition
Bi, H., Perelló-Nieto, M., Santos‐Rodríguez, R., Flach, P. A., & Craddock, I. J. (2022) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-022-03768-2 · Cited by 39
“Murad and Pyun (2017) proposed to use RNN for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences.”
BackgroundSensor-data augmentation for human activity recognition with time-warping and data masking
Jeong, C. Y., Shin, H. C., & Kim, M. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10600-0 · Cited by 38
Machine Learning‐Enhanced Triboelectric Sensing Application
Shang, R., Chen, H., Cai, X., Shi, X., Yang, Y., Wei, X., Wang, J., & Xu, Y. F. (2024) · Advanced Materials Technologies · doi:10.1002/admt.202301316 · Cited by 39
Muñoz-Organero, M., Powell, L., Heller, B., Harpin, V., & Parker, J. (2019) · Sensors · doi:10.3390/s19132935 · Cited by 36
“The authors in [18] not only showed that deep RNNs achieved better results for Human Activity Recognition than other Deep Networks such as Convolutional Neural Networks (CNN) and other shallow methods such as Support Vector Machines (SVM) but also showed that the architecture of the RNN will have an impact in the resu…”
BackgroundMethodA Globally Regularized Joint Neural Architecture for Music Classification
Ashraf, M., Geng, G., Wang, X., Ahmad, F., & Abid, F. (2020) · IEEE Access · doi:10.1109/access.2020.3043142 · Cited by 42
“CNNs are favorable to record the spatial dependencies concerning feature domain [6], [7], whereas RNNs reasonably handle temporal dependencies in sequential data [8].”
BackgroundCapsGaNet: Deep Neural Network Based on Capsule and GRU for Human Activity Recognition
Sun, X., Xu, H., Dong, Z., Shi, L., Liu, Q., Li, J., Li, T., Fan, S., & Wang, Y. (2022) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3153503 · Cited by 38
“Thearchitectureusedin[29]utilizesdeep RNNstobuildactivityrecognitionmodelswhichcancapture long-termdependencyinvariable-lengthinputsequences.”
Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition
Jeyakumar, J. V., Lee, E. S., Xia, Z., Sandha, S. S., Tausik, N., & Srivastava, M. B. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3267529 · Cited by 41
“To avoid feature selection, modern deep learning techniques like CNN [32, 10], Deep Recurrent Neural Networks [18], ConvLSTM [21, 20] are used for activity recognition which directly takes raw data as input.”
MethodThe Future of Human Activity Recognition: Deep Learning or Feature Engineering?
Kanjilal, R., & Uysal, I. (2021) · Neural Processing Letters · doi:10.1007/s11063-020-10400-x · Cited by 42
A multi-scale feature extraction fusion model for human activity recognition
Zhang, C., Cao, K., Lu, L., & Deng, T. (2022) · Scientific Reports · doi:10.1038/s41598-022-24887-y · Cited by 46
“Murad et al. 40 proposed 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 and compared them with methods such as KNN and SVM, and experiments showed that DRNNs can achieve…”
MethodHu, Y., Zhang, X.-Q., Xu, L., Xian He, F., Tian, Z., She, W., & Liu, W. (2020) · IEEE Access · doi:10.1109/access.2020.3003162 · Cited by 36
‘A soundtrack to the insurrection’: street music, marching bands and popular protest
McKay, G. (2007) · Parallax · doi:10.1080/13534640601094817 · Cited by 35
HHAR-net: Hierarchical Human Activity Recognition using Neural Networks
Fazli, M., Kowsari, K., Gharavi, E., Barnes, L., & Doryab, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68449-5_6 · Cited by 44
Study on Human Activity Recognition Using Semi-Supervised Active Transfer Learning
Oh, S., Ashiquzzaman, A., Lee, D. S., Kim, Y., & Kim, J. (2021) · Sensors · doi:10.3390/s21082760 · Cited by 39
Corpus Tools and Methods, Today and Tomorrow: Incorporating Linguists' Manual Annotations
Smith, N., Hoffmann, S., & Rayson, P. (2007) · Literary and Linguistic Computing · doi:10.1093/llc/fqn004 · Cited by 35
MMTSA: Multi-Modal Temporal Segment Attention Network for Efficient Human Activity Recognition
Gao, Z., Wang, Y., Chen, J., Xing, J., Patel, S., Liu, X., & Shi, Y. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3610872 · Cited by 44
Human-Robot Collaboration by Intention Recognition using Deep LSTM Neural Network
Yan, L., Gao, X., Zhang, X., & Chang, S. (2019) · International Conference on Fluid Power and Mechatronics · doi:10.1109/fpm45753.2019.9035907 · Cited by 33
Human activity recognition adapted to the type of movement
Gil-Martín, M., San-Segundo, R., Fernández-Martínez, F., & de Córdoba, R. (2020) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2020.106822 · Cited by 36
Petroșanu, D.-M., & Pîrjan, A. (2020) · Sustainability · doi:10.3390/su13010104 · Cited by 34
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
Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting
Murad, A., Kraemer, F. A., Bach, K., & Taylor, G. (2021) · Sensors · doi:10.3390/s21238009 · Cited by 44
“One class of RNNs is the long short-term memory (LSTM), which is used extensively in sequence modeling tasks, such as modeling language [55], forecasting weather [56] and traffic [57], recognizing human activity [58], and recently forecasting COVID-19 transmission [59].”
Self-citationLSTM-Guided Coaching Assistant for Table Tennis Practice
Lim, S.-M., Oh, H.-C., Kim, J., Lee, J., & Park, J. (2018) · Sensors · doi:10.3390/s18124112 · Cited by 34
“Classical machine learning methods can be considered as alternatives to the LSTM RNN, because they often have similar performance in some applications for HAR [3].”
BackgroundMethodResultInfluentialProgress of Human Action Recognition Research in the Last Ten Years: A Comprehensive Survey
Singh, P. K., Kundu, S., Adhikary, T., Sarkar, R., & Bhattacharjee, D. (2021) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-021-09681-9 · Cited by 36
CLC: A Consensus-based Label Correction Approach in Federated Learning
Zeng, B., Yang, X., Chen, Y., Yu, H., & Zhang, Y. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3519311 · Cited by 37
“Inspired by prior works [30], [19], we adopt one-dimensional CNN on this Human Action Recognition (HAR) task.”
MethodHuman worker activity recognition in a production floor environment through deep learning
Mastakouris, A., Andriosopoulou, G., Masouros, D., Benardos, P., Vosniakos, G.-C., & Soudris, D. (2023) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2023.08.020 · Cited by 34
Khusheef, A. S., Shahbazi, M., & Hashemi, R. (2022) · Progress in Additive Manufacturing · doi:10.1007/s40964-022-00371-x · Cited by 33
“To avoid possible misleading, the F1-score [42] is commonly evaluated, which is not prone to the aforementioned (1) TP + TN TP + TN + FP + FN problem, as it represents a harmonic mean of precision and recall, the two metrics that capture the performance w.r.t. each class.”
MethodTowards data-driven stroke rehabilitation via wearable sensors and deep learning
Kaku, A., Parnandi, A., Venkatesan, A., Pandit, N., Schambra, H., & Fernandez-Granda, C. (2020) · arXiv · doi:10.48550/arxiv.2004.08297 · Cited by 30
“Karungaru (2015), Oukrich et al. (2018) and Murad and Pyun (2017) successfully used recurrent networks like Long Short Term Memory (LSTM) and Bi-LSTM for activity recognition.”
Khusheef, A. S., Shahbazi, M., & Hashemi, R. (2023) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-023-08340-4 · Cited by 33
“Three metrics [56, 57] are used to quantitatively illustrate the models’ performance: • Overall Accuracy: • Class-based F1 score: inwhich,precision c = T P c T P c + FP c ,andrecall c = T P c T P c + FN c .”
PatchHAR: A MLP-Like Architecture for Efficient Activity Recognition Using Wearables
Wang, S., Zhang, L., Wang, X., Huang, W., Wu, H., & Song, A. (2024) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2024.3354261 · Cited by 33
“For fair comparisons, we strictly follow the same split strategy available in recent research literature [19], [20], [36], [37].”
MethodTransition-aware human activity recognition using an ensemble deep learning framework
Khan, S. I., Dawood, H., Khan, M. A., Issa, G. F., Hussain, A., Alnfiai, M. M., & Khan, M. A. (2024) · Computers in Human Behavior · doi:10.1016/j.chb.2024.108435 · Cited by 37
Abnormal behavior recognition using 3D-CNN combined with LSTM
Guan, Y., Hu, W., & Hu, X. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10667-9 · Cited by 30
Park, C., Yi, C., Choi, W. J., Lim, H.-S., Yoon, H. U., & You, S. H. (2023) · Digital Health · doi:10.1177/20552076231217817 · Cited by 34
Human fall detection using pose estimation: From traditional machine learning to vision transformers
Raza, A., Yousaf, M. H., Ahmad, W., Velastín, S. A., & Viriri, S. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109809 · Cited by 34
Intelligent system for human activity recognition in IoT environment
Khaled, H., Abu-Elnasr, O., Elmougy, S., & Tolba, A. S. (2021) · Complex & Intelligent Systems · doi:10.1007/s40747-021-00508-5 · Cited by 31
Petroșanu, D.-M., Pîrjan, A., Căruțașu, G., Tăbușcă, A., Zirra, D., & Perju-Mitran, A. (2022) · Electronics · doi:10.3390/electronics11182940 · Cited by 36
Ankalaki, S., & Thippeswamy, M. N. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15766-3 · Cited by 31
Chan, H., Ouyang, Y., Chen, R., Lai, Y., Kuo, C.-C., Liao, G.-S., Hsu, W.-Y., & Chang, Y. (2023) · Sensors · doi:10.3390/s23010495 · Cited by 28
“The aggregated features are then used to detect the falls during PAs [48,53,54] and classify various types of PAs [55] through a fully connected network.”
MethodMiah, A. S. M., Hwang, Y. S., & Shin, J. (2024) · IEEE Access · doi:10.1109/access.2024.3473828 · Cited by 33
“We preprocessed the dataset based on the existing protocol, where they used an average of N sliding windows [43], [44], [71], [72].”
MethodInfluentialA novel deep LSTM network for artifacts detection in microelectrode recordings
Hosny, M., Zhu, M., Gao, W., & Fu, Y. (2020) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2020.04.004 · Cited by 27
Deep Learning for Classifying Physical Activities from Accelerometer Data
Nunavath, V., Johansen, S., Johannessen, T. S., Jiao, L., Hansen, B. H., Berntsen, S., & Goodwin, M. (2021) · Sensors · doi:10.3390/s21165564 · Cited by 32
“[29], proposed LSTM-based deep RNNs (DRNNs) to build human activity recognition models for classifying activities and developed architectures based on deep layers of unidirectional and bidirectional RNNs.”
BackgroundMethodKnowledge-driven Egocentric Multimodal Activity Recognition
Huang, Y., Yang, X., Gao, J., Sang, J., & Xu, C. (2020) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3409332 · Cited by 32
“In addition, CNN-based [18, 19] and RNN-based [40, 66] architectures have also achieved competitive performances.”
BackgroundMethodRSSI-Based for Device-Free Localization Using Deep Learning Technique
Sukor, A. S. A., Kamarudin, L. M., Zakaria, A., Rahim, N. A., Sudin, S., & Nishizaki, H. (2020) · Smart Cities · doi:10.3390/smartcities3020024 · Cited by 26
“This makes them feasible to be deployed and used in supervised training using an end-to-end neural network [19].”
MethodWu, X., Jin, H., Ye, X., Wang, J., Lei, Z., Liu, Y., Wang, J., & Guo, Y. (2020) · Processes · doi:10.3390/pr9010033 · Cited by 26
“Feature extractors based on the fully convolutional network (FCN) and long short-term memory (LSTM) are used to capture long-term dependencies and extract local features of time series, respectively, and we use the advantages of CNN to automatically learn features [16] in the downsampling transformation representation…”
MethodHuman Activity Recognition for Indoor Localization Using Smartphone Inertial Sensors
Moreira, D., Barandas, M., Rocha, T., Alves, P., Santos, R., Leonardo, R., Vieira, P. A., & Gamboa, H. F. S. (2021) · Sensors · doi:10.3390/s21186316 · Cited by 28
High-Level Features for Human Activity Recognition and Modeling
Hartmann, Y., Liu, H., & Schultz, T. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-38854-5_8 · Cited by 29
“…on various well-established machine learning models such as Long Short-Term Memory (LSTM) [38,53], Basic and Deep Neural Networks [23,37,50], Convolutional Neural Networks [13,24,38,42,52,55], Recurrent Neural Networks [2,9,21,36,38,44], and Hidden Markov Models (HMM) [29,33,40], among others.”
Lowland floristic assessment of Pico da Neblina National Park, Brazil
Boubli, J. P. (2002) · Plant Ecology · doi:10.1023/a:1015832811209 · Cited by 26
Masum, A. K. M., Bahadur, E. H., Shan-A-Alahi, A., Chowdhury, M. A. U. Z., Uddin, M. R., & Noman, A. A. (2019) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt45670.2019.8944512 · Cited by 32
“HAR was led utilizing distinctive techniques [3, 4] and disparate recommendations.”
MethodMasiala, S., Huijbers, W., & Atzmueller, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.03428 · Cited by 30
“c mean of of 76% in the generic model and 84% in the personalized model. However, their method achieved a lower Specificity compared to the most comprehensive FoG detection methods. Also, Murad et al. [37] proposed the use of deep recurrent neural networks (deep RNN) for designing a human activity recognition model, te…”
MethodInertial Measurement Unit Sensors in Assistive Technologies for Visually Impaired People, a Review
Leiva, K. M. R., Jaén-Vargas, M., Codina, B., & Olmedo, J. J. S. (2021) · Sensors · doi:10.3390/s21144767 · Cited by 25
Human Activity Classification Using Multilayer Perceptron
Gorjani, O. M., Byrtus, R., Dohnal, J., Bilík, P., Koziorek, J., & Martínek, R. (2021) · Sensors · doi:10.3390/s21186207 · Cited by 32
“[12] noted that the size of convolutional kernels restricts the captured range of dependencies between data samples and suggested using deep recurrent neural networks instead.”
BackgroundIntelligent Recognition of Multimodal Human Activities for Personal Healthcare
Chakravarthy, S. R. S., Bharanidharan, N., Kumar, V. V., Mahesh, T. R., Bhatia, S., Almusharraf, A. I., & Albalawi, E. M. (2024) · IEEE Access · doi:10.1109/access.2024.3405471 · Cited by 26
“The authors [9] utilized a deep recurrent neural network (DRNN) architecture for recognizing human activities.”
MethodWearable sensors-based assistive technologies for patient health monitoring
Almujally, N. A., Khan, D., Mudawi, N. A., Alonazi, M., Alhasson, H. F., Jalal, A., & Liu, H. (2025) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2025.1437877 · Cited by 28
Modelling match outcomes and decision support for setting a final innings target in test cricket
Scarf, P., & Shi, X. (2005) · IMA Journal of Management Mathematics · doi:10.1093/imaman/dpi010 · Cited by 25
Jeong, C. Y., & Kim, M. (2019) · Sensors · doi:10.3390/s19173688 · Cited by 26
Human Activity Recognition Based on Acceleration Data From Smartphones Using HMMs
Iloga, S., Bordat, A., Kernec, J. L., & Romain, O. (2021) · IEEE Access · doi:10.1109/access.2021.3117336 · Cited by 26
ADAM-sense: Anxiety-displaying activities recognition by motion sensors
Khan, N. S., Ghani, M. S., & Anjum, G. (2021) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2021.101485 · Cited by 25
Human Activity and Gesture Recognition: A Review
Saini, R., & Maan, V. (2020) · International Conference Emerging Trends Communication, Control and Computing · doi:10.1109/iconc345789.2020.9117535 · Cited by 26
“Adopting artificial neural networks for Human activity recognition has been an effective method for extracting information, recently both researchers and industry are attracted to HAR but providing accurate information is a challenging task [1, 2].”
MethodD-SORM: A digital solution for remote monitoring based on the attitude of wearable devices
Abbas, M., Somme, D., & Jeannès, R. L. B. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106247 · Cited by 24
E-democracy: potential for Political Revolution?
Cullagh, K. M. (2003) · International Journal of Law and Information Technology · doi:10.1093/ijlit/11.2.149 · Cited by 24
Jeong, D., Kim, S.-E., Choi, W., & Ahn, S. (2022) · Healthcare · doi:10.3390/healthcare10071255 · Cited by 26
“In regard to the PA classification, the performance of the subject-specific paradigm was better than that of the group-level paradigm, which used the model pretrained with data from other subjects, due to the different sensor locations and behavioral patterns of each subject [38–40].”
MethodPark, J., Lim, W.-S., Kim, D., & Lee, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106543 · Cited by 25
A deep recurrent Q network towards self‐adapting distributed microservice architecture
Magableh, B., & Almiani, M. (2019) · Software Practice and Experience · doi:10.1002/spe.2778 · Cited by 25
“This method works well in many real-world examples as demonstrated in [57], [58].”
MethodA Hierarchical Learning Approach for Human Action Recognition
Lemieux, N., & Noumeir, R. (2020) · Sensors · doi:10.3390/s20174946 · Cited by 29
“More recently, Murad et al. [14] implemented a recurrent neural network (RNN) and demonstrated the prevalence of their method over SVM and k-NN.”
MethodUsing Graphs to Perform Effective Sensor-Based Human Activity Recognition in Smart Homes
Srivatsa, P., & Plötz, T. (2024) · Sensors · doi:10.3390/s24123944 · Cited by 28
“Consequently, CNNs have a restricted ability to capture dependencies between data samples [40].”
BackgroundMulti-modal lifelog data fusion for improved human activity recognition: A hybrid approach
Oh, Y., & Kim, S. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102464 · Cited by 25
Human activity classification using long short-term memory network
Welhenge, A. M., & Taparugssanagorn, A. (2018) · Signal Image and Video Processing · doi:10.1007/s11760-018-1393-7 · Cited by 24
“2 Architecture of LSTM process [16] In Fig.”
BackgroundMethodInfluentialKulchyk, J., & Etemad, A. (2019) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/sensors43011.2019.8956668 · Cited by 22
“For example, in [13], the authors employed deep recurrent networks, while in [14], HAR was performed with deep learning.”
BackgroundAbbasi, S., & Rezaee, K. (2024) · Brain and Behavior · doi:10.1002/brb3.70206 · Cited by 21
Wang, X., Wang, X., Lv, T., Jin, L., & He, M. (2021) · Sensors · doi:10.3390/s21206927 · Cited by 24
“Deep recurrent neural networks (DRNNs) [16] adopt unidirectional, bidirectional, and cascade structures based on the LSTM architecture, which can capture long-range dependencies in input sequences whose lengths are not fixed.”
BackgroundEhiabhi, J., & Wang, H. (2023) · BioMedInformatics · doi:10.3390/biomedinformatics3010014 · Cited by 33
Lee, Y., Wei, M.-Y., & Chen, Y. (2022) · Gait & Posture · doi:10.1016/j.gaitpost.2022.06.011 · Cited by 20
Vision Based Detection and Analysis of Human Activities
Ravipati, A., Kondamuri, R. K., Posonia, A. M., & Mayan, J. A. (2023) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei56765.2023.10125829 · Cited by 20
“Six separate behaviors may be recognised using data from smartphones, and AbdulmajidMurad [7] suggested using a deep Lstm to do so.”
BackgroundHamidi, A., Robertson, B., & Ilow, J. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2023.09.011 · Cited by 23
Pham, C.-H., Huynh‐The, T., Gooya, E. S., Elbouz, M., & Alfalou, A. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107854 · Cited by 24
Smart-Data-Glove-Based Gesture Recognition for Amphibious Communication
Fan, L., Zhang, Z., Zhu, B., Zuo, D., Yu, X., & Wang, Y. (2023) · Micromachines · doi:10.3390/mi14112050 · Cited by 22
“The basic model of deep learning (DL)-based gesture recognition mainly includes the convolutional neural network (CNN) [22], deep neural network (DNN) [23], and recurrent neural network (RNN) methods [24].”
BackgroundFirefly Algorithm-based Hyperparameters Setting of DRNN for Weather Prediction
Ahyar, L. F., Suyanto, S., & Arifianto, A. (2020) · International Conference on Data Science and Its Applications (ICoDSA) · doi:10.1109/icodsa50139.2020.9212921 · Cited by 19
“The RNN is an architecture of neural networks that contains cyclic connections, making it possible to learn data sequentially [29], [30].”
BackgroundMethodharAGE: A Novel Multimodal Smartwatch-based Dataset for Human Activity Recognition
Mallol-Ragolta, A., Semertzidou, A., Pateraki, M., & Schuller, B. W. (2021) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg52635.2021.9666947 · Cited by 22
Javeed, M., Mudawi, N. A., Alabduallah, B. I., Jalal, A., & Kim, W. (2023) · Sensors · doi:10.3390/s23104716 · Cited by 18
“Locomotion classi fi cation accuracy has been used for the performance validation of the proposed multimodal IoT-based locomotion classi fi cation system from the chosen challenging indoor datasets.”
Beyond Mobile Apps: A Survey of Technologies for Mental Well-Being
Woodward, K., Kanjo, E., Brown, D. J., McGinnity, T. M., Inkster, B., Macintyre, D. J., & Tsanas, A. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2020.3015018 · Cited by 18
“RNNs helped increase the accuracy of classifying daily activities by 4% [104] and have also been used to accurately classify raw ECG signals [105] and physical movement from a wearable [106] but little research has been conducted in using recurrent neural networks to classify mental well-being.”
MethodSupervised 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
“These include recurrent neural networks (RNNs) (Murakami & Taguchi, 1991; Murad & Pyun, 2017; Carfi et al., 2018; Koch et al., 2019), long short-term memory (LSTM) (Chen et al., 2016; Singh et al., 2017; Pienaar & Malekian, 2019) and convolutional neural networks (CNN) (Wang et al., 2019; Lee et…”
BackgroundContext-Aware Complex Human Activity Recognition Using Hybrid Deep Learning Models
Omolaja, A., Otebolaku, A., & Alfoudi, A. S. D. (2022) · Applied Sciences · doi:10.3390/app12189305 · Cited by 21
“The authors in [50] applied the RNN successfully on several HAR datasets with very good results.”
MethodA Review of Physical Human Activity Recognition Chain Using Sensors
AlShorman, O., Alshorman, B., & Masadeh, M. (2020) · Indonesian Journal of Electrical Engineering and Informatics (IJEEI) · doi:10.11591/ijeei.v8i3.2312 · Cited by 20
Hong, S., Ham, Y., Chun, J., & Kim, H. (2023) · Sensors · doi:10.3390/s23177635 · Cited by 18
“Therefore, two recurrent neural network (RNN) [74] (RNN and deep recurrent neural network (DRNN) [75,76])-based and two CNN (LeNET [77,78] and AlexNET [79,80])-based approaches were applied to the dataset used in this study.”
MethodInfluentialA FAST DEEP LEARNING TECHNIQUE FOR WI-FI-BASED HUMAN ACTIVITY RECOGNITION
Succetti, F., Rosato, A., Luzio, F. D., Ceschini, A., & Panella, M. (2022) · Electromagnetic waves · doi:10.2528/pier22042605 · Cited by 18
SensorGAN: A Novel Data Recovery Approach for Wearable Human Activity Recognition
Hussein, D., & Bhat, G. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3609425 · Cited by 24
“Recent HAR approaches have used neural networks including multilayer perceptrons (MLP), convolutional neural networks, and recurrent neural networks [5, 22, 25, 39].”
MethodTeng, Q., Tang, Y., & Hu, G. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3364187 · Cited by 18
“Nevertheless, the activity prediction performance of deep learning models [5], [6], [7], [8] may be negatively affected by the inherent biases and limitations imposed by sensory data itself.”
BackgroundA Statistical and Deep Learning Approach for Human Activity Recognition
Masum, A. K. M., Hossain, M. E., Humayra, A., Islam, S., Barua, A., & Alam, M. G. R. (2019) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei.2019.8862610 · Cited by 19
Big data quality prediction informed by banking regulation
Wong, K. Y., & Wong, R. K. (2021) · International Journal of Data Science and Analytics · doi:10.1007/s41060-021-00257-1 · Cited by 17
“To predict DQ, we utilize long short-term memory (“LSTM”) recurrent neural networks (“RNNs”) [91,123,126] to apply to the dataset.”
MethodResult
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.