Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Open accessThe DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index; 8 of the 23 sources its claims cite were checked for support.
Abstract
Introduces DeepConvLSTM, a deep learning architecture combining convolutional and LSTM recurrent units for multimodal wearable activity recognition, outperforming non-recurrent deep networks and handcrafted feature baselines by 4% to 9%.
Overview
CoChat Summary
TL;DR
The paper proposes DeepConvLSTM, a deep framework combining four convolutional layers with two LSTM recurrent layers for wearable activity recognition from raw multimodal sensor data. It reports improved F1 scores over a baseline CNN and prior results on the OPPORTUNITY and Skoda datasets, including 0.915 F1 for OPPORTUNITY gestures with the Null class and 0.958 F1 on Skoda.
Key findings
- On OPPORTUNITY, DeepConvLSTM achieved F1 scores of 0.930 for modes of locomotion without Null, 0.895 for modes with Null, 0.866 for gestures without Null, and 0.915 for gestures with Null; the baseline CNN scored 0.912, 0.878, 0.783, and 0.883, respectively. The paper reports a 6% average improvement over the best OPPORTUNITY challenge submissions and more than 9% improvement on gesture recognition without Null.
- On Skoda, DeepConvLSTM reached 0.958 F1, compared with 0.884 for the baseline CNN, 0.893 for CNN [43], and 0.861 for CNN [23], improving the best reported result by 6%.
- Multimodal fusion improved gesture recognition on OPPORTUNITY without Null: 0.689 F1 with accelerometers only, 0.611 with gyroscopes only, 0.745 with accelerometers + gyroscopes, 0.839 with accelerometers + gyroscopes + magnetic sensors, and 0.864 with the full OPPORTUNITY sensor set.
- DeepConvLSTM had 999,122 parameters versus 7,445,458 for the baseline CNN, a 600% increase for the baseline; training took 340.3 min versus 282.2 min, and classification took 6.68 s versus 5.43 s, with DeepConvLSTM classifying almost 15 min of data per second and achieving 900× real-time on the GPU used.
Methods
- DeepConvLSTM uses four convolutional layers with 64 feature maps each, followed by two dense LSTM layers with 128 cells and a softmax output; the baseline CNN shares the convolutional layers but uses two non-recurrent dense layers with 128 units. Models were trained supervised with cross-entropy loss, mini-batch gradient descent with RMSProp, learning rate 10e-3, decay factor 0.9, mini-batches of 100 segments, and dropout p=0.5 on dense-layer inputs.
- Inputs were sliding windows of 500 ms with 250 ms step size, using raw sensor data with minimal preprocessing: linear interpolation for missing values and per-channel normalization to [0,1]. Evaluation used weighted F1 to address class imbalance.
- Experiments used the OPPORTUNITY dataset (on-body sensors, 113 channels, 30 Hz; Task A: 5-class modes of locomotion/postures; Task B: 18-class sporadic gestures) and the Skoda dataset (one subject, 10 right-arm 3D accelerometers, decimated to 30 Hz, 10 manipulative gestures, about 3 h and about 70 repetitions per gesture). Analyses included comparison to baseline CNN and published results, confusion matrices, sensor-modality fusion, and hyperparameter evaluations of sequence length and number of convolutional layers.
Limitations
- The paper states that DeepConvLSTM has not yet been implemented on a wearable device; the GPU used clearly outperforms current high-end wearable computational power, and training is best envisioned server-side. It also states that pooling was omitted because the sliding-window setup limits downsampling, though pooling could be useful without that requirement, and that training time increases with the number of layers, creating a performance–computational budget trade-off.
- Evident from the text: Skoda evaluation uses one subject and only right-arm sensors, and OPPORTUNITY testing is limited to ADL4 and ADL5 for Subjects 2 and 3, which constrains generalizability. The text does not report cross-validation or statistical significance testing.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures



![Figure 4 Placement of on-body sensors used in the OPPORTUNITYdataset (left: inertial measurements units; right: 3-axis accelerometers) [7].](https://figures.cochat.ai/paper-figures/27c0e4b39d104fe2b5315587d736fd2d/deep-convolutional-and-lstm-recurrent-neural-networks-for-multimodal-wearable-figure-4.jpg)




Verification
Claims the paper makes
5 Valid · 5 Not valid · 13 Not checked · 99 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“The choice of the number of recurrent layers is made following the results presented in [33], where the authors showed that a depth of at least two recurrent layers is beneficial when processing sequential data.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture > 3.1. DeepConvLSTM
What the sources say
- Supportedcites [33] Karpathy, A., Johnson, J., and Li, F.F. (2015). Visualizing and understanding recurrent networks. Cornell Univ. Lab., arXiv:1506.02078. source
Section 4.1 compares recurrent networks with one, two, and three layers on two sequence datasets and states that a depth of at least two is consistently beneficial. This directly supports the attributed finding, within the paper’s tested settings. (LLM, conf=0.94)
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.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“This seems to indicate that although deep learning techniques are often employed with large amounts of data, (e.g., millions of frames in computer vision [22]), they may actually be applicable to problem domains where acquiring annotated data is very costly, such as in supervised activity recognition.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 5. Results and Discussion > 5.4. Discussion
What the sources say
- Supportedcites [22] Pigou, L., Oord, A.V.D., Dieleman, S., van Herreweghe, M., and Dambre, J. (2015). Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video. arXiv Preprint, arXiv:1506.01911. source
The citation is attached to the example of large-scale computer-vision data, not to the citing authors’ conclusion about costly annotation. Section 4.1 (page unavailable) reports 1,720,800 labeled video frames in the gesture-recognition dataset, supporting the cited example of data on the order of millions of frames. (LLM, conf=0.86)
hedgedstates a possible 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 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 baseline CNN also offers better results than the OPPORTUNITY submissions in the recognition of models of locomotion.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 5. Results and Discussion > 5.1. Performance Comparison
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether 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
“From the results, we can also see how the model is able to learn from signals obtained from accelerometers, gyroscopes and magnetometers, fusing them without requiring any specific preprocessing.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 6. Conclusions
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.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“(iv) it is applicable even if the gestures are longer than the observation window.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 5. Results and Discussion > 5.4. Discussion
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: unclear — It is unclear why the paper says it holds.
84 more claims
Create a free account to see all 122 claims and to verify the 2 references still open.
- It may state two separate claims as one. 14
- Probably not a substantial claim. 23
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 cited source doesn’t support the claim as written.
In the citing paper
“However, these complex network framework suffered from low ef ciency and can hardly meet real-time requirements in practice applications.”
From InnoHAR: A Deep Neural Network for Complex Human Activity Recognition (2019) · cites this paper as [19]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe cited source doesn’t support the claim as written.
In the citing paper
“However, due to the lack of filtration techniques applied to multimodal data, the system’s performance was low.”
From A Multimodal IoT-Based Locomotion Classification System Using Features Engineering and Recursive Neural Network (2023) · cites this paper as [15]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“and yield better performances than pure CNNs or LSTM networks [12]”
From Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors (2018) · cites this paper as [12]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The proposed method outperforms other methods, such as those based on deep believe networks (DBNs) [10], SVM [10], and CNNs [13].”
From Deep Recurrent Neural Networks for Human Activity Recognition (2017) · cites this paper as [13]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The popular DeepConvLSTM model [7] can only afford four, moderately-sized convolution layers to learn effective data representations, and two LSTM layers for sequence modeling.”
From Complex Deep Neural Networks from Large Scale Virtual IMU Data for Effective Human Activity Recognition Using Wearables (2021) · cites this paper as [7]
Experimental — accuracy not yet measured
20 more claims about this paper
Create a free account to see every claim other papers make about this one.
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 major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture
“The length of the kernels is the same for every convolutional layer, being defined as Pl=5,∀l=2,⋯,5.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 4. Experimental Setup > 4.2. Performance Measure
“Following the OPPORTUNITY challenge experimental setup, the length of the window is 500 ms, with a step size of 250 ms.”
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“| Total | 996,800 +(128×nc)+nc | 996,800 +(128×nc)+nc | 7,443,136+(128×nc)+nc | 7,443,136+(128×nc)+nc |”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture > 3.3. Model Implementation and Training
Reported 996800 · recomputed 1037888
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“| 6 | Wai,Waf,Wac,Wao: 7232×128 | 942,592 | W: 57,856×128 | 7,405,696 |”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture > 3.3. Model Implementation and Training
Reported 942592 · recomputed 3702784
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“| 7 | Wai,Waf,Wac,Wao: 128×128 | 33,280 | W: 128×128 | 16,512 |”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture > 3.3. Model Implementation and Training
Reported 33280 · recomputed 131072
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 1×
“Other publications showed much deeper networks, such as “GoogLeNet”, which is a 27-layer deep neural network applied to image classification [45].”
BackgroundReducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Speech 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 1×
“Networks using LSTM cells have offered better performance than standard recurrent units in speech recognition, where they gave state-of-the-art results in phoneme recognition [20].”
BackgroundConvolutional networks for images, speech, and time series
LeCun, Y., & Bengio, Y. (1998) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.5555/303568.303704 · Cited by 4,231
The class imbalance problem: A systematic study1
Japkowicz, N., & Stephen, S. (2002) · Intelligent Data Analysis · doi:10.3233/ida-2002-6504 · Cited by 3,295
DeepPose: Human Pose Estimation via Deep Neural Networks
Toshev, A., & Szegedy, C. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.214 · Cited by 3,185 · cited 1×
“Deep CNNs have had a major impact on fields, like content recommendation [24], speech recognition [25] and in computer vision [26–28], where they have become the de facto standard approach.”
BackgroundOverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680 · cited 1×
“Deep CNNs have had a major impact on fields, like content recommendation [24], speech recognition [25] and in computer vision [26–28], where they have become the de facto standard approach.”
BackgroundLee, H., Grosse, R., Ranganath, R., & Ng, A. Y. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553453 · Cited by 2,412 · cited 1×
“Deep learning techniques have outperformed many conventional methods in computer vision [13] and audio classification [14].”
MethodA review of wearable sensors and systems with application in rehabilitation
Patel, S., Park, H., Bonato, P., Chan, L., & Rodgers, M. (2012) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/1743-0003-9-21 · Cited by 2,396 · cited 1×
“, from simple hand gestures to complex activities, such as “cooking a meal”) and the context in which they occur from sensor data is at the core of smart assistive technologies, such as in smart homes [1], in rehabilitation [2], in health support [3,4], in skill assessment [5] or in industrial settings [6].”
Background
Research works printed but not linked: 1
- LeCun, Y., and Bengio, Y. (1998). The Handbook of Brain Theory and Neural Networks, MIT Press.
Cited by
Items 1,301–1,400 of 2,806
Zou, H., Chen, Z., Zhang, J., Wang, L., Zhang, F., Li, J., & Pan, Y. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3378331 · Cited by 18
Overcoming Data Scarcity in Human Activity Recognition*
Konak, O., Liebe, L., Postnov, K. V., Sauerwald, F., Gjoreski, H., Luštrek, M., & Bert Arnrich, A. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc40787.2023.10340387 · Cited by 11
Human Activity Recognition based on Acceleration sensor and Neural Network
Wenzheng, Z. (2020) · International Conference on Orange Technology (ICOT) · doi:10.1109/icot51877.2020.9468785 · Cited by 13
“The experimental results show that the deep structure based on convolution and LSTM cycle layer is better than the previous results and can improve the ability to identify similar activities [9].”
ResultMLPs Are All You Need for Human Activity Recognition
Ojiako, K., & Farrahi, K. (2023) · Applied Sciences · doi:10.3390/app132011154 · Cited by 12
WashSpot: Real-Time Spotting and Detection of Enacted Compulsive Hand Washing with Wearable Devices
Burchard, R., Scholl, P., Lieb, R., Laerhoven, K. V., & Wahl, K. (2022) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3544793.3563428 · Cited by 13
Scoring Performance on the Y-Balance Test Using a Deep Learning Approach
Gil-Martín, M., Johnston, W., San-Segundo, R., & Caulfield, B. M. (2021) · Sensors · doi:10.3390/s21217110 · Cited by 18
He, M., Li, H., Xu, J., Wang, H., Xu, W., & Chen, S. (2021) · Water Science and Engineering · doi:10.1016/j.wse.2021.06.003 · Cited by 10
A Lightweight and Accurate RNN in Wearable Embedded Systems for Human Activity Recognition
Falaschetti, L., Biagetti, G., Crippa, P., Alessandrini, M., Giacomo, D. F., & Turchetti, C. (2022) · Smart innovation, systems and technologies · doi:10.1007/978-981-19-3444-5_40 · Cited by 12
Smart-Badge: A wearable badge with multi-modal sensors for kitchen activity recognition
Liu, M., Suh, S., Zhou, B., Gruenerbl, A., & Lukowicz, P. (2022) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3544793.3560391 · Cited by 17
“The F1score is defined by the equation 1, which decided by the precision ( TP TP+FP ) and the recall ( TP TP+FN ), where TP, FP are the number of true and false positives, respectively, and FN corresponds to the number of false negatives [22].”
BackgroundLSTM with Uniqueness Attention for Human Activity Recognition
Zheng, Z., Shi, L., Wang, C., Sun, L. J., & Pan, G. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30508-6_40 · Cited by 9
Rücker, N., Pflüger, L., & Maier, A. (2021) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-020-00411-4 · Cited by 12
Few-shot pulse wave contour classification based on multi-scale feature extraction
Lu, P., Liu, C., Mao, X., Zhao, Y., Wang, H., Zhang, H., & Guo, L. (2021) · Scientific Reports · doi:10.1038/s41598-021-83134-y · Cited by 11
Singh, A., Pandey, P., & Nandi, G. C. (2020) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-01-2020-0010 · Cited by 10
Tamamori, A., Hayashi, T., Toda, T., & Takeda, K. (2017) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2017.8282239 · Cited by 10
“Especially, in [24], the combination of CNNs and LSTM-RNNs was proposed for HAR, where a stack of CNNs was utilized as feature extractor and a stack of LSTM-RNNs followed.”
MethodImplementation of a Classification System of EEG Signals Based on FPGA
Asanza, V., Constantine-Macías, A., Valarezo, S., & Peláez, E. (2020) · International Conference on eDemocracy & eGovernment · doi:10.1109/icedeg48599.2020.9096752 · Cited by 12
“Some of the machine learning algorithms used to detect motor intentions are: Support Vector Machines (SVM) [21], Artificial Neural Networks (ANN) [21,22], Linear Discriminant Analysis (LDA) [9,21,23] and clustering algorithms [24].”
MethodSports activity recognition with UWB and inertial sensors using deep learning approach
Pająk, I., Krutz, P., Patalas‐Maliszewska, J., Rehm, M., Pająk, G., Schlegel, H., & Dix, M. (2022) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee55066.2022.9882654 · Cited by 14
“…it is considered that reduction of insignificant signals occurs during training of the network by the suitable selection of convolutional filters [17] however, such an approach does not decrease the number of input signals and, as a consequence, the computational effort needed to obtain a…”
BackgroundAssessing the Soldier Survivability Tradespace Using a Single IMU
Mavor, M. P., Chan, V. C. H., Gruevski, K. M., Bossi, L. L. M., Karakolis, T., & Graham, R. B. (2023) · IEEE Access · doi:10.1109/access.2023.3286305 · Cited by 10
“, time series) and the node architecture allowing LSTM nodes to retain memory from previous data windows [23], whereas”
BackgroundMethodInfluentialLiu, J., Zhang, L., Liu, X., Yao, M., Wang, L., Wu, H., & Song, A. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3565646 · Cited by 13
“Following recent literature [29], [45], the window size is set to 30, and each sensor axis is treated as a channel, resulting in 113 channels for a fair comparison.”
InfluentialFlexible Fashion Product Retrieval Using Multimodality-Based Deep Learning
Jo, Y., Wi, J., Kim, M., & Lee, J. Y. (2020) · Applied Sciences · doi:10.3390/app10051569 · Cited by 11
Hand Gesture Recognition on a Resource-Limited Interactive Wristband
Shenglin, Z., Cai, H., Li, W., Liu, Y., & Liu, C. (2021) · Sensors · doi:10.3390/s21175713 · Cited by 13
“…is composed of five procedures: (1) signal acquisition, (2) acceleration coordinate transformation to the world frame, (3) motion mode detection It is composed of five procedures: (1) signal acquisition, (2) acceleration coordinate transformation to the world frame, (3) motion mode detection these”
MethodChatterjee, K., Raju, M., Selvamuthukumaran, N., Pramod, M. J. P., Kumar, B. K., Bandyopadhyay, A., & Mallik, S. (2024) · Information · doi:10.3390/info15020085 · Cited by 11
“Furthermore, to model inter-channel relationships and long-term dependencies within sensory signals, researchers designed 2D convolution with RNNs and LSTM neural networks to capture the long-term sequential correlations [5–7].”
A Review on Human Action Recognition Approaches
Gupta, S. C., Kumar, D., & Athavale, V. A. (2021) · IEEE International Conference on Communication Systems and Network Technologies (CSNT) · doi:10.1109/csnt51715.2021.9509646 · Cited by 11
SensiX++: Bringing MLOps and Multi-tenant Model Serving to Sensory Edge Devices
Min, C., Mathur, A., Acer, U. G., Montanari, A., & Kawsar, F. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3617507 · Cited by 23
“This possibility has uncovered a new era of afordable artiicial intelligence (AI) applications, from personal assistants to recommendation systems to video surveillance available through various edge devices [10, 23, 32, 35, 37, 48, 53, 63].”
BackgroundDeep learning based ankle–foot movement classification for prosthetic foot
Fandakli, S. A., & Okumuş, H. İ. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09780-1 · Cited by 11
“The proposed method’s performance was tested on the Opportunity dataset and the Skoda dataset, showcasing satisfactory results compared to traditional machine learning methods [25].”
Research on Applications of Artificial Intelligence in Business Management of Power Grid Enterprises
Chai, B., Zhang, Q., Chen, Q., Zhao, T., & Gao, K. (2019) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac47372.2019.8997608 · Cited by 10
“Machine translation, semantic understanding, and natural language generation are the key technologies of natural language processing [7].”
BackgroundFusing Object Information and Inertial Data for Activity Recognition
Diete, A., & Stuckenschmidt, H. (2019) · Sensors · doi:10.3390/s19194119 · Cited by 12
“However, recently, Ordóñez et al.[35] also employed Neural Networks for similar tasks.”
BackgroundDesign of a seniors and Alzheimer's disease caring service platform
Lee, C.-W., & Chuang, H.-M. (2021) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-021-01626-3 · Cited by 11
Zhang, S., Ng, W. W. Y., Zhang, J., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67585-5_50 · Cited by 10
Abbas, M., & Jeannès, R. L. B. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3000394 · Cited by 12
“The second path relies on deep Convolutional Neural Networks (CNN) [28] and Long Short-Term Memory (LSTM) recurrent neural networks [29], which automate the extraction of features from raw data inputs acquired from sensors.”
BackgroundOn-Device Lumbar-Pelvic Movement Detection Using Dual-IMU: A DNN-Based Approach
Zhang, Y., Haghighi, P. D., Burstein, F. V., Yao, L., & Cicuttini, F. (2021) · IEEE Access · doi:10.1109/access.2021.3074755 · Cited by 11
“Many studies have taken advantage of these DNN models to recognise various high-level physical activities with higher accuracy, including 1D CNNs [26], CNN-LSTM [27] and Bidirectional LSTM [28].”
BackgroundMethodPhysiological Data-Based Evaluation of a Social Robot Navigation System
Kivrak, H., Uluer, P., Köse, H., Gümüşlü, E., Barkana, D. E., Çakmak, F., & Yavuz, S. (2020) · IEEE RO-MAN · doi:10.1109/ro-man47096.2020.9223539 · Cited by 13
“memory recurrent neural network [23], [24] have been used to recognize the emotions.”
MethodMallick, R., Yebda, T., Benois‐Pineau, J., Zemmari, A., Pech, M., & Amieva, H. (2021) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi50038.2021.9461910 · Cited by 13
“The accuracy scores on UCI-HAR dataset according to [21], on CNN networks and Deep ConvLSTM [22] are around 92%.”
MethodXiang, L., Gu, Y., Wang, A., Shim, V., Gao, Z., & Fernandez, J. (2023) · Journal of Human Kinetics · doi:10.5114/jhk/163059 · Cited by 11
“Human activity could be accurately recognized by inertial measurement unit (IMU) sensors using one-dimensional convolutional neural networks (CNN1D) and long-short term memory (LSTM) networks (Ordóñez and Roggen, 2016).”
MethodInfluentialSensor-based activity recognition via learning from distributions
Qian, H. (2019) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/137691 · Cited by 9
Adapted Long Short-Term Memory (LSTM) for Concurrent\\ Human Activity Recognition
Thapa, K., Al, Z. M. A., & Yang, S. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2021.015660 · Cited by 9
“The HAR process consisted of four phases: data acquisition, preprocessing, feature extraction, and training/testing, as shown in Fig.”
BackgroundInfluentialTemperature monitoring and prediction under different transmission modes
Chen, W., Yang, Q., Gao, S., et al. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107140 · Cited by 9
Sun, J., Ru, J., Chen, Z., Qi, F., Ramos‐Mucci, L., Chen, S., Cribbs, A. P., Deng, L., & Wang, X. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24031878 · Cited by 9
Sensor-Based Open-Set Human Activity Recognition Using Representation Learning With Mixup Triplets
Lee, M., & Kim, S. B. (2022) · IEEE Access · doi:10.1109/access.2022.3221425 · Cited by 12
Detection of social signals for recognizing engagement in human-robot interactionPreprint
Lala, D., Inoue, K., Milhorat, P., & Kawahara, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.10257 · Cited by 21
“We used a long short-term memory (LSTM) network (Hochreiter and Schmidhuber 1997) for the head nodding model, which can be readily applied to gesture recognition (Ord´o˜nez and Roggen 2016).”
MethodCompressed Deep Learning Model For Human Activity Recognition
k, A. A. O., Semwal, V. B., & Soni, V. (2024) · IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS) · doi:10.1109/sceecs61402.2024.10482048 · Cited by 11
“Few studies have addressed these factors, with some like Lane et al.’s [7], [8] approach being unreproducible due to inaccessible datasets.”
BackgroundUhlenberg, L., Haeusler, L. O., & Amft, O. (2024) · IEEE Access · doi:10.1109/access.2024.3513477 · Cited by 16
“The DeepConvLSTM architecture combines convolutional and recurrent layers with a final linear layer and softmax activation [12] (see Fig.”
InfluentialPredicting Performance Improvement of Human Activity Recognition Model by Additional Data Collection
Tanigaki, K., Teoh, T. C., Yoshimura, N., Maekawa, T., & Hara, T. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3550319 · Cited by 12
“In our experiment, a convolutional LSTM model (ConvLSTM) [30] was used as a HAR model because it is widely used in HAR studies [19, 29] and is easy to implement on smart devices.”
MethodAn inertial sensing mechanism for measuring gait parameters and gait energy expenditure
Vidyarani, K. R., Talasila, V., Megharjun, N., Supriya, M. S., Prasad, K. J. R., & Prashanth, G. R. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103056 · Cited by 11
Recognition of Manual Driving Distraction Through Deep-Learning and Wearable Sensing
Li, L., Xie, Z., Xu, X., et al. (2019) · International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design (Driving Assessment Conference) · doi:10.17077/drivingassessment.1670 · Cited by 9
“Very recently, deep-learning techniques, such as convolutional neural network (CNN) have shown a great potential in recognizing human daily activities (Ordóñez & Roggen, 2016).”
ViSig: Automatic Interpretation of Visual Body Signals Using On-Body Sensors
Cao, Y., Dhekne, A., & Ammar, M. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3580797 · Cited by 14
“Others have also proposed on-body sensor solutions to tackle the action recognition problem, most of which concentrate on inertial and magnetic sensors (IMU) [32, 39, 51, 62, 86].”
BackgroundMethodInfluentialAcoustic Anomaly Detection of Mechanical Failure: Time-Distributed CNN-RNN Deep Learning Models
Yong, L. Z., & Nugroho, H. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-3923-5_57 · Cited by 9
Using Gesture Recognition for AGV Control: Preliminary Research
Budzan, S., Wyżgolik, R., Kciuk, M., et al. (2023) · Sensors · doi:10.3390/s23063109 · Cited by 9
Yang, G., Zhang, L., Bu, C., Wang, S., Wu, H., & Song, A. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3321639 · Cited by 14
“Ordóñez et al. [16] introduce a powerful deep network called DeepConvLSTM by exploiting the advantages of convolutional and recurrent structures, which combines CNNs and LSTMs to simultaneously extract local and global activity features.”
BackgroundMethodInfluentialMekruksavanich, S., Phaphan, W., & Jitpattanakul, A. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.02.248 · Cited by 13
Fall Detection System using Wearable Sensor Devices and Machine Learning: A ReviewPreprint
Amir, N. I. M., Dziyauddin, R. A., Mohamed, N., Ismail, N. S. N., Kaidi, H. M., Ahmad, N. B., & Izhar, M. A. M. (2024) · doi:10.36227/techrxiv.171084921.16728034/v1 · Cited by 12
Using Auditory Features for WiFi Channel State Information Activity Recognition
Tegou, T. I., Papadopoulos, A. D., Kalamaras, I., Votis, K., & Tzovaras, D. K. (2019) · SN Computer Science · doi:10.1007/s42979-019-0003-2 · Cited by 9
Yu, J., Zhang, L., Cheng, D., Huang, W., Wu, H., & Song, A. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3457830 · Cited by 14
“Ordó nez and D. Roggen [13] have introduced a network called DeepConvLSTM by incorporating the advantage of recurrent structures, which combines CNN and Long Short-Term Memory (LSTM) units to simultaneously extract local and global activity features.”
BackgroundMethodAccurate and Efficient Human Activity Recognition Through Semi-Supervised Deep Learning
Long, X., Wang, P., Gu, F., Chen, C., & Guo, S. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3561418 · Cited by 11
“Baseline methods include six popular supervised learning baseline methods: CNN [28], DeepConvLSTM [29], LSTM– CNN [30], CNN–GRU [31], Conv-Boost [32], CCBB [33], and four SOTA semi-supervised learning methods: autoen-coder [34], relation prediction [35], -model [36], and pseudolabeling [15].”
Machine Learning-Based Activity Pattern Classification Using Personal PM2.5 Exposure Information
Park, J., & Kim, S. (2020) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph17186573 · Cited by 9
Catch Recognition in Automated American Football Training Using Machine Learning
Hollaus, B., Reiter, B., & Volmer, J. C. (2023) · Sensors · doi:10.3390/s23020840 · Cited by 13
Baumbach, S., Bhatt, A., Ahmed, S., & Dengel, A. R. (2018) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0006590504380445 · Cited by 10
“Ordóñez et al. (Ordóñez and Roggen, 2016) proposed an 8 layer deep architecture based on the combination of convolutional and long shortterm memory (LSTM) recurrent layers, called DeepConvLSTM.”
BackgroundDNN-Based FES Control for Gait Rehabilitation of Hemiplegic Patients
Jung, S., Bong, J. H., Kim, S., & Park, S. (2021) · Applied Sciences · doi:10.3390/app11073163 · Cited by 9
“Specifically, it performs well in extracting features from time-series data, such as EMG [32].”
MethodA Study of Generalization and Fitness Landscapes for Neuroevolution
Rodrigues, N. M., Silva, S., & Vanneschi, L. (2020) · IEEE Access · doi:10.1109/access.2020.3001505 · Cited by 9
“In this study, we focus on the evolution of convolutional neural networks (CNNs), because they are one of the most popular deep neural network architectures with applications including computer vision [14], [15], gestures recognition [16] and activity recognition [17].”
BackgroundEnd-to-End Multi-Modal Behavioral Context Recognition in a Real-Life Setting
Saeed, A., Özçelebi, T., Trajanovski, S., & Lukkien, J. J. (2019) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion43075.2019.9011194 · Cited by 10
Lightweight human activity recognition method based on the MobileHARC model
Gong, X., Zhang, X., & Li, N. (2024) · Systems Science & Control Engineering · doi:10.1080/21642583.2024.2328549 · Cited by 13
“Compared to RNNs, CNNs offer the advantage of high computational efficiency.”
InfluentialData driven turbulence modeling in turbomachinery — An applicability study
Fang, L., Bao, T., Xu, W., et al. (2022) · Computers & Fluids · doi:10.1016/j.compfluid.2022.105354 · Cited by 9
Multi-convLSTM neural network for sensor-based human activity recognition
Li, Z., Liu, Y., Guo, X., & Zhang, J. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1682/1/012062 · Cited by 11
Kia, Z., Yadollahzadeh‐Tabari, M., & Motameni, H. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06743-0 · Cited by 13
“…for HAR, showing how sequential dependencies in sensor data can be captured more effectively compared to traditional CNNs and LSTMs. Similarly Ordóñez and Roggen in [23] combined CNN and LSTM for spatial and temporal feature learning, achieving higher accuracy in recognizing complex activities.”
Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot
Son, C.-S., & Kang, W. (2023) · Bioengineering · doi:10.3390/bioengineering10091082 · Cited by 11
Dataset and Methods for Recognizing Care Activities
Kaczmarek, S., Fiedler, M., Bongers, A., Wibbeling, S., & Grzeszick, R. (2022) · International Workshop on Sensor-based Activity Recognition and Interaction (iWOAR) · doi:10.1145/3558884.3558891 · Cited by 10
“Many of these applications are, however, centered around basic activities such as walking, cycling or driving, activities of daily living such as opening doors or drawers [20, 21, 22] or industrial applications, like order picking [19, 23, 24] or manufacturing [21, 23].”
BackgroundGhorrati, Z., Esmaeili, A., & Matson, T. E. (2024) · IEEE Access · doi:10.1109/access.2024.3462515 · Cited by 12
“According to [43], the reported results for the locomotion classes, the Baseline CNN has achieved an F 1 -Score of 0 .”
BackgroundMethodResultInfluentialThe effect of hyperparameter search on artificial neural network in human activity recognition
Sütő, J. (2021) · Open Computer Science · doi:10.1515/comp-2020-0227 · Cited by 9
“002 — Opportunity Ordonez and Roggen (2016) [4] DeepConvLSTM — 0.”
BackgroundInfluentialLong Text Analysis Using Sliced Recurrent Neural Networks with Breaking Point Information Enrichment
Li, B., Cheng, Z., Xu, Z., Ye, W., Lukasiewicz, T., & Zhang, S. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683812 · Cited by 11
“Another solution is to introduce convolutional components into the recurrent structure [11, 12, 13]; but the convolutional components make it difficult to fully utilize the order information of sequential data.”
BackgroundA Time Series Classification Method Based on 1DCNN-FNN
Zhao, Z., Geng, J., & Jiang, W. (2021) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc52312.2021.9602164 · Cited by 9
“Francisco et al. proposes a deep learning framework[8]: a deep learning framework composed of convolution layer and LSTM cycle layer, which can automatically learn feature representation and model the time dependence between their activation.”
BackgroundHardenVR: Harassment Detection in Social Virtual Reality
Wang, N., Zhou, J., Li, J., Han, B., Li, F., & Chen, S. (2024) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr58804.2024.00033 · Cited by 15
“The convolutional and Long-Short-Term-Memory (LSTM) layers are often used together since they help to better capture the spatial and temporal relationships in the data [50].”
BackgroundData Valuation Algorithm for Inertial Measurement Unit-Based Human Activity Recognition
Kim, Y.-W., & Lee, S. (2022) · Sensors · doi:10.3390/s23010184 · Cited by 11
Elhoseny, M., Abdel-Salam, M., Yang, J., & El‐Hasnony, I. M. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3582598 · Cited by 9
Sensors-based Human Activity Recognition with Convolutional Neural Network and Attention Mechanism
Zhang, W., Zhu, T., Yang, C., Xiao, J., & Ning, H. (2020) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess49938.2020.9237720 · Cited by 15
“By modifying the DeepConvLSTM architecture [9], the LSTM layers are replaced by the attention layer to form the new DeepConvAttn framework.”
MethodInfluentialDiversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep Learning
Zayat, A., Obeed, M., & Chaaban, A. (2022) · Sensors · doi:10.3390/s22249586 · Cited by 9
Al-Nefaie, A. H. A., Aldhyani, T. H. H., Farhah, N. S., & Koundal, D. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1418684 · Cited by 9
Smartphone-sensor-based human activities classification for forensics: a machine learning approach
Moubarak, N. N. I., Omar, N. M. M., & Youssef, V. N. (2024) · Journal of Electrical Systems and Information Technology · doi:10.1186/s43067-024-00157-x · Cited by 10
“…the artifacts that corrupted the data were handled by; (1) linear interpolation, to replace missing data, (2) filing the imbalance of the observations in activities 2 and 5 with data from previous observations as in [16] and distributing the activities between the classes as shown on Table 2.”
MethodClassifying In-Place Gestures with End-to-End Point Cloud Learning
Zhao, L., Lu, X., Zhao, M., & Wang, M. (2021) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar52148.2021.00038 · Cited by 9
“We use the sliding window method as mentioned in [26] to segment the whole dataset into point clouds.”
Human Activity Recognition Based on Transformer via Smart-phone Sensors
Yu, L., Feng, K., & Ren, Z. (2023) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai57533.2023.10201297 · Cited by 11
“Various hybridization models emerged later [18]–[20].”
Nguyen, D.-C., Bailly, G., & Elisei, F. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.09.033 · Cited by 9
“For example, Ordóñez et al combined Convolution Neural Network (CNN) with LSTM to build a DeepConvLSTM framework which is able to recognize human activities from wearable sensors with minimal prepreprocessing [15].”
MethodHuman Activity Recognition in a Free-Living Environment Using an Ear-Worn Motion Sensor
Boborzi, L., Decker, J., Rezaei, R., Schniepp, R., & Wuehr, M. (2024) · Sensors · doi:10.3390/s24092665 · Cited by 9
“The DeepConvLSTM architecture combines a convolutional neural network with a long short-term memory recurrent network (LSTM) and has been widely applied in the past [27].”
MethodA C-LSTM Neural Network for Human Activity Recognition Using Wearables
Yu, S., Qin, L., & Yin, Q. (2018) · International Symposium on Sensing and Instrumentation in 5G and IoT Era (ISSI) · doi:10.1109/issi.2018.8538129 · Cited by 9
Evaluation of deep learning model for human activity recognition
Bhat, O., & Khan, D. A. (2021) · Evolving Systems · doi:10.1007/s12530-021-09373-6 · Cited by 9
Enhanced Prediction Model for Human Activity Using an End-to-End Approach
Park, S., Lee, H. O., Hwang, Y. M., Ko, S., & Lee, B. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3223674 · Cited by 11
“Nowadays, most of the studies [4], [5], [6], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35] on HAR have been conducted using deep learning models (DLMs), such as long short-term memory (LSTM) and convolutional neural network (CNN) when signals obtained using wearable…”
BackgroundDeep learning for time series classificationPreprint
Fawaz, H. I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00567 · Cited by 38
MuJo: Multimodal Joint Feature Space Learning for Human Activity Recognition
Fritsch, S. G., Oguz, C., Rey, V. F., Ray, L. S. S., Kiefer-Emmanouilidis, M., & Lukowicz, P. (2025) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom64205.2025.00020 · Cited by 16
“CNNs are commonly used for image-based activity recognition [14], being combined with RNNs in some cases [25].”
A Novel Approach for Human Activity Recognition Using Vision Based Method
Parida, L., Parida, B. R., Mishra, M. R., Jayasingh, S. K., Samal, T., & Ray, S. (2023) · International Conference on Circuits, Power and Intelligent Systems (CCPIS) · doi:10.1109/ccpis59145.2023.10292055 · Cited by 12
“Using a combination of CNNs and LSTMs, Ord´oez and Roggen [20], Yao et al. [21], and Singh et al. [22] shown a significant improvement in results.”
MethodBeyond 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
“Overall, tangible interfaces and apps provide new opportunities to enhance existing assessment methods, as the convenience and additional functionality lead these technological alternatives to improve the reporting and communicating of mental well-being.”
BackgroundCNN for Elderly Wandering Prediction in Indoor Scenarios
Oliveira, R. F. C., Feres, R., Barreto, F., & Abreu, R. (2022) · SN Computer Science · doi:10.1007/s42979-022-01091-3 · Cited by 12
“Ordóñez and Roggen [30] Activity recognition CNN/RNN”
BackgroundPower System Transient Stability Prediction Algorithm Based on ReliefF and LSTM
Li, B., Wen, T., Hu, C., & Zhou, B. F. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-24274-9_7 · Cited by 9
PATCH: A Plug-in Framework of Non-blocking Inference for Distributed Multimodal System
Wang, J., Wang, G., Zhang, X., Liu, L., Zeng, H., Xiao, L., Cao, Z., Gu, L., & Li, T. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3610885 · Cited by 18
“The methods in this field can be classified into three categories: supervised [39, 48, 58, 67, 78, 79], semi-supervised [49, 74], and unsupervised models [44, 94], depending on if the training data contains the ground truth labels.”
MethodA Time Series Decomposition-Based Interpretable Electricity Price Forecasting Method
Cu, Y., Wang, K. J., Zhang, L., et al. (2025) · Energies · doi:10.3390/en18030664 · Cited by 9
Multi-context embedding based personalized place semantics recognition
Chen, L., Han, M., Shi, H., & Liu, X. (2020) · Information Processing & Management · doi:10.1016/j.ipm.2020.102416 · Cited by 9
Group behavior recognition based on deep hierarchical network
Qiao, S., Wang, L., & Gao, Z. (2020) · Neural Computing and Applications · doi:10.1007/s00521-019-04699-4 · Cited by 9
SensiX: A System for Best-effort Inference of Machine Learning Models in Multi-device Environments
Min, C., Mathur, A., Montanari, A., & Kawsar, F. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3173914 · Cited by 10
“Recently, a number of studies on multi-sensory fusion have been conducted to maximise the inference accuracy while addressing potential system issues such as time synchronisation and missing data [11], [12], [13], [44], [45].”
BackgroundGraph-Structure-Based Multigranular Belief Fusion for Human Activity Recognition
Dong, Y., Li, X., Dezert, J., Zhou, R., Zuo, K., & Ge, S. S. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3270290 · Cited by 11
“10(b), and we can see that the recognition accuracy of A1 (NULL) is the highest, reaching 98.1871%, while the recognition V, including the literature standard recurrent network [47], CNN [48], CNN + LSTM [49], layer-wise deep neural networks [50], Att-based residual network [36], DSmT-KDE [46], etc.”
BackgroundInfluentialHsu, Y.-C., Wang, H., Zhao, Y., Chen, F., & Tsui, K.-L. (2021) · Journal of Medical Internet Research · doi:10.2196/30135 · Cited by 9
Finger Gesture Sensing and Recognition Using a Wi-Fi-based Passive Radar
Lai, Y., Chou, C.-C., Tang, M.-C., et al. (2019) · IEEE MTT-S International Microwave Symposium digest · doi:10.1109/mwsym.2019.8700803 · Cited by 9
“In this study, a neural network model that combines a convolutional neural network (CNN) with a long short-term memory (LSTM) network [11] is used to recognize finger gestures.”
MethodWEARABLE SENSOR-BASED GAIT CLASSIFICATION IN IDIOPATHIC TOE WALKING ADOLESCENTS.
Kim, S. H., Soangra, R., Grant-Beuttler, M., & Aminian, A. (2019) · PubMed · Cited by 9
An Optimal Feature Selection Method for Human Activity Recognition Using Multimodal Sensory Data
Haider, T., Khan, M. H., & Farid, M. S. (2024) · Information · doi:10.3390/info15100593 · Cited by 9
Rizk, H., Amano, T., Yamaguchi, H., & Youssef, M. A. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3176291 · Cited by 8
“A hybrid technique that harnesses LSTM in conjunction with a CNN for activity recognition is proposed in [41], denoted by DeepConvLSTM [41], to leverage their combined advantages.”
Method
Metadata
- Authors
- Ordóñez, F., & Roggen, D.
- Affiliations
- University of Sussex (GB)
- Corresponding author
- Ordóñez, Francisco
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2016-01-18
- Volume
- 16
- Issue
- 1
- Pages
- 115
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC4732148
- OpenAlex
- W2270470215
- Cited by
- 2,761
- References
- 49
- Citations by year
- 2026: 284 · 2025: 256 · 2024: 284 · 2023: 270 · 2022: 319 · 2021: 379 · 2020: 347 · 2019: 288 · 2018: 219 · 2017: 93 · 2016: 21
- FWCI
- 140.52
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Sussex Research Online (University of Sussex) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- Funders
- Google Faculty Research Award (Is deep learning useful for wearable activity recognition?)
- EPSRC (EP/N007816/1)
- 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 › Signal Processing › Time Series Analysis and Forecasting
- Keywords
- human activity recognition, wearable sensors, multimodal sensor fusion, convolutional neural networks, LSTM neural network, temporal dynamics, automatic feature extraction, hyperparameter optimization
- MeSH terms
- Machine Learning, Clothing, Humans, Human Activities, Signal Processing, Computer-Assisted, Databases, Factual, Neural Networks, Computer, Monitoring, Ambulatory
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 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.