Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Open accessThe DOI matches its Crossref record; 48 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. Li F.F. Visualizing and understanding recurrent networks Cornell Univ. Lab. 2015 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. Dambre J. Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video arXiv Preprint 2015 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
- Gers F.A. Schraudolph N.N. Schmidhuber J. Learning precise timing with LSTM recurrent networks J. Mach. Learn. Res. 2003 3 115 143
Cited by
Items 301–400 of 2,807
Jiao, J. R., Zhou, F., Gebraeel, N., & Duffy, V. G. (2020) · International Journal of Production Research · doi:10.1080/00207543.2020.1722324 · Cited by 86
A study of deep neural networks for human activity recognition
Sansano, E., Montoliu, R., & Belmonte Fernández, Ó. (2020) · Computational Intelligence · doi:10.1111/coin.12318 · Cited by 73
“The use of ensembles of LSTMs 23 has been explored, with better classification results than previous deep learning models, including Reference 22.”
InfluentialHuynh-The, T., Hua, C.-H., Tu, N. A., & Kim, D.-S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3013272 · Cited by 72
“For example, Ordóñez and Roggen [43] simply plotted three acceleration signals separately in the time domain before learning deep visual features by a deep CNN, however, this sensory-data-to-image encoding scheme is fragile due to the loss of detail information [42].”
BackgroundMethodInfluentialSensor-Based Human Activity Recognition Using Deep Stacked Multilayered Perceptron Model
Rustam, F., Reshi, A. A., Ashraf, I., Mehmood, A., Ullah, S., Khan, D. M., & Choi, G. S. (2020) · IEEE Access · doi:10.1109/access.2020.3041822 · Cited by 81
“For this purpose, studies including [43]–[46] that use deep convolutional neural networks (CNN) and the study [47] that uses deep convolutional long short term memory (ConvLSTM) are selected.”
Li, B., Yao, Z., Wang, J., Wang, S., Yang, X., & Sun, Y. (2020) · Electronics · doi:10.3390/electronics9111919 · Cited by 81
Industry 4.0-Oriented Deep Learning Models for Human Activity Recognition
Mohsen, S., Elkaseer, A., & Scholz, S. G. (2021) · IEEE Access · doi:10.1109/access.2021.3125733 · Cited by 93
“We see that the accuracy achieved by the CNN-LSTM model, 97.76%, is better than the models referred in [24], [26], [28], [30], [31].”
BackgroundMethodInfluentialDeep Fisher discriminant learning for mobile hand gesture recognition
Li, C., Xie, C., Zhang, B., Chen, C., & Han, J. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.12.023 · Cited by 72
“We also compare the performance of our proposed framwork with the implemented HMM [50], RNN [43], LSTM [55], GRU [31], 335”
BackgroundMethodInfluentialTapID: Rapid Touch Interaction in Virtual Reality using Wearable Sensing
Meier, M., Streli, P., Fender, A. R., & Holz, C. (2021) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr50410.2021.00076 · Cited by 80
“With the emergence of neural network-based processing pipelines, various network architectures have been presented for such recognition [27, 36, 37, 50], which has started to supersede the previously hand-crafted features (e.”
A deep learning approach for parkinson’s disease severity assessment
Aşuroğlu, T., & Oğul, H. (2022) · Health and Technology · doi:10.1007/s12553-022-00698-z · Cited by 83
Efficient Activity Recognition in Smart Homes Using Delayed Fuzzy Temporal Windows on Binary Sensors
Hamad, R. A., Salguero, A., Bouguelia, M.-R., Espinilla, M., & Medina-Quero, J. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2918412 · Cited by 78
“Evaluating the temporal models using a Deep Learning approach has presented significant differences compared to other contexts of activity recognition [24].”
BackgroundMethodLing, C. (2020) · doi:10.1145/3381012 · Cited by 72
“It is commonly used as a feature extractor in time-series data processing [27, 46].”
BackgroundMethodInfluentialWearable Assistive Robotics: A Perspective on Current Challenges and Future Trends
Martínez-Hernández, U., Metcalfe, B., Assaf, T., Jabban, L., Male, J., & Zhang, D. (2021) · Sensors · doi:10.3390/s21206751 · Cited by 90
Akbari, A., & Jafari, R. (2019) · Proceedings of the 18th International Conference on Information Processing in Sensor Networks · doi:10.1145/3302506.3310391 · Cited by 69
“The model above can be implemented with a typical CNN using Softmax activation function at the final layer [18].”
BackgroundMethodInfluentialCoarse-Fine Convolutional Deep-Learning Strategy for Human Activity Recognition
Avilés-Cruz, C., Ferreyra-Ramírez, A., Zúñiga-López, A., & Villegas-Cortéz, J. (2019) · Sensors · doi:10.3390/s19071556 · Cited by 73
Su, M., Peng, H., & Li, S. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115728 · Cited by 97
Deformable Convolutional Networks for Multimodal Human Activity Recognition Using Wearable Sensors
Xu, S., Zhang, L., Huang, W., Wu, H., & Song, A. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3158427 · Cited by 90
An IoT-Based Smart Building Solution for Indoor Environment Management and Occupants Prediction
Floris, A., Porcu, S., Girau, R., & Atzori, L. (2021) · Energies · doi:10.3390/en14102959 · Cited by 86
“Ordóñez and Roggen [42] suggested a DL algorithm for human activity detection that is appropriate for multimodal wearable sensors, such as accelerometers, gyroscopes, and magnetic field sensors.”
BackgroundDigital twin-driven framework for improving self-management of ergonomic risks
Ogunseiju, O. R., Olayiwola, J., Akanmu, A. A., & Nnaji, C. A. (2021) · Smart and Sustainable Built Environment · doi:10.1108/sasbe-03-2021-0035 · Cited by 81
Hierarchical Recurrent Deep Fusion Using Adaptive Clip Summarization for Sign Language Translation
Guo, D., Zhou, W., Li, A., Li, H., & Wang, M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2941267 · Cited by 83
“For example, the DeepConvLSTM model, which combines both convolutional and recurrent neural units, has been proposed [46] to”
BackgroundMethodDeep Learning Based Real-Time Recognition of Dynamic Finger Gestures Using a Data Glove
Lee, M., & Bae, J. (2020) · IEEE Access · doi:10.1109/access.2020.3039401 · Cited by 71
“Recently, there have been studies of gesture spotting using convolutional neural networks (CNNs) [13], [14].”
BackgroundMisra, S., Yoon, C., Kim, K., Managuli, R., Barr, R. G., Baek, J., & Kim, C. (2022) · Bioengineering & Translational Medicine · doi:10.1002/btm2.10480 · Cited by 78
“We arbitrarily divided the data set at the patient level into 137, 34, and 41 sets for training, validation, and testing, respectively for segmentation and classification.”
MethodA Robust Deep Learning Approach for Position-Independent Smartphone-Based Human Activity Recognition
Almaslukh, B., Artoli, A. M., & Al-Muhtadi, J. (2018) · Sensors · doi:10.3390/s18113726 · Cited by 71
“[41] and DBN+HMM in [42]”
Knaak, C., von Eßen, J., Kröger, M., Schulze, F., Abels, P., & Gillner, A. (2021) · Sensors · doi:10.3390/s21124205 · Cited by 73
“In addition to the manufacturing domain, architectures based on CNN and RNN turned out to be successful in applications such as action and emotion recognition in video data [35,36] and wearable activity recognition [37].”
MethodMulti-Resident Activity Recognition in a Smart Home Using RGB Activity Image and DCNN
Tan, T.-H., Gochoo, M., Huang, S.-C., Liu, Y.-H., Liu, S.-H., & Huang, Y.-F. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2866806 · Cited by 70
“Several studies have used DCNN to analyze non-vision sensor signals such as inertial sensors [15]–[18], PIR sensors [19]–[21], ECG [22]–[24], and Doppler effect sensor [25] after the nonvision signals are converted into binary or RGB images for a single person activity recognition.”
MethodBarut, O., Zhou, L., & Luo, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2996578 · Cited by 70
“Then, their results are out-performed by Ordonez and Roggen [17] who combined CNNs with LSTM and proposed a DeepConvLSTM network to address the multimodal wearable activity recognition problem on Opportunity and Skoda data sets.”
MethodHuman Activity Recognition for Production and Logistics—A Systematic Literature Review
Reining, C., Niemann, F., Rueda, F. M., Fink, G. A., & ten Hompel, M. (2019) · Information · doi:10.3390/info10080245 · Cited by 82
“The application covers a wide range of sectors, such as manufacturing and assembling [58,86], warehousing [72,83,85], construction [90] and maintenance [11,14].”
BackgroundMethodInfluentialA survey of identity recognition via data fusion and feature learning
Qin, Z., Zhao, P., Zhuang, T., Deng, F., Ding, Y., & Chen, D. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.10.032 · Cited by 86
Context-Aware Human Activity Recognition (CAHAR) in-the-Wild Using Smartphone Accelerometer
Asim, Y., Azam, M. A., Ehatisham-ul-Haq, M., Naeem, U., & Khalid, A. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2964278 · Cited by 75
“In [30], the authors utilized deep convolutional and LSTM (Long Short-Term Memory) recurrent neural networks (RNN) for multimodal wearable HAR.”
MethodAttention-Based Deep Learning Framework for Human Activity Recognition With User Adaptation
Buffelli, D., & Vandin, F. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3067690 · Cited by 68
“We then consider DeepConvLSTM [28] which is a CNN+LSTM approach, and its new attentive version proposed in [26] that we call DeepConvLSTM-Att.”
MethodUsing a Motion Sensor to Categorize Nonspecific Low Back Pain Patients: A Machine Learning Approach
Abdollahi, M., Ashouri, S., Abedi, M., Azadeh-Fard, N., Parnianpour, M., Khalaf, K., & Rashedi, E. (2020) · Sensors · doi:10.3390/s20123600 · Cited by 69
“Other analogous studies have indeed included a greater number of observations for each class [56,57], particularly when implementing a neural network approach [58].”
BackgroundSingh, R., Nisha, R., Naik, R., Upendar, K., Nickhil, C., & Deka, S. C. (2024) · Journal of Food Measurement & Characterization · doi:10.1007/s11694-024-02789-z · Cited by 87
“By encoding information from different sensor types, autoencoders and VAEs can capture diverse and complementary data facets, which are beneficial for tasks like quality assessment and sorting [110].”
Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals
Nakamura, K., Yeung, S., Alahi, A., & Fei-Fei, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.721 · Cited by 67
“[65, 32] use recurrent networks for single triaxial accelerometer data, [41] for a heart rate controller, and [50] for multimodal wearable sensors.”
BackgroundOutlier Detection in Wearable Sensor Data for Human Activity Recognition (HAR) Based on DRNNs
Munoz-Organero, M. (2019) · IEEE Access · doi:10.1109/access.2019.2921096 · Cited by 69
“[11] where able to outperform other similar studies over the dataset in [6] using a bidirectional LSTM (b-LSTM-S) while the research in [14] used a different architecture based on the combination of Deep Convolutional and LSTM recurrent neural networks for best results over the dataset in [7].”
MethodMekruksavanich, S., & Jitpattanakul, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-39080-y · Cited by 75
Detecting State Changes of Indoor Everyday Objects using Wi-Fi Channel State Information
Ohara, K., Maekawa, T., & Matsushita, Y. (2017) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3131898 · Cited by 72
“Similar to us, Ord´o˜nez et al. [29] employ three convolutional layers and two LSTM layers for acceleration-based activity recognition.”
ResultSensCapsNet: Deep Neural Network for Non-Obtrusive Sensing Based Human Activity Recognition
Pham, C., Nguyen-Thai, S., Tran-Quang, H., Son, T. C., Vu, H., Tran, T.-H., & Le, T. (2020) · IEEE Access · doi:10.1109/access.2020.2991731 · Cited by 77
“Another model in [24] used deep CNNs in a multi-sensor recognition framework which built a new multi-channel time series architecture of CNNs.”
MethodInfluentialMultiCNN-FilterLSTM: Resource-efficient sensor-based human activity recognition in IoT applications
Park, H., Kim, N., Lee, G. H., & Choi, J. K. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.09.024 · Cited by 79
A Mixed Deep Recurrent Neural Network for MEMS Gyroscope Noise Suppressing
Jiang, C., Chen, Y., Chen, S., Bo, Y., Li, W., Tian, W., & Guo, J. Y. (2019) · Electronics · doi:10.3390/electronics8020181 · Cited by 75
A deep learning approach for sepsis monitoring via severity score estimation
Aşuroğlu, T., & Oğul, H. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105816 · Cited by 78
Xu, S., Zhang, L., Tang, Y., Han, C., Wu, H., & Song, A. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3277839 · Cited by 76
“It can be seen that our multi-frequency channel attention outperforms Ordóñez et al.’s result [36] by 2.62 % that uses DeepConvLSTM on OPPORTUNITY dataset.”
MethodInfluentialKim, Y.-W., Joa, K.-L., Jeong, H.-Y., & Lee, S. (2021) · Sensors · doi:10.3390/s21227628 · Cited by 67
What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks?
Qian, H., Tian, T., & Miao, C. (2022) · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539134 · Cited by 67
“In recent years, a large body of research for wearable-based human activity recognition is dedicated to learning discriminative features by leveraging various deep neural networks, including convolutional networks, residual networks, autoencoders and Transformers [7, 22, 26, 33, 41].”
BackgroundDeep learning based multimodal complex human activity recognition using wearable devices
Chen, L., Liu, X., Peng, L., & Wu, M. (2020) · Applied Intelligence · doi:10.1007/s10489-020-02005-7 · Cited by 72
“Ordóñez et al. [26] proposed a deep framework for wearable device based multimodal activity recognition by using convolutional and LSTM recurrent units.”
BackgroundMethodInfluentialAn automatic speed adaption neural network model for planetary gearbox fault diagnosis
Chen, P., Li, Y., Wang, K., & Zuo, M. J. (2020) · Measurement · doi:10.1016/j.measurement.2020.108784 · Cited by 72
Embedded Real-Time Fall Detection with Deep Learning on Wearable Devices
Torti, E., Fontanella, A., Musci, M., Blago, N., Pau, D. P., Leporati, F., & Piastra, M. (2018) · Euromicro Conference on Digital System Design (DSD) · doi:10.1109/dsd.2018.00075 · Cited by 81
“Other authors [23] have proposed a DL technique to detect falls composed by two parts: a Convolutional Neural Network (CNN) and a LSTM.”
MethodTerahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network
Zhang, J., Xing, W., Xing, M., & Sun, G. (2018) · Sensors · doi:10.3390/s18072327 · Cited by 65
Multi-Scale LSTM Model for BGP Anomaly Classification
Cheng, M., Li, Q., Lv, J., Liu, W., & Wang, J. (2018) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2018.2824809 · Cited by 78
“The sequential models in deep learning, including Recurrent Neural Network (RNN) and Long Short-term Memory (LSTM) model, have achieved desirable performance in many sequence classification scenarios [8], [28], [29], [30], [31].”
MethodAlessandrini, M., Biagetti, G., Crippa, P., Falaschetti, L., & Turchetti, C. (2021) · Electronics · doi:10.3390/electronics10141715 · Cited by 79
Gochoo, M., Tahir, S. B. U. D., Jalal, A., & Kim, K. (2021) · IEEE Access · doi:10.1109/access.2021.3078513 · Cited by 67
Lower Limb Kinematics Trajectory Prediction Using Long Short-Term Memory Neural Networks
Zaroug, A., Lai, D. T. H., Mudie, K., & Begg, R. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00362 · Cited by 65
A Study of the Use of Gyroscope Measurements in Wearable Fall Detection Systems
Casilari, E., Álvarez-Marco, M., & García-Lagos, F. (2020) · Symmetry · doi:10.3390/sym12040649 · Cited by 73
Projecting Australia's forest cover dynamics and exploring influential factors using deep learning
Ye, L., Gao, L., Marcos-Martínez, R., Mallants, D., & Bryan, B. A. (2019) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2019.07.013 · Cited by 69
Empirical Study and Improvement on Deep Transfer Learning for Human Activity Recognition
Ding, R., Li, X., Nie, L., Li, J., Si, X., Chu, D., Liu, G., & Zhan, D. (2018) · Sensors · doi:10.3390/s19010057 · Cited by 63
Multi-sensor fusion based on multiple classifier systems for human activity identification
Nweke, H. F., Wah, T. Y., Mujtaba, G., Alo, U. R., & Al-Garadi, M. A. (2019) · Human-centric Computing and Information Sciences · doi:10.1186/s13673-019-0194-5 · Cited by 76
“Furthermore, the magnetometer sensor helps to eliminate the effects of gravity, ensure independent device orientation, and differentiate between sporadic and static activities [11, 12].”
BackgroundMethodLv, M., Xu, W., & Chen, T. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.06.051 · Cited by 64
Automatic Classification of Squat Posture Using Inertial Sensors: Deep Learning Approach
Lee, J., Joo, H., Lee, J., & Chee, Y. (2020) · Sensors · doi:10.3390/s20020361 · Cited by 66
“Ordóñez et al. [15] used an IMU along with a CNN and an RNN combined with long short ‐ term memory models (RNN–LSTM) to classify various human activities such as opening doors or drinking water.”
MethodOn-board Deep-learning-based Unmanned Aerial Vehicle Fault Cause Detection and Identification
Sadhu, V., Zonouz, S., & Pompili, D. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197071 · Cited by 69
“We do not use pooling layers after convolutional layers as our input data has been segmented into windows and the output of the convolutional layers need to be passed through time-series LSTM layers [28].”
MethodTwo-stream transformer network for sensor-based human activity recognition
Xiao, S., Wang, S., Huang, Z., Wang, Y., & Jiang, H. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.099 · Cited by 76
Zhao, J., & Obonyo, E. (2021) · Advanced Engineering Informatics · doi:10.1016/j.aei.2021.101374 · Cited by 73
Keshavarzian, A., Sharifian, S., & Seyedin, S. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.06.009 · Cited by 64
WiCAR: wifi-based in-car activity recognition with multi-adversarial domain adaptation
Wang, F., Liu, J., & Gong, W. (2019) · International Workshop on Quality of Service · doi:10.1145/3326285.3329054 · Cited by 74
“Many existing sensing technologies use cameras [31, 33], wearable sensors [11, 15] and radio-frequency identification (RFID) [5, 26] for activity recognition.”
BackgroundHuman activity recognition using a multi-branched CNN-BiLSTM-BiGRU model
Lalwani, P. D., & Ganeshan, R. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111344 · Cited by 76
Detection of Corona Faults in Switchgear by Using 1D-CNN, LSTM, and 1D-CNN-LSTM Methods
Alsumaidaee, Y. A. M., Yaw, C. T., Koh, S. P., Kiong, T. S., Chen, C. P., Yusaf, T. F., Abdalla, A. N., Ali, K., & Raj, A. A. (2023) · Sensors · doi:10.3390/s23063108 · Cited by 74
A Comparison Study of Classifier Algorithms for Cross-Person Physical Activity Recognition
Sáez, Y., Baldominos, A., & Isasi, P. (2016) · Sensors · doi:10.3390/s17010066 · Cited by 77
Liu, X., Li, Y., & Wang, Q. (2018) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001418500337 · Cited by 63
Choi, J., Choo, Y., & Lee, K. (2019) · Sensors · doi:10.3390/s19163492 · Cited by 63
“Machine learning algorithms [16–20] construct a generalized model that only relies on the given data, known as “training data”.”
BackgroundApplying Machine Learning Algorithms for the Classification of Sleep Disorders
Alshammari, T. A. (2024) · IEEE Access · doi:10.1109/access.2024.3374408 · Cited by 78
“The classification accuracy metric is inappropriate for this kind of dataset with unbalanced labels, and the majority class can obtain a higher accuracy [23].”
BackgroundPREDICTIVE MAINTENANCE OF PHOTOVOLTAIC PANELS VIA DEEP LEARNING
Huuhtanen, T., & Jung, A. (2018) · IEEE Data Science Workshop (DSW) · doi:10.1109/dsw.2018.8439898 · Cited by 84
“How to calculate the local interpolators (based on the input values in the close time-space neighborhood) for the target panel? The problem suggests the use of convolutional layer for the first layer as also used in [19] and [20].”
BackgroundA deep learning-based intrusion detection approach for mobile Ad-hoc network
Meddeb, R., Jemili, F., Triki, B., & Korbaa, O. (2023) · Soft Computing · doi:10.1007/s00500-023-08324-4 · Cited by 63
Badminton Activity Recognition Using Accelerometer Data
Steels, T., Herbruggen, B. V., Fontaine, J., Pessemier, T. D., Plets, D., & Poorter, E. D. (2020) · Sensors · doi:10.3390/s20174685 · Cited by 78
Human Gait Activity Recognition Machine Learning Methods
Slemenšek, J., Fister, I., Geršak, J., Bratina, B., van Midden, V. M., Pirtošek, Z., & Šafarič, R. (2023) · Sensors · doi:10.3390/s23020745 · Cited by 65
Input quality aware convolutional LSTM networks for virtual marine sensors
Oehmcke, S., Zielinski, O., & Krämer, O. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.11.027 · Cited by 64
Heterogeneous Sensor Data Fusion By Deep Multimodal Encoding
Liu, Z., Zhang, W., Lin, S., & Quek, T. Q. S. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2679538 · Cited by 68
“, [6, 12, 24, 36, 48, 60, 72], in DCT as compressed dimensions.”
BackgroundDeep Learning-Based Fast Hand Gesture Recognition Using Representative Frames
John, V., Boyali, A., Mita, S., Imanishi, M., & Sanma, N. (2016) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2016.7797030 · Cited by 68
“In the second category of deep learning-based activity recognition, researchers model the inter-frame temporal information using the recurrent neural network (RNN) [17], [18].”
BackgroundTransformer-based models to deal with heterogeneous environments in Human Activity Recognition
Ek, S., Portet, F., & Lalanda, P. (2023) · Personal and Ubiquitous Computing · doi:10.1007/s00779-023-01776-3 · Cited by 101
“To do so, we implemented a 2-layered CNN model, and a CNN-LSTM (DeepConvLSTM) model [20, 33] that are presented as state-of-the-art models within the HAR community (see performances in Table 3).”
Chan, S., Hang, Y., Tong, C., Acquah, A., Schonfeldt, A., Gershuny, J., & Doherty, A. (2024) · Scientific Data · doi:10.1038/s41597-024-03960-3 · Cited by 61
“Our existing benchmark incorporates common methods used for HAR, future work could also benefit from leveraging more recent modeling techniques using DeepConvLSTM 40,41 , transformers 42 , and self-supervised learning 43–46 .”
Automatic Annotation for Human Activity Recognition in Free Living Using a Smartphone
Cruciani, F., Cleland, I., Nugent, C., McCullagh, P., Synnes, K., & Hallberg, J. (2018) · Sensors · doi:10.3390/s18072203 · Cited by 60
A Low Power Fall Sensing Technology Based on FD-CNN
He, J., Zhang, Z., Wang, X., & Yang, S. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2903482 · Cited by 66
“Additionally, the experimental result from [28] showed that 2 seconds sliding window is better than those of 1 and 3 seconds, it is one of the reasons that the size of the sliding window in this paper is 2 seconds.”
BackgroundInfluentialHyper-Dimensional Computing Challenges and Opportunities for AI Applications
Hassan, E., Halawani, Y., Mohammad, B., & Saleh, H. (2022) · IEEE Access · doi:10.1109/access.2021.3059762 · Cited by 61
“Advancements in deep learning (DL) algorithms has out-20 performed conventional machine learning (ML) approaches in many applications: image classification, voice recogni-22 tion [1], activity recognition [2] and object tracking [3].”
BackgroundZhu, H., Samtani, S., Brown, R. A., & Chen, H. (2021) · MIS Quarterly · doi:10.25300/misq/2021/15574 · Cited by 73
“Such systems require deploying human sensor networks with over 19 motion sensors on a user’s wrists, chest, and other body parts (Murad and Pyun 2016; Ordóñez and Roggen 2016; Hammerla et al. 2016; Yang et al. 2015).”
BackgroundMethodInfluentialA Survey of Deep Learning Based Models for Human Activity Recognition
Khan, N. S., & Ghani, M. S. (2021) · Wireless Personal Communications · doi:10.1007/s11277-021-08525-w · Cited by 69
“For example, a specific subject could be used, or a certain portion based on percentage of data could be kept for validation [4, 80, 82, 86, 92, 93].”
BackgroundMethodInfluentialBoukhechba, M., Cai, L., Wu, C., & Barnes, L. E. (2019) · Smart Health · doi:10.1016/j.smhl.2019.100082 · Cited by 70
Zrenner, M., Gradl, S., Jensen, U. J., Ullrich, M., & Eskofier, B. M. (2018) · Sensors · doi:10.3390/s18124194 · Cited by 67
“Deep learning techniques also show good results in IMU-based classification and regression tasks [14,15].”
MethodGil-Martín, M., San-Segundo, R., Fernández-Martínez, F., & Ferreiros, J. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.103679 · Cited by 69
Serey, J., Alfaro, M. D., Fuertes, G., Vargas, M., Durán, C., Ternero, R., Rivera, R., & Sabattin, J. (2023) · Symmetry · doi:10.3390/sym15020535 · Cited by 87
Human Identification for Activities of Daily Living: A Deep Transfer Learning Approach
Zhu, H., Samtani, S., Chen, H., & Nunamaker, J. F. (2020) · Journal of Management Information Systems · doi:10.1080/07421222.2020.1759961 · Cited by 64
“robustness against gradient miscalculations, we implemented ReLU for all convolution layers [30, 35].”
BackgroundMethodZhao, J., Obonyo, E., & Bilén, S. G. (2021) · Sensors · doi:10.3390/s21041324 · Cited by 69
Wang, C., Luo, H., Zhao, F., & Qin, Y. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2987598 · Cited by 63
Deep, S., & Zheng, X. (2019) · International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) · doi:10.1109/pdcat46702.2019.00055 · Cited by 72
“Hybrid models are reported to produce better recognition scores than pure CNN or LSTM networks [12].”
BackgroundMethodZurbuchen, N., Wilde, A., & Bruegger, P. (2021) · Sensors · doi:10.3390/s21030938 · Cited by 72
“There is a study [36] using Recurrent Neural Networks but there are other algorithms available such as Convolutional Neural Networks with the advantage of automatic feature extraction from time series [46].”
MethodZhou, T., Chen, M., Wang, Y., He, J., & Yang, C. (2020) · Entropy · doi:10.3390/e22030279 · Cited by 59
“Based on the recent success of LSTM networks for time series domains, a convolutional and LSTM recurrent units-based deep framework was proposed in [17] for activity recognition.”
BackgroundNon-invasive cuff-less blood pressure estimation using a hybrid deep learning model
Yang, S., Zhang, Y., Cho, S., Correia, R. G., & Morgan, S. P. (2021) · Optical and Quantum Electronics · doi:10.1007/s11082-020-02667-0 · Cited by 65
Wearable Sensor-Based Gait Analysis for Age and Gender Estimation
Ahad, M. A. R., Ngo, T. T., Antar, A. D., Ahmed, M., Hossain, T., Muramatsu, D., Makihara, Y., Inoue, S., & Yagi, Y. (2020) · Sensors · doi:10.3390/s20082424 · Cited by 69
“In Alg.1 and Alg.2, they used a deep neural network architecture, inspired by the network in [59], where bidirectional LSTM (BLSTM) were explored, instead of [59]’s simple LSTM model.”
MethodDual-Branch Interactive Networks on Multichannel Time Series for Human Activity Recognition
Tang, Y., Zhang, L., Wu, H., He, J., & Song, A. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3193148 · Cited by 67
“On the basis of the advantages of RNN and CNN, [31] introduces a hybrid deep model called DeepConvLSTM that combines convolutional and recurrent units for both local and global feature extraction in multimodal HAR.”
BackgroundMethodInfluentialXiang, L., Wang, A., Gu, Y., Zhao, L., Shim, V., & Fernandez, J. (2022) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2022.913052 · Cited by 77
“The performance improves by fusing the accelerometer, gyroscope, and magnetic field sensors compared to the acceleration or acceleration and angular velocity data (Ordóñez and Roggen, 2016).”
BackgroundMethodInfluentialWeakly Supervised Human Activity Recognition From Wearable Sensors by Recurrent Attention Learning
He, J., Zhang, Q., Wang, L., & Pei, L. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2885796 · Cited by 56
“Ordóñez and Roggen [36] propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units (DeepConvLSTM), which is suitable for multimodal wearable sensors and outperforms CNN.”
BackgroundMethodInfluentialMulti-Modal Deep Analysis for Multimedia
Zhu, W., Wang, X. Y., & Li, H. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2940647 · Cited by 67
Mahmud, T., Sazzad Sayyed, A. Q. M., Fattah, S. A., & Kung, S.-Y. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3015781 · Cited by 58
Wang, S., Li, J., Cao, T., Wang, H., Tu, P., & Li, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3007956 · Cited by 68
“The convolutional layer and the pooled layer are stacked to form a deep structure, and features can be automatically extracted from the original data [23].”
MethodWen, L., Nie, M., Chen, P., Zhao, Y.-N., Shen, J., Wang, C., Xiong, Y., Yin, K., & Sun, L. (2022) · Microsystems & Nanoengineering · doi:10.1038/s41378-022-00358-2 · Cited by 68
“The gating mechanism controls the forgetting, input, and output of information, solving long-term dependence 34 – 36 .”
Background
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.