A Multimodal IoT-Based Locomotion Classification System Using Features Engineering and Recursive Neural Network
Open accessAbstract
Locomotion prediction for human welfare has gained tremendous interest in the past few years. Multimodal locomotion prediction is composed of small activities of daily living and an efficient approach to providing support for healthcare, but the complexities of motion signals along with video processing make it challenging for researchers in terms of achieving a good accuracy rate. The multimodal internet of things (IoT)-based locomotion classification has helped in solving these challenges. In this paper, we proposed a novel multimodal IoT-based locomotion classification technique using three benchmarked datasets. These datasets contain at least three types of data, such as data from physical motion, ambient, and vision-based sensors. The raw data has been filtered through different techniques for each sensor type. Then, the ambient and physical motion-based sensor data have been windowed, and a skeleton model has been retrieved from the vision-based data. Further, the features have been extracted and optimized using state-of-the-art methodologies. Lastly, experiments performed verified that the proposed locomotion classification system is superior when compared to other conventional approaches, particularly when considering multimodal data. The novel multimodal IoT-based locomotion classification system has achieved an accuracy rate of 87.67% and 86.71% over the HWU-USP and Opportunity++ datasets, respectively. The mean accuracy rate of 87.0% is higher than the traditional methods proposed in the literature.
AI snapshot
Written from the paper’s full text.
TL;DR
The paper proposes a multimodal IoT locomotion classification system that fuses ambient, wearable motion, and vision data using feature engineering and a recursive neural network. It reports a mean accuracy of 87.0%, with 87.67% on HWU-USP and 86.71% on Opportunity++.
Key findings
- The proposed system achieved 87.67% accuracy on the HWU-USP dataset and 86.71% on the Opportunity++ dataset, for a mean accuracy of 87.0%.
- The authors state this mean accuracy is higher than traditional multimodal methods compared in the paper.
- Skeleton modeling extracted 11 skeleton points—head, neck, torso, elbows, wrists, knees, and ankles—and was validated through confidence levels and skeleton point accuracies.
- Feature extraction used Pearson correlation for ambient data with a threshold of 0.04, LPCC for motion data, and SLIF for vision data.
Methods
- Ambient data were filtered with a Butterworth filter, wearable motion data with a wavelet quaternion-based filter, and vision data via background subtraction; ambient and motion signals were windowed for 4 s, and skeleton points were extracted from human silhouettes.
- Features were extracted separately by sensor type, fused over time windows, optimized using cross entropy with type-2 fuzzy logic and additive ratio valuation, then classified with a recursive neural network (RvNN).
- Experiments used the HWU-USP dataset (16 participants, 9 ADLs, IMU/ambient/RGBD sensors) and Opportunity++ dataset (12 participants, 17 activities, body-worn IMUs, object sensors, ambient sensors, and video), with 10-fold cross-validation on Matlab using an Intel Core i7 at 2.4 GHz and 24 GB RAM.
Limitations
- The paper states the system did not perform well for complex motion patterns, such as tidying the kitchen or reading a newspaper.
- The authors state they intend to add more feature extraction methods and apply pattern recognition over motion and ambient data to identify static and dynamic motion signals before feature extraction, which they say will help improve the system for real-time applications.
- Evident from the text: although the abstract mentions three benchmarked datasets, the experiments and dataset descriptions use only two datasets, HWU-USP and Opportunity++.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
0 of 10 cited sources checked · 0 supported · 0 flagged
- Findingreasoning
The combination of different feature extraction methods and feature fusion in the proposed system methodology yields improved human skeleton point confidence levels.
“Major enhancement in the accuracy of locomotion classification with improved human skeleton point confidence levels by applying a combination of different feature extraction methods and feature fusion in the proposed system methodology.”
Quote in the paperSubstantial claim - Findingcitation
The proposed system's mean accuracy rate of 87.0% is higher than traditional methods proposed in the literature.
“The mean accuracy rate of 87.0% is higher than the traditional methods proposed in the literature.”
- Also stated in: § 4.2. Experimental Results · plain
“An enhanced mean accuracy rate of 87.0% has been achieved through the proposed system when compared to the other conventional models.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [38] Hajjej, 2022, Deep Human Motion Detection and Multi-Features Analysis for Smart Healthcare Learning Tools, IEEE Access source
Not checked in the free run.
- Also stated in: § 4.2. Experimental Results · plain
- Findingown data
The combination of different feature extraction methods and feature fusion in the proposed system methodology yields major enhancement in accuracy of locomotion classification.
“Major enhancement in the accuracy of locomotion classification with improved human skeleton point confidence levels by applying a combination of different feature extraction methods and feature fusion in the proposed system methodology.”
Quote in the paperSubstantial claim - Findingown data
The proposed multimodal IoT-based locomotion classification system achieved an accuracy rate of 87.67% on the HWU-USP dataset.
“The novel multimodal IoT-based locomotion classification system has achieved an accuracy rate of 87.67% and 86.71% over the HWU-USP and Opportunity++ datasets, respectively.”
- Also stated in: § 4.2. Experimental Results · plain
“The mean accuracy achieved for this experiment was 87.67%.”
Quote in the paperSubstantial claim - Also stated in: § 4.2. Experimental Results · plain
- Findingnone given
The proposed system did not perform well for complex motion patterns, such as tidying the kitchen or reading a newspaper.
“The proposed system did not perform well for complex motion patterns, such as tidying the kitchen or reading a newspaper.”
Quote in the paperSubstantial claim
- Findingown data
The proposed system achieved a mean accuracy rate of 87.0%.
“The mean accuracy rate of 87.0% is higher than the traditional methods proposed in the literature.”
- Also stated in: § 4.2. Experimental Results · plain
“An enhanced mean accuracy rate of 87.0% has been achieved through the proposed system when compared to the other conventional models.”
- Also stated in: § 5. Conclusions · plain
“The proposed multimodal IoT-based locomotion prediction model was able to achieve a mean accuracy rate of 87.0%.”
Quote in the paperSubstantial claim - Also stated in: § 4.2. Experimental Results · plain
- Findingown data
The proposed system achieved an accuracy rate of 86.71% on the Opportunity++ dataset.
“The novel multimodal IoT-based locomotion classification system has achieved an accuracy rate of 87.67% and 86.71% over the HWU-USP and Opportunity++ datasets, respectively.”
- Also stated in: § 4.2. Experimental Results · plain
“It is evident from the table that the offered methodology was able to attain an accuracy rate of 86.71% in this experiment.”
Quote in the paperSubstantial claim - Also stated in: § 4.2. Experimental Results · plain
- Premisecitation
Prior multimodal systems that lacked filtration techniques applied to multimodal data had low performance.
“However, due to the lack of filtration techniques applied to multimodal data, the system’s performance was low.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [15] Ordóñez, F., and Roggen, D. (2016). Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors, 16. source
Not checked in the free run.
- Study design and conductnone given
The system has been validated using confusion matrices, confidence levels, and skeleton point accuracies.
“The system has been validated using confusion matrices, confidence levels, and skeleton point accuracies.”
Quote in the paperSubstantial claim - Interpretationcitation
The RvNN is ideal for the proposed multimodal IoT-based locomotion prediction system because it can learn distributed, structured data.
“We have applied this network because RvNN can be used to learn distributed, structured data. Therefore, it is ideal for our proposed multimodal IoT-based locomotion prediction system.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [32] Murad, A., and Pyun, J.-Y. (2017). Deep Recurrent Neural Networks for Human Activity Recognition. Sensors, 17. source
Not checked in the free run.
- Study design and conductcitation
Skeleton modeling for the extracted human silhouette was validated through confidence levels and skeleton point accuracies.
“Accurate skeleton modeling for the extracted human silhouette was validated through confidence levels and skeleton point accuracies.”
- Also stated in: § 4.2. Experimental Results · plain
“Table 2 provides the confidence levels [35] calculated for each skeleton point extracted from the human silhouette.”
- Also stated in: § 4.2. Experimental Results · plain
“Table 4 explains the confidence levels and recognition accuracy measured against each skeleton point for the human silhouette extracted in our proposed methodology.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [35] Akhter, I., Jalal, A., and Kim, K. (2021, January 12–16). Pose Estimation and Detection for Event Recognition using Sense-Aware Features and Adaboost Classifier. Proceedings of the 2021 International Bhurban Conference on Applied Sciences and Technologies (IBCAST), Islamabad, Pakistan. source
Not checked in the free run.
- Also stated in: § 4.2. Experimental Results · plain
- Premisecitation
Prior locomotion prediction systems that lacked good features had lower accuracy rates.
“However, the lack of good features caused lower accuracy rates.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [12] Madiha, J., Shorfuzzaman, M., Alsufyani, N., Chelloug, S.A., Jalal, A., and Park, J. (2022). Physical human locomotion prediction using manifold regularization. PeerJ Comput. Sci., 8. source
Not checked in the free run.
- Premisecitation
Prior multimodal systems that lacked proper filtration and feature extraction techniques were not able to recognize ADL correctly.
“However, due to the lack of proper filtration and feature extraction techniques applied, the system was not able to recognize the ADL correctly.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [17] Chung, S., Lim, J., Noh, K.J., Kim, G., and Jeong, H. (2019). Sensor Data Acquisition and Multimodal Sensor Fusion for Human Activity Recognition Using Deep Learning. Sensors, 19. source
Not checked in the free run.
- Premisecitation
Conventional single-sensor devices do not serve the purpose as efficiently as required.
“Nonetheless, such devices are based on a single sensor type and do not serve the purpose as efficiently as required [9].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [9] Batool, M., Alotaibi, S.S., Alatiyyah, M.H., Alnowaiser, K., Aljuaid, H., Jalal, A., and Park, J. (2013). Depth Sensors-Based Action Recognition using a Modified K-Ary Entropy Classifier. IEEE Access.
Not checked in the free run.
- Premisecitation
Prior locomotion prediction systems that did not filter noise from raw sensor data had problematic outcomes.
“Though the proposed study achieved good accuracy results, it did not filter the noise from raw sensor data, causing problematic outcomes.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [11] Figueiredo, 2020, Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach, IEEE Access source
Not checked in the free run.
- Interpretationown data
The proposed system is superior to other conventional approaches, particularly multimodal approaches, in the literature.
“experiments performed verified that the proposed locomotion classification system is superior when compared to other conventional approaches, particularly when considering multimodal data.”
- Also stated in: § 5. Conclusions · boosted
“The results from these experiments have shown that our proposed system has outperformed several conventional multimodal approaches in the literature.”
Quote in the paperSubstantial claim - Also stated in: § 5. Conclusions · boosted
- Premisecitation
Prior multimodal systems that did not use hand-crafted features had low accuracy.
“Though the system did not use any hand-crafted features, resulting in low accuracy”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [16] De, 2015, Multimodal Wearable Sensing for Fine-Grained Activity Recognition in Healthcare, IEEE Internet Comput. source
Not checked in the free run.
- Classified as probably not a substantial claim. 3
- May combine two claims. 1
Probably not a substantial claim: may not pass S4 (based).
Interpretationnone givenMultimodal fusion of sensors for locomotion prediction can help in creating predictions that are more accurate.
“This fusion of multi-sensors for locomotion prediction is referred to as the multimodal approach and can help in creating predictions that are more accurate.”
Quote in the paperNot a substantial claimMay combine two claims.
Interpretationown dataThe proposed system attained sufficient outcomes due to robust multimodal IoT-based locomotion classification that shows significant improvement in the classification of ADL in terms of accuracy.
“The proposed system attained sufficient outcomes due to robust multimodal IoT-based locomotion classification that shows significant improvement in the classification of ADL in terms of accuracy.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationPrior multimodal systems that did not use visual sensors were limited.
“However, the system was not able to make use of the visual sensors.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [14] Chavarriaga, 2013, The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition, Pattern Recognit. Lett. source
Not checked in the free run.
Classified as probably not a substantial claim.
Study design and conductnone givenA 10-fold cross-validation technique has been used over the dataset for training purposes.
“A 10-fold cross-validation technique has been used over the dataset for training purposes.”
Quote in the paperSubstantial claim
The paper relies on this without support.
Multimodal IoT-based locomotion classification has helped solve the challenges of motion signal complexity and video processing.
“The multimodal internet of things (IoT)-based locomotion classification has helped in solving these challenges.”
The paper relies on this without support.
The comparison of the proposed system with conventional methods in Table 5 is fair and uses comparable evaluation conditions.
“The comparison of our approach with conventional multimodal state-of-the-art techniques is given in Table 5 [38].”
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?
In [167], outcomes from each pre-processor are merged, resulting in reduction of errors stemming from intricate aspects of motion-related challenges.
“Subsequently, the outcomes from each pre-processor are merged, resulting in a reduction of errors stemming from the intricate aspects of motion-related challenges.”
From A Survey of Video Surveillance Systems in Smart City (2023) · cites this paper as [167]
Sections 3.2 and 3.4 describe separate preprocessing of ambient, motion, and visual data, followed by fusion of features extracted from those data—not direct merging of preprocessor outputs. The Conclusions state that the system was proposed to reduce errors caused by motion-related complexities, but do not establish that the fusion itself produced that reduction; they also note poor performance on some complex motions. Page numbers are unavailable in our copy. (LLM, conf=0.85)
Experimental — accuracy not yet measuredIn [167], data gathered from physical motion, ambient, and vision-based sensors undergoes individual pre-processing tailored to each type.
“In [167], data gathered from physical motion, ambient, and vision-based sensors undergoes individual pre-processing tailored to each type.”
From A Survey of Video Surveillance Systems in Smart City (2023) · cites this paper as [167]
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.
Conflicting number of datasets
MinorThe abstract says the technique uses three benchmarked datasets, but the introduction says two were selected. The paper names and evaluates only HWU-USP and Opportunity++.
“In this paper, we proposed a novel multimodal IoT-based locomotion classification technique using three benchmarked datasets.”
“Two benchmarked IoT-based datasets have been selected to verify the proposed multimodal locomotion classification system.”
Cites
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 1× · see citing works
“The following subsections will explain the three techniques in detail.”
The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition
Chavarriaga, R., Sagha, H., Calatroni, A., Digumarti, S. T., Tröster, G., Millán, J. D. R., & Roggen, D. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.12.014 · Cited by 742 · cited 3× · see citing works
“The suggested methodology has been applied to the HWU-USP dataset.”
InfluentialDeep Recurrent Neural Networks for Human Activity Recognition
Murad, A., & Pyun, J.-Y. (2017) · Sensors · doi:10.3390/s17112556 · Cited by 524 · see citing works
UP-Fall Detection Dataset: A Multimodal Approach
Martínez-Villaseñor, L., Ponce-Espinosa, H., Brieva, J., Moya-Albor, E., Núñez-Martínez, J., & Penafort-Asturiano, C. J. (2019) · Sensors · doi:10.3390/s19091988 · Cited by 404 · see citing works
Chung, S., Lim, J., Noh, K. J., Kim, G., & Jeong, H. (2019) · Sensors · doi:10.3390/s19071716 · Cited by 215 · see citing works
DanHAR: Dual Attention Network for multimodal human activity recognition using wearable sensors
Gao, W., Zhang, L., Teng, Q., He, J., & Wu, H. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107728 · Cited by 214 · see citing works
Quaid, M. A. K., & Jalal, A. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08463-7 · Cited by 185 · see citing works
Self-citationJalal, A., & Mahmood, M. (2019) · Education and Information Technologies · doi:10.1007/s10639-019-09892-5 · Cited by 172 · see citing works
Self-citationNadeem, A., Jalal, A., & Kim, K. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10687-5 · Cited by 165 · see citing works
Self-citationReal-Time Gait Phase Estimation for Robotic Hip Exoskeleton Control During Multimodal Locomotion
Kang, I., Molinaro, D. D., Duggal, S., Chen, Y., Kunapuli, P., & Young, A. J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3062562 · Cited by 164 · see citing works
Jalal, A., Quaid, M. A. K., & Hasan, A. S. (2018) · International Conference on Frontiers of Information Technology (FIT) · doi:10.1109/fit.2018.00026 · Cited by 136 · see citing works
Self-citationDense depth maps-based human pose tracking and recognition in dynamic scenes using ridge data
Jalal, A., & Kim, Y.-H. (2014) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2014.6918654 · Cited by 133 · see citing works
Self-citationMahmood, M., Jalal, A., & Kim, K. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08527-8 · Cited by 131 · see citing works
Self-citationMultimodal Wearable Sensing for Fine-Grained Activity Recognition in Healthcare
De, D., Bharti, P., Das, S. K., & Chellappan, S. (2015) · IEEE Internet Computing · doi:10.1109/mic.2015.72 · Cited by 129 · see citing works
Stochastic Recognition of Physical Activity and Healthcare Using Tri-Axial Inertial Wearable Sensors
Jalal, A., Batool, M., & Kim, K. (2020) · Applied Sciences · doi:10.3390/app10207122 · Cited by 122 · see citing works
Self-citationJalal, A., Quaid, M. A. K., & Kim, K. (2019) · Journal of Electrical Engineering and Technology · doi:10.1007/s42835-019-00187-w · Cited by 117 · see citing works
Self-citationHuman Body Parts Estimation and Detection for Physical Sports Movements
Jalal, A., Nadeem, A., & Bobasu, S. (2019) · International Conference on Communication, Computing and Digital Systems (C-CODE) · doi:10.1109/c-code.2019.8680993 · Cited by 116 · see citing works
Self-citationRecursive Neural Network for Video Deblurring
Zhang, X., Jiang, R., Wang, T., & Wang, J. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3035722 · Cited by 105 · see citing works
Automate Appliances via Gestures Recognition for Elderly Living Assistance
Muneeb, M., Rustam, H., & Jalal, A. (2023) · International Conference on Advancements in Computational Sciences (ICACS) · doi:10.1109/icacs55311.2023.10089778 · Cited by 105 · see citing works
Self-citationAzmat, U., & Jalal, A. (2021) · International Conference on Communication Technologies (ComTech) · doi:10.1109/comtech52583.2021.9616681 · Cited by 91 · see citing works
Self-citationJalal, A., Batool, M., & Kim, K. (2020) · Sustainability · doi:10.3390/su122410324 · Cited by 86 · see citing works
Self-citationAction Recognition in Manufacturing Assembly using Multimodal Sensor Fusion
Al-Amin, M., Tao, W., Doell, D., Lingard, R., Yin, Z., Leu, M. C., & Qin, R. (2019) · Procedia Manufacturing · doi:10.1016/j.promfg.2020.01.288 · Cited by 85 · see citing works
Activity Recognition for Ambient Assisted Living with Videos, Inertial Units and Ambient Sensors
Ranieri, C. M., MacLeod, S., Dragone, M., Vargas, P. A., & Romero, R. A. F. (2021) · Sensors · doi:10.3390/s21030768 · Cited by 84 · see citing works
Javeed, M., Jalal, A., & Kim, K. (2021) · International Bhurban Conference on Applied Sciences and Technology (IBCAST) · doi:10.1109/ibcast51254.2021.9393014 · Cited by 83 · see citing works
Self-citationArtificial Neural Network for Human Object Interaction System Over Aerial Images
Pervaiz, M., & Jalal, A. (2023) · International Conference on Advancements in Computational Sciences (ICACS) · doi:10.1109/icacs55311.2023.10089722 · Cited by 77 · see citing works
Self-citationGimme Signals: Discriminative signal encoding for multimodal activity recognition
Memmesheimer, R., Theisen, N., & Paulus, D. W. R. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341699 · Cited by 69 · see citing works
Gochoo, M., Akhter, I., Jalal, A., & Kim, K. (2021) · Remote Sensing · doi:10.3390/rs13050912 · Cited by 65 · see citing works
Self-citationAkhter, I., Jalal, A., & Kim, K. (2021) · 2021 International Bhurban Conference on Applied Sciences and Technologies (IBCAST) · doi:10.1109/ibcast51254.2021.9393293 · Cited by 58 · see citing works
Self-citationApplication of Type-2 Fuzzy AHP-ARAS for Selecting Optimal WEDM Parameters
Sen, B., Hussain, S. A. I., Gupta, A. D., Gupta, M., Pimenov, D., & Mikołajczyk, T. (2020) · Metals · doi:10.3390/met11010042 · Cited by 43 · see citing works
Depth Sensors-Based Action Recognition Using a Modified K-Ary Entropy Classifier
Batool, M., Alotaibi, S. S., Alatiyyah, M. H., Alnowaiser, K., Aljuaid, H., Jalal, A., & Park, J. (2023) · IEEE Access · doi:10.1109/access.2023.3260403 · Cited by 43 · see citing works
Self-citationA new descriptor for image matching based on bionic principles
Fausto, F., Cuevas, E., & Gonzales, A. (2017) · Pattern Analysis and Applications · doi:10.1007/s10044-017-0605-z · Cited by 37 · see citing works
Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach
Figueiredo, J., Carvalho, S. P., Goncalve, D., Moreno, J. C., & Santos, C. P. (2020) · IEEE Access · doi:10.1109/access.2020.2971552 · Cited by 37 · see citing works
Ghadi, Y. Y., Javeed, M., Alarfaj, M., Shloul, T. A., Alsuhibany, S. A., Jalal, A., Kamal, S., & Kim, D. (2022) · IEEE Access · doi:10.1109/access.2022.3154775 · Cited by 36 · see citing works
Self-citationCiliberto, M., Fortes Rey, V., Calatroni, A., Lukowicz, P., & Roggen, D. (2021) · Frontiers in Computer Science · doi:10.3389/fcomp.2021.792065 · Cited by 35 · cited 2× · see citing works
“The proposed system sufficient outcomes due to robust multimodal The proposed system a tt ained suf-fi cient outcomes due to robust multimodal IoT-based locomotion classi fi cation that shows signi fi cant improvement in the classi fi cation of ADL in terms of accuracy.”
InfluentialZhuo, S., Sherlock, L., Dobbie, G., Koh, Y. S., Russello, G., & Lottridge, D. M. (2020) · Sensors · doi:10.3390/s20030655 · Cited by 35 · see citing works
Wang, L., Ciliberto, M., Gjoreski, H., Lago, P., Murao, K., Okita, T., & Roggen, D. (2021) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3460418.3479373 · Cited by 34 · see citing works
Student’s Health Exercise Recognition Tool for E-Learning Education
Shloul, T. A., Javeed, M., Gochoo, M., Alsuhibany, S. A., Ghadi, Y. Y., Jalal, A., & Park, J. (2022) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.026051 · Cited by 30 · see citing works
Self-citationDeep Activity Recognition based on Patterns Discovery for Healthcare Monitoring
Javeed, M., & Jalal, A. (2023) · International Conference on Advancements in Computational Sciences (ICACS) · doi:10.1109/icacs55311.2023.10089764 · Cited by 30 · see citing works
Self-citationMultimodal sensor fusion in the latent representation space
Piechocki, R. J., Wang, X., & Bocus, M. J. (2023) · Scientific Reports · doi:10.1038/s41598-022-24754-w · Cited by 24 · see citing works
Javeed, M., & Jalal, A. (2021) · International Conference on Innovative Computing (ICIC) · doi:10.1109/icic53490.2021.9692924 · Cited by 21 · see citing works
Self-citationPhysical human locomotion prediction using manifold regularization
Javeed, M., Shorfuzzaman, M., Alsufyani, N., Chelloug, S. A., Jalal, A., & Park, J. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.1105 · Cited by 18 · see citing works
Self-citationDeep Human Motion Detection and Multi-Features Analysis for Smart Healthcare Learning Tools
Hajjej, F., Javeed, M., Ksibi, A., Alarfaj, M., Alnowaiser, K., Jalal, A., Alsufyani, N., Shorfuzzaman, M., & Park, J. (2022) · IEEE Access · doi:10.1109/access.2022.3214986 · Cited by 16 · see citing works
Self-citationEEG Signal Classification using Linear Predictive Cepstral Coefficient Features
Pazhanirajan, S., & Dhanalakshmi, P. (2013) · International Journal of Computer Applications · doi:10.5120/12707-9508 · Cited by 15 · see citing works
Human Activity Recognition via Smartphone Embedded Sensor using Multi-Class SVM
Danyal, & Azmat, U. (2022) · International Multi-Topic Conference · doi:10.1109/inmic56986.2022.9972927 · Cited by 6 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A Survey of Video Surveillance Systems in Smart City
Myagmar-Ochir, Y., & Kim, W. (2023) · Electronics · doi:10.3390/electronics12173567 · Cited by 134 · see citing works
Self-citationIntelligent Localization and Deep Human Activity Recognition through IoT Devices
Alazeb, A., Azmat, U., Mudawi, N. A., Alshahrani, A. S., Alotaibi, S. S., Almujally, N. A., & Jalal, A. (2023) · Sensors · doi:10.3390/s23177363 · Cited by 62 · see citing works
Self-citationMudawi, N. A., Azmat, U., Alazeb, A., Alhasson, H. F., Alabdullah, B. I., Rahman, H., Liu, H., & Jalal, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-94689-5 · Cited by 38 · see citing works
Self-citationBiosensor-Based Multimodal Deep Human Locomotion Decoding via Internet of Healthcare Things
Javeed, M., Abdelhaq, M., Algarni, A. M., & Jalal, A. (2023) · Micromachines · doi:10.3390/mi14122204 · Cited by 15 · see citing works
Self-citationA Deep Learning Framework for Healthy Lifestyle Monitoring and Outdoor Localization
Rafiq, M., Alshammari, N. S., Alhasson, H. F., AlHammadi, D. A., Alshehri, M., Jalal, A., & Liu, H. (2025) · IEEE Access · doi:10.1109/access.2025.3573439 · Cited by 14 · see citing works
Self-citationIntelligent ADL Recognition via IoT-Based Multimodal Deep Learning Framework
Javeed, M., Mudawi, N. A., Alazeb, A., Almakdi, S., Alotaibi, S. S., Chelloug, S. A., & Jalal, A. (2023) · Sensors · doi:10.3390/s23187927 · Cited by 9 · see citing works
Self-citationDing, X., Xu, Y., Zheng, M., Kang, W., & Xiahou, X. (2025) · Systems · doi:10.3390/systems13110974 · Cited by 6 · see citing works
Ashfaq, N., Aziz, Z., Khan, M. H., Nisar, M. A., & Khalid, A. (2025) · IEEE Access · doi:10.1109/access.2025.3577730 · Cited by 5 · see citing works
A Novel Deep Learner for Human Behavior Prediction Over Public Video Surveillance
Alabdullah, B. I., Fatima, B., Alhasson, H. F., Alshehri, M., Alqahtani, Y., Albhassabi, N., & Liu, H. (2025) · IEEE Access · doi:10.1109/access.2025.3579749 · Cited by 2 · see citing works
Intelligent Fine-Grained Daily Living Locomotion Prediction Based on Skeleton Modeling and CNN
Javeed, M., Mudawi, N. A., Alazeb, A., Aljuaid, H., Alatiyyah, M. H., Alnowaiser, K., Algarni, A. M., & Jalal, A. (2024) · Traitement du signal · doi:10.18280/ts.410525 · Cited by 1 · see citing works
Self-citationDeep locomotion prediction learning over biosensors, ambient sensors, and computer vision
Javeed, M., Jalal, A., AlHammadi, D. A., & Lee, B. (2026) · PLoS ONE · doi:10.1371/journal.pone.0342793 · Cited by 1 · see citing works
Self-citationA Robust Fraud Detection System using Deep Belief Network and Restricted Boltzmann Machines
Javeed, M. (2024) · International Conference on Signal Processing and Information Security (ICSPIS) · doi:10.1109/icspis63676.2024.10812592
Self-citationMuñoz, P. S., Orozco, A. S. O., Pabón, J., Gómez, D., Salazar-Cabrera, R., Cerón, J. D., López, D. M., & Blobel, B. G. M. E. (2025) · Journal of Personalized Medicine · doi:10.3390/jpm15050208
Multimodal Transformer Models for Human Action Classification
Varga, Z., Mascaro, E. V., Sliwowski, D., & Lee, D. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-92011-0_5
A Solar-Powered Multimodal IoT Framework for Real-Time Transformer Theft Detection
Ojokoh, P., & Agbolade, O. A. (2025) · Journal of Computing Theories and Applications · doi:10.62411/jcta.14901
Human Activity Recognition: Innovations, Impacts, and Implications for Society
Reshi, B. A., & Kumar, V. (2025) · IEEE Technology and Society Magazine · doi:10.1109/mts.2025.3627977
Two-Person Action Surveillance via Multi-Modal Feature Optimization and Markov Model
Kamal, S., & Jalal, A. (2025) · International Conference on Engineering & Computing Technologies (ICECT) · doi:10.1109/icect66235.2025.11381670
Self-citationA Novel Healthcare Monitoring Systems via Hybrid Features with Naïve Bayes Classifier
Kamal, S., & Jalal, A. (2025) · International Conference on Engineering & Computing Technologies (ICECT) · doi:10.1109/icect66235.2025.11381665
Self-citationPathak, A., Tiwari, V., & Arya, K. V. (2025) · IEEE International Conference on Recent Trends in Computing and Smart Mobility (RCSM) · doi:10.1109/rcsm67767.2025.11507235
- Authors
- Javeed, M., Mudawi, N. A., Alabduallah, B. I., Jalal, A., & Kim, W.
- Affiliations
- Air University (PK)
- Najran University (SA)
- Princess Nourah bint Abdulrahman University (SA)
- Gachon University (KR)
- Corresponding author
- Kim, Wooseong
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2023-05-12
- Volume
- 23
- Issue
- 10
- Pages
- 4716
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC10222771
- OpenAlex
- W4376274976
- Semantic Scholar
- e8db05c3ef8cca9091a8d0e2e8ffd897f6f5cf7d
- Cited by
- 18
- References
- 44
- Citations by year
- 2026: 1 · 2025: 12 · 2024: 1 · 2023: 4
- FWCI
- 1.63
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Deanship of Scientific Research at Najran University (NU/RG/SERC/12/40, PNURSP2023R440, G21S2861919)
- Princess Nourah bint Abdulrahman University Researchers Supporting Project (NU/RG/SERC/12/40, PNURSP2023R440, G21S2861919)
- Ministry of SMEs and Startups (MSS, Korea) (NU/RG/SERC/12/40, PNURSP2023R440, G21S2861919)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Keywords
- multimodal fusion, Internet of Things, activities of daily living, wearable sensors, feature engineering, recursive neural networks, environmental sensing, elderly care, Opportunity dataset
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.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.
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
