The DOI matches its Crossref record; 55 of the 56 references it cites were found in a registry or an index.
Online Fall Detection Using Recurrent Neural Networks on Smart Wearable Devices
Open accessAbstract
Unintentional falls can cause severe injuries and even death, especially if no immediate assistance is given. A fall detection system aims to detect a fall as soon as it occurs, therefore issuing an automatic assistance request. Wearable embedded sensors are emerging as the most viable solution for continuous monitoring since they are more effective, less intrusive and less expensive than other systems. Tailoring a deep learning method to the requirements of microcontrollers entails matching very stringent constraints in terms of both memory and computational power. In addition, datasets acquired with wearable devices are relatively scarce and not necessarily devised for supervised learning. In this work, we discuss the design of a software architecture based on recurrent neural networks which can be effective for fall detection while running entirely onboard a wearable device. The well-known and publicly-available SisFall dataset was adopted and extended with fine-grained temporal annotations to cope with the supervised training of recurrent neural networks. We then show that an appropriate process of architectural minimization together with accurate hyperparameters selection leads to a workable model which compares favorably with other detection techniques. The embedding of the resulting architecture has been validated using a state-of-art hardware device.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Unlike static classifiers, LSTMs maintain an internal memory state, allowing the model to distinguish between a “controlled descent” and a “sudden drop” based on the velocity history of the movement [18].”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [18]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545
TensorFlow: A system for large-scale machine learningPreprint
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.5555/3026877.3026899 · Cited by 16,548
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172
Improving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
A Critical Review of Recurrent Neural Networks for Sequence LearningPreprint
Lipton, Z. C., Berkowitz, J. A., & Elkan, C. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.00019 · Cited by 3,159
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×
“n of the classifier. Indeed, they investigate the use of ANN, KNN, Radial Basis Function (RBF), Probabilistic Principal Component Analysis (PPCA) and Linear Discriminant Analysis (LDA). The authors of [14] utilize a DL technique to detect falls. The architecture is composed by two parts: a Convolutional Network and a R…”
MethodHubara, I., Soudry, D., & Yaniv, R. E. (2016) · arXiv · doi:10.48550/arxiv.1602.02505 · Cited by 1,667
Research works printed but not linked: 3
- 2008, WHO Global Report on Falls Prevention in Older Age
- goodfellow, 2016, Deep Learning
- huang, 2010, Fall detection system for healthcare quality improvement in residential care facilities, J Med Biol Eng, 30, 247, 10.5405/jmbe.30.5.04 · DOI
Cited by
Sorted by citations
Queralta, J. P., Gia, T. N., Tenhunen, H., & Westerlund, T. (2019) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2019.8768883 · Cited by 154
Yu, X., Jang, J., & Xiong, S. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.692865 · Cited by 134
Intelligent Wearable Systems: Opportunities and Challenges in Health and Sports
Yang, L., Amin, O., & Shihada, B. (2024) · ACM Computing Surveys · doi:10.1145/3648469 · Cited by 159
Jain, R., & Semwal, V. B. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3213814 · Cited by 118
“Musci et al. [21] have utilized a graphical annotation tool for assigning the temporal labels to fall activity data for the SisFall dataset, but again it was a manual approach and required a team of experts to perform the task.”
MethodInfluentialCasilari, E., Lora-Rivera, R., & García-Lagos, F. (2020) · Sensors · doi:10.3390/s20051466 · Cited by 106
Wearable Fall Detector Using Recurrent Neural Networks
Luna-Perejón, F., Domínguez-Morales, M., & Balcells, A. (2019) · Sensors · doi:10.3390/s19224885 · Cited by 99
EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network
Alessandrini, M., Biagetti, G., Crippa, P., Falaschetti, L., Luzzi, S., & Turchetti, C. (2022) · Sensors · doi:10.3390/s22103696 · Cited by 96
Wearables and Deep Learning Classify Fall Risk From Gait in Multiple Sclerosis
Meyer, B. M., Tulipani, L. J., Gurchiek, R. D., Allen, D. A., Adamowicz, L., Larie, D., Solomon, A. J., Cheney, N., & McGinnis, R. S. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3025049 · Cited by 91
AI-Reinforced Wearable Sensors and Intelligent Point-of-Care Tests
Yammouri, G., & Lahcen, A. A. (2024) · Journal of Personalized Medicine · doi:10.3390/jpm14111088 · Cited by 92
Diab, M. S., & Rodriguez–Villegas, E. (2022) · IEEE Access · doi:10.1109/access.2022.3206782 · Cited by 92
FEEL: FEderated LEarning Framework for ELderly Healthcare Using Edge-IoMT
Ghosh, S., & Ghosh, S. K. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3233300 · Cited by 80
“[18] proposed a fall detection algorithm leveraging RNN on wearable device data.”
MethodAccelerometer-Based Fall Detection Using Machine Learning: Training and Testing on Real-World Falls
Palmerini, L., Klenk, J., Becker, C., & Chiari, L. (2020) · Sensors · doi:10.3390/s20226479 · Cited by 73
Alessandrini, M., Biagetti, G., Crippa, P., Falaschetti, L., & Turchetti, C. (2021) · Electronics · doi:10.3390/electronics10141715 · Cited by 74
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 70
Self-citationApplying deep learning technology for automatic fall detection using mobile sensors
Wu, X., Zheng, Y., Chu, C., Cheng, L., & Kim, J. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103355 · Cited by 64
Zurbuchen, N., Wilde, A., & Bruegger, P. (2021) · Sensors · doi:10.3390/s21030938 · Cited by 60
NT-FDS—A Noise Tolerant Fall Detection System Using Deep Learning on Wearable Devices
Waheed, M., Afzal, H., & Mehmood, K. (2021) · Sensors · doi:10.3390/s21062006 · Cited by 63
Jaén-Vargas, M., Leiva, K. M. R., Fernandes, F., Gonçalves, S. B., Silva, M. T., Lopes, D. S., & Olmedo, J. J. S. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.1052 · Cited by 71
A practical wearable fall detection system based on tiny convolutional neural networks
Yu, X., Park, S., Kim, D., Kim, E., Kim, J., Kim, W., An, Y., & Xiong, S. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105325 · Cited by 65
A Novel Embedded Deep Learning Wearable Sensor for Fall Detection
Campanella, S., Alnasef, A., Falaschetti, L., Belli, A., Pierleoni, P., & Palma, L. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3375603 · Cited by 57
“Musci et al. [39] used LSTM, a kind of RNN that can record long-term dependencies and is, hence, well suited for sequential input.”
BackgroundMethodResultInfluentialA cross-dataset deep learning-based classifier for people fall detection and identification
Delgado-Escaño, R., Castro, F. M., Cózar, J. R., Marín-Jiménez, M. J., Guil, N., & Casilari, E. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105265 · Cited by 60
Vision Based Real Time Monitoring System for Elderly Fall Event Detection Using Deep Learning
Anitha, G. S., & Priya, S. B. (2021) · Computer Systems Science and Engineering · doi:10.32604/csse.2022.020361 · Cited by 53
A review of wearable sensors based fall-related recognition systems
Liu, J., Li, X., Huang, S., Chao, R., Chao, R., Wang, S., Wang, S., & Liu, L. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.105993 · Cited by 56
Embedding Recurrent Neural Networks in Wearable Systems for Real-Time Fall Detection
Torti, E., Fontanella, A., Musci, M., Blago, N., Pau, D. P., Leporati, F., & Piastra, M. (2019) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2019.102895 · Cited by 47
Self-citationNho, Y., Ryu, S., & Kwon, D. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3054394 · Cited by 47
Kraft, D., Srinivasan, K. K., & Bieber, G. (2020) · Technologies · doi:10.3390/technologies8040072 · Cited by 50
FallNeXt: A Deep Residual Model based on Multi-Branch Aggregation for Sensor-based Fall Detection
Mekruksavanich, S., & Jitpattanakul, A. (2022) · ECTI Transactions on Computer and Information Technology (ECTI-CIT) · doi:10.37936/ecti-cit.2022164.248156 · Cited by 43
Bhavani, K. D., & Ukrit, M. F. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16476-6 · Cited by 42
“In [20], the author discussed the model of a software structure related to RNN that is highly effective in FD while running completely onboard wearable devices.”
Mohammad, Z., Anwary, A. R., Mridha, M. F., Shovon, M. S. H., & Vassallo, M. (2023) · Sensors · doi:10.3390/s23104774 · Cited by 43
“Therefore, we applied the proposal from [9], in which each block is categorized based on the frequency of appearance of the most relevant class.”
MethodInfluentialFall Detection with CNN-Casual LSTM Network
Wu, J. Y., Wang, J., Zhan, A., & Wu, C. (2021) · Information · doi:10.3390/info12100403 · Cited by 39
“Mirto Musci [30] used a fall detection algorithm based on LSTM, taking a long-time sequence as input and automatically extracting temporal information.”
Friedrich, B., Lau, S., Elgert, L., Bauer, J. M., & Hein, A. (2021) · Healthcare · doi:10.3390/healthcare9020149 · Cited by 37
Barshan, B., & Turan, M. Ş. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3280060 · Cited by 40
“Because ML/DL classifiers usually involve complex algorithms that require training, they are computationally more demanding compared to heuristic algorithms [65].”
Ultra low-power, wearable, accelerated shallow-learning fall detection for elderly at-risk persons
Tian, J., Mercier, P. P., & Paolini, C. P. (2024) · Smart Health · doi:10.1016/j.smhl.2024.100498 · Cited by 36
“The ability to recognize, interpret, and monitor these ADLs, along with fall detection, is vital for the effectiveness of context-aware systems (Musci, De Martini, Blago, Facchinetti, & Piastra, 2021; Waheed, Afzal, & Mehmood, 2021).”
Li, J., Gu, X., Qiu, S., Zhou, X., Cangelosi, A., Loo, C. K., & Liu, X. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3369071 · Cited by 37
“The images of CNN, RNN-LSTM, 2D-CNN, DBN, GCN, DAE, TCN, and CNN + RNN come from [118], [119], [120], [121], [122], and [123].”
A Comparison of Machine Learning Algorithms for Fall Detection using Wearable Sensors
Zurbuchen, N., Bruegger, P., & Wilde, A. (2020) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic48513.2020.9065205 · Cited by 34
Jahanjoo, A., Naderan, M., & Rashti, M. J. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-01690-z · Cited by 33
“Similar to Micucci et al. (2015), Figueiredo et al. (2016), Medrano et al. (2014), Jahanjoo et al. (2017), Ozdemir (2016), Fakhrulddin et al. (2017), Musci et al. (2018), Torti et al. (2018), Ramachandran et al. (2018), Pena Queralta et al. (2019), Wu et al. (2019), and Saleh et al. (2019), general…”
BackgroundMethodInfluentialAlizadeh, J., Bogdan, M., Claßen, J., & Fricke, C. (2021) · Sensors · doi:10.3390/s21217166 · Cited by 33
“Additionally, they seem to achieve even higher classification accuracy [33–36].”
BackgroundPatch-Transformer Network: A Wearable-Sensor-Based Fall Detection Method
Wang, S., & Wu, J. Y. (2023) · Sensors · doi:10.3390/s23146360 · Cited by 32
Syed, A. S., Sierra-Sosa, D., Kumar, A., & Elmaghraby, A. S. (2022) · Sensors · doi:10.3390/s22072547 · Cited by 31
Edge Computing Transformers for Fall Detection in Older Adults
Ruiz, J. F.-B., del Rincón, J. M., Dorado, J., del Toro, X., Santofimia, M. J., & López, J. C. (2024) · International Journal of Neural Systems · doi:10.1142/s0129065724500266 · Cited by 29
Luna-Perejón, F., Muñoz-Saavedra, L., Civit-Masot, J., Civit, A., & Domínguez-Morales, M. (2021) · Sensors · doi:10.3390/s21051889 · Cited by 29
A hybrid CNN-LSTM model for involuntary fall detection using wrist-worn sensors
Hu, X., Yu, S., Zheng, J., Fang, Z., Zhao, Z., & Qu, X. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103178 · Cited by 33
Semantic segmentation-based system for fall detection and post-fall posture classification
Mobsite, S., Alaoui, N., Boulmalf, M., & Ghogho, M. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105616 · Cited by 30
Unveiling Fall Origins: Leveraging Wearable Sensors to Detect Pre-Impact Fall Causes
Kiran, S., Riaz, Q., Hussain, M., Zeeshan, M., & Krüger, B. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3407835 · Cited by 26
“An online FDS has been proposed by Musci et al. [27], which uses a wearable microcontroller device equipped with inertial sensors and an RNN.”
MethodFall Detection with Supervised Machine Learning using Wearable Sensors
Giuffrida, D., Benetti, G., Martini, D. D., & Facchinetti, T. (2019) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin41052.2019.8972246 · Cited by 26
Self-citationSaleh, M., Abbas, M., Prud’homm, J., Somme, D., & Jeannès, R. L. B. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3133616 · Cited by 26
Multi-sensor-based Action Monitoring and Recognition via Hybrid Descriptors and Logistic Regression
Hafeez, S., Alotaibi, S. S., Alazeb, A., Mudawi, N. A., & Kim, W. (2023) · IEEE Access · doi:10.1109/access.2023.3275733 · Cited by 24
Demrozi, F., Turetta, C., Kindt, P. H., Chiarani, F., Bacchin, R. A., Valè, N., Pascucci, F., Cesari, P., Smania, N., Tamburin, S., et al. (2023) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2023.3274189 · Cited by 28
Fall Detector Adapted to Nursing Home Needs through an Optical-Flow based CNN
CARLIER, A., PEYRAMAURE, P., Favre, K., & Pressigout, M. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9175844 · Cited by 22
Fall Detection for Shipboard Seafarers Based on Optimized BlazePose and LSTM
Liu, W., Liu, X., Hu, Y., Shi, J., Chen, X., Zhao, J., Wang, S., & Hu, Q. (2022) · Sensors · doi:10.3390/s22145449 · Cited by 22
“Compared with the stacked LSTM [38], the accuracy, specificity, and sensitivity increased by 3.”
MethodNext-generation fall detection: harnessing human pose estimation and transformer technology
Sykes, E. R. (2024) · Health Systems · doi:10.1080/20476965.2024.2395574 · Cited by 25
“…using Support Vector Machines (SVMs; Chen et al., 2021; Liang et al., 2018), kNN (He et al., 2019), Multi-Layer Perceptron (MLP) Alam et al. (2022), Long short-term memory networks (Adhikari et al., 2020), Recurrent Neural Networks (RNN; Musci et al., 2020) and hybrid solutions (Alam et al., 2022).”
Li, A., Bodanese, E., Poslad, S., Huang, Z., Hou, T., Wu, K., & Luo, F. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3290421 · Cited by 20
“Table VI compares the proposed approach with existing state-of-the-art works, which can be broadly categorized into wearable [14], [56], [57], [59], [60], [61] and nonwear-able [10], [23], [25], [26], [27], [28], [58], [62], [63], [64], [65] methods for fall detection.”
MethodFallDeF5: A Fall Detection Framework Using 5G-Based Deep Gated Recurrent Unit Networks
Al-Rakhami, M. S., Gumaei, A., Altaf, M. M., Hassan, M. M., Alkhamees, B. F., Muhammad, K., & Fortino, G. (2021) · IEEE Access · doi:10.1109/access.2021.3091838 · Cited by 19
Yu, X., Koo, B., Jang, J., Kim, Y., & Xiong, S. (2022) · Measurement · doi:10.1016/j.measurement.2022.111785 · Cited by 20
A novel semi-supervised model for pre-impact fall detection with limited fall data
Yu, X., Wan, J., An, G., Yin, X., & Xiong, S. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108469 · Cited by 18
Falaschetti, L., Biagetti, G., Alessandrini, M., Turchetti, C., Luzzi, S., & Crippa, P. (2024) · Sensors · doi:10.3390/s24206721 · Cited by 21
“Windows also overlap by o samples, so that the n -th data window contains samples in the range [ ( w Data windowing is also commonly performed in neural networks and other machine learning frameworks [17,31,45], with w and o being essential hyper-parameters to be established.”
BackgroundReal-time Threshold-Based Fall Detection System Using Wearable IoT
Amir, N. I. M., Dziyauddin, R. A., Mohamed, N., Ismail, N. S. N., Zulkifli, N. S. A., & Din, N. M. (2022) · International Conference on Smart Sensors and Application (ICSSA) · doi:10.1109/icssa54161.2022.9870974 · Cited by 18
“Nevertheless, anyone with a vulnerability, such as mild impairments or a post-operative condition, is at similar risk [5].”
BackgroundEEG-Based Neurodegenerative Disease Classification using LSTM Neural Networks
Alessandrini, M., Biagetti, G., Crippa, P., Falaschetti, L., Luzzi, S., & Turchetti, C. (2023) · IEEE Statistical Signal Processing Workshop (SSP) · doi:10.1109/ssp53291.2023.10208023 · Cited by 17
“Windowing is regularly performed in neural networks and other machine learning algorithms [12], [18], [30], with w and o being important hyper-parameters in such methods.”
BackgroundWearable Fall Detectors Based on Low Power Transmission Systems: A Systematic Review
Villa, M., & Casilari, E. (2024) · Technologies · doi:10.3390/technologies12090166 · Cited by 15
“This becomes particularly striking when considering that one of the major benefits of these long-range wireless communication standards is energy efficiency.”
Al‐qaness, M. A. A., Jiang, Z., & Shen, J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3508877 · Cited by 17
“Convolutional neural networks (CNNs) [13] and recurrent neural networks (RNNs) [14], such as long-short term memory (LSTM) [15] and gated recurrent unit (GRU) [16], have been widely used in fall detection systems.”
Research on CNN-BiLSTM Fall Detection Algorithm Based on Improved Attention Mechanism
Li, C., Liu, M., Yan, X., & Teng, G. (2022) · Applied Sciences · doi:10.3390/app12199671 · Cited by 13
Benoit, A., Escriba, C., Gauchard, D., Estève, A., & Rossi, C. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3364249 · Cited by 18
“These characteristics make Adam particularly well-suited for addressing the challenges inherent in temporal binary classification problems, where features exhibit variations over time, often characterized by sparse or nonuniform behaviors [20], [31], [32], [34], [69], [70], [71].”
BackgroundReal-Time AI-Driven Fall Detection Method for Occupational Health and Safety
Danilenka, A., Sowiński, P., Rachwał, K., Bogacka, K., Dabrowska, A. K., Kobus, M., Baszczyński, K., Okrasa, M., Olczak, W., Dymarski, P., et al. (2023) · Electronics · doi:10.3390/electronics12204257 · Cited by 18
Rodrigues, V. F., Antunes, R. S., Seewald, L. A., Bazo, R., dos Reis, E. S., dos Santos, U. J. L., Righi, R. D. R., da S., L. G., da Costa, C. A., Bertollo, F. L., et al. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.05.006 · Cited by 12
Continuous Wearable-based Fall Detection using Tiny Machine Learning
Cong, D. L., Quang, B. N., Minh, D. T., Cao, D. T., & Ngoc, M. N. (2024) · International Conference on Applying New Technology in Green Buildings (ATiGB) · doi:10.1109/atigb63471.2024.10717707 · Cited by 12
“For fall events, windows containing at least 40% of the total fall duration were labeled as falls, while the remaining windows were labeled as ADL [27], [28].”
MethodEvaluation of Feature Engineering on Wearable Sensor-based Fall Detection
Ramachandran, A., Ramesh, A., & Karuppiah, A. (2020) · International Conference on Information Networking · doi:10.1109/icoin48656.2020.9016479 · Cited by 12
Personalized Fall Detection System
Ngu, A. H. H., Metsis, V., Coyne, S., Chung, B., Pai, R., & Chang, J. (2020) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops48775.2020.9156172 · Cited by 11
A Smartphone Application for Fall Detection Using Accelerometer and ConvLSTM Network
Amara, M. I., Akkouche, A., Boutellaa, E., & Tayakout, H. (2021) · International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH) · doi:10.1109/ihsh51661.2021.9378743 · Cited by 11
Koo, B., Kim, J., Nam, Y., & Kim, Y. (2021) · Sensors · doi:10.3390/s21144638 · Cited by 9
“As new tools, such as hardware interfaces, or frameworks, such as Jetson Nano and TensorFlow Lite, were introduced, novel studies were conducted to pre-impact fall detection using deep learning techniques [38,39].”
BackgroundFall 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 9
Kong, V., Soeng, S., Thon, M., Cho, W.-S., Nayyar, A., & Kim, T.-K. (2025) · PLOS One · doi:10.1371/journal.pone.0325253 · Cited by 8
Microcontroller Implementation of LSTM Neural Networks for Dynamic Hand Gesture Recognition
Leo, K. D., Biagetti, G., Falaschetti, L., & Crippa, P. (2025) · Sensors · doi:10.3390/s25123831 · Cited by 11
Change detection and convolution neural networks for fall recognition
Georgakopoulos, S. V., Tasoulis, S. K., Mallis, G. I., Vrahatis, A. G., Plagianakos, V. P., & Maglogiannis, I. G. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05208-8 · Cited by 8
“[32] through a classifier using recurrent neural net-”
BackgroundMethodPrivacy-Enhancing Fall Detection from Remote Sensor Data Using Multi-Party Computation
Mainali, P., & Shepherd, C. (2019) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3339252.3340500 · Cited by 8
Detecting Falls with Recurrent Autoencoders and Body Acceleration Data
Boutellaa, E. (2019) · International Conference on Image and Signal Processing and their Applications (ISPA) · doi:10.1109/ispa48434.2019.8966875 · Cited by 8
Advancing Human Fall Detection Through Motion Data from Smart Wearable Sensors and CNN-BiGRU Model
Mekruksavanich, S., Phaphan, W., & Jitpattanakul, A. (2024) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess62520.2024.10719052 · Cited by 7
“Musci et al. [28] used a LSTM fall detection method to address this issue.”
MethodLee, H., Sohn, J., Lee, G., Jacobs, J. V., & Lee, S. H. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103413 · Cited by 7
Alessandrini, M., Falaschetti, L., Biagetti, G., Crippa, P., Luzzi, S., & Turchetti, C. (2023) · Sensors · doi:10.3390/s23198039 · Cited by 7
“Indeed data windowing is normally performed in computations involving machine learning and neural networks in particular [25–28].”
MethodUsing Deep Learning and Smartphone for Automatic Detection of Fall and Daily Activities
Wu, X., Cheng, L., Chu, C., & Kim, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-34482-5_6 · Cited by 7
Fall Detection Using Transformer Model
Sharook, K. M., Premkumar, A., Aishwaryaa, R., Amrutha, J. M., & Deepthi, L. R. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-5331-6_4 · Cited by 6
LSTM Gate Disclosure as an Embedded AI Methodology for Wearable Fall-Detection Sensors
Correia, S. D., Roque, P. M., & Matos-Carvalho, J. P. (2024) · Symmetry · doi:10.3390/sym16101296 · Cited by 6
Yu, X., Jang, J., & Xiong, S. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-80713-9_36 · Cited by 6
Villa, M., & Casilari, E. (2025) · Sensors · doi:10.3390/s26010162 · Cited by 4
“…implementing and testing the selected classifier on a wearable device based on the Arduino Nano 33 BLE Sense Rev2 (Arduino S.r.l., Monza, Italy) [49], which incorporates a triaxial accelerometer positioned at the waist, as shown in Figure 2, to assess its performance under conditions closer to…”
Combining Clustering Undersample and Ensemble Learning for Wearable Fall Detection
Zhang, M., & Gong, D. (2022) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar54675.2022.9872285 · Cited by 4
“Musci et al use recurrent neural networks to detect falls and use a weighted cross-entropy loss function to solve the class imbalance problem[18].”
BackgroundMethodSingle Camera based Real Time Framework for Automated Fall Detection
Soni, P. K., & Jain, P. (2022) · doi:10.1109/iccsea54677.2022.9936492 · Cited by 4
Dense & Attention Convolutional Neural Networks for Toe Walking Recognition
Chen, J., Soangra, R., Grant-Beuttler, M., Nanehkaran, Y. A., & Wen, Y. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3272362 · Cited by 5
“The most popular applications include fall detection [8], gait pattern classification in post-stroke patients [9], walking versus running [10], Parkinson’s disease diagnosis [11], [12], among others [13].”
BackgroundLiu, X., & Zhang, H. (2025) · ChemistryOpen · doi:10.1002/open.202400394 · Cited by 4
de la Cal, E., Fáñez, M., Villar, M. A., Villar, J. R., & González, V. M. (2022) · Logic Journal of IGPL · doi:10.1093/jigpal/jzac025 · Cited by 4
Al-Majdi, K., AL-Musawi, R. S. H., Ali, A. H., Abudlmoniem, S. A., & Mezaal, Y. S. (2021) · Periodicals of Engineering and Natural Sciences (PEN) · doi:10.21533/pen.v9i3.2599 · Cited by 4
ProtoPLSTM: An Interpretable Deep Learning Approach for Wearable Fine-Grained Fall Detection
Gao, C., Zhang, T., Jiang, X., Huang, W., Chen, Y., & Li, J. (2022) · IEEE Smart World Congress (SWC) · doi:10.1109/smartworld-uic-atc-scalcom-digitaltwin-pricomp-metaverse56740.2022.00091 · Cited by 4
“Convolutional Neural Networks [8, 9], Recurrent Neural Networks [10–13] and their combined approaches [14, 15] as representative methods of deep learning, have improved the accuracy of fall detection to close to 100%.”
BackgroundMethodBhatti, F. A., Riaz, Q., & Krüger, B. (2025) · IEEE Access · doi:10.1109/access.2025.3641198 · Cited by 3
“Musci et al. [27] proposed an online fall detection system using a wearable microcontroller integrated with inertial sensors and an RNN.”
Deep Learning on Automatic Fall Detection
Monteiro, S., Leite, A., & Pires, E. J. S. (2021) · IEEE Latin American Conference on Computational Intelligence (LA-CCI) · doi:10.1109/la-cci48322.2021.9769783 · Cited by 3
Nehary, E. A., Dey, A., & Rajan, S. (2023) · International Conference on Consumer Electronics · doi:10.1109/icce56470.2023.10043463 · Cited by 3
“Fall detection systems may be considered as assistive technologies [7] and may be categorized into three types based on the sensor modality: 1) systems based on ambient sensors like infrared or vibration sensors, 2) systems based on visual sensors such as video, and 3) systems using wearable…”
BackgroundHu, X., Zhang, W., Ou, H., Mo, S., Liang, F., Liu, J., Zhao, Z., & Qu, X. (2024) · Sports Biomechanics · doi:10.1080/14763141.2024.2315243 · Cited by 4
“The IMU data were filtered with the moving-average filter (window length = 5 data points) and normalised by the z-score method to ensure the data from the gyroscope and accelerometer in the same scale (Musci et al., 2020).”
MCTN: A Multi-Channel Temporal Network for Wearable Fall Prediction
Liu, J., Li, X., Liao, G., Wang, S., & Liu, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43427-3_24 · Cited by 3
Optimal Wearable Sensor Placement for Human Fall Detection Using Machine Learning Models
Vishwakarma, S., Pathak, Y., & Kumar, V. (2025) · International Conference on Computer, Electronics & Electrical Engineering & their Applications (IC2E3) · doi:10.1109/ic2e365635.2025.11167570 · Cited by 2
“Additionally, evaluating different wearable sensor configurations using extensive benchmarking techniques has been crucial in refining the accuracy and real-world applicability of fall detection systems [20, 21].”
A BiLSTM-Attention Model for Fall Event Prediction
Sun, X., Chen, X., Chen, H., & Han, Z. (2025) · International Conference on Mechatronics, Robotics, and Artificial Intelligence (MRAI) · doi:10.1109/mrai65197.2025.11135822 · Cited by 2
“Mirto Musci [12] used an LSTM-based fall detection algorithm that automatically extracts temporal information, with long-term time series as input.”
Fall Prediction by a Spatio-Temporal Multi-Channel Causal Model from Wearable Sensors Data
Liao, G., Liu, J., Liang, Y., Wang, S., & Liu, L. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447297 · Cited by 2
“Recently, deep learning-based models have gained prominence in this field [10, 11, 12, 13, 14], owing to their ability to generate high-level semantic features in latent space.”
BackgroundFall-KAN: Fall impact time estimation Kolmogorov-Arnold Network
Cartocci, N., Gkikakis, A. E., Pera, F., Settino, M. T., Caldwell, D. G., & Ortiz, J. (2024) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme62383.2024.10796549 · Cited by 2
“To annotate the fall period from the SisFall dataset, Musci et al. [28] first defined the standard labeling criteria by consulting experts in the field, then performed the labeling separately and revised it jointly in multiple steps to improve consistency.”
Review on Machine learning and its application in Atmospheric science and Human Behavior Recognition
Chen, H., Jiang, M., Liu, Y., He, J., & Li, H. (2020) · doi:10.1145/3432291.3432311 · Cited by 2
Metadata
- Authors
- Musci, M., De Martini, D., Blago, N., Facchinetti, T., & Piastra, M.
- Affiliations
- University of Pavia (IT)
- Venue
- IEEE Transactions on Emerging Topics in Computing
- Published
- 2021-07-01
- Volume
- 9
- Issue
- 3
- Pages
- 1276-1289
- ISSN
- 2168-6750 (ISSN-L)
- 2376-4562
- OpenAlex
- W2797186212
- Cited by
- 128
- References
- 56
- Citations by year
- 2026: 7 · 2025: 17 · 2024: 25 · 2023: 19 · 2022: 21 · 2021: 19
- FWCI
- 6.80
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Emerging Topics in Computing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Funders
- Regione Lombardia (139625)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Health Professions › Physical Therapy, Sports Therapy and Rehabilitation › Balance, Gait, and Falls Prevention
- Physical Sciences › Engineering › Biomedical Engineering › Advanced Sensor and Energy Harvesting Materials
- Keywords
- fall detection, wearable sensors, recurrent neural networks, embedded deep learning, microcontroller, SisFall dataset, temporal annotation, model compression, hyperparameter optimization, software architecture
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.
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
