Deep Learning for RFID-Based Activity Recognition
Open accessThe DOI matches its Crossref record; 41 of the 42 references it cites were found in a registry or an index.
Abstract
We present a system for activity recognition from passive RFID data using a deep convolutional neural network. We directly feed the RFID data into a deep convolutional neural network for activity recognition instead of selecting features and using a cascade structure that first detects object use from RFID data followed by predicting the activity. Because our system treats activity recognition as a multi-class classification problem, it is scalable for applications with large number of activity classes. We tested our system using RFID data collected in a trauma room, including 14 hours of RFID data from 16 actual trauma resuscitations. Our system outperformed existing systems developed for activity recognition and achieved similar performance with process-phase detection as systems that require wearable sensors or manually-generated input. We also analyzed the strengths and limitations of our current deep learning architecture for activity recognition from RFID data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“We chose to have 3 convolutional layers in our network, with odd-number kernel sizes: 3×3×32, 3×3×64 and 3×3×128, and with stride 1, which have been shown as efficient in the VGG net [30].”
MethodImageNet 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 · cited 7×
“We used the CNN with rectified linear units (ReLUs) because such units train several times faster than traditional tanh units [2,25].”
BackgroundMethodResultInfluentialAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We initialized the learning rate at 0.01 and adjusted it based on the ADAM optimization (Adam Optimizer in TensorFlow) [32].”
MethodInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“Several parameters need to be determined for constructing the convolutional layers [29,2].”
Background(2014) · Cited by 33,419
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260 · cited 1×
“The use of deep learning in recent years has led to great leaps in many fields, from image classification [2] to speech recognition [19].”
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853 · cited 1×
“Earlier research tried to accomplish the complex tasks such as object recognition or activity recognition by using manufactured features, or building a hierarchical model with several layers of classifiers to extract low-level features for final decision making [17,18].”
MethodTensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408 · cited 1×
“The network was developed with a Microsoft Azure cloud computing platform [8] and locally with Google TensorFlow [9].”
MethodTwo-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756 · cited 1×
“Some similarity exists with video data processing where image frames are temporally related and pixels in each frame are spatially related [28].”
Background
Research works printed but not linked: 2
- [24].Abdel-Hamid Ossama, Li Deng, and Dong Yu. "Exploring convolutional neural network structures and optimization techniques for speech recognition." In Interspeech, pp. 3366–3370. 2013.. [Google Scholar]
- [33].Abadi Marfin, et al. "TensorFlow: Large-scale machine learning on heterogeneous systems, 2015." Software available from tensorflow.org.
Cited by
Deep learning for sensor-based activity recognition: A survey
Wang, J., Chen, Y., Hao, S., Peng, X., & Hu, L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.02.010 · Cited by 2,014
“(Li et al., 2016a) added pooling after the fully-connected layers to extract the important features.”
BackgroundInfluentialDeep Learning in Mobile and Wireless Networking: A Survey
Zhang, C., Patras, P., & Haddadi, H. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2904897 · Cited by 1,768
Deep Learning for IoT Big Data and Streaming Analytics: A Survey
Mohammadi, M., Al-Fuqaha, A., Sorour, S., & Guizani, M. (2018) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2018.2844341 · Cited by 1,471
Deep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690
“onal expenses [161]. In addition to wearable sensors, RFID-based activity recognition requires the fusion of multiple RFID signals as well, and CNNs are also commonly used for the early fusion manner [86]. Sensor-based Fusion (SF). In contrast to EF, SF fist considers each modality individually and then fuses differen…”
MethodHuman activity recognition in artificial intelligence framework: a narrative review
Gupta, N., Gupta, S. K., Pathak, R. K., Jain, V., Rashidi, P., & Suri, J. S. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10116-x · Cited by 337
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314
“onal expenses [161]. In addition to wearable sensors, RFID-based activity recognition requires the fusion of multiple RFID signals as well, and CNNs are also commonly used for the early fusion manner [86]. Sensor-based Fusion (SF). In contrast to EF, SF fist considers each modality individually and then fuses differen…”
MethodA Survey on Deep Learning for Human Activity Recognition
Gu, F., Chung, M.-H., Chignell, M., Valaee, S., Zhou, B., & Liu, X. (2022) · ACM Computing Surveys · doi:10.1145/3472290 · Cited by 272
Bouchabou, D., Nguyen, S. M., Lohr, C., LeDuc, B., & Kanellos, I. (2021) · Sensors · doi:10.3390/s21186037 · Cited by 210
“Thus the sensor-based solutions can be divided into three categories, respectively : Wearable [6], Sensor on Objects [7] and Ambient Sensor [8].”
MethodCiFi: Deep convolutional neural networks for indoor localization with 5 GHz Wi-Fi
Wang, X., Wang, X., & Mao, S. (2017) · 2017 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2017.7997235 · Cited by 161
“DCNN is a powerful deep learning technique that has been successfully applied for image recognition [14] and human activity recognition based on sensors [15] and RFID [16], respectively.”
Xu, H., Zhou, P., Tan, R., Li, M., & Shen, G. (2021) · Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/3485730.3485937 · Cited by 150
“Due to the rapid development of deep learning, many works adopt deep neural networks to process IMU data [13, 21, 23, 33, 51].”
BackgroundUbiquitous Localization (UbiLoc): A Survey and Taxonomy on Device Free Localization for Smart World
Shit, R. C., Sharma, S. K., Puthal, D., James, P., Pradhan, B., van Moorsel, A., Zomaya, A. Y., & Ranjan, R. K. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2915923 · Cited by 143
“device-based frameworks on RFID technologies [224] which can be followed in device-free scenarios for localization.”
BackgroundRF Sensing in the Internet of Things: A General Deep Learning Framework
Wang, X., Wang, X., & Mao, S. (2018) · IEEE Communications Magazine · doi:10.1109/mcom.2018.1701277 · Cited by 129
“For example, a deep learning architecture that uses only RFID data for detection of process phases and activities during a trauma is proposed in [11].”
BackgroundLocomotion Activity Recognition Using Stacked Denoising Autoencoders
Gu, F., Khoshelham, K., Valaee, S., Shang, J., & Zhang, R. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2823084 · Cited by 124
“Indeed, deep learning methods have been used for activity recognition in a few recent works [34], [35], [37].”
MethodArtificial Intelligence of Things: A Survey
Siam, M. S. I., Ahn, H., Liu, L., Alam, S., Shen, H., Cao, Z., Shroff, N. B., Krishnamachari, B., Srivastava, M. B., & Zhang, M. (2025) · ACM Transactions on Sensor Networks · doi:10.1145/3690639 · Cited by 129
An RFID Indoor Positioning Algorithm Based on Support Vector Regression
Xu, H., Wu, M., Li, P., Zhu, F., & Wang, R. (2018) · Sensors · doi:10.3390/s18051504 · Cited by 108
“In addition, there have been other improvements based on deep learning [22,23] to improve position accuracy.”
BackgroundLi, Y., Wang, X., & An, L. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3580795 · Cited by 82
“, locomotion [35], daily activity recognition [25], and gesture recognition [34]).”
BackgroundOccupancy detection systems for indoor environments: A survey of approaches and methods
Trivedi, D., & Badarla, V. (2019) · Indoor and Built Environment · doi:10.1177/1420326x19875621 · Cited by 80
“However, Li et al.(79) recognize the activity of occupants by feeding the radio-frequency identification (RFID) data into a deep convolution neural network.”
BackgroundSensing within Smart Buildings: A Survey
Alsafery, W., RANA, O. F., & Perera, C. (2023) · ACM Computing Surveys · doi:10.1145/3596600 · Cited by 78
“Activities on a room-level within building Infrared array, camera, 3D camera, doppler motion, millimeter-wave radio, infrasound, Radio Frequency Identification (RFID), CO2 sensor OPPORTUNITY [130], PPS grouping [165], PAMAP2 [128] [106],[105],[177], [49], [70], [7],[84]”
BackgroundRecent advances in RF-based passive device-free localisation for indoor applications
Palipana, S., Pietropaoli, B., & Pesch, D. (2017) · Ad Hoc Networks · doi:10.1016/j.adhoc.2017.06.007 · Cited by 76
Modeling RFID Signal Reflection for Contact-free Activity Recognition
Wang, Y., & Zheng, Y. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3287071 · Cited by 72
“Some deep learning based methods are proposed to automatically identify human activities [6, 14].”
BackgroundInfluentialAttention-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
“, [25], [36], [45], [48], [58]) first preprocess the data to get a gridlike structure, and then use CNNs.”
BackgroundDeXAR: Deep Explainable Sensor-Based Activity Recognition in Smart-Home Environments
Arrotta, L., Civitarese, G., & Bettini, C. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3517224 · Cited by 68
“Some research efforts considered image-based solutions for environmental sensor data in smart-home environments also encoding the temporal relationships between sensor events [14, 32, 50].”
BackgroundA Survey on CSI-Based Human Behavior Recognition in Through-the-Wall Scenario
Wang, Z., Jiang, K., Hou, Y., Huang, Z., Dou, W., Zhang, C., & Guo, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2922244 · Cited by 68
“With extensive studies and the low cost, RFID-based technique is easily deployed and achieves satisfactory performance in some applications, such as object tracking [26], hand gesture recognition [27], [28], falling detection [29], and activity recognition [30].”
BackgroundHuang, A., Wang, D., Zhao, R., & Zhang, Q. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3328919 · Cited by 68
“Li et al. [18] directly feed the RSSI data into a deep convolutional neural network to recognize activities.”
BackgroundHuman activity recognition: A comprehensive review
Kaur, H., Rani, V., & Kumar, M. (2024) · Expert Systems · doi:10.1111/exsy.13680 · Cited by 68
Concurrent Activity Recognition with Multimodal CNN-LSTM StructurePreprint
Li, X., Zhang, Y., Zhang, J., Chen, S., Marsic, I., Farneth, R. A., & Burd, R. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.01638 · Cited by 68
“Instead of using arbitrary manufactured features, we implemented automatic feature extraction using deep convolutional neural networks (ConvNet), based on successful previous implementations [3][4].”
BackgroundMethodResultInfluentialSelf-citationDeep Learning for Human Activity Recognition on 3D Human Skeleton: Survey and Comparative Study
Hung-Cuong, N., Nguyen, T.-H., Scherer, R., & Le, V.-H. (2023) · Sensors · doi:10.3390/s23115121 · Cited by 64
“Gupta et al. [22] surveyed HAR of people from multi-modal information sources, where information can be sensor-based [23], vision-based [24], RFID-based [25,26], WiFi-based [27,28], and device free [29].”
BackgroundTagRay: Contactless Sensing and Tracking of Mobile Objects using COTS RFID Devices
Chen, Z., Yang, P., Xiong, J., Feng, Y., & Li, X. (2020) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom41043.2020.9155531 · Cited by 64
“Wireless sensing has attracted considerable attentions in the last few years, enabling a large range of applications from coarse-grained activity tracking [20], [23], [26] to fine-grained respiration monitoring [16].”
BackgroundSelf-citationA 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
Sense Me on the Ride: Accurate Mobile Sensing over a LoRa Backscatter Channel
Jiang, H., Zhang, J., Guo, X., & He, Y. (2021) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3485730.3485933 · Cited by 63
“The wireless technologies for sensing range from acoustic [12, 29, 37], RFID [6, 34, 35, 42, 45] and WiFi [26, 27, 39, 43, 46] to LoRa [3, 41, 48] and mmWave [13], while the sensing capabilities extensively cover motion and activity sensing [6, 19, 28], mobility measurement [42, 45], environmental sensing [35], and ma…”
BackgroundTagFree Activity Identification with RFIDs
Fan, X., Gong, W., & Liu, J. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3191739 · Cited by 62
“The U.S. government regulation requires frequency hopping to be enabled for RFID readers, with which the effectiveness of phase measurement can be noticeably affected [11][16].”
BackgroundDeActive: Scaling Activity Recognition with Active Deep Learning
Hossain, H. M. S., Al Haiz Khan, M. A., & Roy, N. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3214269 · Cited by 56
“Li et al. [52] [51] proposed an activity recognition system based on convolutional neural network using passive RFID data.”
BackgroundWhen RFID Meets Deep Learning: Exploring Cognitive Intelligence for Activity Identification
Fan, X., Wang, F., Wang, F., Gong, W., & Liu, J. (2019) · IEEE Wireless Communications · doi:10.1109/mwc.2019.1800405 · Cited by 56
“For example, in real-world indoor scenarios, the received raw RFID signals are the dynamic mixture of many signals from multiple paths, which, as indicated in previous research work [13], may not be accurate enough to be immediately applied to activity identification.”
BackgroundPractically Adopting Human Activity Recognition
Xu, H., Zhou, P., Tan, R., & Li, M. (2023) · Proceedings of the 29th Annual International Conference on Mobile Computing and Networking · doi:10.1145/3570361.3613299 · Cited by 55
“Conventional supervised learning models [15, 25, 27, 64] assume collected labeled dataset is general and thus suffer from severe performance degradation in practice.”
BackgroundA perspective on human activity recognition from inertial motion data
Gomaa, W., & Khamis, M. A. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08863-9 · Cited by 54
Samanta, R. K., Sadhukhan, B., Samaddar, H., Sarkar, S., Koner, C., & Ghosh, M. (2022) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12114 · Cited by 54
Egocentric Activity Recognition on a Budget
Possas, R., Caceres, S. P., & Ramos, F. T. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00625 · Cited by 52
“Traditionally, these devices were attached to several parts of the body [2, 12, 43], to external objects [14, 40] and to the ambient [12, 43] which often limited their use to controlled environments which can be quite different to a real-life setting.”
BackgroundSun, Y., Pargoo, N. S., & Ortiz, J. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3541158 · Cited by 47
“Such a framework would not only facilitate the extraction of features from sensor data but also align these features with vision domain descriptions, thereby enabling a deeper understanding of model outcomes [5], [23], [34], [45], [79].”
MetaSense: Boosting RF Sensing Accuracy Using Dynamic Metasurface Antenna
Lan, G., Imani, M. F., Liu, Z., Manjarrés, J., Hu, W., Lan, A., Smith, D. R., & Gorlatova, M. A. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3070225 · Cited by 48
“As the radio signals are subject to environment and location changes [28], [29], it results in the domain shift problem [30] when using the pretrained classifier for recognition.”
BackgroundMethodInfluentialA Framework for Behavioral Biometric Authentication Using Deep Metric Learning on Mobile Devices
Wang, C., Xiao, Y., Gao, X. H., Li, L., & Wang, J. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3072608 · Cited by 45
“The existing works either develop new variants of applications such as activity recognition [23] and mobile vision [48], [49], or optimize inference execution on mobile devices using reduced precision and weight pruning [2], [4].”
MethodImproved LSTM-Based Abnormal Stream Data Detection and Correction System for Internet of Things
Liu, J., Bai, J., Li, H., & Sun, B. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3079504 · Cited by 40
Real-time and Accurate Gesture Recognition with Commercial RFID Devices
Zhang, S., Ma, Z., Yang, C., Kui, X., Liu, X., Wang, W., Wang, J., & Guo, S. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3211324 · Cited by 40
“Recently, deep learning is also exploited to recognize user’s body activities [23], [35], [36], in which the users need to attach some sensors or RFID tags.”
BackgroundContrastive Accelerometer–Gyroscope Embedding Model for Human Activity Recognition
Koo, I., Park, Y., Jeong, M., & Kim, C. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3222825 · Cited by 40
“…to on-body sensors, object-placed sensors such as radio-frequency identifier (RFID) tags and ambient sensors (e.g., radar, Bluetooth, WiFi, acoustic sensor, and temperature sensor) are often utilized for HAR to detect user interaction with specific objects and the surrounding environments [13], [14].”
MethodActivity Recognition in Sensor Data Streams for Active and Assisted Living Environments
Machot, F. A., Mosa, A. H., Ali, M., & Kyamakya, K. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2764868 · Cited by 40
“Moreover, a human activity recognition model based on RFID and deep convolutional neural network is introduced by [46].”
MethodEdge-Based Transfer Learning for Classroom Occupancy Detection in a Smart Campus Context
Monti, L., Tse, R. T., Tang, S.-K., Mirri, S., Delnevo, G., Maniezzo, V., & Salomoni, P. (2022) · Sensors · doi:10.3390/s22103692 · Cited by 39
“The main limitations of these approaches concern the sensitivity of the system, which is affected by certain environmental conditions, such as humidity [29], and the requirement for additional hardware.”
BackgroundRF-Siamese: Approaching Accurate RFID Gesture Recognition With One Sample
Ma, Z., Zhang, S., Liu, J., Liu, X., Wang, W., Wang, J., & Guo, S. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3217487 · Cited by 39
“W IRELESS sensing has emerged as an amazing technique for various smart applications, e.g., human-machine interaction (HMI) [1], [2], [3], [4], activity recognition [5], [6], [7], [8], and ubiquitous computing [9], [10], [11].”
BackgroundA Survey on Ambient Sensor-Based Abnormal Behaviour Detection for Elderly People in Healthcare
Wang, Y., Wang, X., Arifoğlu, D., Lu, C., Bouchachia, A., Geng, Y., & Zheng, G. (2023) · Electronics · doi:10.3390/electronics12071539 · Cited by 40
Lee, S., Lim, Y., & Lim, K. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102153 · Cited by 39
Deep Room Recognition Using Inaudible Echos
Song, Q., Gu, C., & Tan, R. (2018) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3264945 · Cited by 37
“As the main function of pooling is to reduce the amount of parameters and computation time, as well as increase the CNN’s robustness to data translations, the pooling layers can be omitted for input images with relatively small dimensions [27].”
BackgroundNothing Blocks Me: Precise and Real-Time LOS/NLOS Path Recognition in RFID Systems
Zhang, S., Yang, C., Jiang, D., Kui, X., Guo, S., Zomaya, A. Y., & Wang, J. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2907555 · Cited by 37
“[30] proposed several deep learningbased activity recognition algorithm.”
BackgroundMethodHandwriting Trajectory Reconstruction Using Low-Cost IMU
Pan, T., Kuo, C.-H., Liu, H.-T., & Hu, M. (2018) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2018.2803777 · Cited by 36
“In the past decades, IMU sensor has been widely used in the field of positioning [4], [5] and further utilized to achieve various HCI applications such as human activity recognition [6], gait detection [7], patient resuscitation [8], and sports sciences [9].”
MethodAn approach to automatic process deviation detection in a time-critical clinical process
Yang, S., Sarcevic, A., Farneth, R. A., Chen, S., Ahmed, O. Z., Marsic, I., & Burd, R. S. (2018) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2018.07.022 · Cited by 35
“Although our research group is developing an automatic activity capture approach as part of a different project, we and others have not yet implemented a strategy that is accurate enough for obtaining activity logs required for this workflow analysis [26].”
MethodSelf-citationSequential neural networks for multi-resident activity recognition in ambient sensing smart homes
Natani, A., Sharma, A., & Perumal, T. (2021) · Applied Intelligence · doi:10.1007/s10489-020-02134-z · Cited by 34
“Deep Learning has been used for activity recognition [33–36] in many ways, like using Deep Convolutional Neural Networks for activity recognition from RFID data [37].”
MethodMeyer, J., Frank, A., Schlebusch, T., & Kasneci, E. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3494998 · Cited by 34
“On the other hand, sensor-based systems rely on observations stemming from sensors either attached to an individual’s body [3] or from ambient sensing devices such as RFID-tags [34] installed within a participant’s environment.”
BackgroundBody RFID Skeleton-Based Human Activity Recognition Using Graph Convolution Neural Network
Wang, Z., Chen, Y. J., Zheng, H., Liu, M., & Huang, P. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3333043 · Cited by 31
“The mode recognizes activities based on detecting the occlusion of the body on the tags [36], [37].”
BackgroundContext-aware Adaptive Surgery: A Fast and Effective Framework for Adaptative Model Partition
Wang, H., Guo, B., Liu, J., Liu, S., Wu, Y., & Yu, Z. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3478073 · Cited by 30
“Furthermore, Li et al. [26] consider different scenarios for activity recognition and use CNN to recognize human activities with Radio Frequency Identification (RFID) data.”
BackgroundRFaceID: Towards RFID-based Facial Recognition
Luo, C., Yang, Z., Feng, X., Zhang, J., Jia, H., Li, J., Wu, J., & Hu, W. S. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3494985 · Cited by 29
DeepWalking: Enabling Smartphone-Based Walking Speed Estimation Using Deep Learning
Shrestha, A., & Won, M. (2018) · Globecom · doi:10.1109/glocom.2018.8647857 · Cited by 29
“successful applications in diverse areas such as human activity detection [19][20], and image recognition [21].”
BackgroundKhan, F. N., & Lau, A. P. T. (2019) · China Communications · doi:10.23919/jcc.2019.08.007 · Cited by 28
The Lifespan of Human Activity Recognition Systems for Smart Homes
Hiremath, S. K., & Plötz, T. (2023) · Sensors · doi:10.3390/s23187729 · Cited by 28
“Sensor-based HAR systems comprise on-body or wearable sensing [49], sensors placed on objects [25,50], and ambient or in-the-environment sensors [51].”
BackgroundHuman Activity Recognition based on Real Life Scenarios
Machot, F. A., Ranasinghe, S., Plattner, J., & Jnoub, N. (2018) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2018.8480138 · Cited by 27
“Moreover, a human activity recognition model based on RFID and deep convolutional neural network is introduced by [11].”
MethodProgress Estimation and Phase Detection for Sequential Processes
Li, X., Zhang, Y., Zhang, J., Zhou, M., Chen, S., Gu, Y., Chen, Y., Marsic, I., Farneth, R. A., & Burd, R. S. (2017) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3130936 · Cited by 27
“1 Feature Extraction Similar to the activity recognition [14, 20], our estimation of the process progress relies on both spatial and temporal features.”
BackgroundMethodInfluentialSelf-citationPassive and Context-Aware In-Home Vital Signs Monitoring Using Co-Located UWB-Depth Sensor Fusion
Xie, Z., Zhou, B., Cheng, X., Schoenfeld, E. R., & Ye, F. (2022) · ACM Transactions on Computing for Healthcare · doi:10.1145/3549941 · Cited by 26
“[42] feed RFID data into a convolutional”
BackgroundcDeepArch: A Compact Deep Neural Network Architecture for Mobile Sensing
Yang, K., Xing, T., Liu, Y., Li, Z., Gong, X., Chen, X., & Fang, D. (2019) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2019.2936939 · Cited by 26
“For instance, there are existing works that use deep learning on RFID signals [25], [50] and”
BackgroundTowards General Industrial Intelligence: A Survey of Continual Large Models in Industrial IoTPreprint
Chen, J., He, J., Chen, F., Lv, Z., Tang, J., Li, W., Liu, Z., Yang, H. H., & Han, G. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.01207 · Cited by 26
AIGC for Wireless Sensing: Diffusion-Empowered Human Activity Sensing
Wang, Z., & Mao, S. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3525588 · Cited by 24
“These three technologies have been extensively utilized for activity recognition [16], [17], [18] and 3D pose tracking [19], [20], [21].”
ReActor: Real-time and Accurate Contactless Gesture Recognition with RFID
Zhang, S., Yang, C., Kui, X., Wang, J., Liu, X., & Guo, S. (2019) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/sahcn.2019.8824853 · Cited by 24
“Recently, deep learning is also exploited to recognize user’s body activities [15], [25], in which the users need to attach some sensors or RFID tags.”
BackgroundTamera: Contactless Commodity Tracking, Material and Shopping Behavior Recognition Using COTS RFIDs
Shang, F., Yang, P., Xiong, J., Feng, Y., & Li, X. (2023) · ACM Transactions on Sensor Networks · doi:10.1145/3563777 · Cited by 23
“[17] exploit a deep convolutional neural network for activity recognition with passive RFID readings.”
BackgroundSelf-citationDeepMTD: Moving Target Defense for Deep Visual Sensing against Adversarial Examples
Song, Q., Yan, Z., & Tan, R. (2021) · ACM Transactions on Sensor Networks · doi:10.1145/3469032 · Cited by 21
“The outstanding capability of deep learning in capturing sophisticated patterns have attracted great interests from the embedded sensing research for various applications such as sign language translation [10], audio sensing [18], and surgical activities recognition [22].”
BackgroundSuper Low Resolution RF Powered Accelerometers for Alerting on Hospitalized Patient Bed Exits
Chesser, M., Jayatilaka, A., Visvanathan, R., Fumeaux, C., Sample, A. P., & Ranasinghe, D. C. (2019) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2019.8767398 · Cited by 21
“only one other study has considered the problem of human activity recognition from raw RFID-only data streams using a deep learning paradigm [27].”
StresSense: Real-Time detection of stress-displaying behaviors
Khan, N. S., Qadir, S., Anjum, G., & Uddin, N. (2024) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105401 · Cited by 20
REHSense: Towards Battery-Free Wireless Sensing via Radio Frequency Energy Harvesting
Ni, T., Sun, Z., Han, M., Xie, Y., Lan, G., Li, Z., Gu, T., & Xu, W. (2024) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3641512.3686388 · Cited by 20
“RFID-based sensing systems [38, 39] seem to share the same principles of REHSense because passiveRFID tagsalso integratedwith RFenergy harvesting circuits to scavenge the RF energy sent by the RFID reader.”
Federated Multi-Source Domain Adaptation for mmWave-Based Human Activity Recognition
Zhao, C., Fang, G., Ding, H., Liu, X., Wang, F., Wang, G., Zhao, K., Wang, Z., & Xi, W. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3549705 · Cited by 18
Tag-free indoor fall detection using transformer network encoder and data fusion
Khan, M. Z., Usman, M., Ahmad, J. E., Rahman, M. M. U., Abbas, H. T., Imran, M. A., & Abbasi, Q. H. (2024) · Scientific Reports · doi:10.1038/s41598-024-67439-2 · Cited by 16
State-of-the-art of situation recognition systems for intraoperative procedures
Junger, D., Frommer, S. M., & Burgert, O. (2022) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-022-02520-4 · Cited by 16
“[40] Steps 2016 Object usage (RFID) CNN Trauma resuscitation - RealOp (16) 80.”
BackgroundAIGC for RF-Based Human Activity Sensing
Wang, Z., Yang, C., & Mao, S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3482256 · Cited by 15
“3D human pose estimation typically requires a recurrent DNN to map the RF features into joint rotations for smooth 3D human movements [22]–[24], while classifier-oriented DNNs are mainly used for human activity recognition [25]–[27].”
BackgroundGao, C., Marsic, I., Sarcevic, A., Gestrich-Thompson, W. V., & Burd, R. S. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3580798 · Cited by 14
“Current research on activity recognition mostly relies on visual and sensory data sources to predict activities [5, 10, 42].”
BackgroundSelf-citationWiga: A WiFi-Based Contactless Activity Sequence Recognition System Based on Deep Learning
Huang, S., Wang, D., Zhao, R., & Zhang, Q. (2019) · International Conference on Mobile Ad-Hoc and Sensor Networks (MSN) · doi:10.1109/msn48538.2019.00026 · Cited by 14
“Wiga chooses machine learning to extract the motion characteristics of each segmented signal [13], [14], [17], [18] .”
BackgroundPekgor, M., Arablouei, R., Nikzad, M., & Masood, S. H. (2024) · Sensors · doi:10.3390/s24041233 · Cited by 13
Close the Gap between Deep Learning and Mobile Intelligence by Incorporating Training in the Loop
Wang, C., Xiao, Y., Gao, X., Li, L., & Wang, J. (2019) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3343031.3350904 · Cited by 13
“Take behaviorial authentication [10, 17, 22, 26, 27, 35, 38] and activity recognition [1, 16] for example, behaviorial patterns may evolve due to sickness, injury and emotion, thus intensify the intra-class variations and hamper classification.”
BackgroundEnhancing Representation of Deep Features for Sensor-Based Activity Recognition
Li, X., Nie, L., Si, X., Ding, R., & Zhan, D. (2020) · Mobile Networks and Applications · doi:10.1007/s11036-020-01689-y · Cited by 13
“Given the development of pervasive computing, from the early vision-based transition to the sensor-based, sensor-based AR typically considers not only cost [6, 7] and energy consumption [8, 9] characteristics of sensors but also the feeling humans in using the sensors.”
BackgroundSelf-citationContext Recognition by Wireless Sensing: A Comprehensive Survey
Uchiyama, A., Saruwatari, S., Maekawa, T., Ohara, K., & Higashino, T. (2021) · Journal of Information Processing · doi:10.2197/ipsjjip.29.46 · Cited by 13
“Li et al. [72] employed a CNN to recognize 11 medical and 6 lab activities (e.g., oxygen preparation, blood pressure measurement, and lab-meeting.) by tags attached to objects.”
Enabling Fine-Grained Shopping Behavior Information Acquisition With Dual RFID Tags
Liu, W., Wang, J., Li, B., & Wang, L. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2985852 · Cited by 12
Multi-dimensional task recognition for human-robot teaming: literature review
Baskaran, P., & Adams, J. A. (2023) · Frontiers in Robotics and AI · doi:10.3389/frobt.2023.1123374 · Cited by 12
“Convolutional algorithms typically incorporate only CNNs to learn the spatial features from sensor data for each task and distinguish them by comparing the spatial patterns (e.g., Castro et al., 2015; Li et al., 2016b; Ma et al., 2016; Laput and Harrison, 2019; Li L. et al., 2020).”
MethodMultiple Object Activity Identification Using RFIDs: A Multipath-Aware Deep Learning Solution
Fan, X., Wang, F., Gong, W., Zhang, L., & Liu, J. (2018) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2018.00060 · Cited by 12
“Yet, as indicated in previous research work [19] [20], the reported data may not be accurate enough to be immediately applied to activity identification, due to such factors as the multipath effect and frequency hopping.”
BackgroundResultIndoor Motion Classification Using Passive RF Sensing Incorporating Deep Learning
Iqbal, S., Iqbal, U., Hassan, S. A., & Saleem, S. (2018) · IEEE Vehicular Technology Conference · doi:10.1109/vtcspring.2018.8417859 · Cited by 12
“Similarly, [14] presented a system for activity recognition from passive radio-frequency identification (RFID) data using a deep convolutional neural network.”
BackgroundAutomatic Identification and Categorize Zone of RFID Reading in Warehouse Management System
Choong, C. S., Nasir, A. F. A., Majeed, A. P. P. A., Zakaria, M. A., & Razman, M. A. M. (2020) · Lecture notes in mechanical engineering · doi:10.1007/978-981-15-7309-5_20 · Cited by 12
Pang, B., Liu, S., Wang, H., Guo, B., Wang, Y., Wang, H., Sheng, Z., Wang, Z., & Yu, Z. (2023) · ACM Transactions on Sensor Networks · doi:10.1145/3630098 · Cited by 11
“…latency-sensitive mobile applications ( e.g. , image classification, target recognition) for the evaluation of AdaMEC, including the small-scale AlexNet [26] and VGG16 [44], the medium-scale ResNet-18 [31] and GoogLeNet [45], the multi-target recognition model MobileNet [16] and Tiny-YOLO [41].”
BackgroundMethodHuman Activity Recognition (HAR) in Smart HomesPreprint
Bouchabou, D., Lohr, C., Kanellos, I., & Nguyen, S. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.11232 · Cited by 11
“The sensor-based solutions are generally divided into three categories: Wearable, Sensors on Objects and Ambient Sensors [1].”
BackgroundRFID-based Human Activity Recognition Using Multimodal Convolutional Neural Networks
Golipoor, S., & Sigg, S. (2024) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa61755.2024.10710698 · Cited by 10
“For instance, the authors in [17] exploit Received Signal Strength (RSS) data from RFID readings to feed a CNN and a LSTM, to sense teamwork activities in a trauma resuscitation [17] and daily routine activities [18].”
BackgroundLanguage-Based Process Phase Detection in the Trauma Resuscitation
Gu, Y., Li, X., Chen, S., Li, H., Farneth, R. A., Marsic, I., & Burd, R. S. (2017) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi.2017.50 · Cited by 9
“In the trauma room, RFID performs well at detecting tool usage activities [25].”
Self-citationSpeech-Based Activity Recognition for Trauma Resuscitation
Abdulbaqi, J., Gu, Y., Xu, Z., Gao, C., Marsic, I., & Burd, R. S. (2020) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi48887.2020.9374372 · Cited by 9
“Recently, employing a convolutional neural network (CNN) as a multi-class classifier outperformed the previous approaches [2].”
MethodSelf-citationAdapted Long Short-Term Memory (LSTM) for Concurrent\\ Human Activity Recognition
Thapa, K., Al, Z. M. A., & Yang, S. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2021.015660 · Cited by 9
“Deep learning methods such as long short-term memory (LSTM) [9] and bi-directional LSTM (BLSTM) [10] are used in various domains and tasks, including image processing [11], language recognition [12], and sentence processing [13].”
MethodActivity Recognition Using RFID Phase Profiling in Smart Library
Du, Y., Lim, Y., & Tan, Y. (2019) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2018dap0010 · Cited by 9
Automating medical simulations
Gershov, S., Braunold, D., Spektor, R., Ioscovich, A., Raz, A., & Laufer, S. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104446 · Cited by 8
CHAR: Composite Head-Body Activities Recognition With a Single Earable Device
Zhu, P., Zhu, Y., Li, W., He, Y., Zou, Y., Wu, K., & Leung, V. C. M. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3548647 · Cited by 8
“Researchers have proposed a variety of HAR methods with different sensing modalities including radio frequency (RF) signals [1], [2], [3], acoustic sensors [4], [5], [6], and inertial measurement unit (IMU) [7], [8], [9], [10].”
Detecting computer activities using eye-movement features
Destyanto, T. Y. R., & Lin, R. F. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02683-8 · Cited by 8
“Successful examples could be found in numerous areas, such as health care service (Alem-dar and Ersoy 2017; Li et al. 2016), human-centered design (Wu et al. 2007), and even in the flow of the working process (Staudt et al. 2019).”
Particle Swarm Optimization of Convolutional Neural Networks for Human Activity Prediction
Devarakonda, P. G., & Božić, B. (2022) · IntechOpen eBooks · doi:10.5772/intechopen.97259 · Cited by 8
Deep Learning Approaches for Recognizing Daily Human Activities Using Smart Home Sensors
Sanpote, W., Jantawong, P., Hnoohom, N., Jitpattanakul, A., & Mekruksavanich, S. (2023) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon57770.2023.10139507 · Cited by 8
“Consequently, sensor-based solutions can be classified into three categories: Wearable [10]–[13], Sensor on Objects [14], [15], and Ambient Sensor [16].”
BackgroundGu, Y., Zhang, R., Zhao, X., Chen, S., Abdulbaqi, J., Marsic, I., Cheng, M., & Burd, R. S. (2019) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi.2019.8904713 · Cited by 8
Self-citation
Metadata
- Authors
- Li, X., Zhang, Y., Marsic, I., Sarcevic, A., & Burd, R. S.
- Affiliations
- Rutgers, The State University of New Jersey (US)
- Drexel University (US)
- Children's National (US)
- Venue
- Proceedings of the 14th ACM Conference on Embedded Networked Sensor Systems CD-ROM
- Publisher
- ACM
- Published
- 2016-11-14
- Volume
- 2016
- Pages
- 164-175
- PMC
- PMC6205502
- OpenAlex
- W2548765505
- Cited by
- 150
- References
- 39
- Citations by year
- 2026: 5 · 2025: 12 · 2024: 15 · 2023: 25 · 2022: 15 · 2021: 16 · 2020: 15 · 2019: 22 · 2018: 18 · 2017: 7
- FWCI
- 5.43
- Type
- conference paper
- Language
- en
- Open access
- green
- europepmc.org
- Locations
- ACM Conference on Embedded Networked Sensor Systems (SenSys) (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Institutes of Health
- U.S. National Library of Medicine (R01LM011834)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Computer Networks and Communications › RFID technology advancements
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Indoor and Outdoor Localization Technologies
- Keywords
- activity recognition, passive RFID, deep convolutional neural networks, trauma resuscitation, multi-class classification
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
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.