Deep-Learning-Enhanced Multitarget Detection for End–Edge–Cloud Surveillance in Smart IoT

Zhou, Xiaokang; Xu, Xuesong; Liang, Wei; Zeng, Zhi; Yan, Zheng

doi:10.1109/jiot.2021.3077449

Cited by 241 publications

(63 citation statements)

References 25 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Huang et al 22 established an MMBE model to discover the user's check-in behaviors. Recently, deep learning [23][24][25] and RNN have been proved to be effective in sequence prediction. Liu et al 26 proposed spatial and temporal RNN (ST-RNN) by combining spatiotemporal information.…”

Section: Next Poi Predictionmentioning

confidence: 99%

Bidirectional GRU networks‐based next POI category prediction for healthcare

Liu

Song

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

The Corona Virus Disease 2019 has a great impact on public health and public psychology. People stay at home for a long time and rarely go out. With the improvement of the epidemic situation, people began to go to different places to check in. To maintain public mental health, it is necessary to propose a point‐of‐interest (POI) prediction model which can mine users' interests. However, the current techniques suffer from lower precision during prediction and the practical value is poor, which is due to the sparse data of users' check‐in. Faced with this challenge, we propose an attention‐based bidirectional gated recurrent unit (GRU) model for POI category prediction (ABG_poic). We regard the user's POI category as the user's interest preference because the fuzzy POI category is easier to reflect the user's interest than the POI. This method can alleviate the data sparsity, and protect users' location privacy. Since users' preferences are variable, we utilize a bidirectional GRU to capture the dynamic dependence of users' check‐ins. Furthermore, since the neural network is similar to a “black box” in feature learning, the decision‐making stage is opaque. Thus, we combine the attention mechanism with bidirectional GRU to selectively focus on historical check‐in records, which can improve the interpretability of the model. Considering the time impact on users' check‐in, we utilize the time sliding window in the ABG_poic model. Experiments on two data sets demonstrate that our ABG_poic outperforms the comparison models for POI category prediction on sparse check‐in data.

show abstract

Section: Next Poi Predictionmentioning

confidence: 99%

Bidirectional GRU networks‐based next POI category prediction for healthcare

Liu

Song

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…They attempted computational cost-minimizing. [114], and proposed a tracking algorithm for lightweight models by combining MTCNN and YOLO. In Hossain and Lee, they developed an association metric by integrating it into Deep SORT [115], which combines Kalman filtering and deep learning for tracking in small flight drones with limited computing power.…”

Section: Computational Cost Minimizationmentioning

confidence: 99%

“…Avola et al used Multi-Stream architecture with Faster R-CNN [113] backbone and used Deep Association Metric (Deep SORT), which includes Simple Online and Real-time Tracking. Zhou et al proposed a framework for the real-time security surveillance of smart IoT systems[114], and proposed a tracking algorithm for lightweight models by combining MTCNN and YOLO. In Hossain and Lee, they developed an association metric by integrating it into Deep SORT[115], which combines Kalman filtering and deep learning for tracking in small flight drones with limited computing power.…”

mentioning

confidence: 99%

Multiple Object Tracking in Deep Learning Approaches: A Survey

et al. 2021

View full text Add to dashboard Cite

Object tracking is a fundamental computer vision problem that refers to a set of methods proposed to precisely track the motion trajectory of an object in a video. Multiple Object Tracking (MOT) is a subclass of object tracking that has received growing interest due to its academic and commercial potential. Although numerous methods have been introduced to cope with this problem, many challenges remain to be solved, such as severe object occlusion and abrupt appearance changes. This paper focuses on giving a thorough review of the evolution of MOT in recent decades, investigating the recent advances in MOT, and showing some potential directions for future work. The primary contributions include: (1) a detailed description of the MOT’s main problems and solutions, (2) a categorization of the previous MOT algorithms into 12 approaches and discussion of the main procedures for each category, (3) a review of the benchmark datasets and standard evaluation methods for evaluating the MOT, (4) a discussion of various MOT challenges and solutions by analyzing the related references, and (5) a summary of the latest MOT technologies and recent MOT trends using the mentioned MOT categories.

show abstract

“…To date, Human Activity Recognition (HAR) is still facing many challenges, such as lack of sufficient training data, computationally intensive learning, risk of sensitive information leakage, and lack of personalized models [1][2][3]. The concept of Cyber-Physical-Social Systems (CPSS), which integrates cyber-physical systems, Internet of Things (IoT) technologies, and social media technologies, offers an opportunity for addressing some of these challenges.…”

Section: Introductionmentioning

confidence: 99%

2D Federated Learning for Personalized Human Activity Recognition in Cyber-Physical-Social Systems

Zhou

Liang

et al. 2022

IEEE Trans. Netw. Sci. Eng.

Self Cite

View full text Add to dashboard Cite

The proliferation of the Internet of Things (IoT), wearable computing, and social media technologies bring forward the realization of the so-called Cyber-Physical-Social Systems (CPSS), which is capable of offering intelligent services in many different aspects of our day-to-day life. While CPSS offer a wide variety of data from wearable devices, challenges such as data silos and secure data sharing still remain. In this study, a 2-Dimensional Federated Learning (2DFL) framework, including the vertical and horizontal federated learning phases, is designed to cope with the insufficient training data and insecure data sharing issues in CPSS during a secure distributed learning process. Considering a specific application of Human Activity Recognition (HAR) across a variety of different devices from multiple individual users, the vertical federated learning scheme is developed to integrate shareable features from heterogeneous data across different devices into a full feature space, while the horizontal federated learning scheme is developed to effectively aggregate the encrypted local models among multiple individual users to achieve a high-quality global HAR model. A computationally efficient somewhat homomorphic encryption (SWHE) scheme is then improved and applied to support the parameter aggregation without giving access to it, which enables heterogeneous data sharing with privacy protection across different personal devices and multiple users in building a more precise personalized HAR model. Experiments are conducted based on two public datasets. Comparing with three conventional machine learning methods, evaluation results demonstrate the usefulness and effectiveness of our proposed model in achieving faster and smoother convergence, with better precision, recall, and F1 scores for HAR applications in CPSS.

show abstract

Deep-Learning-Enhanced Multitarget Detection for End–Edge–Cloud Surveillance in Smart IoT

Cited by 241 publications

References 25 publications

Bidirectional GRU networks‐based next POI category prediction for healthcare

Bidirectional GRU networks‐based next POI category prediction for healthcare

Multiple Object Tracking in Deep Learning Approaches: A Survey

2D Federated Learning for Personalized Human Activity Recognition in Cyber-Physical-Social Systems

Contact Info

Product

Resources

About