Victor C. M. Leung’s research while affiliated with Shenzhen University and other places

With the rapid development of Visual Internet of Things (VIoT) and text detection technology, they have been widely combined and applied to many industrial production sites, such as label text detection, achieving impressive results. However, there are still many shortcomings in the text detection technology: 1) The existing VIoT system has very limited detection precision for text with large scale changes, especially for some small-scale text detection; 2) The existing text detection algorithms cannot meet the actual situation, as the labels often contain handwritten texts, and the text to be detected is arbitrary shape; 3) In the actual detection, there are many creases or defects on the text label. To solve the above problems, this paper designs a text detection method based on a multi-scale selection fusion feature pyramid and multi-semantic spatial network to assist the VIoT system in detecting label text. Firstly, a multi-scale selective fusion feature pyramid is designed, which not only uses the texture extraction module to effectively improve the text texture feature and multi-scale feature extraction ability, but also uses the cross-scale selective fusion block to selectively fuse the features of different stages to reduce the influence of pollution on detection. In addition, a multi-semantic spatial network is designed to capture the multi-semantic spatial information of each feature channel by using the multi-scale deep shared one-dimensional convolution, which effectively integrates global context dependence and multi-semantic spatial prior. Experimental results show that the comprehensive index F-measure on the public datasets ICDAR2015, Total-Text and CTW1500 is increased by 5.7%, 3.3%and 3.8% respectively. Furthermore, the precision, recall, and F-measure on the dataset Label-Text are 94.6%, 90.7%and 92.6% respectively. The label text detection VIoT system we designed has been deployed in the field and achieved excellent performance. The code of our proposed method can be found in: https://github.com/rebornone1/MSNet

Top-N recommendation systems are recognized as highly effective for delivering personalized services that cater to the varied interests of users. Nonetheless, current state-of-the-art (SOTA) analyses reveal a marked variability in their performance across users with differing levels of activity, which substantially undermines the quality of personalized recommendation services. Prevailing research tends to overlook this discrepancy, often presuming a uniform probability distribution in user preferences and employing a static model (such as a single latent vector) for user representation. This oversimplification impedes the adaptability of existing models to accommodate the spectrum of user activity levels. In our research, we introduce the variational kernel density estimation (VKDE) approach, an innovative nonparametric method designed to accurately capture the unique preference distributions of individual users. The VKDE framework integrates multiple local distributions to construct a comprehensive global preference profile for each user. We have developed a novel variational kernel function that delineates user-specific interests and constructs each local distribution accordingly. Additionally, we present a tailored sampling strategy that simplifies the complexity of the training process while preserving the efficacy of the recommendations. Empirical evaluations conducted on four widely recognized public datasets demonstrate that our VKDE model achieves superior performance over the SOTA alternatives, significantly enhancing accuracy for users with a broad range of activity levels.

With the rapid development of the internet of things and smart cities, the demand for effective spectrum collaboration has grown significantly. Radio maps play a crucial role in understanding the spatial radio environment, which is essential for wireless applications such as cell planning and radio resource management. However, generating radio maps is a resource-intensive task, as the construction process is complex and the distribution process consumes substantial bandwidth. This article proposes a method that combines semantic communication (SemCom) and generative artificial intelligence (GAI) to optimize the construction and distribution processes of radio maps. By incorporating SemCom, our method transmits only key semantic information during the distribution process, significantly reducing bandwidth usage while ensuring accurate and efficient information transfer. While the diverse generative capabilities of GAI introduce some instability, which could be a limitation in radio map construction, this article achieves precise content decoding through prompts based on multi-modal semantic information, enabling accurate construction and restoration of radio maps. By utilizing SemCom and GAI technologies, the cost of applications of radio maps can be significantly reduced, which is beneficial for stimulating the pace of intelligence evolution in future mobile networks.

Edge computing has emerged as a key paradigm for deploying deep learning-based object detection in time-sensitive scenarios. However, existing edge detection methods face challenges: 1) difficulty balancing detection precision with lightweight models, 2) limited adaptability of generalized deployment designs, and 3) insufficient real-world validation. To address these issues, we propose the Edge Detection Toolbox (ED-TOOLBOX), which utilizes generalizable plug-and-play components to adapt object detection models for edge environments. Specifically, we introduce a lightweight Reparameterized Dynamic Convolutional Network (Rep-DConvNet) featuring weighted multi-shape convolutional branches to enhance detection performance. Additionally, we design a Sparse Cross-Attention (SC-A) network with a localized-mapping-assisted self-attention mechanism, enabling a well-crafted joint module for adaptive feature transfer. For real-world applications, we incorporate an Efficient Head into the YOLO framework to accelerate edge model optimization. To demonstrate practical impact, we identify a gap in helmet detection -- overlooking band fastening, a critical safety factor -- and create the Helmet Band Detection Dataset (HBDD). Using ED-TOOLBOX-optimized models, we address this real-world task. Extensive experiments validate the effectiveness of ED-TOOLBOX, with edge detection models outperforming six state-of-the-art methods in visual surveillance simulations, achieving real-time and accurate performance. These results highlight ED-TOOLBOX as a superior solution for edge object detection.

Facial expressions convey human emotions and can be categorized into macro-expressions (MaEs) and micro-expressions (MiEs) based on duration and intensity. While MaEs are voluntary and easily recognized, MiEs are involuntary, rapid, and can reveal concealed emotions. The integration of facial expression analysis with Internet-of-Thing (IoT) systems has significant potential across diverse scenarios. IoT-enhanced MaE analysis enables real-time monitoring of patient emotions, facilitating improved mental health care in smart healthcare. Similarly, IoT-based MiE detection enhances surveillance accuracy and threat detection in smart security. This work aims at providing a comprehensive overview of research progress in facial expression analysis and explores its integration with IoT systems. We discuss the distinctions between our work and existing surveys, elaborate on advancements in MaE and MiE techniques across various learning paradigms, and examine their potential applications in IoT. We highlight challenges and future directions for the convergence of facial expression-based technologies and IoT systems, aiming to foster innovation in this domain. By presenting recent developments and practical applications, this study offers a systematic understanding of how facial expression analysis can enhance IoT systems in healthcare, security, and beyond.

Unmanned aerial vehicles (UAVs) have gained considerable attention as a platform for establishing aerial wireless networks and communications. However, the line-of-sight dominance in air-to-ground communications often leads to significant interference with terrestrial networks, reducing communication efficiency among terrestrial terminals. This paper explores a novel uplink interference mitigation approach based on the collaborative beamforming (CB) method in multi-UAV network systems. Specifically, the UAV swarm forms a UAV-enabled virtual antenna array (VAA) to achieve the transmissions of gathered data to multiple base stations (BSs) for data backup and distributed processing. However, there is a trade-off between the effectiveness of CB-based interference mitigation and the energy conservation of UAVs. Thus, by jointly optimizing the excitation current weights and hover position of UAVs as well as the sequence of data transmission to various BSs, we formulate an uplink interference mitigation multi-objective optimization problem (MOOP) to decrease interference affection, enhance transmission efficiency, and improve energy efficiency, simultaneously. In response to the computational demands of the formulated problem, we introduce an evolutionary computation method, namely chaotic non-dominated sorting genetic algorithm II (CNSGA-II) with multiple improved operators. The proposed CNSGA-II efficiently addresses the formulated MOOP, outperforming several other comparative algorithms, as evidenced by the outcomes of the simulations. Moreover, the proposed CB-based uplink interference mitigation approach can significantly reduce the interference caused by UAVs to non-receiving BSs.

Fabric metaverse employs intelligence fibers embedded with flexible sensors to unknowingly gather and transmit massive hypermodal data around humans to a deep neural network-based metaverse inference service (DMS) for continual and real-time analysis. Each DMS has one primary branch and multiple side branches that allow early termination of service with differential accuracy and energy consumption. However, the continual provisioning of compute-intensive DMS with varying requirements for service model, accuracy, delay, and reliability poses a challenge for edge servers characterized by restricted computing resources and intermittent green energy. In this paper, we focus on a continual individualized DMS provisioning problem in the fabric metaverse consisting of a side branch insertion subproblem and a server activation and service deployment subproblem, and formulate them as Integer linear Programming and Markov Decision Process, respectively. Then, we propose a green continual inference (GCI) system, where a pruner with provable approximation ratios trims superfluous branches of every model to the given number K to minimize total overflow accuracy between accuracy demands and reserved branches assigned to users. Based on this exit result, each DMS is further divided into several blocks with dependencies to exploit constrained resources of computing and energy in a fine-grained manner. Finally, a learning-based scheduler is merged into GCI to maximize request throughput while minimizing the activation number of edge servers on different demand scenarios, by adaptively activating suitable servers and deploying required blocks and their corresponding backups on selected servers. Theoretical analyses, simulations, and experiments demonstrate that the GCI is promising compared with baseline algorithms.

Recent developments in unmanned aerial vehicles (UAVs) and mobile edge computing (MEC) have provided users with flexible and resilient computing services. However, meeting the computation-intensive and delay-sensitive demands of users poses a significant challenge due to the limited resources of UAVs. To address this challenge, we consider a multi-UAV-assisted MEC system. Based on this system, we formulate a multi-objective optimization problem aiming at minimizing the total task completion delay, reducing the total UAV energy consumption, and maximizing the total number of offloaded tasks. Since the problem is a mixed-integer non-linear programming (MINLP) and NP-hard problem, we propose a joint task offloading, computation resource allocation, and UAV trajectory control (JTORATC) approach. The problem is split into three components to cope with the coupling of these decision variables, and then solved individually to obtain the corresponding decisions. Specifically, the sub-problem of task offloading is solved by using distributed splitting and threshold rounding methods, the sub-problem of computation resource allocation is solved by adopting the Karush-Kuhn-Tucker (KKT) method, and the sub-problem of UAV trajectory control is solved by employing the successive convex approximation (SCA) method. Simulation results show that the proposed JTORATC has superior performance compared with the other benchmark methods.