ZWZheng Wen

Zheng Wen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zheng Wen has a total of 65 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Compensation of Communication Latency in Remote Monitoring Systems by Video Prediction

    by Toshio Sato, Yutaka Katsuyama, Xin Qi, Zheng Wen, Kazuhiko Tamesue, Wataru Kameyama, Yuichi Nakamura, Jiro Katto, Takuro Sato

    Remote video monitoring over networks inevitably introduces a certain degree of communication latency. Although numerous studies have been conducted to reduce latency in network systems, achieving 'zero-latency' is fundamentally impossible for video monitoring. To address this issue, we investigate a practical method to compensate for latency in video monitoring using video prediction techniques. We apply the lightweight PredNet to predict future frames, and their image qualities are evaluated through quantitative image quality metrics and subjective assessment. The evaluation results suggest that for simple movements of the robot arm, the prediction time to generate future frames can tolerate up to 333 ms. The video prediction method is integrated into a remote monitoring system, and its processing time is also evaluated. We define the object-to-display latency for video monitoring and explore the potential for realizing a zero-latency remote video monitoring system. The evaluation, involving simultaneous capture of the robot arm's movement and the display of the remote monitoring system, confirms the feasibility of compensating for the object-to-display latency of several hundred milliseconds by using video prediction. Experimental results demonstrate that our approach can function as a new compensation method for communication latency.


  • Open Access

    Evaluating Large Language Models on Financial Report Summarization: An Empirical Study

    by Xinqi Yang, Scott Zang, Yong Ren, Dingjie Peng, Zheng Wen

    In recent years, Large Language Models (LLMs) have demonstrated remarkable versatility across various applications, including natural language understanding, domain-specific knowledge tasks, etc. However, applying LLMs to complex, high-stakes domains like finance requires rigorous evaluation to ensure reliability, accuracy, and compliance with industry standards. To address this need, we conduct a comprehensive and comparative study on three state-of-the-art LLMs, GLM-4, Mistral-NeMo, and LLaMA3.1, focusing on their effectiveness in generating automated financial reports. Our primary motivation is to explore how these models can be harnessed within finance, a field demanding precision, contextual relevance, and robustness against erroneous or misleading information. By examining each model's capabilities, we aim to provide an insightful assessment of their strengths and limitations. Our paper offers benchmarks for financial report analysis, encompassing proposed metrics such as ROUGE-1, BERT Score, and LLM Score. We introduce an innovative evaluation framework that integrates both quantitative metrics (e.g., precision, recall) and qualitative analyses (e.g., contextual fit, consistency) to provide a holistic view of each model's output quality. Additionally, we make our financial dataset publicly available, inviting researchers and practitioners to leverage, scrutinize, and enhance our findings through broader community engagement and collaborative improvement. Our dataset is available on huggingface.


  • Open Access

    Design and Implementation of Ledger-Based Points Transfer System for IoT Devices in LPWAN

    by Xin Qi, Keping Yu, Toshio Sato, Kouichi Shibata, Isao Konno, Takanori Tokutake, Rikiya Eguchi, Yusuke Maruyama, Zheng Wen, Kazuhiko Tamesue, et al.

    Distributed ledger technology is becoming popular these days because of its high confidentiality, decentralization, and nontampering. It is suitable for replacing centralized security disadvantaged point transfer systems. Low-power wide area network (LPWAN) is capable for long-range communication with low-power consumption. The iconic features like wide area coverage and long battery-powered duration make it best to combine with large-scale IoT application deployment. In both industry and academic field, such combination of LPWAN and point transfer system is highly attended. However, the ledger management system generates too much data that low-bandwidth network such as LPWAN can hardly handle; meanwhile, the processing powers requirement for small IoT devices is challenging. Towards addressing these issues, we design a packet transmission optimizing mechanism for a ledger-based point transfer system (LPTS) in LPWAN to reduce overall data traffic and build a simulator to evaluate its performance. Moreover, we have implemented the system and evaluated in field experiment.

  • Open Access

    Visual Attention and Motion Estimation-Based Video Retargeting for Medical Data Security

    by Qingfang Liu, Baosheng Kang, Qiaozhi Hua, Zheng Wen, Haipeng Li

    Medical data security is an important guarantee for intelligent medical system. Medical video data can help doctors understand the patients’ condition. Medical video retargeting can greatly reduce the storage capacity of data on the premise of preserving the original content information as much as possible. The smaller volume of medical data can reduce the execution time of data encryption and threat detection algorithm and improve the performance of medical data security methods. The existing methods mainly focus on the temporal pixel relationship and foreground motion between adjacent frames, but these methods ignore the user’s attention to the video content and the impact of background movement on retargeting, resulting in serious deformation of important content and area. To solve the above problems, this paper proposes an innovative video retargeting method, which is based on visual attention and motion estimation. Firstly, the visual attention map is obtained from eye tracking data, by K-means clustering method and Euclidean distance factor equation. Secondly, the motion estimation map is generated from both the foreground and background displacements, which are calculated based on the feature points and salient object positions between adjacent frames. Then, the visual attention map, the motion estimation map, and gradient map are fused to the importance map. Finally, video retargeting is performed by mesh deformation based on the importance map. Experiment on open datasets shows that the proposed method can protect important area and has a better effect on salient object flutter suppression.


  • Open Access

    AI-Based W-Band Suspicious Object Detection System for Moving Persons: Two-Stage Walkthrough Configuration and Recognition Optimization

    by Zheng Wen, Keping Yu, Xin Qi, Toshio Sato, San Hlaing Myint, Kazuhiko Tamesue, Yutaka Katsuyama, Hironori Dobashi, Yasushi Murakami, Ikuo Koyama, et al.

    In recent years, terrorist attacks have been spreading worldwide and become a public hazard to human society. The suspicious object detection system is an effective way to prevent terrorist attacks in public places. However, traditional systems face two main challenges: First, they need to conduct security checks at the entrance one by one, which leads to crowding; second, they rely heavily on screeners’ ability to understand security images, which can easily lead to misjudgment. To address these issues, we propose an AI-based W-band suspicious object detection system for moving persons that can perform a two-stage walkthrough screening for suspicious objects in an open area to maintain high throughput. The 1st screening uses millimeter wave radar and cameras to automatically screen suspects who may have concealed suspicious objects in an open area. The 2nd screening involves security personnel using a hybrid imager with active and passive imaging capabilities to identify the specific suspicious objects carried by the suspect. Convolutional neural network (CNN) based artificial intelligence (AI) technology will be used to improve the accuracy and speed of suspicious object detection. We performed an experiment to validate the proposed system. The usability and safety of the system are demonstrated by recognition rate (aka accuracy rate) or both recall and precision rate. In addition, in the process of improving the suspicious object recognition rate by AI techniques, we use generative adversarial network to help build a suspicious object database and successfully validate the effectiveness of the method and the factors affecting the suspicious object recognition rate to optimize the system.


  • An image watermark removal method for secure internet of things applications based on federated learning

    by Hongan Li, Guanyi Wang, Qiaozhi Hua, Zheng Wen, Zhanli Li, Ting Lei

    Watermark adding is one of the important means for image security and privacy protection in Internet of things (IOT) applications based on federated learning. It is often inseparable from adversarial training with watermark removal algorithms. The effect of watermark removal algorithms will directly affect the final result of watermark addition. However, the existing watermark removal algorithms have drawbacks such as incomplete image watermark removal, poor image quality after watermark removal, large demand for training data, and incorrect filling, which seriously affects the development of image information security and privacy protection in IOT applications based on federated learning. To solve the above problems, this paper proposes an improved image watermark removal convolutional network model based on deep image prior. First, we improve the U‐Net network model, using six downsamping layers and six deconvolution layers combined with deep image prior method to reduce the loss of details and perceive high‐level features, thereby improving the ability of the network to extract high‐level features of the image. In addition, we design a new type of loss function which is called stair loss, and add L1 loss and perception loss to establish new constraints. In order to verify the effectiveness of our method, a comprehensive experimental comparison was conducted on the public dataset PASCAL VOC 2012 in the same experimental environment with CGAN and the deep prior method. The experimental results show that the improved model combined with the deep image prior method can extract the high‐level feature information and can directly remove the watermark from the picture without pretraining the network, the L1 loss and perceptual loss can better retain the image structure information and speed up the watermark removal of the model, the stair loss corrects the final output more accurately by correcting the output of each layer; our method improves the learning ability of the model, and under the condition of the same training time, the image quality after watermark removal is higher, and the final watermark removal result is better, which is more suitable for distributed structure of IoT application based on federated learning.


  • Open Access

    Vehicle License Plate Recognition Using Shufflenetv2 Dilated Convolution for Intelligent Transportation Applications in Urban Internet of Things

    by Xiufeng Li, Zheng Wen, Qiaozhi Hua

    Intelligent transportation applications based on urban Internet of Things can improve the efficiency of government services and promote urban modernization. As smart cameras are more and more widely used in cities, artificial intelligence technology is an important force to achieve license plate recognition. An efficient license plate recognition algorithm not only improves the efficiency of traffic management but also saves management costs. This paper proposes a network based on the shufflenetv2 dilated convolution (SDC) model, which includes two parts: license plate location and license plate recognition. SDC model adopts shufflenetv2 as the backbone network, which combines dilated convolution and global context blocks. Therefore, the receptive field and feature expression ability of the model are enhanced. For license plate location, CIOU loss considers not only the coverage area of the bounding box but also the center distance and aspect ratio. For license plate recognition, CTC loss trains the network based on the sequence and solves the sample alignment problem, which improves the accuracy of license plate recognition. The experiments show that the precision of the SDC model in license plate location is 98.7%, which is 5.2%, 5.5%, and 4.1% higher than the precision of Faster-RCNN, YOLOv3, and SSD, respectively. The precision of the SDC model in license plate recognition is 98.2%, which is 5.3%, 3.7%, and 2.9% higher than the precision of LPRNet, AlexNet, and RPNet, respectively.


  • Open Access

    k Nearest Neighbor Similarity Join Algorithm on High-Dimensional Data Using Novel Partitioning Strategy

    by Youzhong Ma, Qiaozhi Hua, Zheng Wen, Ruiling Zhang, Yongxin Zhang, Haipeng Li

    nearest neighbor similarity join on high-dimensional data has broad applications in many fields; several key challenges still exist for this task such as “curse of dimensionality” and large scale of the dataset. A new dimensionality reduction scheme is proposed by using random projection technique, then we design two novel partition strategies, including equal width partition strategy and distance split tree-based partition strategy, and finally, we propose nearest neighbor join algorithm on high-dimensional data based on the above partition strategies. We conduct comprehensive experiments to test the performance of the proposed approaches, and the experimental results show that the proposed methods have good effectiveness and performance.

  • Open Access

    Efficient Multibit Function Encryption for Data Security in Internet of Things

    by Qihong Chen, Mingming Jiang, Yuyan Guo, Dongbing Zhang, Weina Jia, Wen Zheng

    The development of the Internet of Things (IoT) has been facing severe security threats, and the security and fine-grained access control of data in the IoT is one of the security problems that urgently need to deal with. Attribute-based encryption (ABE) schemes over lattice can not only achieve fine-grained access control but also resist quantum attacks. However, most schemes are single-bit encryption, which is inefficient. In this study, a multibit inner product predicate encryption (PE) scheme over lattice is proposed, which effectively expands the plaintext space. The scheme can realize multibit attribute-based encryption with the hidden access structure for data security in the IoT and support And-gate operation in the access structure with multiattribute. The fine-grained access control of ciphertext data can be realized under the condition of ensuring data privacy. The security of the scheme is based on LWE problem, and it can resist quantum attacks, that is, CPA security under the standard model.


  • Open Access

    Adaptive Differential Evolution Algorithm with Simulated Annealing for Security of IoT Ecosystems

    by Qianqian Liu, Xiaoyan Zhang, Qiaozhi Hua, Zheng Wen, Haipeng Li

    With the wide application of the Internet of Things (IoT) in real world, the impact of the security on its development is becoming incrementally important. Recently, many advanced technologies, such as artificial intelligence (AI), computational intelligence (CI), and deep learning method, have been applied in different security applications. In intrusion detection system (IDS) of IoT, this paper developed an adaptive differential evolution based on simulated annealing algorithm (ASADE) to deal with the feature selection problems. The mutation, crossover, and selection processes of the self-adaptive DE algorithm are modified to avoid trapping in the local optimal solution. In the mutation process, the mutation factor is changed based on the hyperbolic tangent function curve. A linear function with generation is incorporated into the crossover operation to control the crossover factor. In the selection process, this paper adopts the Metropolis criterion of the SA algorithm to accept poor solution as optimal solution. To test the performance of the proposed algorithm, numerical experiments were performed on 29 benchmark functions from the CEC2017 and six typical benchmark functions. The experimental results indicate that the proposed algorithm is superior to the other four algorithms.