检索结果-内蒙古大学图书馆

Beyond administrative reports: a deep learning framework for classifying and monitoring crime and accidents leveraging large-scale online news

引用

Neural Computing and Applications 2025年第10期37卷 7183-7205页

作者： Tuarob, Suppawong Tatiyamaneekul, Phonarnun Pongpaichet, Siripen Tawichsri, Tanisa Noraset, Thanapon Faculty of Information and Communication Technology Mahidol University Nakhon Pathom Thailand Department of Computer Science University College London London United Kingdom Puey Ungphakorn Institute for Economic Research Bank of Thailand Bangkok Thailand

The escalating prevalence of violent crimes and accidents underscores the urgent need for efficient and timely monitoring systems. Traditional methods reliant on administrative reports often suffer from significant delays. This paper proposes CRIMSON, a novel framework that leverages large-scale online news to provide real-time insights into crime and accident trends. CRIMSON utilizes a multi-label classification technique that leverages a fine-tuned, pre-trained, cross-lingual language model to accurately categorize news articles. Our experimental results, conducted on a substantial dataset of Thai news articles, demonstrate superior performance, achieving an average F1 score of 86%. Beyond classification, CRIMSON aggregates categorized news into real-time statistics, revealing strong correlations between news-reported incidents and official crime data. This study pioneers online news as a reliable and timely crime and accident monitoring source, offering valuable insights for law enforcement, policymakers, and researchers. © The Author(s) 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Digital PID controllers with fractional variable order techniques and two discrete-time operator variants

引用

Bulletin of the Polish Academy of sciences: Technical sciences 2025年第3期73卷

作者： Mozyrska, Dorota Wyrwas, Malgorzata Oziablo, Piotr Faculty of Computer Science Bialystok University of Technology Bialystok Poland

This paper introduces a control strategy utilizing the fractional variable order PID digital controller (FVOPID). We employ two variants of fractional discrete-time operators with variable order: the Grünwald-Letnikov type and its convolution version. We examine and compare the performance of both controllers types on a higher-order plant. Parameter optimization is conducted using a particle swarm algorithm. © 2025 The Author(s).

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

DiffuSAR: Frequency Domain-Aware Diffusion Model for SAR Image Generation

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 11851-11866页

作者： Ying, Zilu Ke, Wenyu Zhai, Yikui Long, Zhihao Zhou, Jianhong Zhu, Hufei Chen, C. L. Philip Wuyi University School of Electronics and Information Engineering Guangdong Jiangmen529020 China South China University of Technology School of Electronics and Information Engineering Guangzhou510000 China South China University of Technology Faculty of Computer Science and Engineering Guangdong Guangzhou510000 China

In recent years, deep learning-based Synthetic Aperture Radar (SAR) image detection, recognition, and segmentation models achieve remarkable accuracy when trained on large amounts of SAR image samples. However, the acquisition of SAR images tends to be costly. A practical approach to address this issue involves the use of artificially generated training samples to supplement the dataset. Current SAR image generation methods based on Generative Adversarial Networks have issues with generation fidelity and are challenge to converge. Moreover, most of these methods only consider the spatial domain of SAR images without exploring the characteristics of their frequency domain. To tackle the aforementioned problems, we proposed a lightweight frequency domain-aware SAR image generation model based on the Denoising Diffusion Probabilistic Model. The proposed generative model is capable of producing highly realistic artificial SAR image samples while converging stably. Meanwhile, our research reveals that high-frequency components of SAR images play a crucial role in the generation process, and a frequency adjustment module based on the Fast Fourier Transform is implemented in our generation model to prevent interference of high-frequency components by low-frequency components. Tests on the MSTAR dataset highlight our model's advantages in both generation quality and parameter efficiency compared to other cutting-edge image generation models. An additional ablation study also confirms the effectiveness of our proposed frequency adjustment module, which reduces the Fréchet Inception Distance by 2.85%, confirming our hypothesis that high-frequency components are more crucial to SAR image generation. Code is available at https://***/yikuizhai/DiffuSAR. © 2025 IEEE.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

A Holistic Anti-Counterfeiting Platform Using NFC and Blockchain Technologies

引用

computers, Materials and Continua 2025年第3期83卷 4257-4280页

作者： Rajendren Subramaniam Saaidal Razalli Azzuhri Teh Ying Wah Atif Mahmood Vimala Balakrishnan Department of Information System Faculty of Computer Science & Information Technology Universiti Malaya Kuala Lumpur 50603 Malaysia Department of Computer System & Technology Faculty of Computer Science & Information Technology Universiti Malaya Kuala Lumpur 50603 Malaysia Faculty of Data Science and Information Technology INTI International University Nilai 71800 Malaysia

Counterfeiting is still a pervasive global issue, affecting multiple industries and hindering industrial innovation, while causing substantial financial losses, reputational damage, and risks to consumer safety. From luxury goods and pharmaceuticals to electronics and automotive parts, counterfeit products infiltrate supply chains, leading to a loss of revenue for legitimate businesses and undermining consumer trust. Traditional anti-counterfeiting measures, such as holograms, serial numbers, and barcodes, have proven to be insufficient as counterfeiters continuously develop more sophisticated replication techniques. As a result, there is a growing need for more advanced, secure, and reliable methods to prevent counterfeiting. This paper presents a novel, holistic anti-counterfeiting platform that integrates Near Field Communication (NFC)-enabled mobile applications with blockchain technology to provide an innovative, secure, and consumer-friendly authentication mechanism. Our approach addresses key gaps in existing solutions by incorporating dynamic product identifiers, which make replication significantly more difficult. The system enables consumers to verify the authenticity of products instantly using their smartphones, enhancing transparency and trust in the supply chain. Blockchain technology plays a crucial role in our proposed solution by providing an immutable, decentralized ledger that records product authentication data. This ensures that product verification records cannot be tampered with or altered, adding a layer of security that is absent in conventional systems. Additionally, NFC technology enhances security by offering unique identification capabilities, enabling real-time product verification. To validate the effectiveness of the proposed system, real-world testing was conducted across different industries. The results demonstrated the platform’s ability to significantly reduce counterfeit products in the supply chain, offering businesses and cons

关键词： Blockchain near field communication (NFC) anti-counterfeiting

来源：评论

学校读者我要写书评

暂无评论

Depth of Anesthesia Analysis and Prediction with Deep Residual Shrinkage Network and Long Short-Term Memory 24

Depth of Anesthesia Analysis and Prediction with Deep Residu...

引用

13th International Conference on Bioinformatics and Biomedical science, ICBBS 2024

作者： Shen, Xiecheng Qiao, Changwei Xu, Bowen School of Computer Science and Artificial Intelligence University of Nottingham Ningbo China Zhejiang Ningbo China College of Computer Science and Technology Jilin University Jilin Changchun China Faculty of Science and Technology Beijing Normal University-Hong Kong Baptist University United International College Guangdong Zhuhai China

ISBN: (纸本)9798400717956

Precise measurement and control of the depth of anesthesia (DoA) is essential for anesthesiologists to ensure the success of surgery and the safety of patients. Electroencephalogram (EEG) signals, captured by electrodes on the scalp, can indicate the state of consciousness of the brain. However, estimating and predicting DoA via EEG signals still poses a challenge. This paper proposes a refined architecture consisting of a convolution neural network (CNN) based module and a recurrent neural network (RNN) based module, to perform real-time Bispectral Index (BIS), a common commercial indicator of DoA, analysis and BIS prediction. The CNN-based module is a variation of the Deep Residual Shrinkage Network (DRSN), which produces 2 values from the spectrograms of the filtered EEG signals, one representing the real-time analysis of the BIS value, the other representing a crude prediction of the BIS value over a certain period. To simplify the problem, the period is set at 30 seconds in this study. The real-time analysis value, accumulated by time, is then viewed as a time sequence and processed by the RNN-based module, producing one additional value. This newly created value is then concatenated with the crude prediction value to make a refined BIS value prediction. The model is trained on the bio-data of 176 patients who underwent vascular surgery from the public dataset VitalDB. The model achieved satisfying results, with a mean squared error of 42.15 in real-time analysis and 46.92 in prediction. Our model outperformed several existing models in both real-time BIS analysis and BIS prediction and is expected to assist anesthesiologists in preparation for emergencies in clinical practices. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Current and Voltage Calculations of the 400 kV Transmission Line Using Laboratory Measurements and computer Simulation 33rd

Current and Voltage Calculations of the 400 kV Transmission...

引用

33rd International Conference on Organization and technology of Maintenance, OTO 2024

作者： Torma, Matej Fekete, Krešimir Kljajić, Ružica Čvek, Kristijan Faculty of Electrical Engineering Computer Science and Information Technology Osijek University of Osijek Kneza Trpimira 2b Osijek31000 Croatia

ISBN: (纸本)9783031805967

In this paper, the current, voltages, as well as active and reactive power of the 400 kV transmission line are calculated using three different methods. The objective of the paper is to demonstrate and compare three different approaches that are based on laboratory measurement, analytical approach, and computer simulation. Measurements are carried out on the laboratory model of a real-life 400 kV transmission line while analytical approach is conducted using a short line model with lumped parameters. As a last approach, the transmission line is modeled in a computer program for power flow analysis, and power flow simulations with the same parameters as for the previous two methods are performed. All three methods are used to calculate voltages, currents, and powers at the beginning and at the end of the transmission line for a few scenarios. Results are compared and discussed in order to demonstrate the possibilities of the applied approaches for the education of power system engineers. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Power transmission lines

来源：评论

学校读者我要写书评

暂无评论

A Framework for Real-Time Monitoring of Power Consumption of Distributed Calculation on Computational Cluster 15

A Framework for Real-Time Monitoring of Power Consumption of...

引用

15th International Conference on Cloud Computing and Services science, CLOSER 2025

作者： Krechowicz, Adam Faculty of Electrical Engineering Automatic Control and Computer Science Kielce University of Technology al. 1000-lecia PP 7 Kielce Poland

ISBN: (纸本)9789897587474

This paper proposes a framework for real-time monitoring of the power consumption of distributed calculation on the nodes of the cluster. The framework allows to visualize and analyze the provider results based on the context information about the performed calculation. The first part of the framework is devoted to monitoring the power consumption during the execution of machine learning algorithms and the performance of NoSQL storage. The second part is dedicated to the testing of distributed data storage, called Scalable Distributed Two-Layered Data Structure (SD2DS). The results show that the framework can be used in the development of a management system that could schedule computations to take full advantage of renewable energy. Copyright © 2025 by SCITEPRESS - science and technology Publications, Lda.

关键词： Cluster computing

来源：评论

学校读者我要写书评

暂无评论

Learned distributed image compression with decoder side information

引用

Digital Communications and Networks 2025年第2期11卷 349-358页

作者： Yankai Yin Zhe Sun Peiying Ruan Ruidong Li Feng Duan Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University Institute of Natural Sciences Kanazawa University Faculty of Health Data Science and Graduate School of Medicine Juntendo University NVIDIA AI Technology Center NVIDIA Japan

With the rapid development of digital communication and the widespread use of the Internet of Things, multi-view image compression has attracted increasing attention as a fundamental technology for image data communication. Multi-view image compression aims to improve compression efficiency by leveraging correlations between images. However, the requirement of synchronization and inter-image communication at the encoder side poses significant challenges, especially for constrained devices. In this study, we introduce a novel distributed image compression model based on the attention mechanism to address the challenges associated with the availability of side information only during decoding. Our model integrates an encoder network, a quantization module, and a decoder network, to ensure both high compression performance and high-quality image reconstruction. The encoder uses a deep Convolutional Neural Network(CNN) to extract high-level features from the input image, which then pass through the quantization module for further compression before undergoing lossless entropy coding. The decoder of our model consists of three main components that allow us to fully exploit the information within and between images on the decoder side. Specifically, we first introduce a channel-spatial attention module to capture and refine information within individual image feature maps. Second, we employ a semi-coupled convolution module to extract both shared and specific information in images. Finally, a cross-attention module is employed to fuse mutual information extracted from side information. The effectiveness of our model is validated on various datasets, including KITTI Stereo and Cityscapes. The results highlight the superior compression capabilities of our method, surpassing state-of-the-art techniques.

关键词： Digital communication Image compression Side information Channel-spatial attention module Cross-attention module

来源：评论

学校读者我要写书评

暂无评论

UWB System for Frequent Positioning of Moving Objects 21st

UWB System for Frequent Positioning of Moving Objects

引用

21st European, Mediterranean, and Middle Eastern Conference on Information Systems, EMCIS 2024

作者： Paszek, Krzysztof Department of Telecommunications and Teleinformatics Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice44-100 Poland

ISBN: (纸本)9783031813214

Object positioning is an essential issue in the context of autonomous vehicles and AGVs in Industry 4.0 and smart cities. Based on the position, it is possible not only to track objects, but with appropriate positions’ accuracy and frequency, it is possible to prevent dangerous situations. The information about the possibility of a dangerous situation must be available in advance so that the superior system, driver, or operator can take the appropriate action. A UWB is a promising technology for object positioning, even though UWB systems are used for positioning objects in a limited area, mostly indoors. Nothing stands in the way of creating many small areas in high-risk areas, e.g. intersections and manoeuvring yards. This ultra-wideband technology allows to objects positioning with high accuracy of a few centimeters. However, the accuracy of this system depends on the speed of movement of the positioned objects and the ranging frequency to individual stationary reference nodes – anchors. Therefore, it is important to exchange messages in the network of UWB nodes during ranging runs as quickly as possible. This article analyses the modified UWB positioning system, which maximizes the frequency of acquiring the distance between nodes and, thus the frequency of determining the object’s positions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

The Power of PDF-to-Audio Summaries in Modern Learning 4

The Power of PDF-to-Audio Summaries in Modern Learning

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Kawde, Dhanshri Mendhe, Sameer Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Sawangi Wardha442001 India

ISBN: (纸本)9798331523923

PDF -to-audio based summarization technology is designed to enhance information accessibility and efficiency by transforming long written reports into short, audible summaries. AI, NLP, and TTS technologies that have developed recently have made it possible to extract main points without losing context. Yet, current systems have various shortcomings such as inability to process intricate PDF layouts like tables, charts, and annotations, contextual summarization inaccuracies, robotic or unhuman speech synthesis, and limited customization. Furthermore, the absence of multilingual support and easy integration into various platforms hinders wider adoption. These issues are addressed in this paper with a better approach that employs sophisticated NLP methods, context-sensitive summarization algorithms, and adaptive TTS systems. Our goal is to create a strong, user-oriented solution that provides greater summarization accuracy, personalized speech output, and improved accessibility for a variety of users, such as professionals, students, and the disabled. © 2025 IEEE.

关键词： Web Design

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：