检索结果-内蒙古大学图书馆

A Benchmark and Frequency Compression Method for Infrared Few-Shot Object Detection

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Ruiheng Yang, Biwen Xu, Lixin Huang, Yan Xu, Xiaofeng Zhang, Qi Jiang, Zhizhuo Liu, Yu Beijing Institute of Technology State Key Laboratory of Electromechanical Dynamic Control Beijing100081 China University of Technology Sydney School of Electrical and Data Engineering UltimoNSW2007 Australia Anhui Polytechnic University School of Computer and Information Wuhan241000 China Technical University of Munich Data Science in Earth Observation Munich85521 Germany Tsinghua University Shenzhen International Graduate School Shenzhen518055 China Tsinghua University Department of Electronic Engineering Beijing100084 China

Infrared few-shot object detection (IFSOD) aims to detect infrared objects with limited labeled examples. Current infrared datasets, however, suffer from limited diversity in object types and classes, hindering robust evaluation of model generalization on novel classes. To systematically assess dataset quality, we propose metrics for class diversity, instance variability, and object density. By integrating three widely used infrared datasets, we construct the first dataset specifically tailored for IFSOD, increasing instance density to 4.8 (a 1.1 improvement) and expanding the number of classes to 18 (a 5-class increase) compared to the source datasets. Furthermore, frequency analysis of spatial features reveals that sparse annotations introduce spectral bias in the frequency domain. Directly transforming spatial features to the frequency domain, however, mixes background noise with object features, causing spectral leakage and impairing the learning of discriminative features for novel classes. To address these issues, we propose the frequency compression few-shot detection (FC-fsd) method, which incorporates a frequency compression (FC) module. The FC module leverages Discrete Cosine Transform (DCT) within localized windows to reduce spectral leakage and enhance feature clarity. With minimal additional computational overhead, FC-fsd significantly outperforms state-of-the-art methods, achieving nAP50 scores of 28.57 (+13.37) and 35.63 (+2.59) in 1-shot and 2-shot settings, respectively. Our dataset is published at https://***/RuihengZhang/IFSOD-dataset. © 2025 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Indoor Localization Using IoT and Sensor Networks for Human Activity Monitoring

Real-Time Indoor Localization Using IoT and Sensor Networks ...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： V Muthu Ganesh Intekhab Alam Dikshit Sharma Samuka Mohanty Yuvraj Parmar Gautham Krishna Department of Electronics and Communication Engineering Presidency University Bangalore Karnataka India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Engineering and Technology Department of Civil Engineering JAIN (Deemed to be University) Bangalore Karnataka India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

To develop an effective real-time indoor localization methodology by exploiting the Internet of Things (IoT) consists of sensor networks. This tech is to support a more robust HAM application that allows for precise and continuous tracking based on individual locations inside buildings. It uses a combination of IoT devices and sensors to give people in the indoor environment real-time positioning data. Real-time indoor Localization based on IoT and Sensor Networks is a technology that allows evaluating precise continuous tracking of individuals in buildings to monitor human activity by applying advanced techniques such as Wireless sensor networks. Essentially, this technology leverages IoT devices and sensors to give precise real-time location information of people inside buildings. This accurate and reliable indoor positioning uses advanced techniques such as wireless sensor networks, lowenergy Bluetooth, and IoT technologies like RFID; this technology can be achieved only in Hospitals, shopping malls, and offices where it enables you to track human activities from indoor spaces at the current moment”Ǆ Installing sensors and IoT devices throughout the building connected to a central data center or via Natural Activity Limit Parametrization Real-time indoor localization using the Internet of Things (IoT) and sensor networks enables accurate tracking for human activity monitoring inside buildings. This technology uses IoT devices with sensors to give people precise real-time information on their location in an indoor space. This technology provides highly precise and reliable indoor positioning with advanced techniques such as wireless sensor networks, Bluetooth low energy, or RFID. The technology is best suited to tracking human activities in indoor spaces, including hospitals, shopping malls, and offices. This is followed by creating a data layer of network sensors and IOT devices inside the building connected to an on-premises or cloud central server. Sensors capt

关键词： Location awareness Wireless sensor networks Accuracy Hospitals Buildings Real-time systems Internet of Things Security Servers Monitoring

来源：评论

学校读者我要写书评

暂无评论

CLDM-MMNNs: Cross-layer defense mechanisms through multi-modal neural networks fusion for end-to-end cybersecurity—Issues, challenges, and future directions

引用

Information Fusion 2025年 122卷

作者： Ali, Sijjad Wang, Jia Leung, Victor C.M. Bashir, Farhan Bhatti, Uzair Aslam Wadho, Shuaib Ahmed Humayun, Mamoona College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Kampar31900 Malaysia School of Information and Communication Engineering Hainan University Hainan China School of Arts Humanities and Social Sciences University of Roehampton LondonSW15 5PJ United Kingdom

Cybersecurity threats have grown in complexity and scale, necessitating robust defense mechanisms that integrate multiple layers of network security. Multi-modal neural networks (MMNNs) have emerged as a powerful tool for addressing such challenges due to their ability to process and integrate heterogeneous data sources. This review provides an in-depth analysis of cross-layer defense mechanisms that leverage MMNNs for end-to-end cybersecurity. The study explores the foundational principles of MMNNs, their applications in intrusion detection, malware analysis, anomaly detection, and advanced persistent threat (APT) mitigation. The paper emphasizes the synergy between multi-modal data integration and neural network architectures, enabling real-time threat detection and adaptive response. By categorizing existing approaches and highlighting key advancements, this review outlines current limitations, including computational overhead and model interpretability, and suggests future research directions for developing efficient, scalable, and explainable MMNN-based defense systems. © 2025

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Personalised Travel Ratings using AI and Enhancing User Experience Through Multi-Dimensional Analytics

Personalised Travel Ratings using AI and Enhancing User Expe...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Poornima S A. Krishnaveni J. Relin Francis Raj R. Divya G. Vinoth Rajkumar I. Sakthidevi Department of Computer Science Sri Ramakrishna College of Arts and Science for Women Coimbatore India Department of Mechanical Engineering Government College of Engineering Tirunelveli India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Information Technology Adhiyamaan college of Engineering Hosur India Department of Electronics and Communication Engineering J. P. College of Engineering Tenkasi India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

The rapid advancements in Artificial Intelligence (AI) have enabled the development of intelligent systems for personalized travel recommendations. This study proposes a novel framework, Generative Adversarial Networks with Real-Time Analytics for Travel Experience (GAN-RATE), designed to enhance user satisfaction by integrating synthetic data generation and real-time feedback mechanisms. The GAN component addresses the challenge of sparsely rated travel attributes by generating high-quality synthetic data, while the Real- Time Analytics module evaluates user interactions and feedback to refine the recommendation process dynamically. The proposed framework considers multiple dimensions, including comfort, cleanliness, timeliness, entertainment amenities, and customer feedback, ensuring a holistic approach to travel rating prediction. Simulation analysis is conducted to compare the performance of GAN-RATE with existing algorithms. Metrics such as accuracy, mean absolute error (MAE), precision, recall, and computational efficiency are employed to evaluate system performance. Results indicate that GAN-RATE outperforms baseline models in prediction accuracy and adaptability to sparse datasets while demonstrating superior real-time response capabilities. The findings highlight the potential of GAN-RATE in improving user experience through personalized, data-driven recommendations, setting a new benchmark for AI-based travel recommendation systems.

关键词： Training Adaptation models Accuracy Heuristic algorithms Generative adversarial networks Prediction algorithms Real-time systems User experience Recommender systems Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Wearable Biosensors for Continuous Monitoring of Cardiovascular Health

Wearable Biosensors for Continuous Monitoring of Cardiovascu...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Adarsha H Prabhu Ankita Agarwal Anoop Dev Bubun Kumar Mohanta Prateek Garg School of Engineering and Technology Mechaical Engineering JAIN (Deemed to be University) Bangalore Karnataka India Department of Electronics and Communication Engineering Presidency University Bangalore Karnataka India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Wearable biosensors have revolutionized cardiovascular health monitoring. These body-fitted, continuous devices monitor a host of vital signs, including heart rate, blood pressure and oxygen levels. Such real-time monitoring will help detect and take prompt action in case the patient is at any risk of cardiac issues, further leading to a better quality of life and reducing serious illnesses. The non-invasive characteristic is one major benefit of wearable biosensors, as they can be worn day long very comfortably and easily. It also prevents the need for regular or emergency doctor visits and hospitalizations while saving money from healthcare bills with continuous monitoring as well. The biosensors are connected to a Smartphone or monitoring platform, helping healthcare professionals move the patient out of the tracking marquee area. This enables tailored and preventive care by allowing for instant correction of any anomalies. Aside from monitoring, wearable biosensors may play an important part, too. They can be integrated through other devices and also accurate health systems. How do they work? Biosensors for heart, \wearable's provide unprecedented convenience, accuracy and personalization\nor promoting and monitoring human cardiovascular health. The ability to continuously monitor patients in real-time has the potential to improve patient outcomes and transform health care significantly.

关键词： Heart rate Accuracy Medical services Transforms Real-time systems Blood pressure Biosensors Biomedical monitoring Monitoring Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Information-Bearing RIS Enabled NOMA System

引用

IEEE Transactions on Vehicular technology 2025年

作者： Han, Shuai Sun, Zeyang Xu, Sai Xie, Dan Li, Cheng Harbin Institute of Technology School of Electronics and Information Engineering Heilongjiang Harbin150001 China Southeast University National Mobile Communications Research Laboratory Nanjing211111 China Memorial University Electrical and Computer Engineering Faculty of Engineering and Applied Science St. John'sA1B 3X5 Canada

In this correspondence, we investigate an information-bearing reconfigurable intelligent surface (RIS) assisted non-orthogonal multiple access (NOMA) system. In this system, the RIS is segmented into multiple sub-RIS units, each serving as a passive transmitter to deliver information to users via extended backscatter modulation under the NOMA scheme. We aim to maximize the system's weighted sum rate (WSR) by jointly optimizing the active beamformer at the power beacon (PB) and the RIS coefficient vectors, while adhering to constraints related to PB transmission power, RIS coefficients, successive interference cancellation (SIC) decoding rate, and rate fairness. Extensive simulation results verify the feasibility and superiority of the proposed scheme. © 2025 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Uplink Rate-Splitting Multiple Access for Mobile Edge Computing with Short-Packet Communications

arXiv

引用

arXiv 2025年

作者： Xu, Jiawei Zhang, Yumeng Xu, Yunnuo Clerckx, Bruno Imperial College London United Kingdom Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Electronics and Computer Engineering The Hong Kong University of Science and Technology 999077 Hong Kong School of Information Science and Engineering Shandong University Qingdao266237 China

In this paper, a Rate-Splitting Multiple Access (RSMA) scheme is proposed to assist a Mobile Edge Computing (MEC) system where local computation tasks from two users are offloaded to the MEC server, facilitated by uplink RSMA for processing. The efficiency of the MEC service is hence primarily influenced by the RSMA-aided task offloading phase and the subsequent task computation phase, where reliable and low-latency communication is required. For this practical consideration, short-packet communication in the Finite Blocklength (FBL) regime is introduced. In this context, we propose a novel uplink RSMA-aided MEC framework and derive the overall Successful Computation Probability (SCP) with FBL consideration. To maximize the SCP of our proposed RSMA-aided MEC, we strategically optimize: (1) the task offloading factor which determines the number of tasks to be offloaded and processed by the MEC server;(2) the transmit power allocation between different RSMA streams;and (3) the task-splitting factor which decides how many tasks are allocated to splitting streams, while adhering to FBL constraints. To address the strong coupling between these variables in the SCP expression, we apply the Alternative Optimization method, which formulates tractable subproblems to optimize each variable iteratively. The resultant non-convex subproblems are then tackled by Successive Convex Approximation. Numerical results demonstrate that applying uplink RSMA in the MEC system with FBL constraints can not only improve the SCP performance but also provide lower latency in comparison to conventional transmission scheme such as Non-orthogonal Multiple Access (NOMA). © 2025, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

The Role of Cyber-Physical Systems in Revolutionizing Transportation: From Connected Cars to Autonomous Vehicles

The Role of Cyber-Physical Systems in Revolutionizing Transp...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Anilloy Augustine Frank Trapty Agarwal Divya Sharma Arup Kumar Dutta Shikhar Gupta Aravindan M K Department of Electronics and Communication Engineering Presidency University Bangalore Karnataka India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Engineering and Technology Mechaical Engineering JAIN (Deemed to be University) Bangalore Karnataka India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Cyber-physical systems have technologically advanced the transportation industry with their ability to connect physical systems with virtual functions. A cyber-physical system uses real-time data generation and communication technologies to make transportation systems safer, more efficient, more sustainable and more reliable. Connected cars are one of the primary use cases of CPS in transportation. They utilize sensors, cameras, and internet connectivity to capture information regarding road conditions, traffic patterns, and other drivers on the road. This information is then communicated to the backend system for analysis and decision-making to enhance safety or alleviate traffic congestion. It has also contributed towards developing independent vehicles. They employ ACH and CPS technologies to drive on roads driving without the need for human intervention. This could lead to a huge reduction in human error-related accidents and improve the efficiency of transportation. CPS also helps build smart transportation systems or link multiple modes of transport to escape congestion and reduce travel time. For example, it involves the integration of different modes of transportation, such as public transit, ride-sharing services and self-driving cars, to minimize travel time while maximizing usage. CPS has revolutionized the transport sector into a more connected, effective and secures system.

关键词： Technological innovation Connected vehicles Roads Transportation industry Transportation Cyber-physical systems Traffic control Smart transportation Traffic congestion Accidents

来源：评论

学校读者我要写书评

暂无评论

Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding

arXiv

引用

arXiv 2025年

作者： Hu, Jiliang Li, Zuchao Shen, Mengjia Ai, Haojun Li, Sheng Zhang, Jun Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China School of Computer Science Wuhan University Wuhan China Wuhan Second Ship Design and Research Institute Wuhan China National Institute of Information and Communications Technology Japan

Spoken language understanding (SLU) is a structure prediction task in the field of speech. Recently, many works on SLU that treat it as a sequence-to-sequence task have achieved great success. However, This method is not suitable for simultaneous speech recognition and understanding. In this paper, we propose a joint speech recognition and structure learning framework (JSRSL), an end-to-end SLU model based on span, which can accurately transcribe speech and extract structured content simultaneously. We conduct experiments on name entity recognition and intent classification using the Chinese dataset AISHELL-NER and the English dataset SLURP. The results show that our proposed method not only outperforms the traditional sequence-to-sequence method in both transcription and extraction capabilities but also achieves state-of-the-art performance on the two datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Wearable Sensors for Continuous Measurement of Vital Signs in Resource-Limited Settings

Low-Cost Wearable Sensors for Continuous Measurement of Vita...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Jatin Khurana Dasarathy A K Gowri K Ankita Agarwal Sulabh Mahajan Abhijit Pal Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India Department of Civil Engineering School of Engineering and Technology JAIN (Deemed to be University) Bangalore Karnataka India Department of Electronics and Communication Engineering Presidency University Bangalore Karnataka India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Wearable or noninvasive sensors capable of measuring vital signs continuously can help narrow the resource gap in rarefied environments. The challenge for adoption, though, is the cost of traditional sensors and, in particular, the need for such infrastructure in these settings. To this end, the rapid development of inexpensive wearables allows continuous monitoring of vital signs such as heart rate, respiratory rate, blood oxygen saturation, and body temperature. The sensors are also lightweight, portable and non-invasive, making them useful for resource-limited settings that have limited access to medical technologies. Utilizing high-tech components like wireless communication and digital signal processing, the sensors provide fast, continuous, real-time monitoring of vital signs. They are easily operated and require little training. These sensors can wirelessly send the gathered data to smartphones or tablets, enabling healthcare workers to monitor patients remotely in real-time. This helps early identification of any unusual readings, allowing timely intervention. These low-cost, noninvasive sensors can compel a paradigm shift in healthcare delivery for resource-constrained settings. Their ability to monitor vital signs 24/7 without the time and expense of patient visits could save both lives and money at a fraction of the cost offered by traditional sensors. These can help us make an early diagnosis and intervention, thus improving the outcomes of patients. Such sensors may provide a solution for the healthcare disparity gap and achieve low-cost, accessible vital sign monitoring to target individuals who need it most.

关键词： Temperature sensors Training Temperature measurement Wireless communication Costs Surveillance Real-time systems Biomedical monitoring Wearable devices Wearable sensors

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：