检索结果-内蒙古大学图书馆

27th International Symposium on Wireless Personal Multimedia Communications, WPMC 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Sharma, Rashmi Venu, Nookala Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India Department of CSE Pune India Madhav Institute of Technology and Science Deemed University Centre for Internet of Things Gwalior India

ISBN: (纸本)9798350392319

This paper proposes simulation and analysis to discuss how the fading affects the wireless signal waves on different fading levels. Four types of fading: (i) no fading, (ii) a low level of fading, (iii) moderate level of fading and (iv), high level of fading was considered for simulating the signal amplitude over time. Selected fading levels were 'added' to model real world wireless scenarios in which both environmental and interference conditions are at play. The results indicated that in the absence of fading, the amplitude of the signal wave was continuous and not changed significantly;however, from low to severe fading, there could be directly proportional soaring fluctuations in its proper amplitude corresponding to lose of signal strength. Together, these findings underscore the importance of adaptive signal processing techniques and robust modulation strategies in suppressing the degradative effects of fading against the desirable characteristics of proper signal integrity and reliable performance. The findings highlight one reality in communications: understanding fading is critical for designing ultrareliable wireless systems that perform consistently across a variety of operational settings. The knowledge extracted based on this study would further add to novel way of designing robust strategies for Signal resilience and Communication reliability emerged in future wireless networks. © 2024 IEEE.

关键词： Cochannel interference

来源：评论

学校读者我要写书评

暂无评论

Diverse Co-saliency Feature Learning for Text-Based Person Retrieval

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5465-5477页

作者： You, Shuai Chen, Cuiqun Feng, Yujian Liu, Hai Ji, Yimu Ye, Mang School of Internet of Things Nanjing China Anhui University School of Computer Science and Technology Hefei China South China Normal University school of computer Guangdong China NJUPT School of Computer Science Nanjing China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan430072 China

Text-based Person Retrieval (TPR) plays a pivotal role in video surveillance systems for safeguarding public safety. As a fine-grained retrieval task, TPR faces the significant challenge of precisely capturing highly discriminative features across image and text modalities. Existing methods primarily focus on establishing modality-shared feature spaces to bridge cross-modal discrepancies. However, these methods are prone to disturbances from irrelevant information, such as background noises in the visual modality, and often over-emphasize specific local regions while neglecting the capture of diverse discriminative modal features, thereby limiting the robustness of cross-modal matching. In this paper, we introduce a novel framework, termed the Diverse Co-saliency Feature Learning Network (DCFL), which mines the co-saliency information between image and text modalities and enhances the diversity of cross-modal discriminative features while mitigating the interference of noise. Specifically, to construct cross-modal co-saliency features, we devise the Intra-modal Saliency Feature Learning (ISFL) and Cross-modal Saliency Feature Matching (CSFM) modules. ISFL employs a weighted mask mechanism to guide the model in reducing the impact of noise information in both modalities. Complementing ISFL, CSFM establishes consistent relationships between saliency features across modalities, leveraging text descriptions to align pedestrian-relevant visual regions. Furthermore, we propose the Diverse Co-saliency Feature Mining (DCFM) to bolster the diversity of discriminative co-saliency features across both image and text modalities. This module integrates a diversity regularization term, enabling the extraction of varied visual cues and capturing comprehensive features of the target individual. Extensive benchmark experiments demonstrate a substantial superiority of our approach over the state-of-the-art methods. The code will be released publicly. © 2005-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Improving Online Education in Educational Institutions through the Integration of internet of things (IoT) 8

Improving Online Education in Educational Institutions throu...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Ramaraj, Kottaimalai Mathews, Ann Lynsha Helena Pratheeba, Hp Ramani, U. Sujitha, K.L. Thilagaraj, M. Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamilnadu Krishnankoil India Cmr Institute of Technology Department of Computer Science and Engineering Bengaluru India K Ramakrishnan College of Engineering Department of Electrical and Electronics Engineering Trichy India Mvj College of Engineering Department of Computer Science and Engineering Bengaluru India Mvj College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798350367904

A key facilitating infrastructure for building intelligent structures that enable efficient in-person and virtual learning environments is the internet of things (IoT). The shift to smart learning, that includes IoT and Artificial Intelligence (AI) into the educational system, is enticing since it directly affects the motivation of learners, enrolment, participation, and in-depth understanding. Teaching and learning, management, examination, and class monitoring are only a few of the numerous issues that afflict conventional education. Many ingenious approaches to many facets of our lives are being made possible by modern advancements in information and communication technology (ICT);nonetheless, these imaginative concepts aren't adequately incorporated into the framework of education. The COVID-19 pandemic scenario, in specific, has brought out the need for innovative, creative approaches in the field of teaching. The present research examines previous investigations in the field and discusses the following topics: (i) issues with the current educational system and potential fixes;(ii) the shift to smart learning;and (iii) scientific hurdles (such as technological and cultural barriers) in making the move to smart learning. In accordance with these outcomes, creative approaches to the issues with the conventional system-such as smart teaching, smart evaluation, smart school environment, and smart management-are presented. The business and academic community may now include IoT, AI, and ICT into smart learning owing to the aforementioned experimental research's novel developments. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of Emotional Prompts for Generating Videos with High Emotion Consistency 14th

Design and Evaluation of Emotional Prompts for Generating Vi...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Chu, Chao-Ting Chen, You-Yu Chang, Jia-Wei Hung, Jason C. Chunghwa Telecom Laboratories Internet of Things Laboratory No. 99 Dianyan Rd. Yangmei District Taoyuan City32661 Taiwan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan

ISBN: (纸本)9789819623945

Artificial Intelligence Generated Content (AIGC) is an advanced AI technology that can automatically create multimedia content including text, images, sound, and video. With the development of technologies such as ChatGPT, AIGC has made significant progress in natural language processing and exhibits excellent fluency and diversity in human-computer interaction. Text prompt generation is a new challenge for AIGC. Existing models can not only generate video content containing text and image elements, but also strive to weave a world of stories full of emotion and logical coherence to cater to users’ personalized desires. In the process of generating with text prompts, the clever use of adjectives is key to creating engaging scenarios. This study focuses on the design of Emotional Prompts using emotional words, adjectives, and onomatopoeic words to generate videos and sounds with corresponding emotions and further evaluate the emotional consistency of audio and video, enhancing the emotional depth of the content and resonating with the audience. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： AI Generated Diffusion Model Multimodal Learning

来源：评论

学校读者我要写书评

暂无评论

Some New Constructions of AFER-Optimal Binary Linear Block Codes

Some New Constructions of AFER-Optimal Binary Linear Block C...

引用

2023 IEEE International Symposium on Information Theory, ISIT 2023

作者： Abdullah, Murad Mow, Wai Ho The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong The Hong Kong University of Science and Technology Internet of Things Thrust Area Information Hub Hong Kong

ISBN: (纸本)9781665475549

In this paper, we present new constructions for binary linear block codes (BLBCs) that achieve the largest possible minimum Hamming weight and the smallest possible number of minimum-weight codewords (also known as the error coefficient). These [n, k] BLBCs over the additive white Gaussian noise channel, under maximum-likelihood decoding, attain the best possible asymptotic frame error rate (FER) (i.e., at high signal-to-noise ratio) and are said to be asymptotic frame error rate (AFER)-optimal. For l = 0, 1,?, k-1 and all positive integers k and m, we give new constructions of [(2k -1)m+l, k] and [12], [5] AFER-optimal codes. Specifically, we have [(2k - 1) + k, k + 1], [15m + 6, 4], and [15m + 4, 4] BLBCs with error coefficient values of 2, 3 and 4, respectively. These values are significantly smaller than the corresponding best-known values in the literature. © 2023 IEEE.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Deployment Strategy for Low-Power-Consumption Roadside Units in 5G Vehicular Networking 16

Deployment Strategy for Low-Power-Consumption Roadside Units...

引用

16th International Conference on Communication Software and Networks, ICCSN 2024

作者： Wang, Shuai Yang, Xinjie Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China Ningbo Arrowdeep Internet Technology Co. Ltd. Ningbo China

ISBN: (纸本)9798331506322

The low-power-consumption (LPC) operation of Roadside Units (RSUs) is of paramount importance in the 5G Vehicle-to-Infrastructure (V2I) communications within two-dimensional (2-D) internet of Vehicles (IoV) networks. Compared with all RSUs operating at a fixed power, implementation of dynamic power transmission control and operation mode conversion of RSUs based on the actual distribution of vehicles is undoubtedly an intuitive and ideal power optimization solution. To achieve LPC RSU operations, in this paper, a novel concept of candidate communication service area (CCSA) is introduced and a power optimization strategy is established. The main idea of this strategy is to curtail the redundant coverage areas of RSUs while maintaining communications with the vehicles within the system. An enhanced Genetic algorithm (eGA) is proposed to implement this deployment strategy. Extensive simulation results show that the proposed algorithm effectively reduces the aggregate power consumption of RSUs while maintaining robust communication links between RSUs and vehicles. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Reversible Watermarking Method with Low Distortion for the Secure Transmission of Medical Images

引用

computer Modeling in engineering & sciences 2022年第3期130卷 1309-1324页

作者： Rizwan Taj Feng Tao Shahzada Khurram Ateeq Ur Rehman Syed Kamran Haider Akber Abid Gardezi Saima Kanwal School of Computer and Communication Lanzhou University of TechnologyLanzhouChina Faculty of Computing The Islamia University of BahawalpurBahawalpurPakistan Department of Electrical Engineering Government College UniversityLahorePakistan College of Internet of Things Engineering Hohai UniversityChangzhouChina Department of Computer Science COMSATS University IslamabadIslamabadPakistan

In telemedicine,the realization of reversible watermarking through information security is an emerging research ***,adding watermarks hinders the distribution of pixels in the cover image because it creates distortions(which lead to an increase in the detection probability).In this article,we introduce a reversible watermarking method that can transmit medical images with minimal distortion and high *** proposed method selects two adjacent gray pixels whose least significant bit(LSB)is different from the relevant message bit and then calculates the distortion *** use the LSB pairing method to embed the secret matrix of patient record into the cover image and exchange pixel *** results show that the designed method is robust to different attacks and has a high PSNR(peak signal-to-noise ratio)*** MRI image quality and imperceptibility are verified by embedding a secret matrix of up to 262,688 bits to achieve an average PSNR of 51.657 *** addition,the proposed algorithm is tested against the latest technology on standard images,and it is found that the average PSNR of our proposed reversible watermarking technology is higher(i.e.,51.71 dB).Numerical results show that the algorithm can be extended to normal images and medical images.

关键词： LSB reversible watermarking medical images security data distortion

来源：评论

学校读者我要写书评

暂无评论

A Multi-agent Reinforcement Learning based Offloading and Resource Allocation for Vehicle Edge Computing 16

A Multi-agent Reinforcement Learning based Offloading and Re...

引用

16th International Conference on Communication Software and Networks, ICCSN 2024

作者： Yang, Jiazhi Yang, Xinjie Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China Ningbo Arrowdeep Internet Technology Co. Ltd. Ningbo China

ISBN: (纸本)9798331506322

This paper investigates the the challenges of resource allocation optimization for computation offloading in vehicular edge networks. It is assumed that multiple moving vehicles select Mobile Edge Computing (MEC) servers on Road Side Units (RSUs) to offload their computation tasks, for which, MEC servers allocate appropriate resources. To achieve the best balance between minimizing latency and resource consumption to ensure system performance, this study utilizes a Multi-Agent Reinforcement Learning (MARL) framework, where each vehicle and MEC server acts as an agent and learns optimal strategies through interactions with the environment. To improve performance, a new Global Heterogeneous MARL (GHMARL) framework is purposely designed based on existing MARL approaches. The proposed framework trains two Critic networks, namely, a global Critic network to ensure service quality and a local Critic network to ensure resource utilization efficiency. Extensive simulation results demonstrate the performance superiority of this approach over benchmark algorithms. © 2024 IEEE.

关键词： Mobile Edge Computing Multi-Agent Reinforcement Learning Resource allocation Vehicular edge networks

来源：评论

学校读者我要写书评

暂无评论

EVA-MVC: Equitable View-weight Allocation for Generic Multi-View Clustering 25

EVA-MVC: Equitable View-weight Allocation for Generic Multi-...

引用

34th ACM Web Conference, WWW 2025

作者： Fang, Yuan Feng, Xiaofeng Yang, Geping Cai, Ruichu Yang, Yiyang Gong, Zhiguo Hao, Zhifeng School of Computer Science and Technology Guangdong University of Technology Guangzhou China State Key Laboratory of Internet of Things for Smart City University of Macau China College of Engineering Shantou University Shantou China

ISBN: (纸本)9798400712746

Contemporary datasets sourced from the web often adopt a multiview format, collecting data from diverse sources, domains, or modules. Existing methodologies employed to analyze such datasets frequently overlook or inaccurately allocate the view-weights, pivotal metrics reflecting each view’s significance. This work introduces EVA-MVC, a simple yet effective algorithm designed for Equitable View-weight Allocation (EVA) seamlessly integrated with arbitrary Multi-view Clustering (MVC) methods. Within the EVA module, we establish theoretical connections between view supplementarity and Multi-view Subspace Learning (MSL), leading to the partition of views into View Communities (VCs) based on these foundational principles. These VCs exhibit internal supplementarity similarities, facilitating Equitable View-weights Allocation through VC-specific MSL. The proposed EVA process precedes and operates independently of traditional or SOTA MVC approaches, requiring no additional processing or specialized design, making it an ideal preprocessing step for MVC applications. Through comprehensive evaluations across diverse multi-view datasets, our findings reveal that our EVA significantly enhances the effectiveness of mainstream MVC frameworks, resulting in a notable performance improvement. © 2025 Copyright held by the owner/author(s).

关键词： consistency

来源：评论

学校读者我要写书评

暂无评论

SD-MoMa: ANN-based mobility prediction and adaptive handover management in SDWSN

引用

Cluster Computing 2025年第6期28卷 1-15页

作者： Narwaria, Abhishek Mazumdar, Arka Prokash Department of Computer Science and Engineering Malaviya National Institute of Technology Jaipur India Centre for Internet of Things Madhav Institute of Technology and Science (MITSDU) Gwalior India

The growing use of mobile nodes in Wireless Sensor Networks (WSN) improves the system’s Quality of Services (QoS). However, due to the mobility of nodes, the network may suffer various challenges, such as dynamic topology changes, instability in the routing protocol, high energy consumption, and increased control overhead. To deal with these challenges, the Software-Defined Networks (SDN) paradigm has received a lot of attention as it allows networks with limited resources to add new capabilities in order to reduce the overhead brought on by processing and computing in sensor nodes and transfer these energy-intensive tasks to the controller. This paper proposes a Software-defined Distributed Mobility Management (SD-MoMa) framework that employs an Artificial Intelligence (AI) assisted mobility prediction for a Mobile WSN-powered distributed SDN controller. In particular, the SDN controller aims to gather network information from the Mobile Sensor Nodes (MSNs) and predict their successive locations through the MSNs’ current location, direction, and speed using a cutting-edge Artificial Neural Network (ANN) paradigm. Moreover, this mobility prediction enables the controllers to estimate the probability of successful transmission and average latency during the handover of each MSN in the network with frequent topology changes. The ablation and comparative study demonstrate that SD-MoMa exhibits superiority in predicting the future location of Mobile Nodes (MNs). The findings demonstrate that the SD-MoMa framework significantly enhances network performance compared to existing solutions, reducing handover latency by 23%, improving packet delivery ratio by 16%, minimizing control message overhead by 12%, and reduce energy consumption by 27%. These results show that SD-MoMa excels in maintaining network stability and efficiency in dynamic environments with mobile nodes, outperforming state-of-the-art methods across key performance metrics.

关键词：

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：