检索结果-内蒙古大学图书馆

Performance analysis of naive vehicular named data networks

International Journal of Wireless and Mobile Computing 2025年第3期28卷 234-244页

作者： Nithin Rao, R. Sharma, Rinki Department of Computer Science and Engineering Ramaiah University of Applied Sciences Karnataka Bangalore India

Vehicular Named Data Networks (VNDN) is a content centric approach for vehicle networks. The fundamental principle of addressing the content rather than the host, suits vehicular environment. There are numerous challenges such as interest/data flooding, routing, naming schemes, channel constraints and security, among others. The proposed work aims to analyse the behaviour of the naive VNDN under diverse scenarios, which is crucial for devising effective forwarding, caching and security strategies to enhance VNDN’s performance. In this paper, the naive VNDN architecture is implemented and its performance is evaluated by considering the metrics such as Throughput, Packet Delivery Ratio (PDR), Interest Satisfaction Delay (ISD), Interest Satisfaction Ratio (ISR), Copies of Data Packets Processed (CDPP) and Hop Count Difference (HCD). These metrics are tested against varying vehicle speed, network size and interests generated by each vehicle in the network. The simulation results provide insights that should be considered while developing the forwarding strategies and caching mechanisms that will improve the performance of VNDN. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： caching content forwarding data packets delay naming timestamp

来源：评论

学校读者我要写书评

暂无评论

A Novel Lightweight Joint Source-Channel Coding Design in Semantic Communications

引用

IEEE Internet of Things Journal 2025年第11期12卷 18447-18450页

作者： Yu, Xianhua Li, Dong Zhang, Ning Shen, Xuemin Macau University of Science and Technology School of Computer Science and Engineering 999078 China University of Windsor Department of Electrical and Computer Engineering Canada University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Semantic communication has emerged as a promising solution to meet the growing demand for efficient data transmission in the information age. Unlike traditional communication methods that focus on transmitting raw data, semantic communication prioritizes preserving the meaning of transmitted information, which significantly reduces the data volume. However, implementing semantic communication systems in resource-constrained environments, such as Internet of Things (IoT) devices, remains challenging due to limited computational resources. In this letter, we propose a novel lightweight deep learning (DL) model, termed the lightweight image compression and reconstruction network (LICRnet). LICRnet leverages depthwise separable convolution (DSC) and a local and non-local mixture (LNLM) block to significantly reduce computational costs. Additionally, the LNLM incorporates a variable window size-based multi-scale attention mechanism (VW-MSA), enabling it to effectively learn from both local detailed features and global high-level meaningful features. Extensive simulations demonstrate that LICRnet significantly reduces computational complexity while maintaining satisfactory image compression and reconstruction performance, making it highly suitable for deployment in resource-constrained environments. © 2014 IEEE.

关键词： Channel coding

来源：评论

学校读者我要写书评

暂无评论

An optimized multi-scale convolutional autoencoder for efficient abnormal event detection using rgb, depth and optical flow data

引用

Multimedia Tools and Applications 2025年 1-35页

作者： Alqahtani, Abdullah Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University KSA Al-Kharj Saudi Arabia

In this study, we propose a novel framework for detecting abnormal events in surveillance videos, a critical yet challenging task in security applications. This research introduces a robust and efficient solution for video anomaly detection, offering substantial improvements in surveillance systems' ability to detect abnormal events, thereby contributing to enhanced security measures in public spaces. The proposed framework utilizes a Multiscale Convolutional Autoencoder (MSCAE) that processes inputs from RGB, depth, and optical flow video clips, enhancing the detection accuracy in complex scenes characterized by varying object scales, aspect ratios, and occlusions. To address the challenge of noise and preserve edges in video data, we implement a two-pass bilateral smooth filtering method, which is effective for noise-invariant, edge-preserving image smoothing. For object detection within these complex scenes, an enhanced Faster R-CNN model is employed. This model's performance is further refined through transfer learning on a dataset specifically composed of abnormal event videos. We also introduce significant improvements to the region proposal network (RPN) of the Faster R-CNN, particularly in non-maximum suppression (NMS) and anchor generation techniques, to better detect anomalies in diverse and complex environments. Furthermore, the MSCAE is integrated with Long Short-Term Memory (LSTM) neural networks to classify the detected anomalies, creating an end-to-end solution for video anomaly detection. Hyperparameter optimization for our deep learning models is performed using the Chameleon Swarm Algorithm, ensuring optimal model performance. Our framework was rigorously tested on the CUHK Avenue dataset, where it achieved a remarkable 99.5% accuracy, significantly outperforming existing methods and demonstrating the effectiveness of our approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

ComStreamClust: a Communicative Multi-Agent Approach to Text Clustering in Streaming Data

引用

Annals of Data science 2023年第6期10卷 1583-1605页

作者： Najafi, Ali Gholipour-Shilabin, Araz Dehkharghani, Rahim Mohammadpur-Fard, Ali Asgari-Chenaghlu, Meysam Department of Computer Science and Engineering Sabanci University Istanbul Turkey Department of Computer Engineering University of Tabriz Tabriz Iran Computer Engineering Department Isik University Istanbul Turkey Department of Computer Engineering Sharif University of Technology Tehran Iran

Topic detection is the task of determining and tracking hot topics in social media. Twitter is arguably the most popular platform for people to share their ideas with others about different issues. One such prevalent issue is the COVID-19 pandemic. Detecting and tracking topics on these kinds of issues would help governments and healthcare companies deal with this phenomenon. In this paper, we propose a novel, multi-agent, communicative clustering approach, so-called ComStreamClust for clustering sub-topics inside a broader topic, e.g., the COVID-19 and the FA CUP. The proposed approach is parallelizable, and can simultaneously handle several data-point. The LaBSE sentence embedding is used to measure the semantic similarity between two tweets. ComStreamClust has been evaluated by several metrics such as keyword precision, keyword recall, and topic recall. Based on topic recall on different number of keywords, ComStreamClust obtains superior results when compared to the existing methods. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

CRAQL: a novel clustering-based resource allocation using the Q-learning in fog environment

引用

International Journal of Cloud Computing 2024年第3期13卷 243-266页

作者： Ahlawat, Chanchal Krishnamurthi, Rajalakshmi Department of Computer Science and Engineering Jaypee Institute of Information Technology Noida India

Fog computing is an emerging paradigm that provides services near the end-user. The tremendous increase in IoT devices and big data leads to complexity in fog resource allocation. Inefficient resource allocation can lead to resource starvation and unable to complete the task assignment within a specific time. Hence, to enhance the efficiency of the fog resources, it is critical to perform proper resource allocation. This work targets to provide the solution to the resource allocation problem with a novel clustering-based resource allocation using the Q-learning (CRAQL) model. For this purpose, the problem is defined as a decision-making problem and formulated as Markov decision process (MDP). Next, to find the optimal resource, an enhanced optimal resource allocation (EORA) algorithm is proposed and detailed study is performed to analyse the impact of various performance parameters. Simulation results show the comparison of the EORA versus conventional Brute force method by varying the performance parameters such as learning rate and number of trials. The experimental results exhibit optimal solutions with significant improvement in learning rate at an average probability of 0.5 within limited epochs. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Automatic bug assignments without texts: a study

引用

Frontiers of computer science 2024年第4期18卷 211-213页

作者： Zexuan LI Kaixin HUANG Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China

1 Introduction Automatic bug assignment has been well-studied in the past *** textual bug reports usually describe the buggy phenomena and potential causes,engineers highly depend on these reports to fix ***,researchers spend much effort on processing bug reports,aiming for obtaining key information and/or clues for reproducing bugs,analyzing their root causes,assigning them to developers/maintainers,and fixing these ***,our previous research[1]reveals that noises in texts bring adverse impacts to automatic bug assignments unexpectedly,mainly due to insufficiency of classical Natural Language Processing(NLP)techniques.

关键词： bug assignment maintain

来源：评论

学校读者我要写书评

暂无评论

RelaxVR: Cybersickness Reduction in Immersive Virtual Reality through Explainable AI and Large Language Models

引用

IEEE Access 2025年 13卷 84689-84712页

作者： Kundu, Ripan Kumar Hoque, Khaza Anuarul University of Missouri Department of Electrical Engineering Computer Science ColumbiaMO United States

Virtual reality (VR) systems are susceptible to cybersickness, significantly hindering user immersion. Very recently, researchers introduced explainable artificial intelligence (XAI) enabled methods for detecting and explaining cybersickness features. Since XAI methods can identify the dominant features causing cybersickness, we argue that this knowledge can also guide the dynamic adoption of effective cybersickness reduction strategies, unlike state-of-the-art static approaches that rely on fixed methods. This paper introduces a new dataset MazeSick and RelaxVR, an interactive XAI-guided VR cybersickness reduction framework to predict, explain, and reduce cybersickness. Specifically, we propose an innovative XAI-guided cybersickness reduction engine, which selects the most appropriate reduction technique based on XAI-provided feature importance scores from a cybersickness reduction library of different reduction techniques. We also design an interactive dialogue system powered by large language models, enabling users to engage in the VR simulation via voice commands to understand the reasoning of cybersickness and select effective reduction strategies through natural language interaction. We deployed RelaxVR on a consumer-grade VR headset (e.g., HTC VIVE Pro) and validated it through a user study on cybersickness evaluation, where participants were immersed in a custom-built VR Maze simulation. Our results demonstrate that RelaxVR effectively reduces cybersickness with minimal impact on immersion, and 94% of the users agreed that RelaxVR is highly effective for reducing cybersickness and easier to use through the dialogue engine for selecting effective reduction strategies. © 2013 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

IWM-LSTM encoder for abstractive text summarization

引用

Multimedia Tools and Applications 2025年第9期84卷 5883-5904页

作者： Gangundi, Ravindra Sridhar, Rajeswari Department of Computer Science and Engineering National Institute of Technology Tamilnadu Tiruchirappalli620015 India

Sequence-to-sequence models are fundamental building blocks for generating abstractive text summaries, which can produce precise and coherent summaries. Recently proposed, different text summarization models aimed to enhance summarization performance through the use of copying mechanisms, reinforcement learning, and multiple-level encoders. However, there has been limited research on improving the summarization output by modifying the structure of the long short-term memory (LSTM) cell. We introduced an improved version of LSTM called improved working memory LSTM (IWM-LSTM). IWM-LSTM removes the output gate and enhances the input and forget gates by incorporating cell state information into these gates. In our sequence-to-sequence model for text summarization, we replaced the LSTM encoder with a bi-directional IWM-LSTM, resulting in better summaries with minimal training time and less computational intensiveness. Additionally, we utilized Bidirectional encoder representations from transformers (BERT) embeddings to enhance the rouge score. The CNN/DailyMail dataset is used to train and test the model performance. The proposed model achieves better Recall-oriented understudy for gisting evaluation (ROUGE) scores than state-of-the-art models. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Machine learning and data analytics driven model for income tax rebate estimation: A neoteric and benign approach 4th

Machine learning and data analytics driven model for income ...

引用

4th International Conference on Computational Methods in science and Technology, ICCMST 2024

作者： Sharma, Viney Kumar, Achal Singh, Archana Kumar, Manish Department of Computer Science & Engineering Sharda University Agra India Department of Computer Science & Engineering Anand Engineering College Agra India Department of Computer Science & Engineering Chandigarh Engineering College Landran India

ISBN: (纸本)9781032911571

The provision of rebate to needy/underprivileged sections of society has been in practice since long in government organizations. The efficacy of such provisions lies in the fact that whether this rebate reaches people for whom it is intended. The biggest problem in awarding relief lies in the fact that people may not disclose their actual income. This paper conducts a study which strives for proposing a model which helps in assessing the financial status of any person given certain information about that person. This paper aims at proposing a Machine learning and Data Analytics driven model that predict the financial status of a person. The striking feature of this study is that results are applicable not only to income tax rebate problem but with minor customization, the model can be extended to work in other problems also where financial status of a person matters. © 2025 the Author(s).

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Underwater object detection based on enhanced YOLOv4 architecture

引用

Multimedia Tools and Applications 2024年第18期83卷 53759-53783页

作者： Liu, Ching-Hua Lin, Chang Hong Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taiwan

Object detection and image restoration pose significant challenges in deep learning and computer vision. These tasks are widely employed in various applications, and there is an increasing demand for specialized environments where images are prone to blur or noise, which can adversely affect subsequent results. In recent years, significant breakthroughs have been achieved in object detection performance. While some previously proposed methods prioritize high accuracy at the cost of longer inference times, others prioritize speed. Therefore, it is crucial to design an efficient network architecture that maintains both inference speed and high accuracy. This research proposes a network architecture for underwater object detection with an attention mechanism. The proposed approach differentiates itself from other methods by employing a deblurring network as a preprocessing step to restore and enhance the image quality of the underwater dataset. Additionally, in the feature extraction stage of the detection network, channel and spatial feature information are individually enhanced. These adaptive attention features are then integrated into a multi-scale feature fusion. Finally, the cross-stage local method is combined to improve the learning ability of the convolutional neural network while reducing the size of the model. Based on the experimental results, our proposed model architecture achieves leading accuracy and strikes a favorable balance in terms of model size compared to previously proposed methods. Based on our structure, the metrics of AP and AP50 reach 66.8 and 87.6, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Image reconstruction

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：