检索结果-内蒙古大学图书馆

4th International Conference on computer science and Blockchain, CCSB 2024

作者： Wang, Jiao Zhou, Huabing College of Computer Science and Engineering Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798350356502

Infrared and visible light image fusion has gained significant attention due to its advantages in challenging environments. While visible light cameras capture rich texture details under normal conditions, they perform poorly in situations like nighttime or smoke. Infrared sensors, however, can effectively highlight key targets even in extreme conditions by detecting thermal radiation. Most existing fusion methods assume perfectly aligned source images, overlooking geometric distortions and pixel shifts caused by varying camera parameters. To address this, we propose a unified framework for infrared and visible light image registration and fusion. This framework effectively handles misaligned images and introduces semantic constraints to enhance the performance in advanced vision tasks. Additionally, a cross-attention-based feature fusion module is integrated into the network. Experimental results show that our method not only improves fusion quality under misalignment but also enhances the performance of subsequent vision tasks. © 2024 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection in Simulated Military Environment Using Machine Learning and Blockchain

Network Intrusion Detection in Simulated Military Environmen...

引用

2024 International Conference on Smart Systems for Electrical, Electronics, Communication and computer engineering, ICSSEEC 2024

作者： Vijayalakshmi, S. Yellamilli, Rohan Shobikaa, R. Subasree, V. Vidya, R. Keerthanaporkodi, S. PSG College of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350378177

Network Intrusion Detection Systems are critical in bolstering an organization's security infrastructure. The goal of our paper is to design and build a specialized intrusion detection system for simulated military scenarios. The solution classifies network accesses using machine learning techniques and seamlessly integrates the Ethereum blockchain for secure anomalous access record-keeping and auditing. The machine learning component classifies the records as normal or anomalous using the ensemble learning technique, which is the random forest classifier. Feature selection techniques like Variance Threshold, Spearman's correlation coefficient, Pearson's correlation coefficient, Mutual Information and Chi square tests were used to improve the accuracy of the model and reduce dimensionality. The final accuracy of the model was brought to 96.69%. It then sends the records to the blockchain environment for storage. To ensure data integrity and transparency, anomalous access events will be time-stamped, hashed using IPFS, and published to the blockchain. By providing a hash value and a unique id as input, the user will be able to add new anomalous entries. Furthermore, the user will be able to examine the hashed anomalous data for each csv file using the proper id. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Proactive Caching at the Wireless Edge:A Novel Predictive User Popularity-Aware Approach

引用

computer Modeling in engineering & sciences 2024年第8期140卷 1997-2017页

作者： Yunye Wan Peng Chen Yunni Xia Yong Ma Dongge Zhu Xu Wang Hui Liu Weiling Li Xianhua Niu Lei Xu Yumin Dong College of Computer Science Chongqing UniversityChongqing400044China School of Computer and Software Engineering Xihua UniversityChengdu610039China School of Computer and Information Engineering Jiangxi Normal UniversityNanchang330022China Electric Power Research Institute of State Grid Ningxia Electric Power Co. Ltd.Yinchuan750002China College of Mechanical and Vehicle Engineering Chongqing UniversityChongqing400030China School of Computer Science and Technology Beijing Institute of TechnologyBeijing100083China School of Computer Science and Technology Dongguan University of TechnologyDongguan523808China School of Emergency Management Xihua UniversityChengdu610039China College of Computer and Information Science Chongqing Normal UniversityChongqing401331China

Mobile Edge Computing(MEC)is a promising technology that provides on-demand computing and efficient storage services as close to end users as *** an MEC environment,servers are deployed closer to mobile terminals to exploit storage infrastructure,improve content delivery efficiency,and enhance user ***,due to the limited capacity of edge servers,it remains a significant challenge to meet the changing,time-varying,and customized needs for highly diversified content of ***,techniques for caching content at the edge are becoming popular for addressing the above *** is capable of filling the communication gap between the users and content providers while relieving pressure on remote cloud ***,existing static caching strategies are still inefficient in handling the dynamics of the time-varying popularity of content and meeting users’demands for highly diversified entity *** address this challenge,we introduce a novel method for content caching over MEC,i.e.,*** synthesizes a content popularity prediction model,which takes users’stay time and their request traces as inputs,and a deep reinforcement learning model for yielding dynamic caching *** results demonstrate that PRIME,when tested upon the MovieLens 1M dataset for user request patterns and the Shanghai Telecom dataset for user mobility,outperforms its peers in terms of cache hit rates,transmission latency,and system cost.

关键词： Mobile edge computing content caching system average cost deep reinforcement learning collaborative mechanism

来源：评论

学校读者我要写书评

暂无评论

Advancements in Liver Tumor Detection:A Comprehensive Review of Various Deep Learning Models

引用

computer Modeling in engineering & sciences 2025年第1期142卷 91-122页

作者： Shanmugasundaram Hariharan D.Anandan Murugaperumal Krishnamoorthy Vinay Kukreja Nitin Goyal Shih-Yu Chen Deptartment of Artificial Intelligence and Data Science Vardhaman College of EngineeringHyderabad501218India Deptartment of CSE V.S.B College of EngineeringKarur639111India Deptartment of Electrical and Electronics Engineering Vardhaman College of EngineeringHyderabad501218India Centre for Research Impact&Outcome Chitkara UniversityRajpura140401PunjabIndia Department of Computer Science and Engineering School of Engineering and TechnologyCentral University of HaryanaMahendergarh123031HaryanaIndia Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin64002Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and TechnologyYunlin64002Taiwan

Liver cancer remains a leading cause of mortality worldwide,and precise diagnostic tools are essential for effective treatment *** Tumors(LTs)vary significantly in size,shape,and location,and can present with tissues of similar intensities,making automatically segmenting and classifying LTs from abdominal tomography images crucial and *** review examines recent advancements in Liver Segmentation(LS)and Tumor Segmentation(TS)algorithms,highlighting their strengths and limitations regarding precision,automation,and *** metrics are utilized to assess key detection algorithms and analytical methods,emphasizing their effectiveness and relevance in clinical *** review also addresses ongoing challenges in liver tumor segmentation and identification,such as managing high variability in patient data and ensuring robustness across different imaging *** suggests directions for future research,with insights into technological advancements that can enhance surgical planning and diagnostic accuracy by comparing popular *** paper contributes to a comprehensive understanding of current liver tumor detection techniques,provides a roadmap for future innovations,and improves diagnostic and therapeutic outcomes for liver cancer by integrating recent progress with remaining challenges.

关键词： Liver tumor detection liver tumor segmentation image processing liver tumor diagnosis feature extraction tumor classification deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Video Object Segmentation via Weak User Interaction and Temporal Modulation

引用

Chinese Journal of Electronics 2023年第3期32卷 507-518页

作者： FAN Jiaqing ZHANG Kaihua ZHAO Yaqian LIU Qingshan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics College of Computer and Software Nanjing University of Information Science and Technology Engineering Research Center of Digital Forensics Ministry of Education Inspur Suzhou Intelligent Technology Corporation

In unsupervised video object segmentation(UVOS), the whole video might segment the wrong target due to the lack of initial prior information. Also, in semi-supervised video object segmentation(SVOS), the initial video frame with a fine-grained pixel-level mask is essential to good segmentation accuracy. It is expensive and laborious to provide the accurate pixel-level masks for each training sequence. To address this issue, We present a weak user interactive UVOS approach guided by a simple human-made rectangle annotation in the initial frame. We first interactively draw the region of interest by a rectangle, and then we leverage the mask RCNN(region-based convolutional neural networks) method to generate a set of coarse reference labels for subsequent mask propagations. To establish the temporal correspondence between the coherent frames, we further design two novel temporal modulation modules to enhance the target representations. We compute the earth mover's distance(EMD)-based similarity between coherent frames to mine the co-occurrent objects in the two images, which is used to modulate the target representation to highlight the foreground target. We design a cross-squeeze temporal modulation module to emphasize the co-occurrent features across frames, which further helps to enhance the foreground target representation. We augment the temporally modulated representations with the original representation and obtain the compositive spatio-temporal information, producing a more accurate video object segmentation(VOS) model. The experimental results on both UVOS and SVOS datasets including Davis2016,FBMS, Youtube-VOS, and Davis2017, show that our method yields favorable accuracy and complexity. The related code is available.

关键词： Earth Training Codes Annotations Modulation Object segmentation Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Deep Attribute Graph Clustering Based on Dual Information Comparison Strategy 5

Deep Attribute Graph Clustering Based on Dual Information Co...

引用

5th International Conference on Artificial Intelligence and computer engineering, ICAICE 2024

作者： Tan, Shuqiu Zhang, Lei Liu, Yahui College of Computer Science and Engineering Chongqing University of Technology Chongqing China

ISBN: (纸本)9798331528911

Existing deep attribute graph clustering is mainly divided into two stages: upstream graph representation learning and downstream clustering task. The upstream uses graph representation learning to obtain node embeddings, and the downstream uses the K-Means algorithm to cluster the node embeddings obtained by the upstream learning. Although graph representation learning based on contrastive learning has received great attention and achieved good results, there are still some problems. (1) How to use enhancement technology to generate an effective contrast view? (2) How to design an effective contrastive learning mechanism? (3) How to integrate upstream graph contrastive learning and downstream clustering tasks into an end-to-end framework? To solve the above problems, we propose a deep attribute graph clustering algorithm with a composite graph enhancement strategy and a dual information contrast strategy (DAGC-DICS). First, we obtain the augmented graph of the original attribute graph based on the composite graph enhancement strategy, and propose a dual information contrast strategy that can maximize the consistency of nodes in the contrast view. Finally, we design a multi-distribution self-supervision strategy to integrate graph representation learning and clustering tasks into an end-to-end framework. Extensive experiments are conducted on three benchmark datasets to verify the superiority and effectiveness of our method. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Electronic Health Records Reimagined: A Blockchain Approach Combined with IPFS and Brain Tumor Detection Through Machine Learning

Electronic Health Records Reimagined: A Blockchain Approach ...

引用

2024 International Conference on Smart Systems for Electrical, Electronics, Communication and computer engineering, ICSSEEC 2024

作者： Santhi, V. Santhosh, Diyaa Sachitha, C. Samyuktha, N. Ganesh Raja, D. Arun Maran, M. PSG College of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350378177

Our innovative Electronic Health Records (EHR) system represents a paradigm shift in healthcare, seamlessly integrating blockchain, IPFS, and machine learning technologies to address longstanding challenges and propel the industry forward. At its core, our platform ensures data integrity, security, and accessibility through blockchain's decentralized ledger, safeguarding patient information while enabling transparent and immutable records. Leveraging IPFS for file storage enhances efficiency and resilience, allowing medical reports and documents to be securely stored and accessed from anywhere in the world. Machine learning augments our system by offering predictive analytics, empowering healthcare professionals with actionable insights derived from vast datasets. By analyzing trends and patterns, our ML algorithms facilitate early detection of diseases, personalized treatment plans, and proactive healthcare management. This predictive capability revolutionizes patient care, shifting the focus from reactive to preventive medicine. In essence, our EHR solution offers significant benefits for healthcare. It allows healthcare providers to streamline workflows and improve patient outcomes ultimately leading to a more effective, transparent, and patient-centric healthcare ecosystem. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Polyp Segmentation Achieved Through Multi-Scale Feature Fusion Based on Attention Mechanism 11

Polyp Segmentation Achieved Through Multi-Scale Feature Fusi...

引用

11th IEEE International Conference on Behavioural and Social Computing, BESC 2024

作者： Xia, Mingze Zhang, Liguo Yin, Guisheng Dong, Yuxin College Of Computer Science And Technology Harbin Engineering University Harbin China

ISBN: (纸本)9798331531904

Given the high prevalence of colon diseases, it is crucial to utilize computer vision technology for precise polyp segmentation during colonoscopy. However, manual detection becomes increasingly challenging due to the similarity in texture and color between polyp tissue and surrounding normal tissue, leading to higher risks of false positives and missed detections. This study introduces a novel network called CabaNet that prioritizes boundary awareness through coordinate attention. The network consists of four main modules: an encoder utilizing pyramid vision transformer PVT, a cascade part decoder employing Parallel hierarchical aggregation decoder (PHAD) for feature fusion and obtaining a comprehensive semantic global map. Additionally, the refinement pyramid module (RP) enhances feature fusion through a lightweight multi-scale learning strategy. The reverse coordinate attention module (Coo-A) combines features from PHAD and RP to achieve precise and complete edge prediction mapping. Experimental results on five commonly used datasets demonstrate significant improvement in image segmentation accuracy by our proposed model. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Driven Multilingual System for Recognition and Categorization of Medicinal Plants with Extensive Elucidation 9

Deep Learning Driven Multilingual System for Recognition and...

引用

9th International Conference on science, technology, engineering and Mathematics, ICONSTEM 2024

作者： Azhaguramyaa, V.R. Janet, J. Hariharan, A. Kamaleshwaran, A. Albert Joseph, A. Computer Science And Engineering Sri Krishna College of Engineering And Technology Tamil Nadu Coimbatore India Sri Krishna College of Engineering And Technology Dept. of Computer Science And Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350365092

Medicinal plant use is widespread throughout many cultures and geographical areas, frequently entwined with customs and knowledge. The use of technology, especially deep learning, to improve the identification and classification of these plants has gained popularity in recent years. This research introduces a new multilingual system with deep learning capabilities that can identify and classify medicinal plants with a great deal of explanation. The term 'deep learning-driven multilingual system for recognition and categorization of medicinal plants with extensive elucidation' describes an advanced technology that carries out several tasks by utilizing deep learning, one of the most advanced machine learning techniques. Based on pictures, the system can recognize and classify a variety of therapeutic plants. Because users may communicate with the system, ask questions, and get information in their native tongue, it is usable by a wide variety of people across the globe. Apart from identification and classification, the method offers comprehensive clarifications or in-depth accounts of the recognized therapeutic herbs. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Clothing Size Prediction in E-Commerce: A Machine Learning Approach for Improved Customer Experience

Enhancing Clothing Size Prediction in E-Commerce: A Machine ...

引用

2024 International Conference on Smart Systems for Electrical, Electronics, Communication and computer engineering, ICSSEEC 2024

作者： Prakash, J. Nashita, V. Shivani Sri, S. Shri Shivathmika, V. Sivesh, K. Ashwin, V. PSG College of Technology Department Computer Science & Engineering Tamilnadu India

ISBN: (数字)9798350378177

ISBN: (纸本)9798350378177

Clothing and apparel companies face high rates of returns due to customers ordering incorrect sizes. This can be frustrating for customers and is a waste of time and resources for the company, as they have to process the return and potentially restock the item. Uncertainty about fit also deters online purchases, impacting sales. Most currently available systems can predict the size based on all measurements provided by the customer, but that is not always feasible. This brings a need for the integration of Machine Learning to solve this problem of predicting sizes and provide better results with increased accuracy. This paper presents a thorough evaluation of various ML models for size prediction, namely Logistic Regression, K-Nearest Neighbors (KNN), Random Forest, and Decision Tree models. The results indicate that our model showcases considerable promise for enhancing sizing accuracy, with the Random Forest and Decision Tree models achieving noteworthy accuracy scores of 0.99 in shirt size prediction. In the realm of pant size prediction, these models maintain their effectiveness, with an accuracy score of 0.89 and 0.82, respectively. This underscores the potential of our ML model to alleviate sizing woes in the clothing retail industry. © 2024 IEEE.

关键词： Garment industry

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：