检索结果-内蒙古大学图书馆

11th IEEE International Conference on communication Systems and Network Technologies, CSNT 2022

作者： Manimegalai, T. Ravishankar, T. Nadana Kannagi, L. Kannan, K. Anitha, G. School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Data Science and Business System Srm Institute of Science and Technology Chennai Kattankulathur India Department of Computer and Communication Engineering Sri Sairam Institute of Technology Chennai India Department of Ece R.M.K. College of Engineering and Technology Puduvoyal Chennai India Department of Ece Saveetha School of Engineering Simats Chennai India

ISBN: (纸本)9781665480383

Because of the growing quantity of network traffic that is being transmitted across the network in today's modern era, network attack detection has become a necessity. The technique of data mining is extremely important in the hunt for network assaults and anomalies. These strategies aid in the selection and refinement of meaningful and relevant knowledge from enormous data sets, which is beneficial in many situations. The process of data mining aids in the categorisation of important information for Intrusion Detection Systems (IDS). The IDS provides warnings for the network traffic informing it of any foreign intrusions into the network. We show how different data mining methods may be used for intrusion detection to offer a safe network environment in the research article. The J48DT Classifier is utilised for classification in this case. Comparisons based on characteristics such as data accuracy, the discovery of valuable patterns, and the extraction of useful information between approaches are made. © 2022 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Melanoma Boundaries Detection Techniques using Artificial Intelligence 3

Melanoma Boundaries Detection Techniques using Artificial In...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Velmurugan, K. Jayasakthi Srinivasan, P. Gayathri, A. Yuvarani, S. Jeppiaar Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Sona College of Technology Department of Electronics and Communication Engineering Tamil Nadu Salem India Saveetha School of Engineering Department of Cse Tamil Nadu Chennai India Department of Computer Applications Tamil Nadu Perambalur India

ISBN: (纸本)9781665462167

Melanoma is the 6th most successive disease in the United States, with more than 9000 individuals kicking the bucket every year. Fast acknowledgment of melanoma expands an individual's life expectancy, but further developed analytic advancements are as yet required. Skin injury limit anomaly, which addresses the "B"includes in the "ABCD rule", is viewed as a critical clinical component for the early discovery of melanoma. What's more, blue-white line structure evacuation additionally further develops the identification proficiency. In this paper, an AI based location method for distinguishing skin injury limit inconsistencies is presented. The technique involves extricating the skin injury from the dermoscopic images, recognizing the skin sore line, estimating line inconsistency, and prepared famous directed learning models called SVM, RF, DT, and gathering move learning calculations to distinguish line anomaly naturally, bringing about a true choice on whether the skin sore boundary is customary or unpredictable. The method produces excellent results, with 92.6 percent accuracy, 91.3 percent sensitivity, 92.5 percent specificity, and 95.1 percent F-Score, respectively. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Building an Affordable Portable Storage Area Network (SAN) with Raspberry Pi: Design, Implementation, and Performance Evaluation

Building an Affordable Portable Storage Area Network (SAN) w...

引用

sciences and Techniques of Automatic Control and computer Engineering MI-STA, IEEE International Maghreb Meeting of the Conference on

作者： Muhammad Solihin bin Ahmad Nasser Zainab S. Attarbashi Azana Hafizah Mohd Aman Mustafa Ali Abuzaraida Faculty of Information and Communication Technology International Islamic University Malaysia Selangor Malaysia Faculty of Information Science & Technology Universiti Kebangsaan Malaysia Bangi Malaysia Computer Science Department Faculty of Information Technology Misurata University Libya

ISBN: (数字)9798350372632

ISBN: (纸本)9798350372649

In a digital landscape demanding cost-effective yet robust data storage solutions, Portable Storage Area Network (SAN) became an affordable alternative for data storage systems. A portable SAN system using the Raspberry Pi solution offers personal users the ability to easily expand their storage capacity, improve data organization and management, protect their data, and have a flexible and mobile solution. Users can share any sort of data. This project aims to address the increasing demand for efficient storage solutions by constructing a portable SAN system using the Raspberry Pi's compact size and budget-friendly hardware. The proposed SAN system enhances data organization, expands storage capacity, and offers secure, flexible data access. Targeting individual users and small to medium-sized enterprises, the project covers hardware specifications, intricate design elements, and the seamless integration of OpenMedia Vault, Raspberry Pi OS, and the iSCSI protocol. Performance, stability, and practicality of the SAN solution are visually presented through extensive testing, to prove its potential benefits for diverse storage needs.

关键词： Performance evaluation Storage area networks Protocols Memory Organizations Hardware Synchronization

来源：评论

学校读者我要写书评

暂无评论

Predictive Stress Management for Higher Education Faculty Using DCNN and LSTM Models 3

Predictive Stress Management for Higher Education Faculty Us...

引用

3rd International Conference on Integrated Circuits and communication Systems, ICICACS 2025

作者： Lakshmi, C. Jayasaradadevi, P. Chintamaneni, Vijayalakshmi Rajasekar, P. Parivallal, Santhiya Unni, Manu Vasudevan RajaRajeswari College of Engineering Department of Computer Science and Engineering Bengaluru India Visakhapatnam India Vignan Institute of Technology and Science Department of Electronics and Communication Engineering Hyderabad India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India St. Claret College Autonomous Department of Management Bangalore India

ISBN: (纸本)9798331508456

Teachers in higher education, who are already under a lot of strain from both classroom instruction and administrative duties, need to find ways to alleviate the stress that they experience so that they may be more productive and effective in their roles. The commitment of teachers and the quality of education as a whole are profoundly impacted by their well-being. Deep Convolutional Neural Networks (DCNN) and Long Short-Term Memory (LSTM) models are utilised in this research to present a predictive stress management methodology. Included in the methodology are steps for preparing data, extracting features, and training the model. In the preprocessing phase, extensive changes were made to the text data, and TF-IDF was used to effectively extract features and weight terms. With an average accuracy of 93.50%, the model outperformed standalone CNN and LSTM models thanks to its hybrid CNN-LSTM architecture. According to the results, the suggested method effectively reduces problems caused by stress in educators. This study highlights the model's ability to enhance prediction tasks, which can help institutions implement effective stress management strategies. © 2025 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

TGL_sta: Low-resource Textual Graph Learning with Semantic and Topological Awareness via LLMs 39

TGL<sub>sta</sub>: Low-resource Textual Graph Learning with ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Qin Li, Xiaowei Liu, Ziqi Fan, Xiaochen Chen, Xiaojun Pan, Shirui College of Computer Science and Software Engineering Shenzhen University China Institute for Electronics and Information Technology in Tianjin Tsinghua University China School of Information and Communication Technology Griffith University Australia

ISBN: (纸本)157735897X

Textual Graphs (TGs) present a graph-based representation of textual data and find wide applications in real-world scenarios, such as citation networks, knowledge graphs, and social networks. While the traditional “pre-train, fine-tune” framework effectively addresses tasks requiring abundant labeled data, it falls short in scenarios with limited resource or zero-shot learning capabilities, particularly in low-resource textual graph node classification. Additionally, prevalent approaches that convert text nodes into shallow or manually engineered features fail to capture the rich semantic nuances within the text. The conventional methods often neglect the fusion of semantic and topological information, resulting in suboptimal model learning. To overcome these challenges, we proposed a novel method of low-resource textual graph node classification based on large language models, i.e., Textual graph learning with semantic and topological awareness (TGLsta), which comprehensively explores the semantic information, near neighborhood information, and the topology information in textual graphs, where these components are the most important information source contained in textual graphs. Graph prompt tuning for both zero- and few-shot textual graph node classification is further introduced. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

AC-UNet: Adaptive Connection UNet for White Matter Tract Segmentation Through Neural Architecture Search

AC-UNet: Adaptive Connection UNet for White Matter Tract Seg...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yanming Zhu Ari Tchetchenian Xuefei Yin Alan Liew Yang Song Erik Meijering School of Information and Communication Technology Griffith University QLD Australia School of Computer Science and Engineering University of New South Wales NSW Australia

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

White matter tract segmentation in diffusion magnetic resonance images is crucial for brain health analysis. A prevailing method for this task is deep learning using U-shaped networks. Several variants of UNet have been proposed to improve its skip connections, resulting in segmentation improvements. In this paper, we propose a novel neural architecture search-based solution for skip connection optimization, named AC-UNet (Adaptive Connection UNet). It can automatically identify the optimal skip connections of a U-shaped network to construct the best architecture for the task. Moreover, we propose to search non-repeatable operations for each layer, which further extends the exploration of feature aggregation for better segmentation. Experimental results on the largest public tractograms dataset demonstrate the superiority of AC-UNet over mainstream UNet-based architectures.

关键词： Deep learning Image segmentation Adaptive systems Magnetic resonance White matter Task analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

HPViT: A Hybrid Visual Model with Feature Pyramid Transformer Structure

HPViT: A Hybrid Visual Model with Feature Pyramid Transforme...

引用

International Conference on Cybernetics, Robotics and Control (CRC)

作者： JiaXiong Li Hongguang Xiao Yongzhou Li Faculty of Computer and Communication Engineering Changsha University of Science & Technology Changsha China Institute of Microelectronics Chinese Academy of Sciences Beijing Chaoyang China

Recently,the fusion design of Transformer and CNN has significantly improved the efficiency and accuracy of the model. In this work, we propose a hybrid backbone network model –Hybrid Pyramid Vision Transformer(HPViT), which can be used for dense prediction tasks. Compared with the ViT image classification design, HPViT introduces the Transformer structure into CNN and also adopts a pyramid structure, which allows various dense prediction tasks, detection and segmentation tasks, etc. Compared with ViT, HPViT has the following advantages: (1) Compared with the high computational complexity and high memory usage of ViT, HPViT can not only train high-resolution images for density division to capture enough detail information, but also converge faster, occupy less memory, and reduce the computation brought by the Transformer structure through the pyramid structure; (2) HPViT has the advantages of CNNs and Transformer and can be used as a general backbone. (3) Experiments show that HPViT performs well in image classification and object detection, with a top1 accuracy rate of 81.2% on the ImageNet1k dataset. In the task of object detection, RetinaNet+HPViT finetuned on COCO for 12 rounds reached 34.3%AP, while RetinaNet+ResNet50 only had 22.9%AP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI Driven railway crack detection system using Convolutional Neural Network and IoT

AI Driven railway crack detection system using Convolutional...

引用

Advancements in Electrical, Electronics, communication, Computing and Automation (ICAECA), International Conference on

作者： M. Sudha Sri Sivahari P Guma Ali C. Ganesh S. Umamaheswari R. Saranya Electronics and Communication Engineering SNS College of Engineering Coimbatore India Computer Science and Engineering Saveetha School of Enginerring Saveetha Institute of Medical and Technical Sciences Chennai India Computer and Communication Engineering Sri Eshwar College of Engineering Coimbatore India Electronics and Communication Engineering Kumaraguru College of Technology Coimbatore India

ISBN: (数字)9798331525439

ISBN: (纸本)9798331525446

The Railway Track fractures identification Using AI with IoT project aims to increase railway safety by automating the identification of fractures in railway tracks using artificial intelligence (AI) and Internet of Things (IoT) technology. Even minor cracks in railway tracks, which are crucial components of the transportation system, can cause major accidents if they not immediately identified also repaired. Conventional manual assessing technique are expensive, time-consuming, and error-prone. Convolutional Neural Networks, a kind deep learning model, will used in this study to automatically identify cracks in photos of railroad tracks. The model trained on a dataset of track photographs in order to discern parts are defective (cracked) and non-defective (intact). Once trained, The CNN model is employed to analyze images captured by cameras mounted on trains or inspection vehicles as part of a real-time monitoring system driven by the Internet of Things. Every time a fracture is discovered, the system sends the information to the Blynk IoT platform, notifying and alerting maintenance personnel. Additionally, an LCD display and a buzzer alarm are activated in the field to alert technicians to the detected defect. By combining AI and IoT, the initiative aims to reduce overall maintenance costs, improve safety through early fault detection, and speed up the track inspection process. By providing a more automated, accurate, and efficient method of tracking the present state of railroad lines, the system ultimately increases the harmlessness and reliability of railway transit.

关键词： Transportation Railway safety Inspection Rail transportation Liquid crystal displays Real-time systems Maintenance Safety Convolutional neural networks Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Implementing LoRa MIMO System for Internet of Things

arXiv

引用

arXiv 2025年

作者： Ghosh, Atonu Chandan, Sharath Misra, Sudip Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur721302 India Department of Electronics and Communication Engineering Sona College of Technology Tamil Nadu Salem636005 India

Bandwidth constraints limit LoRa implementations. Contemporary IoT applications require higher throughput than that provided by LoRa. This work introduces a LoRa Multiple Input Multiple Output (MIMO) system and a spatial multiplexing algorithm to address LoRa’s bandwidth limitation. The transceivers in the proposed approach modulate the signals on distinct frequencies of the same LoRa band. A Frequency Division Multiplexing (FDM) method is used at the transmitters to provide a wider MIMO channel. Unlike conventional Orthogonal Frequency Division Multiplexing (OFDM) techniques, this work exploits the orthogonality of the LoRa signals facilitated by its proprietary Chirp Spread Spectrum (CSS) modulation to perform an OFDM in the proposed LoRa MIMO system. By varying the Spreading Factor (SF) and bandwidth of LoRa signals, orthogonal signals can transmit on the same frequency irrespective of the FDM. Even though the channel correlation is minimal for different spreading factors and bandwidths, different Carrier Frequencies (CF) ensure the signals do not overlap and provide additional degrees of freedom. This work assesses the proposed model’s performance and conducts an extensive analysis to provide an overview of resources consumed by the proposed system. Finally, this work provides the detailed results of a thorough evaluation of the model on test hardware. © 2025, CC BY-NC-ND.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

DiffusionPCR: Diffusion Models for Robust Multi-Step Point Cloud Registration

arXiv

引用

arXiv 2023年

作者： Chen, Zhi Ren, Yufan Zhang, Tong Dang, Zheng Tao, Wenbing Süsstrunk, Sabine Salzmann, Mathieu Huazhong University of Science and Technology China School of Computer and Communication Sciences EPFL Switzerland Tuke Research China

Point Cloud Registration (PCR) estimates the relative rigid transformation between two point clouds. We propose formulating PCR as a denoising diffusion probabilistic process, mapping noisy transformations to the ground truth. However, using diffusion models for PCR has nontrivial challenges, such as adapting a generative model to a discriminative task and leveraging the estimated nonlinear transformation from the previous step. Instead of training a diffusion model to directly map pure noise to ground truth, we map the predictions of an off-the-shelf PCR model to ground truth. The predictions of off-the-shelf models are often imperfect, especially in challenging cases where the two points clouds have low overlap, and thus could be seen as noisy versions of the real rigid transformation. In addition, we transform the rotation matrix into a spherical linear space for interpolation between samples in the forward process, and convert rigid transformations into auxiliary information to implicitly exploit last-step estimations in the reverse process. As a result, conditioned on time step, the denoising model adapts to the increasing accuracy across steps and refines registrations. Our extensive experiments showcase the effectiveness of our DiffusionPCR, yielding state-of-the-art registration recall rates (95.3%/81.6%) on 3DMatch and 3DLoMatch. Copyright © 2023, The Authors. All rights reserved.

关键词： Linear transformations

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：