检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ai, Qingyao Zhan, Jingtao Liu, Yiqun Dept. of Computer Science and Technology Tsinghua University Beijing China

The chapter discusses the foundational impact of modern generative AI models on information access (IA) systems. In contrast to traditional AI, the large-scale training and superior data modeling of generative AI models enable them to produce high-quality, human-like responses, which brings brand new opportunities for the development of IA paradigms. In this chapter, we identify and introduce two of them in details, i.e., information generation and information synthesis. Information generation allows AI to create tailored content addressing user needs directly, enhancing user experience with immediate, relevant outputs. Information synthesis leverages the ability of generative AI to integrate and reorganize existing information, providing grounded responses and mitigating issues like model hallucination, which is particularly valuable in scenarios requiring precision and external knowledge. This chapter delves into the foundational aspects of generative models, including architecture, scaling, and training, and discusses their applications in multi-modal scenarios. Additionally, it examines the retrieval-augmented generation paradigm and other methods for corpus modeling and understanding, demonstrating how generative AI can enhance information access systems. It also summarizes potential challenges and fruitful directions for future studies. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Automated Skin Cancer Classification and Detection Using Convolutional Neural Networks and Dermoscopy Images

引用

Procedia computer Science 2025年 252卷 108-117页

作者： Umme Sara Utpol Kanti Das Juel Sikder Sudipta Roy Chowdhury Dept. of Computer Science and Engineering National Institute of Textile Engineering and Research Savar Dhaka Bangladesh Dept. of Computer Science and Engineering Rangamati Science and Technology University Rangamati Sadar-4500 Rangamati Bangladesh

The uncontrolled growth of skin cells in the epidermis producing the creation of a mass termed a tumor is a dangerous condition known as skin cancer. Current developments in deep learning artificial intelligence have greatly improved image-based diagnosis. In this study, we included a Skin Lesion Cancer feature extractor Convolutional Neural Network (SLC-CNN) model, which is used for both classification with the SVM classifier and segmentation with XGBoost for skin cancer. In our proposed system, a test image of skin cancer is taken and pre-processed for both classification and segmentation purposes. After applying pre-processing, the test image features are extracted using the SLC-CNN feature extractor, which features are used in SVM to classify the types of skin cancer (Benign and Malignant), and based on the classification result, a trained XGBoost model is called to segment the cancer region. We have tested our system using the dermoscopy image collection from the International Skin Imaging Collaboration (ISIC) and built it in Google Colab to best use the GPU. Our suggested approach has gained a segmentation accuracy of 95.25% and a classification accuracy of 99.6%.

关键词： Skin Lesion Cancer-CNN (SLC-CNN) Skin Cancer Deep Learning Classification Segmentation

来源：评论

学校读者我要写书评

暂无评论

Building Resilient CICD Pipelines: A DevOps Security-First Framework

Building Resilient CICD Pipelines: A DevOps Security-First F...

引用

Computational, Communication and Information technology (ICCCIT), International Conference on

作者： Rashmi Ashtagi Chirag Belani Prasanna Bhalerao Yash Bhalerao Atharva Chawle Dept. of Computer Engineering Vishwakarma Institute of Technology Pune India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

Continuous Integration and Continuous Deployment are now integrated in automated systems that enhance code stability, and accelerate the deployment process as well as improving monitoring of the whole system in the software development field. This document deals with setting up of a strong CI/CD process involving AWS cloud services and DevOps. The infrastructure is built with the help of Terraform which ensures the scalability and repeatability applying the Infrastructure as Code (IaC) approach. A safe Virtual Private Cloud (VPC) is designed consisting of public and private subnets, load balancing for traffic distribution, and CloudFront CDN to improve geographical distribution. Jenkins is used in CI process to perform disk analysis, OWASP and Trivy vulnerability scanning, and making Docker images. The CD phase use ArgoCD for updates on Kubernetes and integrates Monitoring and observability using Prometheus and Grafana. Notifications are produced to JIRA and email communication for improvement. With the help of the offered cloud services and DevOps tool it is possible to consolidate the SDLC and bring effects in code safety, testing and utilization. This document also provides an overview of methods, instruments, and outcomes, demonstrating how the CI/CD automation influences the development and operation positively.

关键词： Cloud computing DevOps Codes Scalability Pipelines Continuous integration Security Observability Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

GlobalLearn: An Efficient Multilingual Textual Summary for Education Videos

GlobalLearn: An Efficient Multilingual Textual Summary for E...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Pratham R Shetty Prateek M Anirudh Krishna R Ranjive M. Farida Begum Dept. Computer Science and Technology PES University Bengaluru India

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

Educational videos have become a preferred medium for learning, offering advantages such as self-paced study, the ability to revisit concepts, and a distraction-free environment. However, the effective- ness of such videos can be amplified through concise, multilingual textual summaries. This paper introduces GlobalLearn, an AI powered educational video to text summarization application that integrates speech recognition, optical character recognition, and NLP-driven large language models(LLMs) to extract and summarize key concepts from educational videos. By integrating audio and visual transcripts, time-stamped summaries, and multilingual capabilities, GlobalLearn ensures accessibility for diverse global audiences. This user-centric approach not only supports efficient learning and revision, but also bridges linguistic barriers, fostering an inclusive educational ecosystem. The paper explores GlobalLearn’s design and technical architecture, and core functionalities to outline its potential impact on modern education.

关键词： Visualization Runtime environment Translation Optical character recognition Education Knowledge based systems Text summarization Speech recognition Multilingual Videos

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Coupling Characteristics of Wheel Polygon and Rail Corrugation in High-Speed Railways 3

Investigation of the Coupling Characteristics of Wheel Polyg...

引用

3rd International Conference on Rail Transportation, ICRT 2024

作者： Gao, Wanlin Yin, Yue Bu, Han Wang, Shiqi Cui, Xiaolu Dept. of Computer Science and Technology Chongqing Jiaotong Univ. Chongqing China Dept. of Rail Transit Chongqing Vocational College of Transportation Research State Univ. Chongqing China Dept. of Mechanical and Electrical Engineering and Vehicle Engineering Chongqing Jiaotong Univ. Chongqing China

ISBN: (数字)9780784485941

ISBN: (纸本)9780784485941

Wheel polygon and rail corrugation are common types of periodic wear in the wheel-rail system. This research investigates their interaction in high-speed railways using friction coupling vibration theory. A finite element model of the wheel-rail system is developed to study friction coupling vibrations in straight sections of long slopes. The study identifies the causes of 22nd-order wheel polygonization and rail corrugation with a 130 mm wavelength and creates wear models for both. The effects of their interaction on friction coupling vibrations are analyzed, with an emphasis on frequency-dependent coupling characteristics. Results indicate that saturated wheel-rail creep forces in long slopes easily trigger friction coupling vibrations, which are worsened by both wheel polygon and rail corrugation, with wheel polygon having a more pronounced impact. These findings offer insights for improving wheel-rail system design and maintenance in high-speed railways. Future research should aim to develop advanced techniques to mitigate the negative effects of wheel polygon and rail corrugation on system performance and safety. © ASCE.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Assessment of Super-Resolution Ultrasound Imaging Using the Erythrocytes Through Comparison with Micro-CT

Assessment of Super-Resolution Ultrasound Imaging Using the ...

引用

Medical Imaging 2025: Ultrasonic Imaging and Tomography

作者： Hansen, Lauge Naur Ráth, Andre Amin-Naji, Mostafa McDermott, Amy Sørensen, Charlotte Mehlin Kjer, Hans-Martin Gundlach, Carsten Dahl, Anders Bjorholm Jensen, Jørgen Arendt Center for Fast Ultrasound Dept. of Health Technology Technical University of Denmark Kgs. Lyngby Denmark Dept. of Applied Mathematics and Computer Science Technical University of Denmark Kgs. Lyngby Denmark Dept. of Physics Technical University of Denmark Kgs. Lyngby Denmark Dept. of Biomedical Sciences University of Copenhagen Copenhagen Denmark

ISBN: (纸本)9781510686021

This work presents a dual-sample validation study of Super-Resolution Ultrasound imaging using the Erythrocytes (SURE) and state-of-the-art laboratory micro-CT data of rat kidneys. The study hypothesizes that SURE images reliably depict cortical radial blood vessels in rat kidneys, assessed by comparing the depicted blood vessels and vessel diameter estimates from registered micro-CT data. Previous qualitative comparisons between SURE images and micro-CT were either made at an insufficient micro-CT voxel size or in a small region of a rat kidney cortex scanned at a higher resolution. Here, micro-CT data of entire rat kidneys scanned at a voxel size of 5 µm is compared to images from the SURE pipeline with peak detection done after blood flow separation. The separation is achieved using Hankel singular value decomposition before peak detection (SURE-Hankel). The analysis shows a consistent depiction of cortical radial vessels in the entire rat kidney using SURE-Hankel and that these blood vessels have estimated diameters around 50 µm to 100 µm. However, discrepancies in the registered images highlight the need for more accurate CT-to-ultrasound image registration techniques. © 2025 SPIE.

关键词： Echocardiography

来源：评论

学校读者我要写书评

暂无评论

LexChain: A Blockchain-based Solution to Safeguard Electronic Evidence in Legal Systems

LexChain: A Blockchain-based Solution to Safeguard Electroni...

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： Neha Adhikari Manan Chhajed Divya Raichura Prasenjit Bhavathankar Dept. of Computer Science and Engineering(AIML) Sardar Patel Institute of Technology Mumbai India Dept. of Computer Engineering(AIML) Sardar Patel Institute of Technology Mumbai India

ISBN: (数字)9798331509934

ISBN: (纸本)9798331509941

The adoption of digitization has revolutionized data storage technology, resulting in improved accessibility, efficiency, collaboration, and reduced storage costs. A significant impact of this can be seen in legal systems such as case management tools and e-evidence in litigation. However, ensuring the integrity and authenticity of digital evidence poses major challenges. Forensic evidence is the most sensitive and tangible part of legal investigations and traditional methods for storing physical records and standard digital practices for document storage and forensic evidence preservation are at risk of manipulation and unauthorized access. Such issues raise concerns about the integrity of evidence in legal cases. Beyond the security concerns, manual processes such as storage, management and authentication of evidence are expensive and suffer from delays. The proposed system addresses these challenges using blockchain technology to build a robust system that securely stores all legal documents and forensic evidence. Utilizing a blockchain framework such as Ethereum can boost the security of the legal system while also automating the legal process and ensuring compliance with data privacy regulations through smart contracts, thus improving efficiency, reducing costs, and ensuring reliability and transparency.

关键词： Costs Digital forensics Storage management Smart contracts Memory Regulation Blockchains Safety Reliability Standards

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Location-Based XML Indexing in Real-Time Wireless Data Broadcasting for IoT Devices

Energy Efficient Location-Based XML Indexing in Real-Time Wi...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Goel, Vikas Sharma, Ashutosh Singh, Mayank Goyal, Amit Kumar Jain, Vikas Kiet Group of Institutions Dept. of It UP Ghaziabad201206 India Ims University Campus Dept. of It UP Ghaziabad201009 India Gl Bajaj Institute of Technology Dept. of Cse Gr. Noida India Chandigarh University Dept. of Cse Punjab 140413 India C.C.S. University Campus Dept. of Computer Application Scriet Meerut India

ISBN: (纸本)9798331508685

The Internet of Things (IoT) is fast revolutionizing a number of sectors by performing real-time data collection and analysis. Effective data broadcasting protocols become increasingly important as IoT devices. Specifically designed for Internet of Things applications, this paper proposes a comprehensive framework for location-based XML indexing in real-time wireless data broadcasting. To enable effective geographic-based XML data searching, we propose a spatial XML indexing technique. Our proposed broadcasting strategy maximizes network use also. The suggested solution ensures energy efficiency of various IoT devices while addressing the issues of scalability and changing data environments. © 2025 IEEE.

关键词： Energy Efficient IoT Location-Based Search (LBS) Wireless Data Broadcasting XML Indexing

来源：评论

学校读者我要写书评

暂无评论

CapT: A Hierarchical Capsule Representation Learning Approach for Class Continual Learning

CapT: A Hierarchical Capsule Representation Learning Approac...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ankita Chatterjee Saransh Patel Jayanta Mukhopadhyay Partha Pratim Das Dept. of Computer Science and Engg. Indian Institute of Technology Kharagpur Kharagpur India Dept. of Computer Science Ashoka University Sonipat India

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Human brain is adept.at continually acquiring new skills through structured patterns without forgetting previous learning, a feat that neural networks struggle to emulate. When these networks are exposed to new information, they tend to experience a significant decline in performance on tasks they were previously trained on, a phenomenon known as catastrophic forgetting. We introduce a novel approach to representation learning that utilizes a hierarchical structure. In our proposed method, individual classes are encapsulated and dynamically routed to maintain relationships between similar classes at different levels. Our model develops into a tree-like architecture, with each phase adding nodes that contain capsules of semantically related classes. During training, only the nodes representing new classes and their children are trained, while the rest of the tree remains frozen. This effectively preserves the representations of older classes.

关键词： Training Representation learning Continuing education Signal processing Routing Acoustics Speech processing Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Bone Fracture Classification in X-ray Images: A Deep Learning Approach Leveraging Transfer Learning

Bone Fracture Classification in X-ray Images: A Deep Learnin...

引用

International Conference on Electrical, computer and Communication Engineering (ECCE)

作者： Md. Sabbir Ahammed Md. Musfiqur Rahman Mridha Md. Taufiq Khan Md. Jamil Chaudhary Md. Fatin Nibbrash Nakib Sakib Imtiaz Md. Ashikuzzaman Ashik Dept. of Computer Science & Engineering Varendra University Rajshahi Bangladesh Dept. of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Bone fracture is a very common medical issue faced by medical practitioners, and fracture detection is quite crucial for treatment. Till now, the most popular diagnosing method for bone fracture is X-ray imaging. However, in many cases, an X-ray image of a fractured bone is prone to human error. Advancements in artificial intelligence (AI) have demonstrated the potential to achieve high accuracy in tasks like X-ray image classification of fractured bone. In this work, we have incorporated a deep learning-based approach to facilitate the diagnosis of bone fracture. We have utilized different pre-trained state-of-the-art (SOTA) convolutional neural networks (CNN), namely, DenseNet, VGG, ResNet, Xception, and EfficientNet as feature extractors, to extract higher-level feature space representations of X-ray images. We have incorporated multiple classifiers, namely Logistic Regression, Random Forest, Linear Regression, XGBoost, and a custom feed-forward network (FFN) to discriminate among the higher-level representations extracted by the aforementioned pre-trained feature extractors. Among the several feature extractor and classifier combinations we have experimented with, DenseNet169 combined with the custom FFN produced the best results, reporting an overall accuracy of 99.48%, Receiver Operating Characteristic Area Under the Curve (ROC-AUC) score of 99.99%, precision of 99.48%, recall of 99.48%, and F1 score of 99.48%. The results demonstrate that combining an appropriate pretrained SOTA CNN model and a classifier can achieve high classification accuracy in the bone-fracture X-ray image classification task. Such a method previews a promising avenue in helping medical practitioners to achieve better diagnostic performance with patient benefit.

关键词： Deep learning Accuracy Transfer learning Feature extraction Bones Convolutional neural networks X-ray imaging Medical diagnostic imaging Random forests Image classification

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：