检索结果-内蒙古大学图书馆

3rd International Conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Kailasam, Khushi Singh, Jaswant Gopika, G.S. Sreekrishna, M. Supriya, S. Sathyabama Institute of Science and Technology Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350396157

Fabric defect detection plays a crucial role in the textile manufacturing industry's quality control process since it guarantees that customers will receive perfect products. Deep Learning (DL) models have demonstrated a great deal of promise in recent years for accurately identifying fabric defects. The proposed fabric defect identification method combines the best features of two architectures: You Only Look Once (YOLOv4) and Region-based Convolutional Neural Network (R-CNN). While YOLOv4 offers quicker and more effective detection, R-CNN generates region recommendations that allow accurate localization of fabric defects. There are two stages in the proposed system. Initially, region proposals are detected using the R-CNN feature extractor and then a convolutional neural network is used for defect classification. YOLOv4 is used for performing object detection in the second step, where the flaws are concurrently classified and localized. The tests carried out on a fabric defect dataset show that the proposed method outperforms the R-CNN and YOLOv4 models separately. The proposed system is appropriate for real-Time fabric flaw detection applications in a variety of sectors due to its high detection accuracy and quick processing time. This study demonstrates how well R-CNN and YOLOv4 together work for fabric flaw detection, providing hope for future developments in the area. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Model-Driven Engineering for Embedded Systems with Non-Functional Properties Analysis Integration: A Review 16

Model-Driven Engineering for Embedded Systems with Non-Funct...

引用

16th International Conference on Developments in eSystems Engineering, DeSE 2023

作者： Kadhim, Omar Jawad Nafea, Ahmed Adil Al-Thiabi, Mohamed Kareem Sallibi, Anas D. Modern Uuniversity for Business & Science Dept. Computer Science Beirut Lebanon College of Computer Science and Information Technology University of Anbar Dept. Artificail Inteligence Ramadi Iraq College of Computer Science and Information Technology University of Anbar Dept. Computer Science Ramadi Iraq College of Computer and Information Technology University of Anbar Department of Computer Sciences Ramadi Iraq

ISBN: (纸本)9798350381344

Model-Driven Engineering (MDE) has revolutionized the realm of embedded system development, providing an avenue for systematic, high-level system design, and automatic code generation. This paper delves into an enhanced approach to MDE, emphasizing the integration of nonfunctional properties analysis. Such an integration ensures that embedded systems not only perform their primary functions, but also adhere to crucial parameters like security, reliability, and efficiency. Through a comprehensive exploration of current tools and technologies, we identify gaps and opportunities in the current landscape. We further discuss the challenges inherent in marrying non-functional attributes with traditional system design and propose innovative solutions to navigate these complexities. Real-world case studies punctuate the discussion, offering tangible insights into the tangible benefits and practical challenges of this integrated approach. In conclusion, the seamless integration of nonfunctional properties into MDE emerges as a pivotal progression, heralding a new era of robust, efficient, and holistic embedded system development. © 2023 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection System Using Decision Tree and KNN Algorithm 3

Network Intrusion Detection System Using Decision Tree and K...

引用

3rd International Conference on Power Electronics and IoT Applications in Renewable Energy and its Control, PARC 2024

作者： Singh, Km Shivani Singh, Khundrapam Johnson National Institute of Technology Dept. of Computer Science and Engineering Manipur Imphal India

ISBN: (纸本)9798350309409

The complexity of attacks is increasing, making it increasingly difficult to effectively discover breaches. A network intrusion detection system is needed to handle the aforementioned problem. An automated software program called a network intrusion detection system alerts administrators when someone attempts to compromise the system by participating in hazardous behaviors. A system or network is protected from harmful invasions by hardware and software firewalls. They function like filters, removing any data that could put the system or network at risk. We aimed to design the best intrusion detection system possible so that it could distinguish between 'normal' and 'attacked' categories of network data with high accuracy. The best accuracy can be obtained by using soft computing techniques like Decision Trees and KNN. We tested a variety of techniques, such as preprocessing the data, feature selection, principal component analysis (PCA) reduction, standardization, and normalization, in order to increase our model's accuracy scores. We also assess the two approaches' results according to their accuracy in order to decide which way is more effective. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Flood Susceptibility Assessment in the Teesta River Basin, India: An Advanced Geospatial Artificial Intelligence Approach Leveraging Spatial Data Augmentation

引用

SN computer Science 2025年第4期6卷 1-22页

作者： Sen, Deepanjan Das, Swarup Dept. of Computer Applications Dr. B. C. Roy Academy of Professional Courses West Bengal Durgapur India Dept. of Computer Science and Technology University of North Bengal West Bengal Siliguri India

Floods are a critical natural catastrophe that has a significant impact on the Teesta River Basin in India, resulting in substantial losses to agriculture, property, and life. This investigation introduces a sophisticated geospatial artificial intelligence framework for the evaluation of flood susceptibility, which employs spatial data augmentation for enhancing models’ reliability. The study uses six machine learning algorithms, involving K-Nearest Neighbours (KNN), Na¨ıve Bayes (NB), Decision Tree (DT), Conditional Inference Tree (CIT), BlackBoost (BBoost), and Model Averaged Neural Network (MANN), to integrate multisource geospatial data, including 30 × 30 m Cartosat-1 satellite derived Digital Elevation Model (DEM). A thorough flood inventory found 317 inundated areas, with original data sources systematically enhanced at a 1:3 ratio to expand the dataset, and the Boruta feature selection technique identified 12 essential flood conditioning elements. The models were assessed using metrics such as accuracy, Kappa, precision, recall, F1 score, and Area Under the Curve (AUC). The KNN model has the maximum accuracy of 91.62% (Kappa = 0.8325), precision of 90.41%, recall of 93.12%, and AUC of 97.80%, classifying around 35% of the basin as high-susceptibility zones. This study underscores the efficacy of machine learning and geospatial analysis in enhancing flood risk management tactics, offering critical insights for disaster management policymakers. Future efforts will concentrate on improving model robustness via comprehensive evaluation across many geographical settings, incorporating real-time meteorological data for dynamic flood forecasting, and creating user-friendly decision support tools for stakehol-ders in disaster management. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Boruta analysis Digital elevation model Flood susceptibility Geospatial artificial intelligence Spatial data augmentation

来源：评论

学校读者我要写书评

暂无评论

Contribution of Algorithm Visualizations to Students' Learning Skills: A Pedagogical Approach 12

Contribution of Algorithm Visualizations to Students' Learni...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Kheder, Harem Ali Varol, Asaf College of Engineering and Computer Sciences Lebanese French University Dept. of Computer Engineering Erbil Iraq College of Engineering and Computer Science The University of Tennessee at Chattanooga Dept. of Engineering Management and Technology ChattanoogaTN United States

ISBN: (纸本)9798350330366

The Domain Algorithm visualizations are multimedia-based representations of algorithms that help students learn how they operate and behave. Algorithm visualizations provide numerous benefits to instructors and students, including an improved understanding of difficult algorithms in programming. By stripping down the complexities of algorithms and presenting them in simplified visual ways, students can obtain a more thorough knowledge of how they perform. Instructional approaches, such as guided instruction or discovery learning, are critical to the pedagogical effectiveness of algorithm representations. Guided instructions can considerably boost learners' overall performance in problem-solving activities that incorporate visualizations. At the same time, discovery education promotes exploration and experimentation, yet it may result in longer learning times and increased mental demands. A combination of these approaches is required for optimal effectiveness of instruction. In this paper, we investigate how the pedagogical effectiveness of algorithm visualizations should be determined by a variety of elements, including student characteristics, visual and cognitive processing ability, algorithm representation, and instructional context based on a literature review and interviews with field experts, and a bunch of recommendations is provided that has witnessed by authors during their long teaching periods. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Single- and Multi-Hop BERT Question Classifier for Open-Domain Question Answering (SiMQC) 31

Single- and Multi-Hop BERT Question Classifier for Open-Doma...

引用

31st International Conference on Electrical Engineering, ICEE 2023

作者： Sayyad, Faeze Zakaryapour Bohlouli, Mahdi Dept. Computer Science and Information Technology Zanjan Iran

ISBN: (纸本)9798350312560

Multi-hop Question Answering has recently received particular attention in research and practice, especially in the context of conversational systems and answering complex questions. Various architectures have been proposed to answer these complex multi-hop questions. However, in real-world scenarios, a conversational system should answer both simple (single-hop) and complex (multi-hop) questions. In this work, we propose an efficient BERT question classifier that supports retrievers in the question-answering systems to process single- and multi-hop questions. We also released a mixed dataset consisting of both single- and multi-hop questions. We show that utilizing our classifier inside the QA system can improve these systems' accuracy and enable them to answer both kinds of questions considering their complexity. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Job Search: A Multi-Model Approach with DRNN-BES, Collaborative Filtering, and LLM-NER Resume Analysis 3

Optimizing Job Search: A Multi-Model Approach with DRNN-BES,...

引用

3rd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2024

作者： Jayakumar, Naveenkumar Patil, Netra Pokal, Roshankumar S. Dev, Rudra Pratap Nair, Sidharth Vellore Institute of Technology School of Computer Science and Engineering Vellore India College of Engineering Dept. of Computer Engineering Pune India

ISBN: (纸本)9798350354348

This research introduces an innovative job recommendation platform designed to optimize the job search process through advanced technology integration. The platform features a sophisticated Resume Analyzer leveraging NLP and ML to meticulously extract candidate information. Coupled with a Recommendation System that employs mixture models such as DRNN-BES and collaborative filtering, it delivers personalized job suggestions tailored to individual profiles. Additionally, the system utilizes state-of-the-art web scraping technologies to continuously update its database with diverse and current job listings from various online sources, ensuring a wide range of opportunities are accessible. This integration of technologies not only refines job-matching precision but also significantly improves the efficiency of connecting job seekers with appropriate opportunities. Initial experimental results underscore the enhanced effectiveness and accuracy of our recommendation system, particularly when incorporating user behavioral data into the collaborative filtering algorithm. This paper demonstrates the transformative potential of integrating AI into job seeking, offering a scalable, unbiased, and time-efficient approach to modern employment challenges. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

CULTURAL LEAF: A LOD PORTAL FOR EXPLORING THE CULTURAL HERITAGE

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and computer Science 2024年第2期86卷 61-72页

作者： Dorobăț, Ilie Cristian Posea, Vlad Boncea, Radu Dept. of Computer Science National University of Science and Technology POLITEHNICA Bucharest Romania National Institute for Research and Development in Informatics-ICI Bucharest Romania

The paper introduces the Cultural Leaf Semantic Portal whose aim is to provide a consolidated user-friendly solution for exploring the 36,132 Romanian artifacts and the 1,086 cultural entities that house them. Using the eCHO framework, the data collected from official sources are subjected to a transformation process through which they are sanitized, temporal expressions are normalized, thus reducing the number of forms in which the centuries and millennia are expressed from 1,733 to only 67, and then they are transformed into semantic structures. Finally, the resulting data is accessible via both a SPARQL endpoint and a semantic portal. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Prediction and Management of Traffic Congestion in Urban Environments 15

Prediction and Management of Traffic Congestion in Urban Env...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Gwalani, Aryan Pai, Abhishek Padalia, Adish Bhavathankar, Prasenjit Devadkar, Kailas Sardar Patel Institute of Technology Dept. of Information Technology Mumbai India Sardar Patel Institute of Technology Dept. of Computer Engineering Mumbai India

ISBN: (纸本)9798350370249

Efficient urban traffic congestion management is paramount for ensuring smooth vehicular flow, minimizing travel time, and reducing environmental pollution. In this context, utilizing intelligent intersection technologies emerges as a promising approach to tackling traffic challenges effectively. This paper presents an in-dept. analysis of the 'Intelligent Intersection' framework, a novel system designed to optimize traffic flow at intersections through advanced sensing, data processing, and control mechanisms. The research integrates the Gated Recurrent Unit (GRU) model for urban traffic prediction, Simulation of Urban Mobility (SUMO) for realistic traffic simulations, and adaptive traffic light control algorithms. Additionally, the integration of Vehicle-to-Infrastructure (V2I) communication, particularly Dedicated Short Range Communication (DSRC), facilitates efficient coordination between vehicles and infrastructure elements. Through comprehensive experimentation and evaluation, the effectiveness of this approach in mitigating traffic congestion, reducing travel time, and promoting sustainable transportation practices is demonstrated. This research contributes to the advancement of intelligent transportation systems and lays the groundwork for future innovations in urban mobility management. © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Ensemble Learning Approach to Predict Eye Diseases from OCT Images 5

A Novel Deep Ensemble Learning Approach to Predict Eye Disea...

引用

5th International Conference on Sustainable Technologies for Industry 5.0, STI 2023

作者： Uddin, Nazim Mia, Md Sajib Uddin, Mohammed Nasir Mahmud, Prince Chandpur Science and Technology University Dept. of Information and Communication Technology Bangladesh Sylhet Engineering College Dept. of Computer Science and Engineering Bangladesh Jagannath University Dept. of Computer Science and Engineering Bangladesh Chandpur Science and Technology University Dept. of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350394290

As the world advances in technology, the classification of eye diseases is thought to have clinical applications since it evaluates and analyzes the results. Optometrists research and diagnose age-related eye problems such as Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), and Drusen using optical coherence tomography (OCT) of the human eye. Because their symptoms are similar, identifying these diseases is challenging and requires hours of expert analysis. The requirements for eye illness classification should be straightforward in nature, structure, and evaluation. Deep Learning Convolutional Neural Network Classification can create a hierarchical representation of images to differentiate between normal and diseased eye patterns for diagnostic purposes. Therefore, this paper aims to implement and define deep learning to classify and identify eye diseases. Using a four-class classification problem, this work investigates the automatic detection of Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), Drusen, and Normal in Optical Coherence Tomography (OCT) pictures. Multi-transfer learning architecture was used in the suggested deep learning Ensemble classification model. The most incredible accuracy of our proposed Ensemble model for multi- class classification was 83%. © 2023 IEEE.

关键词： Optical tomography

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：