检索结果-内蒙古大学图书馆

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Karuppasamy, ArunaDevi Oman College of Management and Technology Department of Computer Science and Management Information System Muscat Oman

ISBN: (纸本)9798350335095

Breast cancer is one of the most common type of cancer affecting women worldwide, and a leading cause of cancer-related deaths. Histopathology image analysis plays a vital role in breast cancer diagnosis. Early diagnosis and accurate classification of breast cancer histopathology images can help for effective treatment. In recent years, deep learning-based image classification methods have shown promising results in automated breast cancer diagnosis. Earlier, Convolutional Neural Network(CNN) had a huge attention in image classification tasks, and also obtained a good performances in histopathology image classification. Recently, Vision Transformer (ViT) based on self-attention mechanism has shown promising results in computer vision tasks, including image classification. In this paper, we review recent ViT-based model for breast cancer histopathology image classification. Furthermore, we summarize the results obtained from our experiments with both CNN and ViT-based models in breast cancer histopathology image classification. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Detection systems for Distributed Denial-of-Service (DDoS) Attack Based on Time Series: A Review 21

Detection Systems for Distributed Denial-of-Service (DDoS) A...

引用

21st International Multi-Conference on systems, Signals and Devices, SSD 2024

作者： Adil Nafea, Ahmed Maad Hamdi, Mustafa Abdulhakeem, Baraa Saad Shakir, Ahmed Thair Alsumaidaie, Mustafa S. Ibrahim Shaban, Ali Muwafaq College of Computer Science and Information Technology University of Anbar Ramadi Dept. Artificail Inteligence Iraq College of Computer Science and IT University of Anbar Ramadi Dept. of Computer Science Iraq College of Computer Science and IT University of Anbar Ramadi Dept. of Information System Iraq College of Applied Sciences University of Anbar Ramadi Dept. of Biophysics Iraq College of Computer Science and Information Technology University of Anbar Ramadi Dept. Information System Iraq

ISBN: (纸本)9798350374131

The Distributed Denial-of-Service (DDoS) attacks are one of the most critical threats to the stability and security of the Internet. With the increasing number of devices connected to the Internet, the frequency and severity of DDoS attacks are also increasing. To mitigate the impact of DDoS attacks, intelligent detection systems are becoming increasingly important. This paper reviews the recent literature on intelligent techniques, including machine learning (ML), Deep Learning (DL), and artificial intelligence (AI), for detecting DDoS attacks. We will provide an overview of the existing research in the field and analyse the trends in using time series data analysis for DDoS attack detection. A taxonomy and conceptual framework for DDoS mitigation are presented. This study highlights the use of several intelligent techniques for detecting DDoS attacks and evaluates the performance utilizing real datasets and also discusses future research directions in this field. © 2024 IEEE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Transformers Embeddings for Question Answering in Arabic Private Documents 8

A Comparative Study of Transformers Embeddings for Question ...

引用

8th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data Science, BCD 2023

作者： Al Daoud, Essam Samara, Ghassan Al Daoud, Laith Al Jaidi, Mohammad Zarqa University Computer Science Department Jordan Jordan University of Science and Technology Computer Information System Department Jordan

ISBN: (纸本)9798350373615

Question answering (QA) tasks in natural language processing (NLP) are tricky, particularly when used with Arabic private documents. This is due to the complexity of Arabic language and the lack of sufficient annotated datasets for Arabic QA. Recent research findings have demonstrated the effectiveness of transformer embeddings for English QA. Their efficiency for QA in Arabic private documents, however, has not been fully investigated. In this study, various transformer embeddings for QA in Arabic private documents are compared. The effectiveness of these embeddings is evaluated by assessing a golden dataset extracted from private documents. The results show that the accuracy of QA in Arabic private documents can be significantly improved by combining transformer embeddings with count vectorization. Furthermore, different transformer embeddings have distinct strengths and weaknesses. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Sports Events Recognition Using Multi Features and Deep Belief Network

引用

computers, Materials & Continua 2024年第10期81卷 309-326页

作者： Bayan Alabdullah Muhammad Tayyab Yahay AlQahtani Naif Al Mudawi Asaad Algarni Ahmad Jalal Jeongmin Park Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science Applied CollegeKing Khalid UniversityAbha61421Saudi Arabia Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Engineering Korea Polytechnic UniversitySiheung-siGyeonggi-do237Republic of Korea

In the modern era of a growing population,it is arduous for humans to monitor every aspect of sports,events occurring around us,and scenarios or *** recognition of different types of sports and events has increasingly incorporated the use of machine learning and artificial *** research focuses on detecting and recognizing events in sequential photos characterized by several factors,including the size,location,and position of people’s body parts in those pictures,and the influence around those *** approaches utilized,here are feature descriptors such as MSER(Maximally Stable Extremal Regions),SIFT(Scale-Invariant Feature Transform),and DOF(degree of freedom)between the joint points are applied to the skeleton ***,for the same purposes,other features such as BRISK(Binary Robust Invariant Scalable Keypoints),ORB(Oriented FAST and Rotated BRIEF),and HOG(Histogram of Oriented Gradients)are applied on full body or *** integration of these techniques increases the discriminative nature of characteristics retrieved in the identification process of the event,hence improving the efficiency and reliability of the entire *** extracted features are passed to the early fusion and DBscan for feature fusion and *** deep belief,network is employed for *** results demonstrate a separate experiment’s detection average recognition rate of 87%in the HMDB51 video database and 89%in the YouTube database,showing a better perspective than the current methods in sports and event identification.

关键词： Machine learning silhouettes extremal regions joint points scalable keypoints

来源：评论

学校读者我要写书评

暂无评论

Improving Route-Finding Performance of Dijkstra Algorithm and Maintaining Path Visual Cue Using Douglas-Peucker Algorithm 23

Improving Route-Finding Performance of Dijkstra Algorithm an...

引用

8th International Conference on Sustainable information Engineering and technology, SIET 2023

作者： Pinandito, Aryo Kharisma, Agi Putra Akbar, Muhammad Aminul Information System Department Faculty of Computer Science Universitas Brawijaya Malang Indonesia Media Game and Mobile Technology Laboratory Information System Department Faculty of Computer Science Universitas Brawijaya Malang Indonesia

ISBN: (纸本)9798400708503

Smartphones and their mobile applications have become an inseparable part of modern daily life. One of them is a public transportation app that helps people commute with public transportation. Many public transportation service providers have mobile applications as a companion for their customers to improve their quality of service. The application provides useful information and/or important features regarding their service, such as timetables or route finding for public transit. Such features run a slow algorithm to provide real-time or time-based information to the users. Dijkstra is one example of an algorithm that allows users to find the shortest path from one location to another in a public transit network. However, Dijkstra is categorized as a greedy algorithm because it looks at all possible solutions. It takes longer for Dijkstra to find the optimum solution when the number of points in a network graph is high. This study attempted to improve the overall route-finding processing time and reduce the memory footprint while keeping the visual cue of a route path reasonably consistent by utilizing Douglas-Peucker line simplification algorithm to simplify the path and reduce the number of points that Dijkstra algorithm processes. The result suggested that Douglas-Peucker simplification process took 0.5% additional memory footprint and put 5.13% additional processing time into the overall route-finding processing time. However, it reduces the overall memory footprint and processing time by 72.56% and 80.83%, respectively. The result conveyed a significant improvement in the practical implementation of Douglas-Peucker algorithm to reduce the input for the Dijkstra algorithm in finding the optimal route, thereby improving the overall route-finding performance. © 2023 ACM.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

I-Know: Revolutionizing Knowledge Management with Interactive Quizzes 1

I-Know: Revolutionizing Knowledge Management with Interactiv...

引用

1st IEEE Karachi Section Humanitarian technology Conference, Khi-HTC 2024

作者： Zulkifli, Zahidah Halim, Muhammad Darwish Bin Abdul Shaffei, Arief Iskandar Bin Alsaiari, Nisrin International Islamic University Malaysia Kulliyyah of Information and Communication Technology Department of Information System Malaysia Arab Open University Faculty of Computer Studies Saudi Arabia

ISBN: (纸本)9798350373042

This project focuses on the development of a website system designed to facilitate knowledge acquisition for students enrolled in the Kulliyyah of information Communication and technology (KICT) at the International Islamic University Malaysia (IIUM). The aim is to alleviate the information overload experienced by new intake students during the Taaruf week (orientation week). Despite its establishment in 2010, KICT faces a persistent challenge where new students remain unaware of crucial system details, including rules, regulations, and academic matters. To address this issue, the project endeavors to provide a comprehensive platform enabling new students to access pertinent information and knowledge about KICT. An analysis of seven similar existing systems has been conducted, highlighting their main functions, advantages, and disadvantages. The system Development Life Cycle methodology has been selected for its practicality in guiding the project through the phases of Final Year Project (FYP) 1 and FYP2. Data collection involved surveying 30 KICT students to identify challenges faced by new students in obtaining the necessary information. Results underscore the urgent need for a technically guided application to enhance student understanding of KICT. The logical design of the app encompasses a Use Case Diagram, Use Case Narrative, Activity Diagram, Interface Flow, Low-Fidelity Design, and Interface Flow. The 'i-know' system has been developed using PHP, HTML, CSS, and Javascript, with connectivity to MySQL through phpMyAdmin for user authentication. The User Acceptance Test (UAT) was conducted during implementation, following beta testing. The paper concludes with insights into the system's effectiveness and its potential to address the identified challenges faced by new KICT students. © 2024 IEEE.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuning for Identifying Tree Seedling Mortality Using Logistic Regression on Environmental and Factors

Hyperparameter Tuning for Identifying Tree Seedling Mortalit...

引用

2024 International Conference on Advanced information Scientific Development, ICAISD 2024

作者： Wildah, Siti Khotimatul Latif, Abdul Universitas Bina Sarana Informatika Computer Technology Jakarta Indonesia Universitas Bina Sarana Informatika Information System Jakarta Indonesia

ISBN: (纸本)9798350392036

Tree-seedling mortality is a significant challenge in forest management and agricultural practices, particularly in areas affected by climate change. The primary causes of seedling mortality are related to environmental factors and soil conditions. The early identification of these factors is crucial for improving seedling survival and land productivity. While existing studies have applied machine learning techniques to predict seedling mortality, they have often overlooked the importance of hyperparameter tuning in enhancing model performance. This study addresses this gap by focusing on the impact of hyperparameter tuning on the Logistic Regression models used to predict tree seedling mortality. Using a tree survival prediction dataset containing diverse environmental and soil factors, the model was optimized to achieve significant improvements. The tuned Logistic Regression model outperformed the standard approaches, achieving an accuracy of 93.71% and AUC of 97.81%. These results underscore the importance of hyperparameter optimization in boosting predictive accuracy, and demonstrate its potential to support improved forest conservation and management efforts more effectively than traditional models. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Image Classification of Disease Detection in Paddy Crops Using Transfer Learning Approach 5

Image Classification of Disease Detection in Paddy Crops Usi...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Nithjapoopathy, S. Pratheesh, B. Sansayan, N. Abishaalini, S. Rupasinghe, Lakmal Liyanapathirana, Chethana Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

Rice serves as the cornerstone of Sri Lanka's diet, contributing 45% of total calories and 40% of protein intake, essential for food security. It's not just sustenance;the rice industry is a major force, providing employment to 1.8 million individuals, directly and indirectly, from diligent farmers to traders and retailers. This sector significantly contributes to government revenue through taxes and exports, with 10% of rice production being exported, bolstering foreign exchange earnings. Moreover, rural households rely on rice for income, uplifting living standards and fighting poverty. However, the existing methods for disease detection, rice quality prediction, and soil quality assessment are often slow and subjective. This research advocates the use of cutting-edge deep learning techniques, specifically Convolutional Neural Networks (CNN), to tackle these challenges. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ResPocket: A Multi-Scale Feature Fusion Method for Improving Protein Binding Site Detection

ResPocket: A Multi-Scale Feature Fusion Method for Improving...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Xiaoli Yang, Wenli Chen, Yaoyu Liao, Xiongwei Wu, Zimo Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology China

ISBN: (纸本)9798350386226

Accurate detection of protein binding sites is critical for facilitating drug design. Most existing models rely on features at a single scale, leading to the loss of crucial global or local structural information. Therefore, this paper proposes a novel 3D model (ResPocket), to fully capture the multi-scale features of proteins. First, Residual Block (ResB) based on U-Net is used to capture features from different scales, including global and local structural information. Then, an Enhanced Attention Module (EAM) is designed to encode semantic dependencies by effectively capturing global context information. In addition, ResPocket focuses on learning local information about protein pockets with Self-Guided Mask Block (SGMB), to increase the robustness of the overall model and reduce its dependence on external mask guidance. Experimental results show that ResPocket improves by an average of 4.89% on DCA Top-n, by an average of 1.48% and 2.25% on DCC and DVO metrics, respectively. © 2024 IEEE.

关键词： Binding sites

来源：评论

学校读者我要写书评

暂无评论

ML-Driven HR system: Candidate Assessment for Enhanced Recruitment Outcomes 3

ML-Driven HR System: Candidate Assessment for Enhanced Recru...

引用

3rd International Conference on Automation, Computing and Renewable systems, ICACRS 2024

作者： Dixon, G.C. Srithanujan, S. Ranaweera, H.D.T.N. Ariyarathne, R.M.P.M. Weerasinghe, K.L. Gamage, N. Department of Information Technology SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka Department of Computer System engineering SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka Department of Computer Science and Software Engineering SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka

ISBN: (纸本)9798331532420

This study developed and implemented a machine learning-driven HR system designed to enhance recruitment outcomes, particularly in online interviews. Challenges such as candidate impersonation, interview question memorization, and deepfake manipulations were addressed. The system incorporated several critical processes utilizing advanced algorithms: pre-interview shortlisting employed Support Vector Machines (SVM) achieving 92% accuracy;cognitive skills assessment utilized adaptive testing methods powered by fine-tuned Large Language Models (LLMs) with 88% accuracy;emotional intelligence evaluation was conducted using deep learning-based emotion detection algorithms attaining 85% accuracy;face verification leveraged Convolutional Neural Networks (CNNs) for identity and deepfake detection with 90% accuracy;online video interviews were analyzed through integrated audio-visual processing techniques;language proficiency testing employed Natural Language Processing (NLP) models reaching 87% accuracy;analysis of thinking patterns was performed using sentiment analysis algorithms with 83% accuracy;and candidate grading was facilitated by ensemble learning methods ensuring consistent and reliable evaluations. The results demonstrated the system’s effectiveness in verifying candidate authenticity and assessing competence, providing a robust solution for modern recruitment challenges. © 2024 IEEE.

关键词： Support vector machines

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：