检索结果-内蒙古大学图书馆

2022 International Conference on Algorithms, Microchips and Network Applications

作者： Huang, Huihui Xu, Qiangqiang Feng, Weigong Faculty of Data Science City University of Macao Macao China School of Information Technology Beijing Institute of Technology Zhuhai China

ISBN: (纸本)9781510653290

With massive data, complex information, and the increasingly expanding huge stock pool, it is always difficult for investors to quickly and accurately choose stocks with good inherent value and predictable constant growth. Therefore, stock analysis before investment is vital. In this paper, by applying classical K-means clustering algorithm in data mining, 100 US stocks randomly selected from Yahoo Finance are first classified into different performance groups based on their historical trading data in the recent one year, then detailed analysis of the typical stocks in each performance group is given from the perspective of technical analysis, attempting to find some important features for simple and rapid evaluation of stock investment value, in addition, corresponding investment advice is also proposed based on some statistical analysis index. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Source Camera Identification Algorithm Based on Multi-Scale Feature Fusion

引用

Computers, Materials & Continua 2024年第8期80卷 3047-3065页

作者： Jianfeng Lu Caijin Li Xiangye Huang Chen Cui Mahmoud Emam School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Shangyu Institute of Science and Engineering Hangzhou Dianzi UniversityShaoxing312300China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityZhejiang Police CollegeHangzhou310000China Faculty of Artificial Intelligence Menoufia UniversityShebin El-Koom32511Egypt

The widespread availability of digital multimedia data has led to a new challenge in digital *** source camera identification algorithms usually rely on various traces in the capturing ***,these traces have become increasingly difficult to extract due to wide availability of various image processing *** Neural Networks(CNN)-based algorithms have demonstrated good discriminative capabilities for different brands and even different models of camera ***,their performances is not ideal in case of distinguishing between individual devices of the same model,because cameras of the same model typically use the same optical lens,image sensor,and image processing algorithms,that result in minimal overall *** this paper,we propose a camera forensics algorithm based on multi-scale feature fusion to address these *** proposed algorithm extracts different local features from feature maps of different scales and then fuses them to obtain a comprehensive feature *** representation is then fed into a subsequent camera fingerprint classification *** upon the Swin-T network,we utilize Transformer Blocks and Graph Convolutional Network(GCN)modules to fuse multi-scale features from different stages of the backbone ***,we conduct experiments on established datasets to demonstrate the feasibility and effectiveness of the proposed approach.

关键词： Source camera identification camera forensics convolutional neural network feature fusion transformer block graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Decompose, Enrich, and Extract! Schema-aware Event Extraction using LLMs.

arXiv

引用

arXiv 2024年

作者： Shiri, Fatemeh Nguyen, Van Moghimifar, Farhad Yoo, John Haffari, Gholamreza Li, Yuan-Fang Department of Data Science AI Faculty of Information Technology Monash University Australia Information Sciences Division Defence Science and Technology Group Australia

Large Language Models (LLMs) demonstrate significant capabilities in processing natural language data, promising efficient knowledge extraction from diverse textual sources to enhance situational awareness and support decision-making. However, concerns arise due to their susceptibility to hallucination, resulting in contextually inaccurate content. This work focuses on harnessing LLMs for automated Event Extraction, introducing a new method to address hallucination by decomposing the task into Event Detection and Event Argument Extraction. Moreover, the proposed method integrates dynamic schema-aware augmented retrieval examples into prompts tailored for each specific inquiry, thereby extending and adapting advanced prompting techniques such as Retrieval-Augmented Generation. Evaluation findings on prominent event extraction benchmarks and results from a synthesized benchmark illustrate the method’s superior performance compared to baseline approaches. © 2024, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Analysis of Factors Influencing Early Detection of Breast Cancer

Analysis of Factors Influencing Early Detection of Breast Ca...

引用

Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE), International Conference on

作者： Hassal Malik Sonia Umaira Ahmad Sial Faisal Bukhari Department of Data Science Faculty of Computing and Information Technology University of the Punjab Lahore Pakistan

ISBN: (数字)9798331504861

ISBN: (纸本)9798331504878

Carcinoma, particularly breast cancer, poses a formidable challenge, especially in Pakistan where it stands as the most prevalent cancer among women. This research investigates the complex landscape of breast cancer in Pakistan, utilizing a dataset from local hospitals. Through comprehensive statistical analyses and advanced machine learning techniques, including XGBoost and RandomForest, the study uncovers significant associations between socio-economic and psychological factors and the timing of breast cancer diagnosis among Pakistani women. Factors such as embarrassment, fear of treatment, and lack of awareness emerge as crucial determinants. The findings provide valuable insights for tailored interventions and contribute to the global fight against breast cancer.

关键词： Hospitals Statistical analysis Psychology Machine learning Forestry Market research Breast cancer Timing Decision trees Socioeconomics

来源：评论

学校读者我要写书评

暂无评论

A deep learning fusion model for accurate classification of brain tumours in Magnetic Resonance images

引用

CAAI Transactions on Intelligence technology 2024年第4期9卷 790-804页

作者： Nechirvan Asaad Zebari Chira Nadheef Mohammed Dilovan Asaad Zebari Mazin Abed Mohammed Diyar Qader Zeebaree Haydar Abdulameer Marhoon Karrar Hameed Abdulkareem Seifedine Kadry Wattana Viriyasitavat Jan Nedoma Radek Martinek Department of Information Technology Lebanese French UniversityErbilIraq Department of Computer Science University of ZakhoZakhoKurdistan RegionIraq Department of Computer Science College of ScienceNawroz UniversityDuhokKurdistan RegionIraq Department of Artificial Intelligence College of Computer Science and Information TechnologyUniversity of AnbarRamadiIraq Department of Telecommunications VSB‐Technical University of OstravaOstravaCzech Republic Department of Cybernetics and Biomedical Engineering VSB‐Technical University of OstravaOstravaCzech Republic Department of Computer Network and Information Security Technical College of Informatics-AkreDuhok Polytechnic UniversityDuhokIraq Information and Communication Technology Research Group Scientific Research CenterAl‐Ayen UniversityThi‐QarIraq College of Computer Sciences and Information Technology University of KerbalaKarbalaIraq College of Agriculture Al‐Muthanna UniversitySamawahIraq Department of Applied Data Science Noroff University CollegeKristiansandNorway Faculty of Commerce and Accountancy Chulalongkorn Business SchoolChulalongkorn UniversityBangkokThailand

Detecting brain tumours is complex due to the natural variation in their location, shape, and intensity in images. While having accurate detection and segmentation of brain tumours would be beneficial, current methods still need to solve this problem despite the numerous available approaches. Precise analysis of Magnetic Resonance Imaging (MRI) is crucial for detecting, segmenting, and classifying brain tumours in medical diagnostics. Magnetic Resonance Imaging is a vital component in medical diagnosis, and it requires precise, efficient, careful, efficient, and reliable image analysis techniques. The authors developed a Deep Learning (DL) fusion model to classify brain tumours reliably. Deep Learning models require large amounts of training data to achieve good results, so the researchers utilised data augmentation techniques to increase the dataset size for training models. VGG16, ResNet50, and convolutional deep belief networks networks extracted deep features from MRI images. Softmax was used as the classifier, and the training set was supplemented with intentionally created MRI images of brain tumours in addition to the genuine ones. The features of two DL models were combined in the proposed model to generate a fusion model, which significantly increased classification accuracy. An openly accessible dataset from the internet was used to test the model's performance, and the experimental results showed that the proposed fusion model achieved a classification accuracy of 98.98%. Finally, the results were compared with existing methods, and the proposed model outperformed them significantly.

关键词： brain tumour deep learning feature fusion model MRI images multi‐classification

来源：评论

学校读者我要写书评

暂无评论

An Assessment of The Talent Management Practices At Aceh Government: A Way Forward In Leveraging AI

An Assessment of The Talent Management Practices At Aceh Gov...

引用

Computing Innovation, Intelligence, Technologies and Education (CIITE), International Conference on

作者： Vidra Rinata Marini Othman Rajermani Thinakaran Faculty of Data Science and Information Technology INTI International University Negeri Sembilan Malaysia

ISBN: (数字)9798350377286

ISBN: (纸本)9798350377293

This study aims to assess talent management practices within the Aceh Government and look into the potential use of Artificial Intelligence (AI) to improve existing strategies. The utilization of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) to summarize relevant research aims to enhance talent acquisition, retention, and development within the government sector. This study will conduct a literature review on methods for managing talent and the integration of AI in government, using the PRISMA approach. This article suggests integrating AI into talent management in the Aceh Government. The text is a thorough review that provides practical advice for effectively tackling challenges in talent management. The article seeks to suggest solutions for optimizing talent processes and enhancing organizational performance by exploring the benefits and limitations of AI integration in the Aceh Government. The assessment will provide guidance for the integration of AI in talent management within the Aceh Government, assisting decision-makers in aligning policies with government objectives. The paper will explore the ramifications of AI in talent management, encompassing advancements in efficiency, augmented decision-making capabilities, and tailored development initiatives. This study will tackle issues such as data protection and workforce preparedness, providing suggestions for optimizing the advantages of AI. This study offers a thorough evaluation of talent management within the Aceh Government and proposes the incorporation of AI to improve its efficacy.

关键词： Technological innovation Ethics Systematics Government Education Decision making Artificial intelligence Stress Systematic literature review Recruitment

来源：评论

学校读者我要写书评

暂无评论

Deep E-Cue:Systematic Deep Network for Multimodal Emotional Cues Recognition in Email Communication 4

Deep E-Cue:Systematic Deep Network for Multimodal Emotional ...

引用

4th International Conference on Ubiquitous Computing and Intelligent information Systems, ICUIS 2024

作者： Revathi, K. Pabitha, C. Theresa, W. Gracy Chawengsaksopark, Pornpimol Sathiyanarayanan, Mithileysh Srm Valliammai Engineering College Department of Information Technology Chennai India Panimalar Engineering College Department of Artificial Intelligence and Data Science Chennai India Shinawatra University Faculty of Engineering Pathum Thani Thailand

ISBN: (纸本)9798331529635

Organizations require virtual communication because efficient communication is essential to successful company operations. Among the features of virtual communication typically email communication, which is textual and asynchronous, meaning that the sender and the recipient do not encounter it simultaneously. Email can be troublesome because it eliminates in-person interactions, which can distort our capacity to develop interpersonal cues that are essential for communicating, exchanging information, and establishing trust. The proposed research is aimed to investigate the adaptability of emotional cues in email communication. A deep learning model is built to extract the emotional cues in email considering multiple parameters like text, audio, video and context of communication. The proposed models achieve accuracy of 96.86%, precision of 97.44%, and sensitivity of 97.69% which is highest score when compared to other existing models. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Digital Forensics Meets Blockchain: Enhancing Evidence Authenticity and Traceability

Digital Forensics Meets Blockchain: Enhancing Evidence Authe...

引用

Cyber Resilience (ICCR), International Conference on

作者： Salam Al-E‘mari Yousef Sanjalawe Sharif Makhadmeh Hamzah Alqudah Department of Information Security Faculty of Information Technology University of Petra Amman Jordan Department of Cybersecurity Faculty of Information Technology American University of Madaba Amman Jordan Department of Data Science and Artificial Intelligence Faculty of Information Technology University of Petra Amman Jordan Department of Data Science and Artificial Intelligence Faculty of Information Technology American University of Madaba Amman Jordan

ISBN: (数字)9798350394962

ISBN: (纸本)9798350394979

In the rapidly evolving landscape of cybercrime, ensuring the authenticity and traceability of digital evidence has become paramount. This paper explores the integration of blockchain technology with digital forensics as a novel approach to address these concerns. Blockchain, with its inherent characteristics of immutability and decentralization, can offer significant advancements in ensuring tamper-proof storage and chronological verification of forensic artifacts. By merging these two domains, we introduce a framework that not only bolsters the authenticity of digital evidence but also facilitates a robust traceability mechanism. Through a detailed case study, we demonstrate the practicality and effectiveness of this integrated approach, highlighting its potential to revolutionize current forensic methodologies. However, we also delve into the challenges posed, such as scalability, privacy, and legal implications, and suggest future research avenues. Leveraging blockchain technology in the realm of digital forensics has the potential to redefine evidence integrity and the forensic investigation landscape.

关键词： Privacy Scalability Digital forensics Merging Blockchains Computer crime Resilience

来源：评论

学校读者我要写书评

暂无评论

Transforming Finger Vein Template in Multi-instance Scenario 10

Transforming Finger Vein Template in Multi-instance Scenario

引用

10th International Conference on information and Communication technology, ICoICT 2022

作者： Cai, Shuxian Yau, Wei Chuen Ong, Thian Song Teng, Jackson Horlick School of Computing and Data Science Xiamen University Malaysia Sepang Malaysia Multimedia University Faculty of Information Science and Technology Melaka Malaysia

ISBN: (数字)9781665481656

ISBN: (纸本)9781665481656

Unlike single biometric systems, multi-instance biometric systems can reduce the risk of user privacy leakage. Meanwhile, maintaining biometric security also requires template protection. However, there is still limited study focusing on template protection in multi-instance biometrics. To address such issues, this paper proposes a method for multi-instance finger vein template protection. In this work, the vein features of different finger instances are extracted at feature fusion and image fusion levels using Gabor filter method, respectively. For feature transformation, the Gabor feature blocks are transformed with Bloom filters to extract the finger vein template for secure storage and verification. When analyzing the performance, the experiments are mainly conducted with the constant key scenario to be compared with performance of the baseline Gabor feature extraction method and the genuine key scenario. It is shown that this proposed method effectively improves system performance, with equal error rate (EER) as low as 5.00% in constant key scenario, while maintaining zero error rate in genuine key scenario. Besides, the proposed method is also examined for the properties of unlinkability and irreversibility as required for a template protection method. © 2022 IEEE.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Multi-Classification Refactoring Framework Using Hopfield Neural Network for Sustainable Software Development

引用

IEEE Access 2025年 13卷 31785-31808页

作者： Almogahed, Abdullah Mahdin, Hairulnizam Hyeon Gu, Yeong Al-Masni, Mohammed A. Alzaeemi, Shehab Abdulhabib Omar, Mazni Alawadhi, Abdulwadood Obaid Barraood, Samera Rehman Gilal, Abdul Ameen Bakather, Adnan Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Parit Raja Johor86400 Malaysia Sejong University College of AI Convergence Department of Artificial Intelligence and Data Science Seoul05006 Korea Republic of King Fahd University of Petroleum and Minerals Interdisciplinary Research Center in Finance and Digital Economy Business School Dhahran31261 Saudi Arabia Universiti Utara Malaysia School of Computing Sintok06010 Malaysia Hadhramout University College of Computers and Information Technology Department of Computer Science Hadhramaut Yemen Florida International University Knight Foundation School of Computing and Information Sciences MiamiFL33199 United States

Adopting high-quality source code is the ultimate way through which software evolution can be ensured as sustainable. Continuous refactoring in complex software systems ensures longevity and increases architecture knowledge sustainability. However, decision-making about refactoring is a challenge because the benefits of refactoring are vague and very difficult for the developers to quantify, as different refactoring strategies have different effects on quality attributes. No research has developed a multi-classification refactoring framework using artificial neural networks (ANN), specifically hopfield neural networks (HNN), to classify refactoring strategies and improve external software quality and sustainability. Therefore, this study proposes a multi-classification refactoring framework using HNN that classifies refactoring strategies by their impact on external quality attributes. Five stages have been conducted to perform this study, including selecting case studies, identifying the external quality attributes, identifying the most commonly used refactoring strategies in practice, conducting the experiments, and conducting the classification process using HNN. The proposed framework categorizes the refactoring strategies into three categories (positive, negative, and ineffective). By providing clear classifications and descriptions of each strategy, the proposed framework helps developers make informed decisions about how to improve the design and structure of their code. It helps developers mitigate risks associated with code changes by providing guidance on which strategies are likely to yield positive results for specific quality attributes. The proposed multi-classification refactoring framework enhances software sustainability by enhancing critical quality attributes. It supports maintainability, adaptability, and long-term viability, helping to ensure that the software systems remain relevant, efficient, and valuable over time. © 2025 IEEE.

关键词： Hopfield neural networks

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：