检索结果-内蒙古大学图书馆

4th International Conference on Informatics, Multimedia, Cyber and Information System, ICIMCIS 2022

作者： Mas Diyasa, I Gede Susrama Kraugusteeliana Saputra, Wahyu S.J. Upn 'Veteran' Jawa Timur Departement of Data Science Surabaya Indonesia Upn 'Veteran' Jakarta Faculty of Computer Science Jakarta Indonesia

ISBN: (纸本)9781665473279

Sperm cells contain two types of chromosomes: X and Y. The sex of a child is determined by the sperm cell that fertilizes the egg containing an X or Y chromosome. The X chromosome decides the female gender, while the Y chromosome determines the gender man. To determine the type of chromosome, the process of classifying the types of chromosomes contained in sperm cells is carried out. Developing a system for classifying X and Y chromosomes using the Convolutional Neural Network (CNN) algorithm aims to classify sperm cells carrying X or Y chromosomes. This CNN algorithm was chosen because this algorithm is perfect for the object detection process in the image. The CNN algorithm in this study uses two kinds of epoch values, namely 10 and 20. And using three kinds of number of neurons, namely 16, 32 and 128. The highest accuracy obtained in testing the number of epochs is 10 and the number of neurons is 16, and the number of epochs is 20 and the number of neurons is 32, which is 75,36%. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multilingual Knowledge Graph Completion via Multimodal Decouple and Relation-based Ensemble Inference 29

Multilingual Knowledge Graph Completion via Multimodal Decou...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Liu, Xiaojing Jiang, Xuesong Yi, Fengge Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

The objective of Multimodal Knowledge Graph Completion (MKGC) is to forecast absent entities within a knowledge graph by leveraging additional textual and visual modalities. Existing studies commonly utilize a singular relationship embedding to depict all modalities within an entity pair, thus connecting several relationships derived from diverse modalities. However, this coupling may introduce interference from conflicting information between modalities, as the relationships between modalities for a given entity pair can be contradictory. Moreover, existing Ensemble Inference methods fail to dynamically adjust modal weights based on their differences and importance, despite the varying contributions of different modalities. In this paper, we propose the Multimodal Decouple and Relation-based Ensemble inference (MDRE) model. For each modality, we construct corresponding relationship embeddings and build separate triple representations to avoid interferences among modalities. During the training phase, we employ confidence-constrained training with temperature scaling to alleviate conflicting information in textual and visual modalities. For inference, we utilize the Relation-based Ensemble Inference method to adjust modal weights at the relationship level, thus achieving improved prediction results. Experimental results on two datasets demonstrate that MDRE outperforms existing single-modal and multimodal knowledge graph completion methods in terms of performance. © 2023 IEEE.

关键词： knowledge graph knowledge graph completion multimodal fusion

来源：评论

学校读者我要写书评

暂无评论

Improving Machine Learning Performance for Diabetes Prediction

Improving Machine Learning Performance for Diabetes Predicti...

引用

International Conference on Advanced Intelligent Systems for Sustainable Development, AI2SD 2023

作者： Benabderrahmane, Jawad Kasri, Mohammed El Guabassi, Inssaf El Ansari, Anas Beni-Hssane, Abderrahim Laroseri Laboratory Computer Science Department Faculty of Sciences Chouaib Doukkali University El Jadida Morocco MASI Laboratory Mohammed First University Nador Morocco High School of Artificial Intelligence and Data Science Ibn Zohr University Taroudant Morocco

ISBN: (纸本)9783031543173

Diabetes is a formidable ailment characterized by elevated glucose levels in the bloodstream. Hence, it can cause many complications if it remains untreated and unidentified. Machine learning algorithms play a crucial role in early-stage detection and prediction of diabetes. This research aims to enhance the accuracy of diabetes mellitus prediction by using several techniques within the realm of machine learning. In this regard, the Pima Indians Diabetes dataset was used. Then, different machine learning algorithms have been applied separately or using ensemble learning. As a result, Support Vector Machine achieved an accuracy of 77.89%. Moreover, an empirical assessment of ensemble learning methodology involving the voting classifier and Bagging is conducted alongside contemporary techniques and base classifiers. The ensemble approach demonstrates its prowess, with the voting classifier achieving a result of 90.11%. Notably, the Bagging Classifier emerges as the frontrunner, attaining a remarkable accuracy value of 96.69%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Service Management in Industry 4.0: The Role of AI-Powered Chatbots

Enhancing Service Management in Industry 4.0: The Role of AI...

引用

2024 Advances in science and Engineering Technology International Conferences, ASET 2024

作者： Albeshr, Asraa Mohammed Alnajjar, Fady Abdulmouti, Hassan Mubin, Omar College of Information Technology Uae University Alain United Arab Emirates Faculty of Engineering Higher College of Technology Engineering Technology & Science Sharjah United Arab Emirates School of Computer Data and Mathmatical Science Westren Sydney University Sydney Australia

ISBN: (纸本)9798350344134

In the era of Industry 4.0, where digital transformation is crucial, developing advanced chatbot system becomes essential to revolutionize service management and bolstering business continuity. By leveraging Artificial Intelligence (AI) within such industrial frameworks, smartchatbots promise to streamline operations, ensure seamless customer interactions, and drive efficiency, thereby fortifying businesses in today's competitive landscape. This study presents an adaptable smart chatbot model designed to mimic and absorb the expertise of technical officers within a factory setting, responding to employee technical queries. This approach aims to alleviate the burden on technical personnel while enhancing response efficiency. Unlike traditional systems, this adaptive model benefits from continuous learning capabilities, enabling it to refine its responses over time based on new interactions and corrections made by technical officers. Furthermore, the chatbot's 24/7 availability and the collaborative feedback mechanism for evaluating its responses ensure that it not only meets but exceeds user expectations. Through detailed analysis and empirical evidence, we demonstrate how this chatbot significantly enhances work quality and operational continuity, setting a new benchmark for digital service management in the context of Industry 4.0. The results from conducting surveys among the technical officers regarding the chatbot's usefulness were overwhelmingly positive. All participants expressed high satisfaction, confirming that the implementation of such a smart chatbot model significantly reduces their load and enhances the user experience. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Enhancing face recognition performance: a comprehensive evaluation of deep learning models and a novel ensemble approach with hyperparameter tuning

引用

Soft Computing 2024年第20期28卷 12399-12424页

作者： Selvaganesan, Jana Sudharani, B. Shekhar, S. N. Chandra Vaishnavi, K. Priyadarsini, K. Raju, K. Srujan Rao, T. Srinivasa Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R & ampD Institute of Science and Technology Avadi Tamil Nadu Chennai600062 India Guntur Dist. Andhra Pradesh Vadlamudi India Department of Electronics and Communication Engineering Sreenidhi Institute of Science and Technology Telangana Hyderabad501301 India Department of Computer Science and Engineering Sona College of Technology Tamil Nadu Salem636005 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Science and Engineering CMR Technical Campus Medchal Telangana Hyderabad501401 India Department of Electronics and Communication Engineering Aditya Engineering College Surampalem533437 India

In response to growing security concerns and the increasing demand for face recognition (FR) technology in various sectors, this research explores the application of deep learning techniques, specifically pre-trained Convolutional Neural Network (CNN) models, in the field of FR. The study harnesses the power of five pre-trained CNN models—DenseNet201, ResNet152V2, MobileNetV2, SeResNeXt, and Xception—for robust feature extraction, followed by SoftMax classification. A novel weighted average ensemble model, meticulously optimized through a grid search technique, is introduced to augment feature extraction and classification efficacy. Emphasizing the significance of robust data pre-processing, encompassing resizing, data augmentation, splitting, and normalization, the research endeavors to fortify the reliability of FR systems. Methodologically, the study systematically investigates hyperparameters across deep learning models, fine-tuning network depth, learning rate, activation functions, and optimization methods. Comprehensive evaluations unfold across diverse datasets to discern the effectiveness of the proposed models. Key contributions of this work encompass the utilization of pre-trained CNN models for feature extraction, extensive evaluation across multiple datasets, the introduction of a weighted average ensemble model, emphasis on robust data pre-processing, systematic hyperparameter tuning, and the utilization of comprehensive evaluation metrics. The results, meticulously analyzed, unveil the superior performance of the proposed method, consistently outshining alternative models across pivotal metrics, including Recall, Precision, F1 Score, Matthews Correlation Coefficient (MCC), and Accuracy. Notably, the proposed method attains an exceptional accuracy of 99.48% on the labeled faces in the wild (LFW) dataset, surpassing erstwhile state-of-the-art benchmarks. This research represents a significant stride in FR technology, furnishing a dependable and accurate

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Supervised Machine Learning Approach to Housing Market

Supervised Machine Learning Approach to Housing Market

引用

2023 International Conference for Technological Engineering and its Applications in Sustainable Development, ICTEASD 2023

作者： Mohd Ismayatim, Izat Hakimi Najiah Zakaria, Hanis Ramadhani, Ihsanul Arifin Abdullah, Nurzulaikah Ridzuan, Fakhitah Mustafa, Wan Azani Al-Farouni, Mohammed Universiti Malaysia Kelantan Faculty of Data Science and Computing Kota Bharu Malaysia Universitas Mercu Buana Faculty of Computer Science Jakarta Indonesia Universiti Malaysia Perlis Faculty of Electrical Engineering & Technology Perlis Arau02600 Malaysia The Islamic University Faculty of Engineering Najaf Iraq

ISBN: (纸本)9798350336474

Understanding the multifaceted factors influencing housing prices is crucial for facilitating informed decision-making among diverse stakeholders, including homebuyers, sellers, investors, and policymakers. Therefore, the primary objective of this research is to develop a predictive model for housing prices utilizing regression analysis. By leveraging machine learning techniques, such as regression and classification analysis, this study aims to uncover the intricate relationships between various factors and housing prices, ultimately providing valuable insights to stakeholders involved in the real estate market. Through rigorous data analysis and model development, this research seeks to enhance understanding and contribute to more accurate predictions in the realm of housing price dynamics. © 2023 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Question Embedding on Weighted Heterogeneous Information Network for Knowledge Tracing

引用

ACM Transactions on Knowledge Discovery from data 2024年第1期19卷 1-28页

作者： Sun, Jianwen Du, Shangheng Zhou, Jianpeng Yuan, Xin Shen, Xiaoxuan Liang, Ruxia National Engineering Research Center of Educational Big Data Central China Normal University Wuhan China Faculty of Artificial Intelligence in Education Central China Normal University Wuhan China Shanghai Institute of Artificial Intelligence for Education East China Normal University Shanghai China School of Computer Science and Technology East China Normal University Shanghai China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

Knowledge Tracing (KT) aims to predict students' future performance on answering questions based on their historical exercise sequences. To alleviate the problem of data sparsity in KT, recent works have introduced auxiliary information to mine question similarity, resulting in the enhancement of question embeddings. Nonetheless, there remains a gap in developing an approach that effectively incorporates various forms of auxiliary information, including relational information (e.g., question-student, question-skill relation), relationship attributes (e.g., correctness indicating a student's performance on a question), and node attributes (e.g., student ability). To tackle this challenge, the Similarity-enhanced Question Embedding (SimQE) method for KT is proposed, with its central feature being the utilization of weighted and attributed meta-paths for extracting question similarity. To capture multi-dimensional question similarity semantics by integrating multiple relations, various meta-paths are constructed for learning question embeddings separately. These embeddings, each encoding different similarity semantics, are then fused to serve the task of KT. To capture finer-grained similarity by leveraging the relationship attributes and node attributes on the meta-paths, the biased random walk algorithm is designed. In addition, the auxiliary node generation method is proposed to capture high-order question similarity. Finally, extensive experiments conducted on six datasets demonstrate that SimQE performs the best among 10 representative question embedding methods. Furthermore, SimQE proves to be more effective in alleviating the problem of data sparsity. © 2024 Copyright held by the owner/author(s).

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

A Holistic Anti-Counterfeiting Platform Using NFC and Blockchain Technologies

引用

computers, Materials and Continua 2025年第3期83卷 4257-4280页

作者： Rajendren Subramaniam Saaidal Razalli Azzuhri Teh Ying Wah Atif Mahmood Vimala Balakrishnan Department of Information System Faculty of Computer Science & Information Technology Universiti Malaya Kuala Lumpur 50603 Malaysia Department of Computer System & Technology Faculty of Computer Science & Information Technology Universiti Malaya Kuala Lumpur 50603 Malaysia Faculty of Data Science and Information Technology INTI International University Nilai 71800 Malaysia

Counterfeiting is still a pervasive global issue, affecting multiple industries and hindering industrial innovation, while causing substantial financial losses, reputational damage, and risks to consumer safety. From luxury goods and pharmaceuticals to electronics and automotive parts, counterfeit products infiltrate supply chains, leading to a loss of revenue for legitimate businesses and undermining consumer trust. Traditional anti-counterfeiting measures, such as holograms, serial numbers, and barcodes, have proven to be insufficient as counterfeiters continuously develop more sophisticated replication techniques. As a result, there is a growing need for more advanced, secure, and reliable methods to prevent counterfeiting. This paper presents a novel, holistic anti-counterfeiting platform that integrates Near Field Communication (NFC)-enabled mobile applications with blockchain technology to provide an innovative, secure, and consumer-friendly authentication mechanism. Our approach addresses key gaps in existing solutions by incorporating dynamic product identifiers, which make replication significantly more difficult. The system enables consumers to verify the authenticity of products instantly using their smartphones, enhancing transparency and trust in the supply chain. Blockchain technology plays a crucial role in our proposed solution by providing an immutable, decentralized ledger that records product authentication data. This ensures that product verification records cannot be tampered with or altered, adding a layer of security that is absent in conventional systems. Additionally, NFC technology enhances security by offering unique identification capabilities, enabling real-time product verification. To validate the effectiveness of the proposed system, real-world testing was conducted across different industries. The results demonstrated the platform’s ability to significantly reduce counterfeit products in the supply chain, offering businesses and cons

关键词： Blockchain near field communication (NFC) anti-counterfeiting

来源：评论

学校读者我要写书评

暂无评论

PGTNet: A Process Graph Transformer Network for Remaining Time Prediction of Business Process Instances

arXiv

引用

arXiv 2024年

作者： Elyasi, Keyvan Amiri van der Aa, Han Stuckenschmidt, Heiner Data and Web Science Group University of Mannheim Germany Faculty of Computer Science University of Vienna Austria

We present PGTNet, an approach that transforms event logs into graph datasets and leverages graph-oriented data for training Process Graph Transformer Networks to predict the remaining time of business process instances. PGTNet consistently outperforms state-of-the-art deep learning approaches across a diverse range of 20 publicly available real-world event logs. Notably, our approach is most promising for highly complex processes, where existing deep learning approaches encounter difficulties stemming from their limited ability to learn control-flow relationships among process activities and capture long-range dependencies. PGTNet addresses these challenges, while also being able to consider multiple process perspectives during the learning process. © 2024, CC BY-NC-ND.

关键词： Process monitoring

来源：评论

学校读者我要写书评

暂无评论

Application of Support Vector Machines for Breast Calcification Cluster Detection and Mass Classification 4

Application of Support Vector Machines for Breast Calcificat...

引用

2022 4th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2022

作者： Huang, Yucheng Chen, Guangshun Chen, Jiyun Li, Dalin Liang, Yanchun Du, Wei School of Computer Science Zhuhai College of Science and Technology Zhuhai519041 China Faculty of Data Science City University of Macau 999078 China College of Computer Science and Technology Jilin University Changchun130012 China

Breast cancer has become "the most common cancer worldwide", and it is an urgent problem in the medical field to improve the detection rate of breast cancer through early diagnosis and treatment. Based on the current research on medical image processing, our work selects breast images from the MIAS database for pre-processing, segmentation, texture feature extraction and classification, and conducts an in-depth investigation and experimental validation on the theoretical basis of support vector machine algorithm, kernel function selection, and key parameter optimization. The results show the effectiveness of support vector machines in detecting abnormal areas and classifying masses in breast images and provide research ideas for breast cancer diagnosis. © Published under licence by IOP Publishing Ltd.

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：