检索结果-内蒙古大学图书馆

4th International Informatics and software Engineering Conference, IISEC 2023

作者： Samarakoon, H.M.W.T.C.B. Ovitigala, A.U. Wijesinghe, G.A.T.T. Weerasinghe, K.M.L.P. Karunathilake, G.K.B.V. Weerathunga, Ishara Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350318036

Skin health significantly affects a person's overall wellbeing, which includes both physical and emotional aspects. The objective of this study is to develop an integrated system for recommending skincare products that integrates image processing, machine learning, sentiment analysis, and user feedback analysis to deliver individualized skincare advice and boost user satisfaction. Utilizing deep learning algorithms and face cues, the system uses user image analysis to detect important skin features, skin type, acne severity, and dark spots with extraordinary accuracy. Using sentiment analysis and clustering, the program identifies popular skincare products and tailors' recommendations to user preferences. Recommendations are further personalized by collaborative filtering. By using image analysis to identify allergies and other negative effects, user safety is increased. The technique prioritizes data safety and includes model training, sentiment analysis, image processing, and user input analysis. Initial findings demonstrate the excellent accuracy of skin issue detection and severity prediction. By allowing users from a variety of user demographics to make informed skincare decisions, this complete framework has the potential to change the skincare industry. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Comparing Accuracy and Time of Support Vector Machine with Different Kernels for Handwritten Digits Classification

Comparing Accuracy and Time of Support Vector Machine with D...

引用

2023 International Conference Automatics and Informatics, ICAI 2023

作者： Kalcheva, Neli Marinova, Ginka Todorova, Maya Penev, Ivaylo Technical University of Varna Department 'Software and Internet Technology' Varna Bulgaria Technical University of Varna Department 'Computer Systems and Technologies' Varna Bulgaria

ISBN: (纸本)9798350312911

The aim of this publication is to compare the accuracy and time performance of the Support Vector Machine method with different kernels in image classification within the field of machine learning. In the classification of handwritten digits using the Support Vector Machine approach, we employed the following kernels: polynomial kernel, linear kernel, sigmoid radial kernel, and radial basis kernel. The results indicate that the algorithm employing the radial basis kernel achieved the highest accuracy, while the linear kernel algorithm demonstrated the fastest performance. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Identification of Diabetic Related Eye Diseases Using Deep Learning 5

Identification of Diabetic Related Eye Diseases Using Deep L...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Wijesinghe, K.H. Dilshan, U.K.T. Dilshan, K.B.G.L. Tharupathi, M.A.U. Kasthuriarachchi, Sanvitha Rajapaksha, Samantha Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350358131

Visual disability seems to be increasing and widespread worldwide. Current diagnostics require manual expertise for diagnosis. The advancement of Artificial Intelligence research for medical applications has been in focus in recent years. Fundus images and oct images are valuable sources of information to help ophthalmologists diagnose vision disorders or eye diseases. Early detection can improve the chances of recovery and prevent blindness. The application of an intelligent computer-based approach to classifying different eye disorders is extremely beneficial for both diagnosis and prevention. The proposed expert system for diagnosing diabetic macular edema, diabetic retinopathy, cataracts, and glaucoma diseases is discussed in this research study. It is based on deep learning image processing techniques. For the detection of eye diseases, software used retinal and OTC images. This study presents Yolo, UNET, customized CNN, and Auto ML model-based system for detecting eye diseases. For the tasks of disease identification and grading, the suggested methods each obtained more than 87% accuracy. The primary objective of this study is to achieve automated identification of eye disease images. This is accomplished through the implementation of a deep learning model alongside advanced image processing techniques, enabling the automatic classification of eyes into either a healthy or diseased category. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

An Integrated Machine Learning Framework for Effective Classification of Water

An Integrated Machine Learning Framework for Effective Class...

引用

2023 International Conference on Energy, Power, Environment, Control, and Computing, ICEPECC 2023

作者： Aleem, Isha Ur Rehman, Attique Javaid, Sabeen Ali, Tahir Muhammad University of Sialkot Department of Software Engineering Sialkot Pakistan GULF University for Sciences and Technology Department of Computer Science Mubarak Al-Abdullah Kuwait

ISBN: (纸本)9781665476010

Water is an essential need for all living things. The problem people are facing especially in urban areas is the diseases that have been caused by water which is mainly Dengue or malaria because there are many metals such as ammonium aluminum silver and other bacterial or viral things present in water. The first step toward a healthy lifestyle is to drink purified water. In this paper, the methodology that has been used here is to detect whether the water people are using for drinking purposes is safe enough to use or not in the data set and the specific methodology is binomial type as yes or no, 912 for positive states and 7084 negative states which means that 0.8864 for 0 and 0.114 for 1. The ratio for negative is far higher than the positive one. We tested the model in two ways first with simple feature extraction, smote Upsampling and with vote ensemble. In smote Upsampling accuracy with the random forest is 88.21 % (highest). The classification error of random forest is 11.7% and with the highest rate is 94.73% which is recall and specificity is 81.71% which is the lowest in the random forest whereas with vote ensemble the combinations of two algorithms have been used and the highest accuracy is from naive Bayes and KNN and the accuracy from them is 96.00% with the classification error of 6% only its precision rate is higher which is 98.89% and lowest specificity of 75.00%. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Alignment efficient image-sentence retrieval considering transferable cross-modal representation learning

引用

Frontiers of computer Science 2024年第1期18卷 77-91页

作者： Yang YANG Jinyi GUO Guangyu LI Lanyu LI Wenjie LI Jian YANG School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Department of Computing Hong Kong Polytechnic UniversityHong Kong 100872China State Key Lab.for Novel Software Technology Nanjing UniversityNanjing 210094China 14th Research Institute of China Electronics Technology Group Corporation Nanjing 210094China guangyu.li2017@***

Traditional image-sentence cross-modal retrieval methods usually aim to learn consistent representations of heterogeneous modalities,thereby to search similar instances in one modality according to the query from another modality in *** basic assumption behind these methods is that parallel multi-modal data(i.e.,different modalities of the same example are aligned)can be obtained in *** other words,the image-sentence cross-modal retrieval task is a supervised task with the alignments as ***,in many real-world applications,it is difficult to realign a large amount of parallel data for new scenarios due to the substantial labor costs,leading the non-parallel multi-modal data and existing methods cannot be used *** the other hand,there actually exists auxiliary parallel multi-modal data with similar semantics,which can assist the non-parallel data to learn the consistent ***,in this paper,we aim at“Alignment Efficient Image-Sentence Retrieval”(AEIR),which recurs to the auxiliary parallel image-sentence data as the source domain data,and takes the non-parallel data as the target domain *** single-modal transfer learning,AEIR learns consistent image-sentence cross-modal representations of target domain by transferring the alignments of existing parallel ***,AEIR learns the image-sentence consistent representations in source domain with parallel data,while transferring the alignment knowledge across domains by jointly optimizing a novel designed cross-domain cross-modal metric learning based constraint with intra-modal domain adversarial ***,we can effectively learn the consistent representations for target domain considering both the structure and semantic ***,extensive experiments on different transfer scenarios validate that AEIR can achieve better retrieval results comparing with the baselines.

关键词： image-sentence retrieval transfer learning semantic transfer structure transfer

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of the Bernoulli and Multinomial Naive Bayes Classifiers for Text Classification in Machine Learning

Comparative Analysis of the Bernoulli and Multinomial Naive ...

引用

2023 International Conference Automatics and Informatics, ICAI 2023

作者： Kalcheva, Neli Marinova, Ginka Todorova, Maya Technical University of Varna Department 'Software and Internet Technology' Varna Bulgaria Technical University of Varna Department 'Computer Systems and Technologies' Varna Bulgaria

ISBN: (纸本)9798350312911

The purpose of the report is a comparative analysis of the Bernoulli and Multinomial Naive Bayes classifiers in text classification for machine learning. The conducted research demonstrates that when classifying English user comments, the accuracy and precision of the Multinomial Naive Bayes classifier are higher than those of the Bernoulli Naive Bayes classifier, with the difference increasing with the volume of data. Both the Bernoulli and Multinomial Naive Bayes classifiers have identified a higher percentage of negative comments as belonging to their respective classes and a lower percentage of positive comments as belonging to their respective classes when classifying English user opinions. The Multinomial Naive Bayes classifier has higher values for the recall parameter of positive comments compared to the Bernoulli Naive Bayes classifier, whereas the Bernoulli Naive Bayes classifier has higher values for the recall parameter of negative comments compared to the Multinomial Naive Bayes classifier. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Development of a Prediction System for Criminality and Suicidal in Sri Lanka 5

Development of a Prediction System for Criminality and Suici...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Ranasinghe, D.P.D. Fernando, R.D.T.S. Girambe, D.G. Arambegama, D.M.H.K.D. Chathurika, Bhagyanie Jayasinghe, Dulani Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350358131

This research confronts the growing challenges of rising suicide rates and crime in Sri Lanka through a dual approach, harnessing advanced machine learning and time series analysis. The innovative methodology, merging 'Feature Importance Weighting and Ensemble of Diverse Trees with the Random Forest Regressor,' achieves impressive accuracy of 93% for factors and 94% for methods. Additionally, the accuracy rates of 94% for education and 93% for occupationbased predictions enhance this comprehensive approach, offering a profound understanding of suicidal incidents and enabling precise prevention strategies. Simultaneously this study employs an ensemble of AutoRegressive Integrated Moving Average (ARIMA) models for crime prediction. This approach consistently attains high accuracy, often surpassing 90%, such as 96% and 97%. Utilizing multiple models enhances predictive accuracy and hotspot identification, granting law enforcement and policymakers flexibility to address enduring yearly hotspots and evolving dynamic hotspots. This research bridges the comprehension of suicide and crime dynamics in Sri Lanka, providing invaluable insights for evidence-based policies and targeted interventions. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspective 15

Knowledge Graph Reasoning with Logics and Embeddings: Survey...

引用

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Zhang, Wen Chen, Jiaoyan Li, Juan Xu, Zezhong Pan, Jeff Z. Chen, Huajun Zhejiang University School of Software Technology Ningbo China The University of Manchester Department of Computer Science Manchester United Kingdom Zhejiang University College of Computer Science and Technology Hangzhou China The University of Edinburgh School of Informatics Edinburgh United Kingdom

ISBN: (纸本)9798331508821

Knowledge graph (KG) reasoning is becoming increasingly popular in both academia and industry. Conventional KG reasoning based on symbolic logic is deterministic, with reasoning results being explainable, while modern embedding-based reasoning can deal with uncertainty and predict plausible knowledge, often with high efficiency via vector computation. A promising direction is to integrate both logic-based and embedding-based methods, with the vision of having advantages for both. It has attracted wide research attention with more and more works published in recent years. In this paper, we comprehensively survey these works, focusing on how logics and embeddings are integrated. We first briefly introduce preliminaries, then systematically categorize and discuss works of logic and embedding-aware KG reasoning from different perspectives, and finally conclude and discuss the challenges and further directions. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Smart Gradational Vehicle Disassembling and Troubleshooting Support Assistant 5

Smart Gradational Vehicle Disassembling and Troubleshooting ...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Tennakoon, Suvin Wickramasinha, Pamuditha Ranathunga, Hasini Ulpathakumbura, Chathuranga Kasthurirathna, Dharshana Samaratunge Arachchillage, Udara Srimath S. Sri Lanka Institute Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute Information Technology Department of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350358131

The world of vehicle service and troubleshooting can be daunting for individuals without specialized training. Vehicle manuals are often complex and challenging to comprehend, while relying on experienced mechanics for assistance can be inconvenient and expensive. To address these challenges, this research paper presents the development of an interactive vehicle service assistance system that empowers vehicle owners to independently service and troubleshoot their vehicles. The proposed system encompasses four key components: a knowledgebase construction, write semantic rules (SWRL), real-time object identification using YOLO model, audio feedback and stepwise guidance for customer. The knowledgebase is used for stepwise guidance for disassembling engine through employing marker-less Augmented Reality (AR). The knowledgebase component offers user-friendly access to troubleshooting techniques based on insights from experienced mechanics. By providing stepwise instructions accompanied by AR based visualization, users can effectively learn the process of deconstructing and assembling different components of their automobiles. The proposed system enhances vehicle troubleshooting experiences by enabling owners to acquire the necessary skills to self-troubleshooting without involving external assistance and empower individuals to take control of their own vehicles. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Feature Learning for Cross-Project software Defect Prediction

引用

computers, Materials & Continua 2023年第10期77卷 161-180页

作者： Ahmed Abdu Zhengjun Zhai Hakim A.Abdo Redhwan Algabri Sungon Lee School of Software Northwestern Polytechnical UniversityXi’anChina School of Computer Science Northwestern Polytechnical UniversityXi’anChina Department of Computer Science Hodeidah UniversityPO Box 3114Al-HudaydahYemen Research Institute of Engineering and Technology Hanyang UniversityAnsanKorea Department of Robotics Hanyang UniversityAnsanKorea

Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source *** existing CPDP approaches rely on static metrics or dynamic syntactic features,which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties,such as complex design patterns,relationships between multiple functions,and dependencies in different software projects,that are important for *** paper introduces a novel approach,a graph-based feature learning model for CPDP(GB-CPDP),that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs(CFGs)and data dependency graphs(DDGs).These graphs capture the structural and data dependencies within the source *** proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long Short-Term Memory(LSTM)networks to learn predictive *** process involves graph construction,feature learning through graph embedding and LSTM,and defect *** evaluation using nine open-source Java projects from the PROMISE dataset demonstrates that GB-CPDP outperforms state-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve(AUC).The results showcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction.

关键词： Cross-project defect prediction graphs features deep learning graph embedding

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：