检索结果-内蒙古大学图书馆

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Pradeep Kumar S CH Hussaian Basha C. Arun Prasath G. Amirthayogam Syed Ismail Abdul Lathif R. Leelavathi Computer Science Design Department Rajalakshmi Engineering College Thandalam Chennai Department of Electrical and Electronics Engineering SR University Warangal Department of ECE Mahendra Engineering College Namakkal Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Department of Data Science and Business Systems SRM Institute of Science and Technology Chennai Department of Biomedical Engineering Velalar College of Engineering and Technology Erode

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Blockchain technology represents a modern supply chain management revolution which fixes operational challenges while providing enhanced transparency at reduced costs. The research develops HB-SCOF (Hybrid Blockchain-Enabled Supply Chain Optimization Framework) which combines blockchain self-verification databases with automatic smart contracts to maintain continuous supply chain observation and evaluate data credibility. The framework integrates tamper-proof transaction tracking mechanisms with unified supply chain network connectivity for securing data transmission as a trust delivery method through unbreakable shared databases. The retail-industry case study demonstrated a 25% decrease in expenses stemming from agency elimination alongside enhanced flow management and better stock distribution. The system demonstrates its effectiveness through assessments of key performance indicators including transaction speed and data accuracy together with business cost efficiency. This part looks at implementation methods through training stakeholders in addition to transforming organizational policies which produce successful outcomes. Blockchain technology labs verify its capability to enhance supply chain management efficiency while showing realistic deployment methods.

关键词： Training Costs Supply chain management Supply chains Smart contracts Key performance indicator Blockchains Stakeholders Internet of Things Optimization

来源：评论

学校读者我要写书评

暂无评论

Image based and Point Cloud based Methods for 3D View Reconstruction in Real-time Environment

Image based and Point Cloud based Methods for 3D View Recons...

引用

IEEE Annual computing and Communication Workshop and Conference (CCWC)

作者： Arya Agrawal Teena Sharma Nishchal K. Verma Shantaram Vasikarla School of Computer Science and Engineering Vellore Institute of Technology Vellore India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Guwahati India Dept. of Electrical Engineering Indian Institute of Technology Kanpur India Dept. of Computer Science California State University Northridge CA

3D view reconstruction in a real-time unknown environment poses several challenges to vision-based applications. Herein, this paper outlines real-time experimental results and analysis of 3D view reconstruction methods. Since real-time experimentation requires inputs from different sensors, this paper outlines the results of methods from the following categories: image based methods and point cloud based methods. This paper explains the detailed steps involved in 3D view reconstruction followed by an explanation of the methods. It provides detailed discussions, advantages, limitations, and empirical results, along with presenting differences between algorithms. For analysis of experimental results, two benchmarked datasets i.e., KITTI 3D benchmark suite and ShapeNet are considered. Furthermore, the paper explores potential future scopes, including the utilization of generative models, unsupervised learning, advanced sensors, and many more.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information

arXiv

引用

arXiv 2024年

作者： Zhang, Mingkun Li, Jianing Chen, Wei Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Empowering Oral Healthcare: CNN-Assisted Diagnosis for Improved Patient Outcomes

Empowering Oral Healthcare: CNN-Assisted Diagnosis for Impro...

引用

data science and Information System (ICDSIS), IEEE International Conference on

作者： Vaishnavi Garrepalli Vishwanath Gupta S Abhishek T Anjali Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Verizon Data Services India pvt Ltd Hyderabad India Rolls-Royce Inc Bangalore India

ISBN: (数字)9798350381665

ISBN: (纸本)9798350381672

In today’s world, health is very important, and among the many aspects of well-being, oral wellness is one of the crucial components. Diagnostic investigation in everyday clinical procedures primarily consists of reviewing periapical radiography, which visualizes dental anatomy such as teeth, bone, and soft tissues within the oral cavity. Nonetheless, subjective errors may arise during human interpretation of dental radiographs which also take a lot of time. Most of these dental X-rays have an important role in diagnosing various conditions like Implant, Fillings, Cavity, and Impacted teeth under accurate assessment of classification of dental radiographs. These imaging techniques can help dentists detect anomalies within the mouth through this diagnosis process. To improve the accuracy of diagnosis and reduce the costs of clinical operations, this study presents a novel approach that automates the detection of problematic teeth and other dental diseases using these x-ray images using CNN (Convolutional Neural Networks) architecture VGG19 for making the right diagnosis choices.

关键词： Accuracy Computational modeling Teeth X-rays Feature extraction Dentistry Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning to Predict IFC Project Success and Failure 1

Leveraging Machine Learning to Predict IFC Project Success a...

引用

1st International Conference for Women in computing, InCoWoCo 2024

作者： Jayanthi, S. Ganesan, Jeya Begum, Ismatha Ramesh, E. Balaraman, Ravikumar Gunasree, Sunkam The ICFAI Foundation for Higher Education Faculty of Science and Technology Department of AI&DS Telangana India Sri Sairam Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Guru Nanak Institute of Technology Department of Information Technology Telangana Ibrahimpatnam India ICFAI Business School The ICFAI Foundation for Higher Education Department of Finance and Accounting Telangana India Teegala Krishna Reddy Engineering College Department of Information Technology Telangana India

ISBN: (纸本)9798331518943

This research expounds on the efficacy and impact of a machine learning-based approach in managing the investment services projects of the International Finance Corporation (IFC). It is achieved by focusing on the impact of financial interventions and project completion. We used a detailed dataset to assess trends in project status over time. The details about the growth of completed and active projects and the fluctuations in pending stages, like signing, disbursement, and approval are available in the dataset. We experimented with the ML models, including Random Forest, Gradient Boosting, Logistic Regression, SVC, and Decision Tree, to predict project outcomes. These models are evaluated with the metrics such as, accuracy, precision, recall, F1-score, and ROC AUC. After rigorous experiments, we observed that Gradient Boosting achieved the highest accuracy (90.76%) and Random Forest closely followed (90.43%). We identified significant trends that include a high success rate in project completion, an incremental growth in active projects, and a low occurrence of hold and pending approval statuses. We also performed statistical analysis and observed that loans dominate IFC's financial support and risk management and guarantees see less use. Additionally, correlations between total investments and other financial products highlight a diversified investment strategy. The findings emphasize opportunities for improving project approval efficiency, managing bottlenecks, and implementing data-driven decision-making to optimize investment strategies and enhance sustainable development outcomes. This research offers actionable insights for policymakers, demonstrating how ML can improve project management processes and maximize the impact of IFC investments in developing economies. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Research on NARX wind speed prediction network based on Copula 27

Research on NARX wind speed prediction network based on Copu...

引用

27th International Conference on Automation and computing, ICAC 2022

作者： Wu, Dizhi Dai, Jun Zhang, Taihao Yu, Shengping Xing, Bing Chen, Liangyin SiChuan University School of Computer Science ChengDu China The Second Research Institute CASRI ChengDu China Northeastern University Liaoning China Chongqing Innovation Center of Industrial Big-Data Chongqing China

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Accurate wind speed forecasting is the key to ensure the safe and stable access of wind energy to the grid system. Accurate wind speed forecasting can avoid the unnecessary loss of wind turbines due to high wind speed, and it is also helpful for wind power forecasting. However, the wind speed data is different from the general time series data, and the intermittency of the wind brings great volatility due to the weak continuity. There are a large number of peak points within the range of high wind speed. These peak points make it difficult to achieve accurate wind speed forecasting, no improvement method has been proposed for these wind speed characteristics in existing studies. This work proves the inaccuracy of maximum wind speed prediction through mathematical modeling, analyzes the correlation between meteorological data and wind speed in the data set, and proposes to take the most dependent meteorological data as an additional input to train the network, and through the copula connection function, it is proved that there is a tail dependence between the new parameters and the maximum wind speed. It can be used as a new method to improve the prediction accuracy of high wind speed peak. © 2022 IEEE.

关键词： Wind speed

来源：评论

学校读者我要写书评

暂无评论

Exclusion Vis: A Visual Interactive System for Exclusion Analysis in Life Insurance Using Machine Learning Techniques

Exclusion Vis: A Visual Interactive System for Exclusion Ana...

引用

International Conference on Behavior, Economic and Social computing (BESC)

作者： Md Rafiqul Islam Lam Nguyen Thanh Thao Shanjita Akter Prome Md. Kowsar Hossain Sakib Cesar Sanin Guandong Xu Weidong Huang Information Systems Australian Institute of Higher Education Sydney Australia College of Business & Management UinUniversity Vietnam School of Computer Science Taylors University Malaysia Data Science Institute University of Technology Sydney Australia TD School University of Technology Sydney Australia

ISBN: (数字)9798331531904

ISBN: (纸本)9798331531911

Exclusion analysis in life insurance stands out as a crucial task in minimizing customer risks. Numerous insur-ance companies have implemented artificial intelligence (AI) solutions to streamline processes and mitigate customer-related risks, specifically leveraging machine learning (ML) technolo-gies. While some studies have acknowledged its significance, there needs to be more to deliver comprehensive research on exclusion analysis utilizing advanced techniques. Thus, this paper focuses on exclusion classification blending with visual interactive systems (Vis), aiming to comprehend data obtained from customer disclosure information. To tackle this challenge, 1) we initiate the investigation by employing various multi-label classifiers, 2) apply several ML techniques, utilizing data from a prominent Australian insurance company, where support vector classification (SVC) and random forest (RF) emerges as the superior performer, and 3) we introduce a visual interactive system called Exclusion Vis, meticulously crafted to facilitate in-depth exploration of the obtained results. The evaluation of Exclusion Vis further underscores its superiority compared to existing systems.

关键词： Industries Visualization Social computing Interactive systems Insurance Static VAr compensators Vectors Classification algorithms Risk management Random forests

来源：评论

学校读者我要写书评

暂无评论

CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning

arXiv

引用

arXiv 2022年

作者： Meng, Chutong Ao, Junyi Ko, Tom Wang, Mingxuan Li, Haizhou ByteDance China Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China

Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to a sequence of discrete codes, and perform code representation learning, where we predict the code representations based on a masked view of the original speech input. Unlike the prior self-distillation approaches of which the teacher and the student are of the same modality, our target model predicts representations from a different modality. CoBERT outperforms the most recent state-of-the-art performance on the ASR task and brings significant improvements on the SUPERB speech translation (ST) task. Our code and models are released at https://***/mct10/CoBERT. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

A Point Cloud Gridding Method for Detecting Rail Intruding Foreign Object 15

A Point Cloud Gridding Method for Detecting Rail Intruding F...

引用

15th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Beijing 2024

作者： Xu, Shaowei Liu, Wei Yang, Yang Jin, Xiaozhao He, Jin Chengdu Jiaoda Guangmang Technology Co. Ltd. Chendu China Chengdu SinoRail Electronics Co. Ltd. Chendu China Chengdu Aerospace Science and Industry Big Data Research Institute Co. Ltd. Chendu China School of Automation Chengdu University of Information Technology Chendu China

ISBN: (纸本)9798350354010

Intruding foreign objects (IFO) pose a serious threat to railway safety operations. Existing detection algorithms often suffer from significant false alarms and missed detections, rendering them ineffective in practical IFO detection. To address this issue, we propose a point cloud gridding method for detecting rail IFO. Firstly, this method provides effective IFO detection hardware by selecting an appropriate lidar angular resolution based on the requirements for detecting IFO. Secondly, we map pillar point clouds to Bird's Eye View (BEV) to form detection grids, enabling effective IFO detection and improving detection accuracy and recall rates. Extensive experiments and real-world applications have demonstrated the effectiveness of this method. © 2024 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Improving Heart Disease Prediction with Stacked Ensemble Learning: A Comparison of Binary and Multiclass

Improving Heart Disease Prediction with Stacked Ensemble Lea...

引用

Women in computing (InCoWoCo), International Conference for

作者： Amirthaa M Gerardine Immaculate Mary Anitha Julian Anto Lourdu Xavier Raj Selvarathinam School of Electronics Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Saveetha Engineering College Chennai Tamilnadu India Data Science and Analytics Grand Valley State University Michigan USA

ISBN: (数字)9798331518943

ISBN: (纸本)9798331518950

Heart disease prediction remains a critical area of research due to its significant impact on public health. This paper, titled “Improving Heart Disease Prediction with Stacked Ensemble Learning: A Comparison of Binary and Multiclass,” presents a comprehensive study comparing the performance of binary and multiclass classification models for heart disease prediction. Utilizing two distinct datasets, one for binary classification and one for multiclass classification. The study evaluates various machine learning and deep learning models, with a focus on stacked ensemble methods. The Binary Classification Results leveraging the Preprocessing-and-PCA-on-Heart-Disease-dataset, the study evaluated several models including Random Forest, Support Vector Machine (SVM), XGBoost, Gradient Boosting, Deep Learning model, and Logistic Regression. The results indicate that the Stacking Ensemble model achieved the highest accuracy of 90.2%, outperforming individual models where Random Forest (88.5%), SVM (89.1%), XGBoost (89.7%), Gradient Boosting (88.0%) and Deep Learning (89.1%). The Multiclass Classification study using the UCI Heart Disease dataset, when applied the same models, the Stacking Ensemble model achieved an accuracy of 64.1%, which, although superior to other individual models such as Random Forest (58.1%), SVM (54.3%), Gradient Boosting (59.2%) and Deep Learning model (57.6%) fell short compared to XGBoost, which attained an accuracy of 65.8%. This outcome highlights the challenges associated with multiclass classification in heart disease prediction.

关键词： Heart Support vector machines Deep learning Accuracy Stacking Predictive models Boosting Ensemble learning Random forests Diseases

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：