检索结果-内蒙古大学图书馆

Observation points classifier ensemble for high-dimensional imbalanced classification

CAAI Transactions on Intelligence Technology 2023年第2期8卷 500-517页

作者： Yulin He Xu Li Philippe Fournier‐Viger Joshua Zhexue Huang Mianjie Li Salman Salloum College of Computer Science&Software Engineering Shenzhen UniversityShenzhenChina Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen UniversityShenzhenChina Faculty of Information Technology Macao University of Science and TechnologyMacaoChina School of Computing National University of SingaporeSingaporeSingapore

In this paper,an Observation Points Classifier Ensemble(OPCE)algorithm is proposed to deal with High-Dimensional Imbalanced Classification(HDIC)problems based on data processed using the Multi-Dimensional Scaling(MDS)feature extraction ***,dimensionality of the original imbalanced data is reduced using MDS so that distances between any two different samples are preserved as well as ***,a novel OPCE algorithm is applied to classify imbalanced samples by placing optimised observation points in a low-dimensional data ***,optimization of the observation point mappings is carried out to obtain a reliable assessment of the unknown *** experiments have been conducted to evaluate the feasibility,rationality,and effectiveness of the proposed OPCE algorithm using seven benchmark HDIC data *** results show that(1)the OPCE algorithm can be trained faster on low-dimensional imbalanced data than on high-dimensional data;(2)the OPCE algorithm can correctly identify samples as the number of optimised observation points is increased;and(3)statistical analysis reveals that OPCE yields better HDIC performances on the selected data sets in comparison with eight other HDIC *** demonstrates that OPCE is a viable algorithm to deal with HDIC problems.

关键词： classifier ensemble feature transformation high-dimensional data classification imbalanced learning observation point mechanism

来源：评论

学校读者我要写书评

暂无评论

Accounting for systemic risk in analysis of crisis scenarios 21

Accounting for systemic risk in analysis of crisis scenarios

引用

21st International ISCRAM Conference, ISCRAM 2024

作者： Gonzalez, Jose J. Abbas, Reem Paulsen, Sigurd University of Agder Kristiansand Norway Department of Computer Science and Software Engineering Auckland University of Technology Auckland New Zealand Dept. of Organization Crisis Management and Information Security Kristiansand Norway

Systemic risk is ubiquitous in our increasingly globalised world owing to the interconnections within and across sectors. However, a review of National Risk Assessments performed in OECD member countries reveals that systemic risk is rarely mentioned, and it is never accounted for in those assessments. A powerful method accounts for systemic risk and identifies mitigating strategies using participatory modelling with stakeholders: strategy mapping with Strategyfinder. The risk model is represented as a directed graph consisting of risk nodes and directed edges (arrows) expressing causal influences. The method originated in the management of large, complex projects, and it has been applied to systemic risks in critical infrastructures and pandemics. We demonstrate the Strategyfinder method using a scenario describing a cyberattack on electronic communication infrastructure leading to serious consequences for health and lives. The scenario is borrowed from the report Analysis of Risk Scenarios by the Norwegian Directorate for Civil Protection. © 2024 information Systems for Crisis Response and Management, ISCRAM. All rights reserved.

关键词： Cascading effects Disaster risk reduction National Risk Assessments Risk scenarios Vicious cycles

来源：评论

学校读者我要写书评

暂无评论

Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild 38

Locating What You Need: Towards Adapting Diffusion Models to...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Yang, Jianan Gao, Chenchao Xiao, Zhiqing Zhao, Junbo Wu, Sai Chen, Gang Wang, Haobo College of Computer Science and Technology Zhejiang University China Institute of Blockchain and Data Security China School of Software Technology Zhejiang University China International School of Information Science and Engineering Dalian University of Technology China

The recent large-scale text-to-image generative models have attained unprecedented performance, while people established adaptor modules like LoRA and DreamBooth to extend this performance to even more unseen concept tokens. However, we empirically find that this workflow often fails to accurately depict the out-of-distribution concepts. This failure is highly related to the low quality of training data. To resolve this, we present a framework called Controllable Adaptor Towards Out-of-Distribution Concepts (CATOD). Our framework follows the active learning paradigm which includes high-quality data accumulation and adaptor training, enabling a finer-grained enhancement of generative results. The aesthetics score and concept-matching score are two major factors that impact the quality of synthetic results. One key component of CATOD is the weighted scoring system that automatically balances between these two scores and we also offer comprehensive theoretical analysis for this point. Then, it determines how to select data and schedule the adaptor training based on this scoring system. The extensive results show that CATOD significantly outperforms the prior approaches with an 11.10 boost on the CLIP score and a 33.08% decrease on the CMMD metric. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Drowsy Driving Detection System Using Face Detection 3

Drowsy Driving Detection System Using Face Detection

引用

3rd International Conference on Technological Advancements in Computational sciences, ICTACS 2023

作者： Mirabdullayev, Ismoiljon Ahamed Ayoobkhan, Mohamed Uvaze Jasmine Hashana, A.M. Khan Subair Ali, Liayakath Ali Software Engineering New Uzbekistan University Tashkent Uzbekistan Computer Science and Engineering Francis Xavier Engineering College Tirunelveli India School of Information Technology Digital Media and Mass Communication Tmc Institute in Tashkent Tashkent Uzbekistan

ISBN: (纸本)9798350342338

Drowsy driving poses a major threat to road safety, demanding effective solutions. To address this issue, this paper introduces a cutting-edge drowsy driving detection system that leverages advanced face detection algorithms to analyze real-time facial features. By closely monitoring eye movements and mouth patterns, the system is capable of accurately identifying early signs of fatigue. In response, timely warnings are promptly issued to the driver through various means, including audible alarms, visual cues, or even physical interventions. Although the system holds great potential in enhancing road safety, there are still challenges to overcome, particularly regarding accuracy and adaptability. However, ongoing research endeavors aim to refine the algorithms and integrate additional physiological and behavioral measures, with the goal of further improving the system's capabilities. By preventing accidents caused by drowsiness, this innovative system demonstrates a promising pathway towards bolstering road safety. By addressing the critical issue of drowsy driving, it contributes significantly to the overall safety of drivers and passengers alike, making our roads a safer place for everyone. © 2023 IEEE.

关键词： allowed distraction time braking distance deep learning driver's fatigue level Drowsy driving face analysis reaction distance

来源：评论

学校读者我要写书评

暂无评论

SeeMe: An intelligent edge server selection method for location-aware business task computing over IIoT

SeeMe: An intelligent edge server selection method for locat...

引用

作者： Dou, Wanchun Liu, Bowen Duan, Jirun Dai, Fei Qi, Lianyong Xu, Xiaolong State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China School of Computer Science Qufu Normal University Qufu China School of Computer and Software Nanjing University of Information Science and Technology Nanjing China

In the past few years, latency-sensitive task computing over the industrial internet of things (IIoT) has played a key role in an increasing number of intelligent applications, such as intelligent self-driving vehicles and unmanned aircraft systems. The edge computing paradigm provides a basic functional infrastructure for across-domain business task computing on distributed edge servers. With this observation, a trade-off between the mobile devices and the fixed edge servers is needed to run moving task computing in a low-latency way. Given this challenge, an intelligent server selection method, named SeeMe, is proposed in this paper. Technically speaking, this method aims at minimizing the communication capacity and the transferring capacity in a multiobjective optimization way to find a low-latency edge server. The experiments and comparison analysis verify the availability of our method. © 2022 John Wiley & Sons Ltd.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

PROBEXPERT: An Enhanced Q&A Platform for Reducing Time Spent on Learning and Finding Answers 7

PROBEXPERT: An Enhanced Q&A Platform for Reducing Time Spent...

引用

7th IEEE International conference for Convergence in Technology, I2CT 2022

作者： Thennakoon, Kamal Ekanayake, Dasun Marapana, Thanura Ranasinghe, Ashen Wijendra, Dinuka R. Gamage, Anjalie Sri Lanka Institute of Information Technology Department of Computer Science & Software Engineering Malabe Sri Lanka

ISBN: (纸本)9781665421683

The World Wide Web contains a wide range of material from a variety of fields. However, when concerns towards the computer science domain, information users find on the internet may not be up-to-date due to the rapid pace of change and having to spend less time on the internet for researching and debugging tasks is an added luxury. Having an expertise level while providing answers through a platform is convenient for users, yet when a user signs into a platform, the user must start from the beginning, regardless of the level of competence in the field. Moreover, not having a proper way to evaluate the existing programming knowledge is another obstacle. To address mentioned complications, researchers of this paper have introduced a new e-learning platform- 'ProbExpert'. The platform has been constructed with machine learning and deep learning approaches such as NLP, keyword extraction, semantic information analysis, cosine similarity, and information summarization. With aforesaid technologies, ProbExpert provides systems in automated answering, optimized answer generation, structured question-based quiz evaluation together with a fully automated portfolio generation with a novel user ranking algorithm based on the bell curve. © 2022 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis In Uzbek Texts In The Restaurant Field 3

Sentiment Analysis In Uzbek Texts In The Restaurant Field

引用

3rd IEEE International Conference on Problems of Informatics, Electronics and Radio engineering, PIERE 2024

作者： Kumushoy, Niyazmetova Farogat, Yusupova Ogabek, Sobirov Urgench Branch of Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi Department of Software Engineering Urgench Uzbekistan Urgench State University Department of Computer Science Urgench Uzbekistan

ISBN: (纸本)9798331516321

Sentiment analysis plays a crucial role in natural language processing, particularly in evaluating user comments and extracting valuable insights for classification tasks. This analysis can significantly impact customer satisfaction and influence a company's future development. In our study, we focused on feedback from restaurants in Tashkent, collected via Google Maps. We constructed a dataset that reflects user sentiments and applied logistic regression models for analysis. Through our evaluation, we found that proper preprocessing steps, such as stemming-especially important for agglutinative languages like Uzbek-greatly enhance model performance. These steps help in reducing words to their root forms, allowing the model to better understand the underlying sentiments. Our best-performing model achieved an impressive accuracy of 91%, demonstrating the effectiveness of our approach. The results highlight the importance of sentiment analysis in the restaurant industry, providing actionable insights that can help businesses improve their services and customer experiences. By leveraging user feedback, companies can make informed decisions that foster growth and enhance customer loyalty. Overall, our research underscores the potential of sentiment analysis in driving business success through careful data handling and analysis techniques. © 2024 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

News-Driven Stock Price Forecasting in Indian Markets: A Comparative Study of Advanced Deep Learning Models 3

News-Driven Stock Price Forecasting in Indian Markets: A Com...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Attaluri, Kaushal Tripathi, Mukesh Kumar Reddy, Srinithi Shivendra Software Engineer-Machine Learning and AI Pegasystems India Worldwide Pvt Ltd Hyderabad India Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Vasavi College of Engineering Department of Information Technology Hyderabad India D. K. College Department of Computer Application Bihar Dumraon India

ISBN: (纸本)9798350354171

Forecasting stock market prices is a challenging task for traders, analysts, and engineers due to the myriad of variables influencing stock prices. However, the advent of artificial intelligence (AI) and natural language processing (NLP) has significantly advanced stock market forecasting. AI's ability to analyze complex data sets allows for more informed predictions. Despite these advancements, stock price forecasting remains an area where AI has not yet achieved optimal results. In this paper, we forecast stock prices using 30 years of historical data from various national banks in India sourced from the National Stock Exchange. We employ advanced deep learning models, including multivariate multi-step Long Short-Term Memory (LSTM), Facebook Prophet with LightGBM and Optuna, and Seasonal Auto-Regressive Integrated Moving Average (SARIMA). Additionally, we analyze news data from tweets and reliable sources like Business Standard and Reuters, recognizing their significant impact on stock price movements. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

From Data to Diagnosis: Investigating Approaches in Mental Illness Detection 2

From Data to Diagnosis: Investigating Approaches in Mental I...

引用

2nd International Conference of Intelligent Methods, Systems and Applications, IMSA 2024

作者： Montasser, Reem Kadry Mazen, Sherif A. Helal, Iman M. A. October University for Modern Sciences and Arts Faculty of Computer Science Software Engineering Department Giza Egypt Cairo University Faculty of Computers and Artificial Intelligence Information Systems Department Giza Egypt

ISBN: (纸本)9798350362633

Mental illness is a considerable global public health problem, impacting both individual well-being and society's health. The growing popularity of social media and the increase of other data sources led to more research interest in detecting mental illness with a particular focus on utilizing and fusing emotional information. Artificial intelligence techniques like natural language processing and others, have shown encouraging improvements in recognizing complex relationships in a wide range of textual data, including clinical notes, social media posts, and interviews. In this paper, we assess the different branches of artificial intelligence based on previous research in mental illness detection, discussing methods, trends, challenges, and future research directions. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

E-tutor: Comprehensive Student Productivity Management System for Education 4

E-tutor: Comprehensive Student Productivity Management Syste...

引用

4th International Conference on Advancements in Computing, ICAC 2022

作者： Silva, Kumuditha Induwara, Rashmin Wimukthi, Malshan Poornika, Sathsarani Samaratunge Arachchillage, Udara Srimath S. Jayalath, Thilini Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398090

With the advancement of technology, e-learning has emerged as predominant in the education sector. As students, parents, and educators acknowledged, adopting e-learning can offer several benefits over traditional learning techniques. Since more individuals are becoming acclimated to online learning platforms, these online platforms can provide a simple, instructive, and efficient mode of delivery. This novel approach could be improved with the aid of Artificial Intelligence (AI) to comprehend consumers more thoroughly and provide valuable and better-suited services. Most sectors in education, including universities, swiftly adapted to new educational methodologies because of their flexibility and productivity. Nevertheless, there are some downsides that young demography experiences, such as less instructiveness, distraction due to the absence of teachers, and poor IT literacy. Consequently, these drawbacks would recede the capability of students to assimilate content during the lecture. Therefore, the main objective of this research is to implement an E-learning platform with AI learning analytics to enhance students' performance regularly while reducing the significant drawbacks of the E-learning platforms. This research consists of students' focus detection, essay-based answer evaluation, note summarization, mind map generation, and personalized guidance facilities. © 2022 IEEE.

关键词： Object detection

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：