检索结果-内蒙古大学图书馆

2019 2nd International Conference on Mathematics and Natural sciences, IConMNS 2019

作者： Gunadi, I.G.A. Artha, I.P.M.K. Christyaditama, I.G.P. Wicaksana, G.A.S. Martina, I.M. Departement of Physics and Natural Science Teaching Universitas Pendidikan Ganesha Indonesia Magister Program of Computer Science Universitas Pendidikan Ganesha Indonesia

Many studies raise the issue of analysis on the quality of coffee beans (green beans). Green beans are the term used to indicate coffee beans before roasting. The importance of analyzing the quality of coffee beans not only in coffee beans but also in rice seeds. Rice seeds are used as a mixture in the roasting process of coffee. Analysis of the quality of roasted coffee is very important. In roasted coffee beans can be damaged and changes to the coffee beans. Some types of damage to coffee beans include, blackened seeds, partially blackened seeds, browned seeds, broken seeds, perforated seeds, epidermis seeds, horned skin seeds, too young seeds, spotted seeds, and dirty seeds. This study focuses on one of the damage factors, namely broken coffee beans after broken beans. In this study, analysis of roasted coffee quality was determined by shape analysis. The shape analysis uses elongation values. there are two categories of classification, the first class of coffee is of good quality, and the second is coffee with poor grade. Classification is good if the elongation value is more than 0.85, for other conditions it is classified as bad. The results of this study have the following accuracy values, at coffee with a classification of good accuracy of 93.4%, while those at coffee with a bad classification of accuracy are 78.5%. © Published under licence by IOP Publishing Ltd.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

A CNN-based Stock Price Trend Prediction with Futures and Historical Price 1

A CNN-based Stock Price Trend Prediction with Futures and Hi...

引用

1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020

作者： Wu, Jimmy Ming-Tai Li, Zhongcui Srivastava, Gautam Frnda, Jaroslav Diaz, Vicente Garcia Lin, Jerry Chun-Wei Shandong University of Science and Technology School of Computer Science and Engineering China Brandon University Department of Mathematics and Computer Science Brandon Canada University of Zilina Department of Quantitative Methods and Economic Informatics Zilina Slovakia University of Oviedo School of Computer Engineering Oviedo Spain Western Norway University of Applied Sciences Department of Computer Science Electrical Engineering and Mathematical Sciences Bergen Norway

ISBN: (纸本)9781665404839

In this paper, focusing on the task of feature extraction using financial time series as well as trend prediction for prices, a new stock sequence array convolutional neural network model is presented. This model shows promising results in improving the accuracy in stock trading forecasts. The implemented model collects data from historical sources and futures (leading indicators) of stocks. The model then uses arrays as the input map for a Convolutional Neural Network (CNN) framework. Through in-depth experimental results using the Taiwanese stock market, we are able to show that the designed approach achieves strong results. Furthermore, where compared with state-of-the-art similar models, our results show promising performance among all compared approaches. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An ensemble technique to detect fabricated news article using machine learning and natural language processing techniques

An ensemble technique to detect fabricated news article usin...

引用

2020 International Conference for Emerging Technology, INCET 2020

作者： Sangamnerkar, Saarthak Srinivasan, R. Christhuraj, M.R. Sukumaran, Rajeev SRM Institute of Science and Technology Computer Science and Engineering Chennai India Indian Institute of Technology Teaching Learning Center Chennai India

ISBN: (纸本)9781728162218

Fake news or fabricated news, refers to false information published under the guise of being authentic news, often to influence political views. Fabricated news articles are a threat to people's trust in the government and in effect, one of the biggest threats that modern-day democracies are facing. As the menace of fake news is growing with each passing day, so is the research community getting more actively involved in curbing this issue. This paper reviews the current progress of the advancements done to solve the issue. The paper also presents various ensemble techniques to perform the binary classification of news articles. Additionally, the paper focuses on sources of articles to widen misclassification tolerance and make more accurate predictions. Evaluation metrics such as accuracy score, precision, recall, f-1 score have been used to make comparison among various models. The best performing model has been an ensemble of Decision Tree, Logistic Regression, Bagging Classifier used with a hard-voting ensemble technique, which gives the accuracy of over 88%. © 2020 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Research on the role of computer technology in the interaction of contemporary e-commerce network consumption

Research on the role of computer technology in the interacti...

引用

2020 International Conference on Building Technology and computer science, BTCS 2020

作者： Zhang, Weiwei EC Teaching Group School of Computer Science Information Engineering Guizhou University of Commerce 550014 China

With the rapid development of computer technology, the progress of Internet technology and the popularization of intelligent terminals, consumers are constantly inclined to online shopping and computer technology, and gradually shift to mobile terminals, resulting in mobile shopping and computer technology, and into the era of fragmentation and we media. computer technology has become the super entry point of E-commerce, and mobile social E-commerce combined with computer technology, E-commerce and mobile terminal has also become a new trend. © Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence.

关键词： computer terminals

来源：评论

学校读者我要写书评

暂无评论

Understanding Fairness Surrogate Functions in Algorithmic Fairness

arXiv

引用

arXiv 2023年

作者： Yao, Wei Zhou, Zhanke Li, Zhicong Han, Bo Liu, Yong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China TMLR Group Department of Computer Science Hong Kong Baptist University Hong Kong

It has been observed that machine learning algorithms exhibit biased predictions against certain population groups. To mitigate such bias while achieving comparable accuracy, a promising approach is to introduce surrogate functions of the concerned fairness definition and solve a constrained optimization problem. However, it is intriguing in previous work that such fairness surrogate functions may yield unfair results and high instability. In this work, in order to deeply understand them, taking a widely used fairness definition—demographic parity as an example, we show that there is a surrogate-fairness gap between the fairness definition and the fairness surrogate function. Also, the theoretical analysis and experimental results about the "gap" motivate us that the fairness and stability will be affected by the points far from the decision boundary, which is the large margin points issue investigated in this paper. To address it, we propose the general sigmoid surrogate to simultaneously reduce both the surrogate-fairness gap and the variance, and offer a rigorous fairness and stability upper bound. Interestingly, the theory also provides insights into two important issues that deal with the large margin points as well as obtaining a more balanced dataset are beneficial to fairness and stability. Furthermore, we elaborate a novel and general algorithm called Balanced Surrogate, which iteratively reduces the "gap" to mitigate unfairness. Finally, we provide empirical evidence showing that our methods consistently improve fairness and stability while maintaining accuracy comparable to the baselines in three real-world datasets. Our code is available at https://***/yw101004244/Understanding-Fairness-Surrog ate-Functions. Copyright © 2023, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Comparative analyses of multi-criteria methods in supplier selection problem 26

Comparative analyses of multi-criteria methods in supplier s...

引用

26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022

作者： Paradowski, Bartosz Szyjewski, Zdzislaw Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence Methods and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology Szczecin ul. Zolnierska 49 Szczecin71-210 Poland Institute of Management University of Szczecin ul. Cukrowa 8 Szczecin71-004 Poland

The ever-growing interest in multi-criteria decision-making methods requires research that would compare them with each other as the decision-makers would need help choosing the appropriate method. It is important to highlight the differences between them, because using different methods may result in discrepancies in the obtained rankings. Additionally, it is worthwhile for the research to take into account the problems whose solution is extremely valuable. To this end, we present a comparison of five multi-criteria decision-making methods: TOPSIS, VIKOR, COMET, SPOTIS, and MARCOS in the supplier selection problem. The conducted research showed significant differences in the evaluation of the preferences of the alternatives and some discrepancies in the obtained rankings. © 2022 The Authors. Published by Elsevier B.V.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Rule-based expert system supporting Individual Education-and-Therapeutic Program composition in SYSABA 26

Rule-based expert system supporting Individual Education-and...

引用

26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022

作者： Kolodziejczyk, Joanna Grzegorczyk-Dluciak, Nela Kuliga, Ewa Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence Methods and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Zolnierska 49 Szczecin71-210 Poland Polish Association of Behavioral Therapy Os. Wysokie 7 Krakow31-819 Poland

System for Applied Behavioral Analysis (SYSABA) is a freeware web-based software developed in Poland that aids therapists who work with developmentally disordered children. A pioneer in Poland application is adapted to Applied Behavior Analysis (ABA) methodology and is compliant with the Polish Regulation of the Ministry of Education. A part of SYSABA is a module that helps compose a compliant with Polish regulations and ABA methodology, the Individual Education-and-Therapeutic Program (pol. IPET). This development process is guided by an expert system, including specialists' knowledge of the subject. The IPET composition is demanding and time-consuming, and the decisions made by the therapist will influence the treatment results. Because there are many paths to the final curriculum, the decision-making module in SYSABA was designed to improve and standardize the process. The paper provides details of the IPETs expert module design in SYSABA. The expert knowledge of long-term supervisors was expressed in a set of regulations and constraints supplying a rule-based expert system. The unstructured expertise was translated into a logical SYSABA two-level framework. Thirty-six rules guiding skill and behavior curricula were created. The effectiveness of the expert system was confirmed by a survey after one year of SYSABA usage. © 2022 The Authors. Published by Elsevier B.V.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Home Safety IoT Monitoring Method Based on ZigBee Networking

A Novel Home Safety IoT Monitoring Method Based on ZigBee Ne...

引用

International Conference on Wireless Communications, Networking and Applications, WCNA 2021

作者： An, Ning Li, Peng Wang, Xiaoming Wu, Xiaojun Dang, Yuntong School of Computer Science Shaanxi Normal University Xi’an710119 China Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism Xi’an710119 China Key Laboratory of Modern Teaching Technology Ministry of Education Xi’an710062 China Engineering Laboratory of Teaching Information Technology of Shaanxi Province Xi’an710119 China School of Music Shaanxi Normal University Xi’an710119 China

ISBN: (纸本)9789811924552

This paper realizes the design of home safety early warning system by studying the wireless communication networking technology of ZigBee and WiFi, as well as sensor communication technology, which is based on taking home safety monitoring as the application background. In this study, CC2530 chip was used as ZigBee wireless communication module. A novel home security IoT monitoring method was proposed through sensor triggering, human activity trajectory perception algorithm design, and wireless networking and communication optimization. Meanwhile, the safety early warning and remote monitoring of home staff can be realized, and home safety can be guaranteed. The system can achieve the purpose of home monitoring and early warning with low software and hardware cost through the experimental design and result analysis. It can not only provide reference for the design of sensor communication system, but also provide technical reference for aging society and response. © 2022, The Author(s).

关键词： Zigbee

来源：评论

学校读者我要写书评

暂无评论

Practical Study of Selected Multi-Criteria methods Comparison 26

Practical Study of Selected Multi-Criteria Methods Compariso...

引用

26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022

作者： Wieckowski, Jakub Szyjewski, Zdzislaw Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence Methods and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology Szczecin ul. Zolnierska 49 Szczecin71-210 Poland Institute of Management University of Szczecin ul. Cukrowa 8 Szczecin71-004 Poland

Multi-Criteria Decision Analysis (MCDA) methods enable a comprehensive analysis of decision options to identify the most preferred values. However, the abundance of these techniques, using different transformations in the calculations, can cause a divergence of results. However, the resulting rankings should be as consistent and reliable as possible. In this paper, we used the TOPSIS, COPRAS, SPOTIS, and COMET methods to examine the consistency of their results in the practical problem of laptop evaluation. The rankings were then compared with the reference ranking. The research showed that among the methods listed, the COPRAS method's results differed the most from the others. In turn, this technique ensured a ranking in line with the reference ranking. Based on the results, it can be established that the methods used are characterized by high consistency of results. © 2022 The Authors. Published by Elsevier B.V.

关键词： Preferred numbers

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models

arXiv

引用

arXiv 2023年

作者： Wang, Xiaolei Tang, Xinyu Zhao, Wayne Xin Wang, Jingyuan Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China China School of Information Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China School of Computer Science and Engineering Beihang University China

The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs), which rely on natural language conversations to satisfy user needs. In this paper, we embark on an investigation into the utilization of ChatGPT for CRSs, revealing the inadequacy of the existing evaluation protocol. It might overemphasize the matching with ground-truth items annotated by humans while neglecting the interactive nature of CRSs. To overcome the limitation, we further propose an interactive Evaluation approach based on LLMs, named iEvaLM, which harnesses LLM-based user simulators. Our evaluation approach can simulate various system-user interaction scenarios. Through the experiments on two public CRS datasets, we demonstrate notable improvements compared to the prevailing evaluation protocol. Furthermore, we emphasize the evaluation of explainability, and ChatGPT showcases persuasive explanation generation for its recommendations. Our study contributes to a deeper comprehension of the untapped potential of LLMs for CRSs and provides a more flexible and realistic evaluation approach for future research about LLM-based CRSs. The code is available at https://***/RUCAIBox/iEvaLM-CRS. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics

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：