检索结果-内蒙古大学图书馆

2nd International Conference on Technology Innovation and Its Applications, ICTIIA 2024

作者： Ritonga, Ihdi Syahputra Candra, Ade Budiman, Mohammad Andri Universitas Sumatera Utara Data Science and Artificial Intelligence Program Medan Indonesia

ISBN: (纸本)9798350351613

This research aims to optimize library services through user segmentation analysis and to determine the correlation between user activities and student graduation levels using the K-Means clustering algorithm. By analyzing this relationship, the study seeks to enhance both library service effectiveness and student academic success. The methodology involves several stages: data collection, preprocessing (including data merging and cleaning), and data modeling. The K-Means clustering method is specifically used to segment library users based on various factors and to identify patterns that correlate with student graduation levels. The dataset comprises circulation data and student graduation data from the UIN Padangsidimpuan Academic Information System (SIAKAD), including variables such as study duration, Grade Point Average (GPA), and loan levels. The analysis resulted in the identification of three distinct clusters: Cluster 0, Cluster 1, and Cluster 2. These clusters are characterized by different lengths of study, GPA, and library loan levels, providing insights into the preferences and needs of library users. The findings suggest that tailored library services, informed by these clusters, can potentially enhance student engagement and academic performance. For example, libraries could develop specialized discussion services related to student research, thereby improving thesis quality and research outcomes. Additionally, optimizing digital-based library services can further support student success. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

The Explainable Analytics for Exploring Misdiagnoses 24

The Explainable Analytics for Exploring Misdiagnoses

引用

8th International Conference on Medical and Health Informatics, ICMHI 2024

作者： Pai, HAO-Ting Chung, Wen-Cheng Fang, Xin-Hong Hsu, Yu-Hsin Huang, Shu-Ting Bachelor Program of Big Data Applications in Business National Pingtung University Pingtung Taiwan Bachelor Program of Artificial Intelligence National Yunlin University of Science and Technology Douliou Taiwan

ISBN: (纸本)9798400716874

Current AI-driven methods in healthcare show significant limitations in addressing misdiagnoses, often leading to serious consequences. This work highlights the inadequacy of state-of-the-art AI in managing diagnostic errors through experiments with public real-world datasets, namely "Bone Marrow Transplant: Children" and "Breast Cancer Wisconsin (Original)". We propose two novel scoring measures—Local-score and Global-score—to enhance the accuracy of Transparent Classification (TC). Experimental results indicate that Global-score improves recall but may reduce precision, whereas Local-score slightly lowers recall for better precision. These findings suggest that both Local-score and Global-score can effectively identify misdiagnoses, marking a substantial improvement over traditional AI methods. This research offers a new perspective in employing explainable AI to address the challenges of misdiagnoses, thereby improving patient care and medical diagnostic accuracy. © 2024 ACM.

关键词： Explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Utilization of K-Means Clustering to Examine Library User Segmentation's Impact on Student Graduation Rates

Utilization of K-Means Clustering to Examine Library User Se...

引用

Technology Innovation and Its Applications (ICTIIA), International Conference on

作者： Ihdi Syahputra Ritonga Ade Candra Mohammad Andri Budiman Master of Data Science and Artificial Intelligence Program Universitas Sumatera Utara Medan Indonesia

ISBN: (数字)9798350351613

ISBN: (纸本)9798350351620

关键词： Technological innovation Correlation Clustering methods Merging Clustering algorithms data collection Libraries data models Cleaning Information systems

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Inference Engine to Predict Uncertain Sugar Content for Sugar Industry 9th

A Hybrid Inference Engine to Predict Uncertain Sugar Content...

引用

9th International Conference on Computer science and Computational intelligence, ICCSCI 2024

作者： Asrol, Muhammad Napthaleni Utama, Ditdit Nugeraha Suharjito Harito, Christian Syafrudin, Muhammad Industrial Engineering Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia Department of Artificial Intelligence and Data Science Sejong University Seoul05006 Korea Republic of

The sugar industry is facing challenges in increasing productivity to meet consumer demand. One opportunity for productivity improvement lies in ensuring sugar content. This study proposes a hybrid model to predict sugar content by considering uncertainty factors. A hybrid model combining fuzzy subtractive clustering, and a fuzzy inference system is proposed to predict sugar content. The clustering results using silhouette and fuzzy subtractive clustering successfully identified 6 cluster centres from 2225 datasets collected in a sugar industry in East Java Province. The hybrid inference engine model is designed with fuzzy rules derived from the clustered data. Two inference models are developed: triangular and Gaussian fuzzy numbers. The testing results indicate that the hybrid model with triangular fuzzy numbers shows the smallest error with an R2 value of 0.95. This model is possible to applied in the sugar industry for decision makers in improving productivity with taking attention into uncertain factors influencing sugar content. © 2024 The Authors.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Specific Expert Learning: Enriching Ensemble Diversity via Knowledge Distillation

引用

IEEE Transactions on Cybernetics 2023年第4期53卷 2494-2505页

作者： Kao, Wei-Cheng Xie, Hong-Xia Lin, Chih-Yang Cheng, Wen-Huang Yuan-Ze University Department of Electrical Engineering Taoyuan320 Taiwan Institute of Electronics National Yang Ming Chiao Tung University Hsinchu300 Taiwan National Chung Hsing University Artificial Intelligence and Data Science Program Taichung400 Taiwan

In recent years, ensemble methods have shown sterling performance and gained popularity in visual tasks. However, the performance of an ensemble is limited by the paucity of diversity among the models. Thus, to enrich the diversity of the ensemble, we present the distillation approach - learning from experts (LFEs). Such method involves a novel knowledge distillation (KD) method that we present, specific expert learning (SEL), which can reduce class selectivity and improve the performance on specific weaker classes and overall accuracy. Through SEL, models can acquire different knowledge from distinct networks with various areas of expertise, and a highly diverse ensemble can be obtained afterward. Our experimental results demonstrate that, on CIFAR-10, the accuracy of the ResNet-32 increases 0.91% with SEL, and that the ensemble trained by SEL increases accuracy by 1.13%. Compared to state-of-the-art approaches, for example, DML only improves accuracy by 0.3% and 1.02% on single ResNet-32 and the ensemble, respectively. Furthermore, our proposed architecture also can be applied to ensemble distillation (ED), which applies KD on the ensemble model. In conclusion, our experimental results show that our proposed SEL not only improves the accuracy of a single classifier but also boosts the diversity of the ensemble model. © 2013 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

EUDRL: Explainable Uncertainty-Based Deep Reinforcement Learning for Portfolio Management 15

EUDRL: Explainable Uncertainty-Based Deep Reinforcement Lear...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Lina, Jia Banda, Shahab S. Paib, Hao-Ting Rawal, Bharat S. International Graduate School of Artificial Intelligence Yunlin County Douliu City Taiwan Bachelor Program of Big Data Applications National Pingtung University Pingtung Taiwan Department of Computer Science and Digital Technologies University GgramblingLA United States

ISBN: (纸本)9798350370249

Supervised deep learning (SDL) has shown remarkable success in various financial applications, such as stock prediction and fraud detection. However, SDL's reliance on class labels renders it unsuitable for portfolio management (PM) tasks, where such labels are often unavailable. To address this limitation, we propose a novel two-level architecture based on deep reinforcement learning (DRL) for PM, which does not require class labels. Our approach comprises several local agents that provide trading decisions and uncertainty assessments for individual stocks, and a global agent that makes portfolio management decisions based on the outputs of the local agents. Additionally, we incorporate the concept of explainable AI (XAI) into our framework using the SHAP (Shapley additive explanations) method, enhancing the transparency and interpretability of the global agent's decisions. Our experimental results demonstrate that the proposed architecture consistently yields profitable outcomes in the market. ©2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Resume Recommendation using RNN Classification and Cosine Similarity 7th

Resume Recommendation using RNN Classification and Cosine Si...

引用

7th International Scientific Conference on Intelligent Information Technologies for Industry, IITI 2023

作者： Huseyinov, Ilham Diallo, Issa Raed, Mhd Wasim Software Engineering Department Istanbul Aydin University Istanbul Turkey Graduate Institute of Science Artificial Intelligence and Data Science Program Istanbul Aydin University Istanbul Turkey Computer Engineering Department Istanbul Aydin University Istanbul Turkey

ISBN: (纸本)9783031437885

One way to save time and resources in the human recruitment and hiring process is to post open job positions on the Internet, but the overload of applications creates challenges for hiring managers and companies to select an adequate candidate. One of the solutions is to apply intelligent tools such as Deep Learning and recommender system algorithms to speed up the hiring process and identify the right candidates. In this paper, we propose a two-fold algorithmic approach to 1) building an RNN classifier for resume classification;2) using cosine similarity for resume recommendation to find a candidate that fits job requirements best after selecting all the resumes that belong to the right category. The performance of the proposed RNN classifier is evaluated in terms of accuracy, precision, recall, F1-score, and confusion matrix criteria. The experiment results have shown that the RNN classifier performs better than the other classifiers such as GNB, Linear SVM, RF, and BERT on the same dataset. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach To The Prediction Of Bank Customer Churn Problem 3

A Machine Learning Approach To The Prediction Of Bank Custom...

引用

3rd International Informatics and Software Engineering Conference, IISEC 2022

作者： Huseyinov, Ilham Okocha, Omobola Istanbul Aydin University Software Engineering Department Istanbul Turkey Graduate Institute of Science Artificial Intelligence and Data Science Program Istanbul Aydin University Istanbul Turkey

ISBN: (数字)9781665459952

ISBN: (纸本)9781665459952

Customers in the banking industry nowadays have many options when deciding where to invest their money. Customer retention and churn have thus emerged as crucial challenges for the majority of banks. This research tries to solve the customer churn problem by applying machine learning algorithms. Classifiers such as Logistic Regression, Support Vector Machine, Random Forest, Gradient Boosting, eXtreme Gradient Boosting, and Light Gradient Boosting are employed. To this end, first, the irrelevant features are removed by applying a feature selection technique, and the most pertinent features are identified, second, the resulting data set is balanced using the SMOTE method. The results of experiments on classifiers with balanced data and with imbalanced data are compared in terms of accuracy, recall, precision, and performance. In the case of imbalanced data (before the SMOTE is applied) no classifier over-performed others. In the case of balanced data (after SMOTE is applied) the Random Forest classifier outrightly overperformed other classifiers. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

AN INTERPRETABLE GENERALIZATION MECHANISM FOR ACCURATELY DETECTING ANOMALY AND IDENTIFYING NETWORKING INTRUSION TECHNIQUES

arXiv

引用

arXiv 2024年

作者： Pai, Hao-Ting Kang, Yu-Hsuan Chung, Wen-Cheng Bachelor Program of Big Data Applications in Business National Pingtung University Taiwan International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Taiwan Bachelor Program of Artificial Intelligence National Yunlin University of Science and Technology Taiwan

The increasing complexity of modern network environments presents formidable challenges to Intrusion Detection Systems (IDS) in effectively mitigating cyber-attacks. Recent advancements in IDS research, integrating Explainable AI (XAI) methodologies, have led to notable improvements in system performance via precise feature selection. However, a thorough understanding of cyber-attacks requires inherently explainable decision-making processes within IDS. In this paper, we present the Interpretable Generalization Mechanism (IG), poised to revolutionize IDS capabilities. IG discerns coherent patterns, making it interpretable in distinguishing between normal and anomalous network traffic. Further, the synthesis of coherent patterns sheds light on intricate intrusion pathways, providing essential insights for cybersecurity forensics. By experiments with real-world datasets NSL-KDD, UNSW-NB15, and UKM-IDS20, IG is accurate even at a low ratio of training-to-test. With 10%-to-90%, IG achieves Precision (PRE)=0.93, Recall (REC)=0.94, and Area Under Curve (AUC)=0.94 in NSL-KDD;PRE=0.98, REC=0.99, and AUC=0.99 in UNSW-NB15;and PRE=0.98, REC=0.98, and AUC=0.99 in UKM-IDS20. Notably, in UNSW-NB15, IG achieves REC=1.0 and at least PRE=0.98 since 40%-to-60%;in UKM-IDS20, IG achieves REC=1.0 and at least PRE=0.88 since 20%-to-80%. Importantly, in UKM-IDS20, IG successfully identifies all three anomalous instances without prior exposure, demonstrating its generalization capabilities. These results and inferences are reproducible. In sum, IG showcases superior generalization by consistently performing well across diverse datasets and training-to-test ratios (from 10%-to-90% to 90%-to-10%), and excels in identifying novel anomalies without prior exposure. Its interpretability is enhanced by coherent evidence that accurately distinguishes both normal and anomalous activities, significantly improving detection accuracy and reducing false alarms, thereby strengthening IDS reliability an

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

An Overview of Facial Micro-Expression Analysis: data, Methodology and Challenge

引用

IEEE Transactions on Affective Computing 2023年第3期14卷 1857-1875页

作者： Xie, Hong-Xia Lo, Ling Shuai, Hong-Han Cheng, Wen-Huang National Yang Ming Chiao Tung Univresity Institute of Electronics Hsinchu300093 Taiwan National Yang Ming Chiao Tung Univresity Department of Electrical and Computer Engineering Hsinchu300093 Taiwan National Chung Hsing University Artificial Intelligence and Data Science Program Taichung40227 Taiwan

Facial micro-expressions indicate brief and subtle facial movements that appear during emotional communication. In comparison to macro-expressions, micro-expressions are more challenging to be analyzed due to the short span of time and the fine-grained changes. In recent years, micro-expression recognition (MER) has drawn much attention because it can benefit a wide range of applications, e.g., police interrogation, clinical diagnosis, depression analysis, and business negotiation. In this survey, we offer a fresh overview to discuss new research directions and challenges these days for MER tasks. For example, we review MER approaches from three novel aspects: macro-to-micro adaptation, recognition based on key apex frames, and recognition based on facial action units. Moreover, to mitigate the problem of limited and biased ME data, synthetic data generation is surveyed for the diversity enrichment of micro-expression data. Since micro-expression spotting can boost micro-expression analysis, the state-of-the-art spotting works are also introduced in this paper. At last, we discuss the challenges in MER research and provide potential solutions as well as possible directions for further investigation. © 2010-2012 IEEE.

关键词： Surveys

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：