检索结果-内蒙古大学图书馆

Addressing Imbalance in Health Datasets: A New Method NR-Clustering SMOTE and Distance Metric Modification

Computers, Materials & Continua 2025年第2期82卷 2931-2949页

作者： Hairani Hairani Triyanna Widiyaningtyas Didik Dwi Prasetya Afrig Aminuddin Department of Electrical Engineering and Informatics Faculty of EngineeringUniversitas Negeri MalangMalang65145Indonesia Department of Computer Science Universitas BumigoraMataram83127Indonesia Department of Computer Graphic and Multimedia Faculty of ComputingCollege of Computing and Applied SciencesUniversiti Malaysia Pahang Al-Sultan AbdullahPekan26600Malaysia

An imbalanced dataset often challenges machine learning, particularly classification methods. Underrepresented minority classes can result in biased and inaccurate models. The Synthetic Minority Over-Sampling Technique (SMOTE) was developed to address the problem of imbalanced data. Over time, several weaknesses of the SMOTE method have been identified in generating synthetic minority class data, such as overlapping, noise, and small disjuncts. However, these studies generally focus on only one of SMOTE’s weaknesses: noise or overlapping. Therefore, this study addresses both issues simultaneously by tackling noise and overlapping in SMOTE-generated data. This study proposes a combined approach of filtering, clustering, and distance modification to reduce noise and overlapping produced by SMOTE. Filtering removes minority class data (noise) located in majority class regions, with the k-nn method applied for filtering. The use of Noise Reduction (NR), which removes data that is considered noise before applying SMOTE, has a positive impact in overcoming data imbalance. Clustering establishes decision boundaries by partitioning data into clusters, allowing SMOTE with modified distance metrics to generate minority class data within each cluster. This SMOTE clustering and distance modification approach aims to minimize overlap in synthetic minority data that could introduce noise. The proposed method is called “NR-Clustering SMOTE,” which has several stages in balancing data: (1) filtering by removing minority classes close to majority classes (data noise) using the k-nn method;(2) clustering data using K-means aims to establish decision boundaries by partitioning data into several clusters;(3) applying SMOTE oversampling with Manhattan distance within each cluster. Test results indicate that the proposed NR-Clustering SMOTE method achieves the best performance across all evaluation metrics for classification methods such as Random Forest, SVM, and Naїve Bayes, compared t

关键词： SMOTE modification Clustering-SMOTE manhattan distance

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Smart Pharmacy Systems: Enhancing Drug Safety and Operational Efficiency 19

Leveraging Large Language Models for Smart Pharmacy Systems:...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Osheba, Abdelrahman Abou-El-Ela, Ahmed Adel, Osama Maaod, Youssef Abuhmed, Tamer El-Sappagh, Shaker Faculty of Computer Science and Engineering Galala University Egypt College of Computing and Informatics Sungkyunkwan University Korea Republic of

ISBN: (纸本)9798331507817

Adverse drug reactions (ADRs) remain a crucial challenge in healthcare systems, highly contributing to patient mortality. We present an innovative smart pharmacy system that utilizes advanced large language models (LLMs) to enhance drug safety and pharmacy operational efficiency. Our system integrates real-time data from patient's prescriptions, medication databases, and electronic health records (EHR) to automate the detection of potential drug interactions, optimizing clinical decision-making and reducing ADR-related risks. The system's architecture is designed to easily manage prescription processing for patients, inventory management and control, and Pharmacist consultations through an intelligent chatbot interface. Key features include real-time tracking of medication expiration and inventory levels, an interaction checker API for identifying and mitigating risky drug combinations, and an LLM-powered chatbot for accurate data analysis and visualization. By combining advanced computational techniques with AI-driven insights, our smart pharmacy system not only improves medication safety but also eases pharmacy operations. This transformative approach holds the potential to significantly reduce ADR-related hospital admissions and enhance overall healthcare delivery. Our research underscores the vital role of AI and LLMs in modern pharmacy practice, offering an inclusive solution that integrates easily into existing healthcare infrastructures. The proposed smart pharmacy system can be plugged into hospital EHR systems to automatically track patient medications. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

An enhanced LSTM method for financial market forecasting 2

An enhanced LSTM method for financial market forecasting

引用

2nd International Conference on Big Data, Computational Intelligence, and Applications, BDCIA 2024

作者： Sun, Yu Mutalib, Sofianita Guangdong University of Science and Technology Guangdong Dongguan523083 China School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam40450 Malaysia

ISBN: (纸本)9781510689053

To effectively enhance the prediction accuracy of financial time series and improve the interpretability of the structural parameters of the prediction model, this paper proposes a long short-term memory (LSTM) stock price prediction model optimized in two stages based on Bayesian and Particle Swarm Optimization (BPSO-LSTM). This model represents an innovative advancement of the traditional LSTM framework, specifically designed to address complex nonlinear problems characterized by long-term dependencies, particularly in stock indices. Initially, the Bayesian algorithm is employed to optimize the core parameters of the LSTM model, establishing a foundation for subsequent Particle Swarm Optimization. Following this, an adaptive particle swarm algorithm is utilized to further refine the core parameters obtained through Bayesian Optimization, ensuring a high degree of compatibility between the characteristics of stock data and the network topology, thereby significantly improving the prediction accuracy of stock prices. Results from the prediction of the S&P 500 and Hang Seng Index indicate that the two-stage BPSO-LSTM model not only enhances prediction accuracy but also demonstrates strong universal applicability. © 2025 SPIE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Intelligent and Secure Evolved Framework for Vaccine Supply Chain Management Using Machine Learning and Blockchain

引用

SN Computer Science 2025年第2期6卷 1-28页

作者： Abdel-salam, Mahmoud Elhoseny, Mohamed El-hasnony, Ibrahim M. Faculty of Computers and Information Science Mansoura University Mansoura Egypt College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

Supply chain management (SCM) ensures that fragile goods are delivered from their origin to their destination without suffering any damage. The COVID-19 pandemic’s widespread has exposed systemic weaknesses in SCM across a variety of sectors, particularly healthcare. This paper aims to tackle issues related to vaccine expiration and fraudulent vaccine records by facilitating vaccine traceability and innovative contract features. The proposed model suggests utilizing an intelligent and secure framework that merges machine learning intelligent techniques with blockchain technology. The proposed model utilizes the Ethereum blockchain’s characteristics to establish novel smart contracts between diverse participants in the supply chain. In addition, the proposed model presents two modules to assist in predicting the demand for vaccines and analyzing the sentiment of vaccine reviews to improve the quality of vaccines. Therefore, an Improved Honey Badger Algorithm (IHBA) is presented to enhance the performance of the Long Short-Term Memory (LSTM) algorithm in predicting vaccine demand besides the credibility evaluation of reviews. For the vaccine demand prediction module, a real dataset obtained from the centers for Disease Control and Prevention (CDC) is collected and the proposed model is applied obtaining the minimum RMSE of 1.3828 for the prediction results compared with other approaches. For the review analysis module, a publicly available dataset from the University of California, Irvine (UCI) is used, and the proposed model achieved a high accuracy of user reviews of 90.6% compared with other related approaches. The proposed model is compared with other related metaheuristic algorithms and the standard deep learning optimizers. The proposed new algorithm outperforms other competitors for tuning the hyperparameters of deep learning models. Finally, the proposed system presents implications for sustainable supply chain management, enterprise operations, and public pol

关键词： Blockchain HBA Intelligent LSTM Intelligent machine learning Intelligent model Machine learning Supply chain management Sustainability Traceability

来源：评论

学校读者我要写书评

暂无评论

Sociotechnical AI Education Course Design for CS Majors and Non-Majors 56

Sociotechnical AI Education Course Design for CS Majors and ...

引用

56th Annual SIGCSE Technical Symposium on Computer Science Education, SIGCSE TS 2025

作者： Tadimalla, Sri Yash Maher, Mary Lou UNC Charlotte College of Computing and Informatics Charlotte NC United States

ISBN: (纸本)9798400705328

As generative AI increasingly integrates into society and education, the number of institutions implementing AI usage policies and offering introductory AI courses is rising. These introductory AI courses mustn't replicate the "gateway/weed-out" phenomenon observed in introductory computer science courses like CS1 and CS2. Literature in computer science education suggests that interventions such as summer camps, bridge courses, and socio-technical courses have improved the sense of belonging and retention among students from underrepresented groups, thereby broadening participation in computer science. Building on previous work to create a socio-technical curriculum for all ages and education levels, this paper presents a course for teaching introductory AI concepts that adopts a socio-technical approach, complete with weekly activities and content designed for broad access. The course has been taught as a 1-credit general education course, primarily for freshmen and first-year students from various majors, and a 3-credit course for CS majors at all levels. This paper provides a curriculum and resources to teach a socio-technical introductory AI course. This approach is important because it not only democratizes AI education across diverse student backgrounds but also equips all students with the critical socio-technical multidisciplinary perspective necessary to navigate and shape the future ethical landscape of AI technology. © 2025 Copyright held by the owner/author(s).

关键词： AI curriculum AI education intro to AI socio-technical AI literacy

来源：评论

学校读者我要写书评

暂无评论

Web Service Prediction and Composition Based on Harris Hawks Optimization and Deep Learning

引用

SN Computer Science 2025年第5期6卷 1-25页

作者： Elhoseny, Mohamed Abdel-salam, Mahmoud El-hasnony, Ibrahim M. College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Faculty of Computers and Information Science Mansoura University Mansoura Egypt

QoS-aware service composition suffers from many problems due to the uncertainties of its working environment. Besides, the many candidate services for service composition consume more processing and execution time. This paper presents a four-phases framework for reliable dynamic Web service composition. The preprocessing phase helps to reduce the percentage of missing values of the dataset. Then, clustering phase applies self-organizing maps (SOM) algorithm to cluster the QoS data to reduce data sparsity and cold-start problems of web services. Then, the prediction phase predicts uncertain QoS values of services using an optimized LSTM deep learning model. In the composition module, an improved hybrid optimization algorithm IHHO-SWO is the proposed integrating the Spider Wasp Optimizer (SWO) and is applied to generate a composite service that fits the end user requirements. An exhaustive experimental and statistical study validates the superior performance of the suggested framework. The study reveals that the framework is able to successfully deal with service prediction and composition challenges such as outlier handling, cold start, and data sparsity, lowering these problems considerably. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Classification Data analysis Harris Hawk Optimization Prediction model Service composition Spider Wasp Optimization

来源：评论

学校读者我要写书评

暂无评论

Bias analysis of AI models for undergraduate student admissions

引用

Neural computing and Applications 2025年第12期37卷 7785-7795页

作者： Van Busum, Kelly Fang, Shiaofen Department of Computer Science and Software Engineering Butler University IndianapolisIN United States Computing and Engineering Indiana University Luddy School of Informatics Indiana University Indianapolis IndianapolisIN United States

Bias detection and mitigation is an active area of research in machine learning. This work extends previous research done by the authors Van Busum and Fang (Proceedings of the 38th ACM/SIGAPP Symposium on Applied computing, 2023) to provide a rigorous and more complete analysis of the bias found in AI predictive models. Admissions data spanning six years was used to create an AI model to determine whether a given student would be directly admitted into the School of Science under various scenarios at a large urban research university. During this time, submission of standardized test scores as part of a student’s application became optional which led to interesting questions about the impact of standardized test scores on admission decisions. We developed and analyzed AI models to understand which variables are important in admissions decisions, and how the decision to exclude test scores affects the demographics of the students who are admitted. We then evaluated the predictive models to detect and analyze biases these models may carry with respect to three variables chosen to represent sensitive populations: gender, race, and whether a student was the first in his/her family to attend college. We also extended our analysis to show that the biases detected were persistent. Finally, we included several fairness metrics in our analysis and discussed the uses and limitations of these metrics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Distribution-flexible subset quantization for post-quantizing super-resolution networks

引用

Science China(Information Sciences) 2025年第3期68卷 163-180页

作者： Yunshan ZHONG Mingbao LIN Jingjing XIE Yuxin ZHANG Fei CHAO Rongrong JI Institute of Artificial Intelligence Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of ChinaXiamen University Tencent Youtu Lab Department of Artificial Intelligence School of Informatics Xiamen University Peng Cheng Laboratory

This paper introduces distribution-flexible subset quantization(DFSQ), a post-training quantization method for super-resolution networks. Our motivation for developing DFSQ is based on the distinctive activation distributions of current super-resolution models, which exhibit significant variance across samples and channels. To address this issue, DFSQ conducts channel-wise normalization of the activations and applies distribution-flexible subset quantization(SQ), wherein the quantization points are selected from a universal set consisting of multi-word additive log-scale values. To expedite the selection of quantization points in SQ, we propose a fast quantization points selection strategy that uses K-means clustering to select the quantization points closest to the centroids. Compared to the common iterative exhaustive search algorithm, our strategy avoids the enumeration of all possible combinations in the universal set, reducing the time complexity from exponential to linear. Consequently, the constraint of time costs on the size of the universal set is greatly relaxed. Extensive evaluations of various super-resolution models show that DFSQ effectively improves performance even without fine-tuning. For example, for 4-bit EDSR×2 on the Urban benchmark, DFSQ obtains 0.242 dB PSNR gains.

关键词： super-resolution post-training quantization distribution-flexible subset quantization neural network

来源：评论

学校读者我要写书评

暂无评论

GAProtoNet: A Multi-head Graph Attention-based Prototypical Network for Interpretable Text Classification 31

GAProtoNet: A Multi-head Graph Attention-based Prototypical ...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wen, Ximing Tan, Wenjuan Weber, Rosina O. College of Computing and Informatics Drexel University Philadelphia United States Department of Computer Science Tsinghua University Beijing China

ISBN: (纸本)9798891761964

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on text classification tasks with their powerful word embeddings, but their black-box nature, which leads to a lack of interpretability, has been a major concern. In this work, we introduce GAProtoNet, a novel white-box Multi-head Graph Attention-based Prototypical Network designed to explain the decisions of text classification models built with LM encoders. In our approach, the input vector and prototypes are regarded as nodes within a graph, and we utilize multi-head graph attention to selectively construct edges between the input node and prototype nodes to learn an interpretable prototypical representation. During inference, the model makes decisions based on a linear combination of activated prototypes weighted by the attention score assigned for each prototype, allowing its choices to be transparently explained by the attention weights and the prototypes. Experiments on multiple public datasets show our approach achieves superior results without sacrificing the accuracy of the original black-box LMs. We also compare with four alternative prototypical network variations and our approach achieves the best accuracy and F1 among all. Our case study and visualization of prototype clusters also demonstrate the efficiency in explaining the decisions of black-box models built with LMs. Our codes are available at https://***/ximingwen/GAProtoNet. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Evaluating Subtle Positive–Negative Facial Expression Transitions for Monitoring Changes in Personal Internal States 21st

Evaluating Subtle Positive–Negative Facial Expression Trans...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Zhang, Junyao Shimonishi, Kei Ueda, Hirotada Kondo, Kazuaki Nakamura, Yuichi Graduate School of Informatics Kyoto University Kyoto Japan Academic Center for Computing and Media Studies Kyoto University Kyoto Japan

ISBN: (纸本)9789819601219

Predicting the internal conditions of people who have difficulties explaining their internal states because of dementia or other problems has gained increasing attention. Monitoring internal states requires precise evaluation of weak (less intense) facial expressions, which is challenging due to the significant influence of individual characteristics on facial expressions. For instance, a person may look more like they are smiling or frowning than others even when they are in a neutral state. In addition, ambiguous changes may occur. For example, subtle changes from neutral to positive facial expressions could be similar to those from neutral to negative expressions, which further complicates the evaluation of facial expressions. Conventional FER systems designed for various people with various personal differences often have difficulties in detecting and indexing such subtle changes caused by motion artifacts that exceed the displacement of feature points. In this study, we developed a personalized and customized facial expression recognition (FER) model that can monitor changes in a person’s internal state by recognizing the transitions in their daily facial expressions. The model employs image comparison to monitor a specific person. It is tailored to each individual by training it with the individual’s actual facial expressions. This model is not universal but can be adjusted to individual emotional nuances. To account for arbitrary transitions along positive–negative facial expressions, we developed a two-stage FER framework comprising three deep neural networks (DNNs). The proposed framework uses images without detecting facial feature points. The first stage performs binary classification on the input image pairs and categorizes each image as positive or negative. The second stage compares the images to predict the direction of changes, i.e., whether the expression shifts toward positive or negative. This stage is trained on transitional image pairs, focusing

关键词： Deep neural networks

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：