检索结果-内蒙古大学图书馆

Deep Learning Quantitative Susceptibility Mapping With Reduced Training Time Based on Local Field Transformation

IEEE Transactions on Emerging Topics in Computational Intelligence 2025年第2期9卷 1527-1538页

作者： Wu, Ming-Long Huang, De-Rong Cheng, Jhih-Shan National Cheng Kung University Department of Computer Science and Information Engineering Tainan701 Taiwan National Cheng Kung University Institute of Medical Informatics Tainan701 Taiwan

A quantitative susceptibility mapping (QSM) approach using single-orientation imaging data is proposed in this study. The proposed method generates local field maps at five predefined orientations via deep learning from single-orientation local field maps, followed by physical dipole inversion using the analytical Calculation of Susceptibility through Multiple Orientation Sampling (COSMOS) algorithm. We termed the method pseudo COSMOS (pCOSMOS). By isolating the physical dipole inversion process from deep learning, training of the neural network model becomes greatly accelerated. Brain imaging data from 10 healthy subjects (7 training and 3 testing) acquired at 3T with five different orientations relative to the main magnetic field were included to evaluate the reconstruction quality. Results compared against two iterative (Morphology Enabled Dipole Inversion or MEDI, and Structural Feature-based Collaborative Reconstruction or SFCR) and two deep learning QSM approaches (QSMnet and Learned Proximal Convolutional Neural Network or LPCNN) using COSMOS as the reference standard revealed that the susceptibility maps obtained from pCOSMOS yielded global quantitative performance comparable to QSMnet and LPCNN, while being prominently superior to MEDI and SFCR. Estimation errors in magnetic susceptibility were between 0.01 and 0.02 ppm voxel-wise, and 0.006 ± 0.004 ppm for five selected gray matter areas. Visual inspection further suggested better preserved tissue boundaries in pCOSMOS than QSMnet and LPCNN. Training time was reduced from 2 days for LPCNN and 12 hours for QSMnet to 3.2 hours for pCOSMOS. It is concluded that the proposed pCOSMOS method is an alternative deep learning QSM approach when computational efficiency is essential. © 2017 IEEE.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

An AI-Enabled Framework for Transparency and Interpretability in Cardiovascular Disease Risk Prediction

引用

computers, Materials & Continua 2025年第3期82卷 5057-5078页

作者： Isha Kiran Shahzad Ali Sajawal ur Rehman Khan Musaed Alhussein Sheraz Aslam Khursheed Aurangzeb Department of Computer Science University of Engineering and TechnologyLahore39161Pakistan Dipartimento di Farmacia e Biotecnologie Alma Mater Studiorum—Universita di BolognaBologna40126Italy Department of Information Sciences University of EducationLahore54770Pakistan Department of Computer Science National Textile UniversityKarachi CampusKarachi74900Pakistan Department of Computer Science National Textile UniversityFaisalabad37610Pakistan Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Electrical Engineering Computer Engineeringand InformaticsCyprus University of TechnologyLimassol3036Cyprus Department of Computer Science CTL EurocollegeLimassol3077Cyprus

Cardiovascular disease(CVD)remains a leading global health challenge due to its high mortality rate and the complexity of early diagnosis,driven by risk factors such as hypertension,high cholesterol,and irregular pulse *** diagnostic methods often struggle with the nuanced interplay of these risk factors,making early detection *** this research,we propose a novel artificial intelligence-enabled(AI-enabled)framework for CVD risk prediction that integrates machine learning(ML)with eXplainable AI(XAI)to provide both high-accuracy predictions and transparent,interpretable *** to existing studies that typically focus on either optimizing ML performance or using XAI separately for local or global explanations,our approach uniquely combines both local and global interpretability using Local Interpretable Model-Agnostic Explanations(LIME)and SHapley Additive exPlanations(SHAP).This dual integration enhances the interpretability of the model and facilitates clinicians to comprehensively understand not just what the model predicts but also why those predictions are made by identifying the contribution of different risk factors,which is crucial for transparent and informed decision-making in *** framework uses ML techniques such as K-nearest neighbors(KNN),gradient boosting,random forest,and decision tree,trained on a cardiovascular ***,the integration of LIME and SHAP provides patient-specific insights alongside global trends,ensuring that clinicians receive comprehensive and actionable *** experimental results achieve 98%accuracy with the Random Forest model,with precision,recall,and F1-scores of 97%,98%,and 98%,*** innovative combination of SHAP and LIME sets a new benchmark in CVD prediction by integrating advanced ML accuracy with robust interpretability,fills a critical gap in existing *** framework paves the way for more explainable and transparent decision-making in he

关键词： Artificial Intelligence cardiovascular disease(CVD) explainability eXplainable AI(XAI) interpretability LIME machine learning(ML) SHAP

来源：评论

学校读者我要写书评

暂无评论

RGB-D Video Mirror Detection

RGB-D Video Mirror Detection

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Xu, Mingchen Herbert, Peter Lai, Yu-Kun Ji, Ze Wu, Jing School of Computer Science and Informatics Cardiff University United Kingdom School of Engineering Cardiff University United Kingdom

ISBN: (纸本)9798331510831

Mirror detection aims to identify mirror areas in a scene, with recent methods either integrating depth information (RGB-D) or making use of temporal information (video). However, utilizing both data is still under-explored due to the lack of a high-quality dataset and an effective method for the RGB-D Video Mirror Detection (DVMD) problem. To the best of our knowledge, this is the first work to address the DVMD problem. To exploit depth and temporal information in mirror segmentation, we first construct a large-scale RGB-D Video Mirror Detection Dataset (DVMD-D), which contains 17977 RGB-D images from 273 diverse videos. We further develop a novel model, named DVMDNet, which can first locate the mirrors based on triple consistencies: local consistency, cross-modality consistency and global consistency, and then refine the mirror boundaries through content discontinuity, taking the temporal information within videos into account. We conduct a comparative study on the DVMD dataset, evaluating 12 state-of-the-art models (including single-image mirror detection, single-image glass detection, RGB-D mirror detection, video shadow detection, video glass detection, and video mirror detection methods). Code is available from https://***/UpChen/2025_DVMDNet. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

End-to-end optimized ensemble model for Alzheimer’s disease detection 19

End-to-end optimized ensemble model for Alzheimer’s disease...

引用

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

作者： Hassan, Abdelrahman 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

Alzheimer's disease (AD) is a progressive neurodegenerative disorder with an increasing prevalence among the elderly, making early and accurate diagnosis critical for effective intervention and management. This paper introduces an end-to-end machine learning pipeline optimized for detecting AD using multimodal data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The study proposes an ensemble model that integrates key modalities—demographics, cognitive scores, neuropsychological assessments, and MRI data—via early fusion to enhance AD detection. Various machine learning models, including Logistic Regression, Gradient Boosting, AdaBoost, XGBoost, Support Vector Machine, and Neural Networks, are compared, and feature selection is optimized through Recursive Feature Elimination, ANOVA F-value, and mutual information methods, with mutual information showing the most efficacy. With further hyperparameter tuning, the highest accuracy is achieved at 95.85%, with Gradient Boosting as the top-performing model. Additional experiments assess and evaluate individual modality contributions, underscoring the predictive value of cognitive scores and neuropsychological features. To enhance clinical interpretability, we incorporate model explainability using LIME and SHAP, which identify key features influencing model predictions across different AD stages. Explainable AI (XAI) is essential in healthcare for providing transparency and supporting clinician confidence by highlighting which biomarkers, such as MMSE, CDRSB, and PTAU, contribute most to diagnostic outcomes. This study demonstrates classical machine learning's potential in AD diagnostics, offering a pathway to cost-effective and clinically viable models for neurodegenerative disease management. © 2025 IEEE.

关键词： Adversarial machine learning

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

Design and In-training Optimization of Binary Search ADC for Flexible Classifiers 25

Design and In-training Optimization of Binary Search ADC for...

引用

30th Asia and South Pacific Design Automation Conference, ASP-DAC 2025

作者： Lozano Duarte, Paula Carolina Afentaki, Florentia Zervakis, Georgios Tahoori, Mehdi Department of Computer Science Karlsruhe Inst. of Tech. Karlsruhe Germany Computer Engineering and Informatics Department Univ. of Patras Patras Greece

ISBN: (纸本)9798400706356

Flexible Electronics (FE) offer distinct advantages, including mechanical flexibility and low process temperatures, enabling extremely low-cost production. To address the demands of applications such as smart sensors and wearables, flexible devices must be small and operate at low supply voltages. Additionally, target applications often require classifiers to operate directly on analog sensory input, necessitating the use of Analog to Digital Converters (ADCs) to process the sensory data. However, ADCs present serious challenges, particularly in terms of high area and power consumption, especially when considering stringent area and energy budget. In this work, we target common classifiers in this domain such as MLPs and SVMs and present a holistic approach to mitigate the elevated overhead of analog to digital interfacing in FE. First, we propose a novel design for Binary Search ADC that reduces area overhead 2× compared with the state-of-the-art Binary design and up to 5.4× compared with Flash ADC. Next, we present an in-training ADC optimization in which we keep the bare-minimum representations required and simplifying ADCs by removing unnecessary components. Our in-training optimization further reduces on average the area in terms of transistor count of the required ADCs by 5× for less than 1% accuracy loss. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Feature analysis and selection for BGP anomaly detection 28

Feature analysis and selection for BGP anomaly detection

引用

28th Conference on Innovation in Clouds, Internet and Networks, ICIN 2025

作者： Hakimi, Rifqy Reed, Martin J. School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (纸本)9798331542399

Automated incidence reporting requires accurate and timely anomaly detection. This paper considers this in the context of the Border Gateway Protocol (BGP). BGP is crucial for Internet routing but is vulnerable to attacks due to a lack of widespread authentication. While rare, BGP disruptions can be highly detrimental to Internet performance and security. Detecting BGP anomalies helps network operators protect their networks and improve Internet reliability. In this work, we investigate and develop anomaly detection for BGP using Machine-Learning. We extract relevant features of BGP control plane messages from RIPE RIS and RouteViews public datasets. After extracting features, we employ various feature selection algorithms to extract the most relevant features and explore balancing the datasets. Finally, we explore detection latency, an important operating parameter for automated anomaly detection. The results show that BGP anomalies can be detected in the order of seven minutes when using real attack data and that the observation point for the BGP data has a significant effect on anomaly detection. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Early Parkinson's Disease Detection and Classification using Machine Learning and Neutrosophic Sets

引用

Neutrosophic Sets and Systems 2025年 82卷 873-886页

作者： Oudah, Hasan H. Metwaly, Ahmed A. Eassa, Mohamed Abdelhafeez, Ahmed Nagm, Ahmad M. Salama, Ahmed S. College of Arts Department of Journalism Ahl Al Bayt University Karbala Iraq Department of Computer Science Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Engineering and Electronics Cairo Higher Institute for Engineering Computer Science and Management New Cairo Egypt

Optimizing therapy and rehabilitation for Parkinson's disease (PD) requires early identification and precise evaluation of the illness's course. However, there is disagreement about the best way to use gait analysis to categorize the severity of motor symptoms and identify early-stage Parkinson's disease. The precision of machine learning (ML) models in identifying early and intermediate stages of Parkinson's disease was assessed in this study. Six ML models are used in this study for the prediction of PD. Different metrics are used to evaluate ML models such as accuracy, precision, recall, f1-score, and AUC score. Then we propose a multi-criteria decision-making methodology (MCDM) to evaluate the ML models and select the best one. Two MCDM methods are used such as CRITIC method to compute the criteria weights and the TOPSIS method to rank the alternatives. These methods are used under the bipolar neutrosophic sets (BNSs) to deal with uncertainty information. The results show the support vector machine is the best ML model for the prediction of PD. © 2025, University of New Mexico. All rights reserved.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

A fusion of machine learning and cryptography for fast data encryption through the encoding of high and moderate plaintext information blocks

引用

Multimedia Tools and Applications 2025年第8期84卷 5349-5375页

作者： Shafique, Arslan Mehmood, Abid Alawida, Moatsum Elhadef, Mourad Rehman, Mujeeb Ur School of Biomedical Engineering University of Glasgow Glasgow United Kingdom Department of Computer Sciences Abu Dhabi University Abu Dhabi United Arab Emirates Cyber Technology Institute School of Computer Science and Informatics De Montfort University Leicester United Kingdom

Within the domain of image encryption, an intrinsic trade-off emerges between computational complexity and the integrity of data transmission security. Protecting digital images often requires extensive mathematical operations for robust security. However, this computational burden makes real-time applications unfeasible. The proposed research addresses this challenge by leveraging machine learning algorithms to optimize efficiency while maintaining high security. This methodology involves categorizing image pixel blocks into three classes: high-information, moderate-information, and low-information blocks using a support vector machine (SVM). Encryption is selectively applied to high and moderate information blocks, leaving low-information blocks untouched, significantly reducing computational time. To evaluate the proposed methodology, parameters like precision, recall, and F1-score are used for the machine learning component, and security is assessed using metrics like correlation, peak signal-to-noise ratio, mean square error, entropy, energy, and contrast. The results are exceptional, with accuracy, entropy, correlation, and energy values all at 97.4%, 7.9991, 0.0001, and 0.0153, respectively. Furthermore, this encryption scheme is highly efficient, completed in less than one second, as validated by a MATLAB tool. These findings emphasize the potential for efficient and secure image encryption, crucial for secure data transmission in rea-time applications. © The Author(s) 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Knowledge augmented significant language model-based chatbot for explainable diabetes mellitus prediction 19

Knowledge augmented significant language model-based chatbot...

引用

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

作者： Elfayoumi, Mazen AbouElazm, Mohamed Mohamed, Omar Abuhmed, Tamer El-Sappagh, Shaker Faculty of Computer Science and Engineering Galala University Egypt Faculty of Computer Science Goldsmith UOL United Kingdom College of Computing and Informatics Sungkyunkwan University Korea Republic of

ISBN: (纸本)9798331507817

This study proposes an innovative diabetes prediction chatbot that utilizes large language models (LLMs) to determine the likelihood of diabetes based on specific patient inputs. Unlike conventional machine learning models and in addition to providing precise, individualized, robust prediction of diabetes augmented by the percentage of its confidence, this chatbot provides detailed text-based explanations for its individual predictions and enhances user’s understanding by retrieving and presenting similar cases using case-based reasoning techniques. Utilizing key health indicators such as hypertension status, heart disease presence, smoking history, BMI, HbA1c level, and blood glucose levels, the chatbot not only predicts the presence of diabetes but also educates users about the underlying reasons for each prediction. The system's explanation module promotes transparency and trust in the predictive process. The proposed architecture integrates the retrieval augmented generation (RAG) technique with prompt engineering across multiple LLMs, including Llama 3.1, GPT-3.5, and Gemma2. This approach augments the chatbot’s responses with contextually relevant data from similar past cases, thereby enhancing both relevance and accuracy. Furthermore, RAG minimizes LLM hallucinations while enhancing them with up-to-date, precise, personalized medical information. The objective of this chatbot is to offer healthcare professionals and patients a dependable, educational instrument for early detection of diabetes supported by transparent AI principles. This will have a positive effect on preventative healthcare measures. © 2025 IEEE.

关键词： Prediction models

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：