检索结果-内蒙古大学图书馆

2023 International Conference on Data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Kayalvizhi, M. Senthil Kumar, G. Tushal, V. Yashvanth, M. Santhosh, G. Chennai Institute of Technology Department of Biomedical Engineering Chennai India Chennai Institute of Technology Department of Computer Science and Business Systems Chennai India

ISBN: (纸本)9798350348910

Alzheimer's disease is a neurodegenerative disorder affecting millions worldwide, causing cognitive decline. Early detection is crucial for effective treatment, but manual diagnosis is error-prone and time-consuming. This study proposes a deep learning-based model for diagnosing and classifying Alzheimer's disease using VGG-16 CNN architectures. The model uses the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, which includes MRI scans from individuals with Alzheimer's and healthy controls. The model uses a pre-trained VGG-16 convolutional neural network as the base, fine-tuning on the dataset, and data augmentation techniques. The trained model achieves a 96.75% accuracy on the testing dataset, distinguishing MRI scans between Alzheimer's patients and healthy controls. The VGG-16 architecture demonstrated superior performance during training and testing. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Drift-free localisation using prior cross-source map for indoor low-light environments

引用

IET Cyber-systems and Robotics 2023年第1期5卷 122-131页

作者： Junyi Tao Weichen Dai Da Kong Jiayan Wan Bin He Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhouChina School of Computer Science Hangzhou Dianzi UniversityHangzhouChina Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province HangzhouChina

In this study,a localisation system without cumulative errors is ***,depth odometry is achieved only by using the depth information from the depth *** the point cloud cross-source map registration is realised by 3D particle filtering to obtain the pose of the point cloud relative to the ***,we fuse the odometry results with the point cloud to map registration results,so the system can operate effectively even if the map is *** effectiveness of the system for long-term localisation,localisation in the incomplete map,and localisation in low light through multiple experiments on the self-recorded dataset is *** with other methods,the results are better than theirs and achieve high indoor localisation accuracy.

关键词： indoor positioning robots

来源：评论

学校读者我要写书评

暂无评论

A Channel-Attention Convolutional Neural Network for Protein-DNA Binding Residue Prediction

A Channel-Attention Convolutional Neural Network for Protein...

引用

2024 International Conference on New Trends in Computational Intelligence, NTCI 2024

作者： Song, Jiazhi Song, Chuyi Zhang, Chenrui Jiang, Jingqing College of Computer Science and Technology Inner Mongolia Minzu University Inner Mongolia China College of Mathematics Science Inner Mongolia Minzu University Inner Mongolia China

ISBN: (纸本)9798331517021

Accurately identifying protein-DNA binding residues is important for protein function annotation and drug design. Previous studies have used classic machine learning algorithms like support vector machines (SVMs) and random forest (RF) to predict protein-DNA binding residues. However, as new machine learning techniques are being developed, the prediction performance could be further improved. In this paper, a convolutional neural network (CNN) based framework is proposed for protein-DNA binding residues prediction, named Se-Residual-Inception network, which includes stacked Inception blocks with short-cut connection and channel-attention mechanism. We examine the performance of proposed Se-Residual-Inception network on the benchmark dataset and independent testing set, and achieve the area under the ROC curve (AUC) values of 0.882 and 0.848, respectively. The prediction performance indicates that our proposed method can precisely identify the DNA binding residues in protein sequences, which can provide assistive directions for wet-lab experiments. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Involvement of Autistic Adults in the Participatory Design of technology: A Scoping Review 25

Involvement of Autistic Adults in the Participatory Design o...

引用

2025 CHI Conference on Human Factors in Computing systems, CHI 2025

作者： Maye, Laura Hansen, Nicolai Brodersen School of Computer Science and Information Technology University College Cork Cork Ireland Computer Science Aalborg University Aalborg Denmark

ISBN: (纸本)9798400713941

Research in HCI and autism has become more focused on involving autistic adults in technological design. In this paper, we present the results of a scoping review analysis of 11 projects across 18 papers that focused on including autistic adults in the design of technology that impacts their lives. This paper contributes a deeper understanding of how autistic adults were involved in participatory design processes. Our findings reveal mixed positions on how the lived autistic perspective was harnessed to direct the application of topics and technologies chosen. Most projects employed infrastructures to enhance participation (e.g., providing multiple modes to participate or employing a tailored methodology). We pose future opportunities for autistic involvement, for example, in topics and technologies where autistic research is employed (e.g., autism diagnosis and machine learning), reviewing the importance of formal diagnosis for inclusion, and harnessing the multiple expertise of autistic adults. © 2025 Copyright held by the owner/author(s).

关键词： autistic adults participatory design scoping review

来源：评论

学校读者我要写书评

暂无评论

Counterfactual Trajectories Prediction for Features of Non-Communicable Disease

Counterfactual Trajectories Prediction for Features of Non-C...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Sun, Zhoujian Zhang, Wenzhuo Huang, Zhengxing Luo, Cheng Zhejiang Lab Hangzhou China Zhejiang Univeristy College of Biomedical Engineering and Instrument Science Hangzhou China Zhejiang University College of Computer Science and Technology Hangzhou China

ISBN: (纸本)9798350386226

Non-communicable disease is the leading cause of death, emphasizing the need for accurate prediction of disease progression and informed clinical decision-making. Machine learning (ML) models have shown promise in this domain by capturing non-linear patterns within patient features. However, existing ML-based models cannot provide causal interpretable predictions and estimate treatment effects, limiting their decision-making perspective. In this study, we propose a novel model called causal trajectory prediction (CTP) to tackle the limitation. The CTP model combines trajectory prediction and causal discovery to enable accurate prediction of disease progression trajectories and uncover causal relationships between features. By incorporating a causal graph into the prediction process, CTP ensures that ancestor features are not influenced by the treatment of descendant features, thereby enhancing the interpretability of the prediction. By estimating the bounds of treatment effects, the CTP provides valuable insights for clinical decision-making. We evaluate the performance of the CTP using simulated and real medical datasets. Experimental results demonstrate that our model has the potential to assist clinical decisions. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

DTRadar: Accelerating Search Process of Decision Trees in Packet Classification 28

DTRadar: Accelerating Search Process of Decision Trees in Pa...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Yu, Jiashuo Huang, Long Zhu, Longlong Zhang, Dong Wu, Chunming College of Computer and Data Science Fuzhou University Fuzhou China Zhicheng College Fuzhou University Fuzhou China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798350300482

Packet classification is an essential part of computer networks. Existing algorithms propose a partition process to address the memory explosion problem of the decision tree algorithm caused by the huge number of rules with multiple fields. However, the search process requires traversing multiple trees generated by the partition, which reduces the search efficiency. The existing algorithms take simple approaches to optimize the search process, which is low efficiency or high hardware overhead. In this paper, we propose DTRadar, a framework for expediting the decision tree packet lookup process. Its key idea is building an abstract One-Big-Tree(OBT) for multiple decision trees by establishing the middle data structure. DTRadar considers each decision tree as a splittable tree and organizes these subtrees by intermediate data structures. Extensive experiments show that DTRadar benefits existing decision tree-based solutions in classification time by 61.60%, and the memory footprint only increased by 4.21% on average. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Predicting Student Behavior Using a Neutrosophic Deep Learning Model

引用

Neutrosophic Sets and systems 2025年 76卷 288-310页

作者： Shitaya, Ahmed Mohamed Wahed, Mohamed El Syed Abd El Khalek, Saied Helemy Ismail, Amr Shams, Mahmoud Y. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Computer Science Faculty of computer and information sciences Suez Canal University Egypt Department. of Communication and Computer Engineering Air Defense University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt

We developed an information system using an object-oriented programming language and a distributed database (DDB) consisting of multiple interconnected databases across a computer network, managed by a distributed database management system (DDBMS) for easy access. An intelligent system was designed to assess the difficulty level of preliminary exams and select top-performing advanced students using a Neutrosophic Deep Learning Model. The dataset was randomly split into training (80%) and testing (20%) sets, and the model, trained with the Adam optimizer at a 0.001 learning rate over 50 epochs, incorporated early stopping based on validation loss. This system, implemented at a traditional Egyptian university, achieved a 95% accuracy in predicting student dropout. Student behavior, influenced by personal, environmental, and academic factors, is often evaluated subjectively, leading to inconsistent results. Traditional machine learning approaches struggle with the inherent uncertainty in behavioral data. To address this, we combined neutrosophic theory—a mathematical framework that accounts for truth, falsity, and indeterminacy—with deep learning, which excels at learning complex data relationships, to predict student outcomes such as dropout rates. Evaluating the model on student data, including attendance and grades, showed superior accuracy, achieving a determination coefficient of 0.95, demonstrating the approach's potential for identifying at-risk students and enabling targeted interventions. © 2025, University of New Mexico. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Trailblazing Framework of Security Assessment for Traffic Data Management

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 1853-1875页

作者： Abdulaziz Attaallah Khalil al-Sulbi Areej Alasiry Mehrez Marzougui Neha Yadav Syed Anas Ansar Pawan Kumar Chaurasia Alka Agrawal Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science Al-Qunfudah Computer CollegeUmm Al-Qura UniversityMeccaSaudi Arabia College of Computer Science King Khalid UniversityAbha61421Saudi Arabia Department of Information Technology Babasaheb Bhimrao Ambedkar UniversityLucknow226025Uttar PradeshIndia Department of Computer Applications Babu Banarasi Das UniversityLucknow226028Uttar PradeshIndia

Connected and autonomous vehicles are seeing their dawn at this *** provide numerous benefits to vehicle owners,manufacturers,vehicle service providers,insurance companies,*** vehicles generate a large amount of data,which makes privacy and security a major challenge to their *** complicated machine-led mechanics of connected and autonomous vehicles increase the risks of privacy invasion and cyber security violations for their users by making them more susceptible to data exploitation and vulnerable to cyber-attacks than any of their *** could have a negative impact on how well-liked CAVs are with the general public,give them a poor name at this early stage of their development,put obstacles in the way of their adoption and expanded use,and complicate the economic models for their future *** the other hand,congestion is still a bottleneck for traffic management and *** research paper presents a blockchain-based framework that protects the privacy of vehicle owners and provides data security by storing vehicular data on the blockchain,which will be used further for congestion detection and *** devices placed along the road are used to communicate with passing cars and collect their *** collected data will be compiled periodically to find the average travel time of vehicles and traffic density on a particular road ***,this data will be stored in the memory pool,where other devices will also store their *** a predetermined amount of time,the memory pool will be mined,and data will be uploaded to the blockchain in the form of blocks that will be used to store traffic *** information is then used in two different ***,the blockchain’s final block will provide real-time traffic data,triggering an intelligent traffic signal system to reduce ***,the data stored on the blockchain will provide historical,statistical data that can facilitate the

关键词： Connected and autonomous vehicles(CAVs) traffic data management ethereum blockchain road side units smart cities

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Complexities of the Human Body: Advanced Computational Anatomy for Precision Medicine 24

Unveiling the Complexities of the Human Body: Advanced Compu...

引用

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Lakshmi Parvathi, A. Lavanya, V. Muthamizh Selvam, M. Venu Gopal, I. Raihana Parveen, R. Vijayarajan, V. Department of CSE QIS College of Engineering and Technology Andhra Pradesh Ongole India Department of AIMLDS QIS College of Engineering and Technology Andhra Pradesh Ongole India Department of ECE QIS College of Engineering and Technology Andhra Pradesh Ongole India School Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798400709586

Concept of the Study: The human body is an intricate matrix, and solving health problems through modern medicine requires us to lay out the insides of this matrix in full force from within. Computational Anatomy (CA) is a rapidly growing field that uses novel computational tools and techniques to model detailed anatomical structures. Despite enormous medical imaging and image analysis advances, their use in clinical routines still has numerous limitations. Research Gap: While technology in medicine has advanced substantially, the clinical application of computational anatomy still needs to be improved regarding these methodologies for incorporating it into precision medicine practice. Objective: In this study, we provide evidence that computational anatomy, with high-resolution imaging, machine-learning, and biomechanical simulations, can improve diagnostic accuracy, individualized treatments, and patient outcomes through them. Methods: We use cutting-edge computational and machine learning methods to understand anatomical variabilities, predict clinical output measures, and stratify treatment planning. Such processes allow one to perform more detailed evaluations on their subjects with structure-per-level identity, helping to individualize them in clinical decision-making. Results: This implies that diagnostics considering individual anatomical variations could be more accurate with computational anatomy. These results could also pave the way toward personalized therapy, leading to a paradigm shift in clinical practice. Conclusion: The present study fills the unmet need by presenting a complete framework to include computational anatomy in clinical practice. These findings suggest that computational anatomy can revolutionize medicine, giving rise to even more precise and economical health care and leading to better patient outcomes. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-Based Method for Classifying Yoga Poses using Deep Convolutional Neural Networks

Transfer Learning-Based Method for Classifying Yoga Poses us...

引用

2023 Innovations in Power and Advanced Computing Technologies, i-PACT 2023

作者： Vallabhaneni, Nagalakshmi Panneer, Prabhavathy Sundaram, Venkatesan Meenakshi School of Computer Science Engineering and Information Systems VIT University Vellore India Department of Computer Science and Engineering National Institute of Technology Puducherry India

ISBN: (纸本)9798350325188

Yoga is a popular practice that aims to improve one's health and well-being through physical postures, breathing exercises, and meditation. The growing popularity of yoga has prompted researchers to focus on automating the process of classifying yoga poses. Using deep convolutional neural networks (CNNs) and transfer learning, we present a deep learning-based method for correctly categorizing yoga postures in this research. The primary goal of this study is to develop an efficient method for automatically recognizing and categorizing yoga poses in given photographs. The impressive success of deep CNNs in picture classification tasks is exploited here to accomplish this goal. We also use transfer learning, a method for customizing pre-trained CNN models for our unique yoga posture categorization task. This paper presents a Transfer Learning based Method for Yoga Poses classification using Deep Convolutional Neural Networks (TLMYPC-DCNN). The proposed model uses the Yoga Posture Dataset for classification of images. Initially, this model starts with pre-processing the input images by splitting input data into three groups such as training set, validation set and test data. The deep learning CNN model will be trained using the training data, and then its parameters will be tweaked using the validation data. Finally, the test data will be used to assess how well the data performs. A convolutional neural network (CNN) model called MobileNetV2 will be applied to the model photos. The experimental results show that the suggested TLMYPC-DCNN based technique with transfer learning is effective at accurately and reliably classifying yoga poses. © 2023 IEEE.

关键词： Deep Convolutional Neural Networks MobileNetV2 Transfer Learning Yoga Pose classification

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：