检索结果-内蒙古大学图书馆

A Comparative Analysis of CNN and Transfer Learning Algorithms in Predicting Alzheimer's Disease Stages Using Neuroimaging

A Comparative Analysis of CNN and Transfer Learning Algorith...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Sharma, Meenakshi Bhagat, Bhavneet Kumari, Vandana Bhumi Sharma, Naman Singh, Dipti Global Group of Institutes Department of Computer Science Engineering Amritsar India Guru Nanak Dev University Department of Computer Science Engineering Amritsar India

ISBN: (纸本)9798350373783

Alzheimer's disease (AD) prediction plays a critical role in early detection and intervention, allowing for better patient care and management. This paper investigates the predictive capabilities and state-of-art of Convolutional Neural Networks (CNN) and transfer learning models, including Inception V3, Resnet-18, and Resnet-50, for the progression of Alzheimer's disease (AD). The Alzheimer's disease Neuroimaging Initiative (ADNI) dataset used in this study, which includes multimodal neuroimaging, clinical, genetic and demographic data, the research aims to provide accurate predictions at various stages of the EA. This dataset enables robust training and evaluation of deep learning algorithms to predict AD progression. The data undergoes preprocessing and feature engineering to prepare a robust data set. Evaluations covering accuracy, precision, recall and F1 score, using k-fold cross-validation, are performed to measure the performance of the chosen algorithms. CNN and Inception V3 demonstrate remarkable performance with an accuracy of 93.75% and 94%. Comparative analyzes include exploration of Inception V3, Resnet-18, and Resnet-50, shedding light on their individual contributions to AD prediction. This paper contributes to the development of reliable and efficient deep learning approaches for early prediction and diagnosis of AD, with the potential to improve patient outcomes. Comparing the predictive capabilities of CNNs and transfer learning models provides valuable insights into their effectiveness in modeling AD progression. © 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

Analytical and FE Modeling of a Wound Rotor Induction Motor with Static Inclined Eccentricity

Analytical and FE Modeling of a Wound Rotor Induction Motor ...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Shiekh, Solihah Sharief Pillay, Pragasen Concordia University Department of Electrical and Computer Engineering MontrealQC Canada

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376067

This paper models both analytically and using finite element analysis (FEA), a prevalent mechanical fault in wound rotor induction motors (WRIMs). Variations in air gap length axially and circumferentially result in inclined eccentricity, a condition likely in practice than assuming a uniform eccentricity along the motor shaft. A 2-D modified winding function approach is employed for analytical modeling. A 3-D FEA is essential for detailed evaluation, but due to reduce computations, segmented 2-D FEA model is proposed. This model, which divides the shaft into segments, enables identification of fault-sensitive components. Consequently, a prediction curve is constructed for evaluating components under various degrees of eccentricity. This study also conducts a comparative analysis of axially non-uniform and uniform eccentricity faults, focusing on the 13th harmonic component as a key fault indicator. Experimental data, along with numerical and analytical models, show strong agreement, validating the findings related to eccentricity faults in WRIMs. © 2024 IEEE.

关键词： Rotors (windings)

来源：评论

学校读者我要写书评

暂无评论

A Robust Malware Classification Approach Leveraging Explainable AI

A Robust Malware Classification Approach Leveraging Explaina...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Hafiz, Md. Ferdous Bin Khan, Niaz Ashraf Kamal, Zahid Hossain, Sohrab Barman, Shohag University of Liberal Arts Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh East Delta University Department of Computer Science and Engineering Chittagong Bangladesh

ISBN: (纸本)9798350375237

Malware detection is a critical aspect of cybersecurity, with the constant evolution of malicious software posing significant challenges to computer systems and networks. Traditional security measures often struggle to detect obfuscated malware, which employs sophisticated techniques to evade detection. This research explores the utilization of memory analysis techniques coupled with machine learning and deep learning algorithms, augmented by Explainable AI (XAI), to enhance malware detection and classification. Leveraging a well-balanced dataset specifically tailored for memory analysis, various algorithms including Random Forest, XGBoost, Logistic Regression, LSTM, GRU, ANN, and hybrid models were employed for multiclass classification. Ensemble methods were also implemented to improve classification accuracy. The results demonstrate the efficacy of ensemble methods like Random Forest and XGBoost in accurately detecting obfuscated malware, with Random Forest achieving an impressive accuracy of 87.30%. Furthermore, the integration of GRU and LSTM architectures in hybrid models showed promising results, highlighting the effectiveness of combining different neural network architectures for improved performance in multiclass classification tasks. Through Explainable AI techniques such as LIME, insights into the underlying features and decision criteria influencing classification outcomes were provided, enhancing the interpretability and transparency of the models. This research contributes to advancing the field of malware detection and combating evolving cyber threats, with practical implications for real-world cybersecurity applications. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Towards a Scalable Reference-Free Evaluation of Generative Models 38

Towards a Scalable Reference-Free Evaluation of Generative M...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ospanov, Azim Zhang, Jingwei Jalali, Mohammad Cao, Xuenan Bogdanov, Andrej Farnia, Farzan Department of Computer Science & Engineering The Chinese University of Hong Kong Hong Kong Department of Cultural and Religious Studies The Chinese University of Hong Kong Hong Kong School of Electrical Engineering and Computer Science University of Ottawa Canada

While standard evaluation scores for generative models are mostly reference-based, a reference-dependent assessment of generative models could be generally difficult due to the unavailability of applicable reference datasets. Recently, the reference-free entropy scores, VENDI [1] and RKE [2], have been proposed to evaluate the diversity of generated data. However, estimating these scores from data leads to significant computational costs for large-scale generative models. In this work, we leverage the random Fourier features framework to reduce the computational price and propose the Fourier-based Kernel Entropy Approximation (FKEA) method. We utilize FKEA's approximated eigenspectrum of the kernel matrix to efficiently estimate the mentioned entropy scores. Furthermore, we show the application of FKEA's proxy eigenvectors to reveal the method's identified modes in evaluating the diversity of produced samples. We provide a stochastic implementation of the FKEA assessment algorithm with a complexity O(n) linearly growing with sample size n. We extensively evaluate FKEA's numerical performance in application to standard image, text, and video datasets. Our empirical results indicate the method's scalability and interpretability applied to large-scale generative models. The codebase is available at https://***/aziksh-ospanov/FKEA. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prescribed-Time Nash Equilibrium Seeking for Pursuit-Evasion Game

引用

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1518-1520页

作者： Lei Xue Jianfeng Ye Yongbao Wu Jian Liu D.C.Wunsch Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationNanjing 210096 School of Automation Southeast UniversityNanjing 210096China Department of Electrical and Computer Engineering Missouri University of Science and TechnologyRollaMO 65409 USA IEEE

Dear Editor,This letter is concerned with prescribed-time Nash equilibrium(PTNE)seeking problem in a pursuit-evasion game(PEG)involving agents with second-order *** order to achieve the prior-given and user-defined convergence time for the PEG,a PTNE seeking algorithm has been developed to facilitate collaboration among multiple pursuers for capturing the evader without the need for any global ***,it is theoretically proved that the prescribedtime convergence of the designed algorithm for achieving Nash equilibrium of ***,the effectiveness of the PTNE method was validated by numerical simulation results.A PEG consists of two groups of agents:evaders and *** pursuers aim to capture the evaders through cooperative efforts,while the evaders strive to evade *** is a classic noncooperative *** has attracted plenty of attention due to its wide application scenarios,such as smart grids[1],formation control[2],[3],and spacecraft rendezvous[4].It is noteworthy that most previous research on seeking the Nash equilibrium of the game,where no agent has an incentive to change its actions,has focused on asymptotic and exponential convergence[5]-[7].

关键词： seeking prescribed convergence

来源：评论

学校读者我要写书评

暂无评论

An Integrated Representation & Compression Scheme Based on Convolutional Autoencoders with 4D-DCT Perceptual Encoding for High Dynamic Range Light Fields 8

An Integrated Representation & Compression Scheme Based on C...

引用

8th IEEE International Conference on Information and Communication Technology, CICT 2024

作者： Khaidem, Sally Sharma, Mansi Indian Institute of Technology Madras Department of Electrical Engineering Chennai India Thapar Institute of Engineering and Technology Department of Computer Science and Engineering Patiala India

ISBN: (纸本)9798331531539

The emerging and existing light field displays are highly capable of realistic presentation of 3D scenes on auto-stereoscopic glasses-free platforms. However, the large size of light field data presents a significant drawback for 3D displays and streaming purposes. When a light field has a high dynamic range (HDR), its size increases drastically. This paper proposes a novel compression algorithm specifically designed for high dynamic range light fields that achieves perceptually lossless compression. The algorithm leverages inter-view and intra-view correlations within the HDR light field by treating it as a four-dimensional volume. This compression technique is based on the 4D-DCT Uniform Colour Space (4DDCT-UCS) algorithm. Further encoding of 4DDCT-UCS processed images using High-Efficiency Video Coding (HEVC) eliminates intra-frame, inter-frame, and intrinsic redundancies in HDR light field data. Our comparison with state-of-the-art coders like JPEG-XL and existing HDR video coding algorithms demonstrates the superior compression performance of the proposed scheme for real-world light fields. © 2024 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Analysis of Data Extraction Techniques on Medical Health Records 1

Analysis of Data Extraction Techniques on Medical Health Rec...

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Ruwali, Abhishek Bisht, Lavanya Narang, Harshit Das, Purushottam Dhanalakshmi, R. Yadav, Satya Prakash Graphic Era Hill University Computer Science and Engineering Dehradun India Indian Institute of Information Technology Department of Computer Science and Engineering Tamil Nadu Tiruchirappalli India Department of Computer Science and Engineering Greater Noida201306 India

ISBN: (纸本)9798350371802

Extracting cancer-related information from unstructured text presents challenges that require accurate identification and extraction techniques. This study compares three methods: keyword-based matching, regular expression pattern matching, and deep learning-based approaches. The study proposes evaluation metrics including file comparison, cosine similarity, and k-means clustering with Jaccard similarities. The findings demonstrate that the deep learning- based approach achieves the highest accuracy of 99.06%, outperforming the keyword-based (34.27%) and regular expression methods (93.58%). © 2024 IEEE.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Enhancing Maize Leaf Disease Prediction with Advanced Machine Learning Models

Enhancing Maize Leaf Disease Prediction with Advanced Machin...

引用

Congress on Smart Computing Technologies, CSCT 2023

作者： Kanakaprabha, S. Venu Gopal, G. Saranya, N. Ganesh Kumar, G. Sape, Chittibabulu Raju, Yallapragada Ravi Department of Computer Science and Engineering Rathinam Technical Campus Anna University Coimbatore India Department of Computer Science and Engineering KL Education Foundation Guntur India Department of Computer Science and Engineering Dr. N.G.P Institute of Technology Coimbatore India Department of Information Technology Hindusthan Institute of Technology Coimbatore India Department of Computer Science and Engineering Aditya College of Engineering Surampalem India Department of Computer Science and Engineering Madanapalle Institute of Technology and Science Andrapradesh Madanapalle India

ISBN: (纸本)9789819750801

The main goal of this research is to apply cutting-edge machine learning methods to predict maize leaf disease more accurately. Crucial staple crop maize is susceptible to a number of leaf diseases that can have a major negative influence on output and food security. Traditional disease detection techniques frequently lack accuracy and speed. We use cutting-edge machine learning methods, especially deep learning algorithms and Convolutional Neural Networks (CNNs), to solve this. We train and fine-tune our models using a large dataset that includes multiple disease categories, such as Common Rust, Gray Leaf Spot, Blight, and Healthy leaves. Our results show that these sophisticated models provide a significant improvement in the accuracy of disease prediction, allowing for earlier interventions and better crop health management techniques. This study advances precision agriculture by giving farmers and agronomists a trustworthy tool to increase the sustainability of maize output. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Implementation of High-Fidelity Models of IPMSM Drive Systems in Offline and Real-Time Simulators 3

Efficient Implementation of High-Fidelity Models of IPMSM Dr...

引用

3rd IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2024

作者： Tahim, Ekamjot Singh Kaushik, Abhay Rahman, Shadman Saqlain Ramesh, Rahul Raman Jatskevich, Juri University of British Columbia Department of Electrical and Computer Engineering Vancouver Canada

ISBN: (纸本)9798331540319

Interior permanent magnet synchronous machines (IPMSMs) are widely used in industrial applications, electric propulsion and precision applications. Accurate and efficient simulations of IPMSM drives are essential for the design and tuning of such systems. Field-oriented control (FOC) is commonly used to achieve precise control by decoupling the stator currents into flux- and torque-controlling components. The FOC-based controllers, however, require addressing the nonlinear flux-current relationships in IPMSMs caused by saliency, magnetic saturation, and cross-coupling effects. Different methods, such as parameter estimation and look-up tables (LUTs) techniques, are used to model these nonlinearities, with LUTs offering accuracy but demanding substantial memory allocation. Alternatively, memory-compact models such as polynomial-based models are used when systems impose constraints on memory allocation. This paper presents the efficient implementation of both the LUT-based and polynomial-based IPMSM drive system models for offline and real-time simulators. The accuracy of the models is verified through offline studies performed in MATLAB/Simulink and OPAL-RT's OP5700 real-time simulator. The obtained results demonstrate the difference in system resource utilization, such as memory requirement and computational efficiency, when using LUT-based and polynomial-based IPMSM models. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Space-Time Graph Planner for Unsignalized Intersections with CAVs 16th

Space-Time Graph Planner for Unsignalized Intersections wit...

引用

16th Annual International Conference on Combinatorial Optimization and Applications, COCOA 2023

作者： Mutlu, Caner Cardei, Ionut Cardei, Mihaela Department of Electrical Engineering and Computer Science Florida Atlantic University Boca RatonFL33431 United States

ISBN: (纸本)9783031496103

Emerging autonomous intersection management systems control the entry order and trajectory for connected and autonomous vehicles ready to traverse a road intersection. They aim to compute trajectories that are safe and optimal in order to reduce congestion, environmental impact, and to cut travel time. We propose a novel approach for computing the fastest waypoint trajectory using search in a discretized space-time graph that produces collision-free paths with variable vehicle speeds complying with traffic rules and vehicle dynamics constraints. The resulting trajectories allow high levels of intersection sharing, high evacuation rate, with a low algorithm runtime even with large scenarios with 1200 vehicles (5.5 s on a laptop). © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Travel time

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：