检索结果-内蒙古大学图书馆

Stochastic Approximation Beyond Gradient for Signal Processing and machine learning

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2023年 71卷 3117-3148页

作者： Dieuleveut, Aymeric Fort, Gersende Moulines, Eric Wai, Hoi-To Ecole Polytech CMAP UMR 7641 Palaiseau France Univ Toulouse Inst Math Toulouse CNRS UPS F-31062 Toulouse 9 France Chinese Univ Hong Kong Shatin Hong Kong Peoples R China

Stochastic Approximation (SA) is a classical algorithm that has had since the early days a huge impact on signal processing, and nowadays on machine learning, due to the necessity to deal with a large amount of data observed with uncertainties. An exemplar special case of SA pertains to the popular stochastic (sub)gradient algorithm which is the working horse behind many important applications. A lesser-known fact is that the SA scheme also extends to non-stochastic-gradient algorithms such as compressed stochastic gradient, stochastic expectation-maximization, and a number of reinforcement learning algorithms. The aim of this article is to overview and introduce the non-stochastic-gradient perspectives of SA to the signal processing and machine learning audiences through presenting a design guideline of SA algorithms backed by theories. Our central theme is to propose a general framework that unifies existing theories of SA, including its non-asymptotic and asymptotic convergence results, and demonstrate their applications on popular non-stochastic-gradient algorithms. We build our analysis framework based on classes of Lyapunov functions that satisfy a variety of mild conditions. We draw connections between non-stochastic-gradient algorithms and scenarios when the Lyapunov function is smooth, convex, or strongly convex. Using the said framework, we illustrate the convergence properties of the non-stochastic-gradient algorithms using concrete examples. Extensions to the emerging variance reduction techniques for improved sample complexity will also be discussed.

关键词： Signal processing algorithms Convergence machine learning algorithms Approximation algorithms Random variables Lyapunov methods Monte Carlo methods Stochastic approximation convergence analysis compressed stochastic gradient expectation maximization

来源：评论

学校读者我要写书评

暂无评论

LAMANet: A Real-Time, machine learning-Enhanced Approximate Message Passing Detector for Massive MIMO

引用

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS 2023年第3期31卷 382-395页

作者： Brennsteiner, Stefan Arslan, Tughrul Thompson, John S. S. McCormick, Andrew Univ Edinburgh Inst Micro & Nano Syst Sch Engn Edinburgh EH9 3FF Scotland Univ Edinburgh Inst Digital Commun Sch Engn Edinburgh EH9 3FF Scotland Alpha Data Parallel Syst Ltd Edinburgh EH11 1DQ Scotland

Model-driven machine learning for signal detection in the physical layer of mobile communication systems combines well-known detector structures with learned parameters. Recent work has shown high detection performance in massive multiple-input-multiple-output (MIMO) detection;however, thorough complexity analysis and real-time processing hardware are lacking. This work proposes a novel machine learning enhanced approximate message passing (AMP) algorithm named LAMANet and its hardware implementation. The algorithm solves some major challenges of previous proposals such as the complete loss of performance in untrained detectors and the still high computational complexity compared to traditional massive MIMO detection methods. We provide a comprehensive complexity comparison, simulations of the symbol error rate (SER) performance over realistic channel models, and a field-programmable gate array (FPGA) implementation capable of processing LAMANet in real time. The results show a similar detection performance of LAMANet to previous machine learning-enhanced algorithms, while the computational effort is reduced to a level where real-time computation in hardware becomes comparable to traditional detection methods.

关键词： machine learning algorithms Detectors Real-time systems Massive MIMO machine learning Approximation algorithms Hardware Approximate message passing (AMP) field-programmable gate array (FPGA) machine learning massive multiple-input-multiple-output (MIMO) real-time signal detection

来源：评论

学校读者我要写书评

暂无评论

An Integrated Nature-Inspired Algorithm Hybridized Adaptive Broad learning System for Disease Classification

引用

IEEE ACCESS 2023年 11卷 31636-31656页

作者： Parhi, Pournamasi Bisoi, Ranjeeta Dash, Pradipta Kishore Siksha O Anusandhan Deemed be Univ Dept Comp Sci Engn Bhubaneswar 751030 Odisha India Siksha O Anusandhan Deemed be Univ Multidisciplinary Res Cell Bhubaneswar 751030 Odisha India

Classification of different deadly diseases using machine learning algorithms helps in making the health care system more robust. This, not only reduces the human errors during diagnosis of disease due to inexperience but also helps the physician for taking an emergency action earlier to biopsy. As the genomic data undergoes through the malediction of excessive dimension problem, both the selection of the remarkable genes and classification of these data efficiently still remain as a demanding research problem. To obtain the notable features from high dimensional data, by using a nature-inspired algorithm, is a Non-deterministic Polynomial-time (NP)-Hard problem. Therefore, a researcher can apply new algorithm to solve this issue. In this suggested approach, an integrated natured-inspired algorithm i.e., Sine-Cosine (SC) based Monarch Butterfly Optimization (SC-MBO) is merged with an Adaptive Broad learning System (ABLS) called SC-MBO-ABLS, to find out the most notable genetic features and classify the genomic data at the same time. In the preliminary stage, a feature extraction method i.e. Kernel based Fisher Score (K-FS) is applied to extract a notable key gene subset. Then, this extracted key gene subset goes through further execution with the SC-MBO-ABLS method. To examine the effectiveness of the presented method, ten genomic datasets are considered. Here, several performance evaluators (i.e., Precision, Matthews Correlation Coefficient, Sensitivity, Kappa, Specificity, and F-score) are used for a neutral estimation of the presented approach. This presented model is compared with SC-MBO wrapped Multilayer Perceptron (SC-MBO-MLP), SC-MBO wrapped Extreme learning machine (SC-MBO-ELM), and SC-MBO wrapped Kernel Extreme learning machine (SC-MBO-KELM). Further, sixteen existing standard models are compared to prove the supremacy of the presented method. Moreover, an analysis of Variance i.e., ANOVA test is carried out for statistical evaluation of the proposed work.

关键词： Feature extraction Classification algorithms Bioinformatics learning systems Genomics Metaheuristics machine learning algorithms Genomic data high dimensionality notable genes feature extraction kernel fisher score classification sine-cosine adaptive broad learning system integrated monarch butterfly

来源：评论

学校读者我要写书评

暂无评论

Automated Stroke Prediction Using machine learning: An Explainable and Exploratory Study With a Web Application for Early Intervention

引用

IEEE ACCESS 2023年 11卷 52288-52308页

作者： Mridha, Krishna Ghimire, Sandesh Shin, Jungpil Aran, Anmol Uddin, Md. Mezbah Mridha, M. F. Marwadi Univ Dept Comp Engn Rajkot 360003 India Univ Aizu Dept Comp Sci & Engn Aizu Wakamatsu 9658580 Japan Amer Int Univ Bangladesh Dept Comp Sci Dhaka 1229 Bangladesh

Stroke is a dangerous medical disorder that occurs when blood flow to the brain is disrupted, resulting in neurological impairment. It is a big worldwide threat with serious health and economic implications. To solve this, researchers are developing automated stroke prediction algorithms, which would allow for early intervention and perhaps save lives. The number of people at risk for stroke is growing as the population ages, making precise and effective prediction systems increasingly critical. wo In a comparison examination with six well-known classifiers, the effectiveness of the proposed ML technique was explored in terms of metrics relating to both generalization capability and prediction accuracy. To give insight into the black-box machine learning models, we also studied two kinds of explainable techniques, namely SHAP and LIME, in this study. SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-agnostic Explanations) are well-established and reliable approaches for explaining model decision-making, particularly in the medical industry. The findings of the experiment revealed that more complicated models outperformed simpler ones, with the top model obtaining almost 91% accuracy and the other models achieving 83-91% accuracy. The proposed framework, which includes global and local explainable methodologies, can aid in standardizing complicated models and gaining insight into their decision-making, which can enhance stroke care and treatment.

关键词： Stroke (medical condition) machine learning Predictive models Prediction algorithms machine learning algorithms Medical services Medical diagnostic imaging Stroke prediction data leakage explainable machine learning ANOVA test SHAPE LIME

来源：评论

学校读者我要写书评

暂无评论

A Study on Different Deep learning algorithms Used in Deep Neural Nets: MLP SOM and DBN

引用

WIRELESS PERSONAL COMMUNICATIONS 2023年第4期128卷 2913-2936页

作者： Naskath, J. Sivakamasundari, G. Begum, A. Alif Siddiqua Natl Engn Coll Dept Comp Sci & Engn Kovilpatti Tamil Nadu India S Abdur Rahman Crescent Inst Sci & Technol Dept Comp Sci & Engn Chennai Tamil Nadu India

Deep learning is a wildly popular topic in machine learning and is structured as a series of nonlinear layers that learns various levels of data representations. Deep learning employs numerous layers to represent data abstractions to implement various computer models. Deep learning approaches like generative, discriminative models and model transfer have transformed information processing. This article proposes a comprehensive review of various deep learning algorithms Multi layer perception, Self-organizing map and deep belief networks algorithms. It first briefly introduces historical and recent state-of-the-art reviews with suitable architectures and implementation steps. Moreover, the various applications of those algorithms in various fields such as wireless networks, Adhoc networks, Mobile ad-hoc and vehicular ad-hoc networks, speech recognition engineering, medical applications, natural language processing, material science and remote sensing applications, etc. are classified.

关键词： machine learning algorithms Multi layer perception Self organising maps Deep belief networks Deep neural nets Application of algorithms

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Dependable Deep Feature Extraction and Ensemble-Based machine learning Approach for Breast Cancer Detection

引用

IEEE ACCESS 2023年 11卷 87694-87708页

作者： Sharmin, Selina Ahammad, Tanvir Talukder, Md. Alamin Ghose, Partho Jagannath Univ Dept Comp Sci & Engn Dhaka 1100 Bangladesh Bangladesh Univ Business & Technol Dept Comp Sci & Engn Dhaka 1216 Bangladesh

Breast cancer is a prevalent and life-threatening disease that requires effective detection and diagnosis methods to improve patient outcomes. Deep learning (DL) and machine learning (ML) techniques have emerged as powerful tools in breast cancer detection, offering benefits such as improved accuracy and efficiency. However, existing methods have scalability and performance limitations, emphasizing the need for further research. In this paper, we propose a hybrid dependable breast cancer detection approach that combines the power of DL using a pre-trained ResNet50V2 model and ensemble-based ML methods. The integration of DL enables the approach to learn and extract hidden patterns from complex breast cancer images, while ML algorithms contribute interpretability and generalization capabilities. We conducted extensive experiments using a breast histopathology image-based publicly available Invasive Ductal Carcinoma (IDC) dataset comprising samples of different sizes. The results obtained from our rigorous experiments provide compelling evidence for our hybrid model's robustness and high performance. We achieved a higher accuracy rate of 95%, precision of 94.86%, recall of 94.32%, and F1 score of 94.57% compared to state-of-the-art models. We also identified Light Boosting Classifier (LGB) as the most suitable ML model in conjunction with the ResNet50V2 architecture. The results of this research offer significant contributions to breast cancer detection through an innovative approach, comprehensive performance analysis, and dependable assessment. Moreover, it has the potential to assist medical professionals in making informed decisions, improving patient care, and enhancing outcomes for breast cancer patients.

关键词： Breast cancer Feature extraction Convolutional neural networks machine learning algorithms Training Boosting Histopathology Deep learning Transfer learning breast histopathology image deep learning machine learning transfer learning

来源：评论

学校读者我要写书评

暂无评论

BiLSTM and SqueezeNet With Transfer learning for EEG Motor Imagery Classification: Validation With Own Dataset

引用

IEEE ACCESS 2023年 11卷 136422-136436页

作者： Lazcano-Herrera, Alicia Guadalupe Fuentes-Aguilar, Rita Q. Ramirez-Morales, Adrian Alfaro-Ponce, Mariel Tecnol Monterrey Sch Engn & Sci Monterrey 64849 Mexico Tecnol Monterrey Inst Adv Mat Sustainable Mfg Monterrey 64849 Mexico UPIITA Inst Politecn Nacl Mexico City 07340 Mexico

Transfer learning (TL) is a methodology that allows the re-train of a machine learning (ML) algorithm (like Neural Networks or NN's) for a new task with the advantage of the previous training acquired knowledge;with this methodology, it is possible to train NNs for a new task even if the data is scarce. The present study uses this approach to train NNs to classify Electroencephalography (EEG) signals that include Movement/Imagery (MI), first with a publicly available data set and then using it to validate the training process of a small dataset of acquired data. The first part of the article describes the methodology for acquiring EEG signals that imitated the information found in the publicly available dataset Physionet Motor/Imagery. The second part compares the training process for NNs. The first NN is a Bidirectional Long-Short Term Memory (BiLSTM) trained from scratch with the Physionet dataset, and the second NN is a CNN called SqueezeNet trained following the TL method with the small acquired dataset, reaching an accuracy of 91.25% in the BiLSTM with the scratch method and an accuracy of 92.33% with the transfer learning method for the EEG MI signal classification.

关键词： Electroencephalography Task analysis Training Classification algorithms Transfer learning Prediction algorithms machine learning algorithms BCI EEG signal processing machine learning transfer learning motor/imagery

来源：评论

学校读者我要写书评

暂无评论

machine learning-Aided Nonhomogeneity Detection Method for Airborne Radar

IEEE TRANSACTIONS ON RADAR SYSTEMS

引用

IEEE TRANSACTIONS ON RADAR SYSTEMS 2025年 3卷 220-232页

作者： Wang, Zeyu Chen, Hongmeng Xu, Shuwen Li, Ming Beijing Univ Posts & Telecommun Sch Informat & Commun Engn State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Inst Radio Measurement Beijing 100854 Peoples R China Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Shaanxi Peoples R China

The weight vector in space-time adaptive processing (STAP) algorithm will lead to notches at the position of the interfering targets when there are interfering targets in the training data. If these interfering targets are close to the target of interest on the space-time spectrum, the target signal self-nulling occurs. To deal with this problem, a machine learning-aided nonhomogeneity detection (ML-NHD) method is proposed. More specifically, the subaperture smoothing technique is first performed on each training data to obtain the subaperture sample covariance matrices (SCMs). We prove that when the airborne radar works in side-looking mode and the clutter foldover factor is an integer, the numbers of large eigenvalues (EIGs) of the subaperture SCMs are different for the ordinary training data samples and outlier training data samples. Then, four features are constructed based on the differences in the characteristics of EIGs and eigenvectors of the subaperture SCMs. Finally, a binary classifier based on support vector machine (SVM) is trained to classify the ordinary training data and the outlier training data. The performance assessment shows that the ML-NHD method can detect the outlier training data effectively and achieves better performance of clutter suppression compared with the conventional methods.

关键词： Training data Clutter Covariance matrices Airborne radar Vectors Eigenvalues and eigenfunctions Radar detection Training Radar clutter machine learning algorithms machine learning nonhomogeneity detection space-time adaptive processing (STAP)

来源：评论

学校读者我要写书评

暂无评论

machine learning tool-based prediction and forecasting of municipal solid waste generation rate: a case study in Guwahati, Assam, India

引用

INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY 2023年第11期20卷 12207-12230页

作者： Singh, T. Uppaluri, R. V. S. Indian Inst Technol Guwahati Ctr Environm Gauhati 781039 India Indian Inst Technol Guwahati Dept Chem Engn Gauhati 781039 India

Integrated large-scale solid waste management (SWM) policies are the need of the hour to design, develop and sustain SWM models. An accurate prediction and forecasting of municipal solid waste generation (MSWG) rate are essential for such advanced strategies. The primary objective of this study is to examine the criticality of demographic and socio-economic parameters for the fair prediction and forecasting of the MSWG rate. machine learning (ML) models were formulated by mapping solid waste quantities at the municipal level with socio-economic and demographic variables of Guwahati city. Tree-based ML algorithms, namely decision tree (DT), random forest (RF) and gradient boosting (GB), were applied to build the models with 1936 data size. The moving average (MA) approaches were adapted for the forecasting of the MSWG rate. Model validation resulted in a root mean square error, RMSE (3.01), mean absolute error, MAE (2.86) and coefficient of determination, R-2 (0.99) for the GB model and correlation coefficient (r) of 0.82 between observed and predicted values and thereby resulted in best performance in conjunction with DT and RF. With the exponential MA, the forecasted RMSE and R-2 for GB, RF and DT were 2.12, 3.63 and 4.22;and 0.981, 0.972 and 0.967, respectively. However, with a model accuracy of 97%, the computation time for GB model (19.18 min) exhibited maximum due to its high complexity. The overall methodology involved developing effective tools to aid in regional SWM and planning through the integration of data sources in the public domain, pre-processing and modelling from diverse sources.

关键词： Municipal solid waste Modelling machine learning algorithms Prediction Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep Generative learning Models for Cloud Intrusion Detection Systems

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第1期53卷 565-577页

作者： Ly Vu Quang Uy Nguyen Nguyen, N. Diep Dinh Thai Hoang Dutkiewicz, Eryk Le Quy Don Tech Univ Informat Technol Dept Hanoi 10000 Vietnam Univ Technol Sydney Sch Elect & Data Engn Ultimo NSW 2007 Australia

Intrusion detection (ID) on the cloud environment has received paramount interest over the last few years. Among the latest approaches, machine learning-based ID methods allow us to discover unknown attacks. However, due to the lack of malicious samples and the rapid evolution of diverse attacks, constructing a cloud ID system (IDS) that is robust to a wide range of unknown attacks remains challenging. In this article, we propose a novel solution to enable robust cloud IDSs using deep neural networks. Specifically, we develop two deep generative models to synthesize malicious samples on the cloud systems. The first model, conditional denoising adversarial autoencoder (CDAAE), is used to generate specific types of malicious samples. The second model (CDAEE-KNN) is a hybrid of CDAAE and the K-nearest neighbor algorithm to generate malicious borderline samples that further improve the accuracy of a cloud IDS. The synthesized samples are merged with the original samples to form the augmented datasets. Three machine learning algorithms are trained on the augmented datasets and their effectiveness is analyzed. The experiments conducted on four popular IDS datasets show that our proposed techniques significantly improve the accuracy of the cloud IDSs compared with the baseline technique and the state-of-the-art approaches. Moreover, our models also enhance the accuracy of machine learning algorithms in detecting some currently challenging distributed denial of service (DDoS) attacks, including low-rate DDoS attacks and application layer DDoS attacks.

关键词： Cloud computing Denial-of-service attack Computer crime machine learning algorithms Deep learning Intrusion detection Support vector machines Cloud systems conditional denoising adversarial autoencoder (CDAAE) deep learning generative models intrusion detection (ID)

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：