检索结果-内蒙古大学图书馆

A Novel Multi-Objective Rat Swarm Optimizer-Based Convolutional Neural Networks for the Diagnosis of COVID-19 Disease

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2022年第3期56卷 198-208页

作者： Sayed, Gehad Ismail Canadian Int Coll CIC Sch Comp Sci Cairo Egypt Cairo Univ Fac Comp & Artificial Intelligence Cairo Egypt

Early detection of coronavirus disease (COVID-19) is considered an essential task for disease control and cure. Thus, an automated diagnosis of COVID-19 is highly desirable. This paper introduces a novel diagnosis approach, namely, RSO-AlexNet-COVID-19. The proposed hybrid approach is based on the rat swarm optimizer (RSO) and convolutional neural network (CNN). RSO is used to find the optimal values for the hyperparameters of the AlexNet architecture to achieve a high level of diagnostic accuracy of COVID-19. It obtained overall classification accuracy of 100% for CT images datasets and an accuracy of 95.58% for the X-ray images dataset. Moreover, the performance of the proposed hybrid approach is compared with other CNN architecture, Inception v3, VGG16, and VGG19.

关键词： coronavirus multi-objective hyperparameters optimization convolutional neural networks rat swarm optimizer

来源：评论

学校读者我要写书评

暂无评论

Investigating deep feedforward neural networks for classification of transposon-derived piRNAs

引用

COMPLEX & INTELLIGENT SYSTEMS 2022年第1期8卷 477-487页

作者： da Costa, Alisson Hayasi Correa dos Santos, Renato Augusto Cerri, Ricardo Univ Fed Sao Carlos Dept Comp Sci Sao Carlos Brazil Univ Sao Paulo Sch Pharmaceut Sci Ribeirao Preto Ribeirao Preto Brazil Univ Estadual Campinas Inst Biol Campinas Brazil

PIWI-interacting RNAs (piRNAS) form an important class of non-coding RNAs that play a key role in gene expression regulation and genome integrity by silencing transposable elements. However, despite the importance of piRNAs and the large application of deep learning in computational biology, there are few studies of deep learning for piRNAs prediction. Still, current methods focus on using advanced architectures like CNN and variations. This paper presents an investigation on deep feedforward network models for classification of human transposon-derived piRNAs. We developed a lightweight predictor (when compared to other deep learning methods) and we show by practical evidence that simple neural networks can perform as well as better than complex neural networks when using the appropriate hyperparameters. For that, we train, analyze and compare the results of a multilayer perceptron with different hyperparameter choices, such as numbers of hidden layers, activation functions and optimizers, clarifying the advantages and disadvantages of each choice. Our proposed predictor reached a F-score of 0.872, outperforming other state-of-the-art methods for human transposon-derived piRNAs classification. In addition, to better access the generalization of our proposal, we also showed it achieved competitive results when classifying piRNAs of other species.

关键词： piRNAs classification Neural networks Deep learning hyperparameters optimization

来源：评论

学校读者我要写书评

暂无评论

A deep neural network for predicting soil texture using airborne radiometric data

引用

RADIATION PHYSICS AND CHEMISTRY 2024年 221卷

作者： Maino, Andrea Alberi, Matteo Barbagli, Alessio Chiarelli, Enrico Colonna, Tommaso Franceschi, Michele Gallorini, Fabio Guastaldi, Enrico Lopane, Nicola Mantovani, Fabio Petrone, Dario Pierini, Silvio Raptis, Kassandra Giulia Cristina Strati, Virginia Xhixha, Gerti Univ Ferrara Dept Phys & Earth Sci I-44122 Ferrara Italy INFN Ferrara Sect I-44122 Ferrara Italy GeoExplorer Impresa Sociale Srl I-52100 Arezzo Italy Univ Tirana Fac Nat Sci Dept Phys Blv Zogu 1 Tirana 1001 Albania

The ternary nature of soil texture, defined by its proportions of clay, silt, and sand, makes it challenging to predict through linear regression models from other soil attributes and auxiliary variables. The most promising results in this field have been recently achieved by Machine Learning methods which are able to derive nonlinear, non -site -specific models to predict soil texture. In this paper we present a method of constructing a pair of Deep Neural Network (DNN) algorithms that can predict clay and sand soil contents from Airborne Gamma Ray Spectrometry data of K and Th ground abundances. We tested the algorithm ' s hyperparameters through various configurations to optimize the DNNs ' performance, effectively avoiding underfitting and overfitting of the models. This led to the creation of a highresolution 20 m x 20 m soil texture map from dense AGRS data, significantly refining the previous map ' s granularity. The application of the obtained DNN models to unseen sites can be supported by future training on additional textural classes.

关键词： Deep neural network hyperparameters optimization Airborne gamma-ray spectroscopy Soil texture mapping Potassium Thorium

来源：评论

学校读者我要写书评

暂无评论

Ensembles of evolutionarily-constructed support vector machine cascades

引用

KNOWLEDGE-BASED SYSTEMS 2024年 288卷

作者： Dudzik, Wojciech Nalepa, Jakub Kawulok, Michal Silesian Tech Univ Dept Algorithm & Software Akademicka 16 PL-44100 Gliwice Poland

Support vector machine (SVM) is a well -established and widely -used classifier, but it is also known for high time and memory complexity of the training process. Coupled with its sensitivity to the model hyperparameters, it is often quite challenging to apply SVMs in practice to classify real -life data. At the same time, classifier ensembles composed of many light base models are known to achieve high classification performance, but SVMs are not exploited extensively here. In this paper, we propose a new approach that consists in creating an ensemble of SVM cascades, each of which is constructed using an evolutionary algorithm for training set selection and hyperparameter optimization. The obtained ensembles allow for high classification performance and they scale well for large datasets. The results of our experimental validation performed for over 40 datasets indicate that the proposed technique is competitive compared with the state-of-the-art methods for constructing ensembles. To deeper understand the proposed technique, we report and discuss the outcome of an extensive ablation study coupled with visualizations obtained for 2D datasets that enrich our qualitative analysis.

关键词： Support vector machine Evolutionary algorithm Ensemble learning Training set selection hyperparameters optimization

来源：评论

学校读者我要写书评

暂无评论

Battery temperature estimation at wide C-rates using the LSTM model based on polarization characteristics

引用

JOURNAL OF ENERGY STORAGE 2024年 101卷

作者： Liu, Liang Xu, Guangguang Wang, Yun Wang, Limei Liu, Jian Jiangsu Univ Automot Engn Res Inst Zhenjiang 212013 Peoples R China Jiangsu Autoparts New Energy Technol Co Ltd Zhenjiang 212132 Peoples R China Univ British Columbia Fac Appl Sci Sch Engn Kelowna BC V1V 1V7 Canada

Data-driven based approaches have achieved significant results in estimating battery temperature. Nevertheless, the present challenge emanates from the dearth of theoretical guidance governing the training strategy of the model, leading to an inefficient training process and constrained accuracy, especially under specific conditions. In this paper, a Long Short-Term Memory (LSTM) neural network based on polarization characteristics is proposed to estimate the battery discharge temperature. Firstly, the LSTM temperature estimation model is established and the hyperparameters are optimized by Genetic Algorithm (GA). The results show that the accuracy of the traditional model is less satisfactory, with the Maximum Error (ME) of 3.79 degrees C. Subsequently, the voltage and polarization heat production characteristics of the battery are analyzed under various discharge conditions. It is found that the heat production of the battery is smaller at 0-1.5C, and the heat production characteristics are similar at medium-rate, but the change of heat production is significant when C-rate exceeds 3C. Finally, a LSTM temperature estimation model based on polarization characteristics is proposed, which divides the datasets according to heat production characteristics. Further, a strategy for predicting temperatures in later stages based on limited data from the current condition is also proposed, this mothed combines with the transfer learning method to rapidly develop models for different high-rate conditions. The ME of the model on the test set is 1.1 degrees C, and the training time is reduced by 32.93 s. The results show that the LSTM temperature estimation model based on polarization characteristics has higher accuracy and training efficiency than the traditional LSTM temperature estimation model.

关键词： Battery temperature estimation Polarization characteristics LSTM neural network Genetic algorithm hyperparameters optimization

来源：评论

学校读者我要写书评

暂无评论

SOH and RUL prediction of lithium batteries based on fusions of RLOESS filtered electrochemical and thermal features by bidirectional gated recurrent unit network

引用

JOURNAL OF ENERGY STORAGE 2024年 102卷

作者： Xia, Fei Yu, Yun Chen, Jiajun Shanghai Univ Elect Power Coll Automat Engn Shanghai 200090 Peoples R China Pegasus Power Energy Co Ltd Hangzhou 310019 Peoples R China

Accurate state of health (SOH) and remaining useful life (RUL) prediction in real time are crucial for a reliable battery management system (BMS). Currently, conventional prediction methods utilizing single-source features are unable to comprehensively analyze battery degradation, thereby restricting the generality and accuracy of battery SOH and RUL prediction. To address this limitation, we propose a novel prediction method that employs a bidirectional gated recurrent unit (BiGRU) network with multi-source feature fusion. Initially, constant current (CC) charging curves, differential thermal voltammetry (DTV) curves, and differential thermal capacity (DTC) curves, which incorporate coupling information between DTV and incremental capacity analysis (ICA), are analyzed. Features containing thermal and electrochemical information pertinent to battery degradation are extracted from CC, DTV and DTC curves which are smoothed by Robust Locally Weighted Scatterplot Smoothing (RLOESS) filter. Then, useful features are chosen with Pearson correlation analysis. Moreover, to enhance the efficiency and accuracy of our prediction model, particle swarm optimization algorithm based on tripartite competition mechanism (TCMPSO) is used to further optimize the hyperparameter of BiGRU. The uncertainty of RUL prediction result is analyzed by Monte Carlo (MC) simulation. Two battery degradation datasets from NASA Ames Prognostics Center and Oxford University are utilized to validate the proposed method. The proposed method can predict SOH and RUL of battery accurately. The root mean square error (RMSE) and the mean absolute error (MAE) for SOH prediction results could reach below 0.3 % and 0.6 %, respectively. The maximum RUL absolute error (AE) of NASA and Oxford battery is within 3 and 100, respectively.

关键词： Llithium-ion batteries State of health Remaining useful life Electrochemical and thermal feature collaborative analysis Bidirectional gated recurrent unit network hyperparameters optimization

来源：评论

学校读者我要写书评

暂无评论

Breast cancer diagnosis using optimized deep convolutional neural network based on transfer learning technique and improved Coati optimization algorithm

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartB期255卷

作者： Emam, Marwa M. Houssein, Essam H. Samee, Nagwan Abdel Alohali, Manal Abdullah Hosney, Mosa E. Minia Univ Fac Comp & Informat Al Minya Egypt Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Technol POB 84428 Riyadh 11671 Saudi Arabia Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst POB 84428 Riyadh 11671 Saudi Arabia Luxor Univ Fac Comp & Informat Luxor Egypt

Breast cancer is a significant health concern due to its aggressive nature and high mortality rates. Early detection is crucial to improving patient outcomes. Thermography, a non-invasive and cost-effective method, utilizes heat from the breast surface to detect abnormalities, with the Database for Mastology Research (DMR) leveraging infrared images for research purposes. Deep learning (DL), particularly convolutional neural networks (CNNs), shows promise in accurately classifying breast cancer images. However, CNNs face challenges with hyperparameters. To address these challenges, this article proposes a new DL model, the optimized DenseNet model (LFR-COA-DenseNet121-BC), incorporating a boosted metaheuristic algorithm called LFRCOA. This algorithm, a developed version of the Coati optimization Algorithm (COA), integrates Random opposition -based learning (ROB), Brownian motion, and L & eacute;vy Flight (LF) schemes. The proposed model achieved impressive results, accurately classifying 99.97% of the test set. Comparison with established models such as VGG16, VGG19, DenseNet201, InceptionV3, Xception, and MobileNet revealed superior performance of the LFR-COA-DenseNet121-BC model, with 99.97% accuracy, 99.96% sensitivity, and 99.9% specificity. Further comparison with COA-DenseNet121 highlighted the superiority of LFR-COA-DenseNet-BC. In addition, LFR-COA was evaluated at the IEEE Congress on Evolutionary Computation held in 2022 (CEC 2022), and realworld medical scenarios showcased the effectiveness of LFR-COA compared to existing optimization algorithms. LFR-COA consistently outperformed the original COA algorithm and other well-known counterparts in various statistical, convergence, and diversity measures, affirming its efficacy in breast cancer classification.

关键词： Breast cancer Deep learning Convolutional neural networks (CNNs) Randomized L'evy flight coati optimization algorithm (LFR-COA) hyperparameters optimization

来源：评论

学校读者我要写书评

暂无评论

XGBoost based solutions for detecting fraudulent credit card transactions

XGBoost based solutions for detecting fraudulent credit card...

引用

International Conference on Advanced Creative Networks and Intelligent Systems (ICACNIS) - Blockchain Technology, Intelligent Systems, and the Applications for Human Life

作者： El Kafhali, Said Tayebi, Mohammed Hassan First Univ Settat Fac Sci & Tech IR2M Lab Settat Morocco

ISBN: (纸本)9798350334449

Due to the emigration of businesses to the internet, credit cards have become a widely used tool for customers to pay for purchases both online and offline. However, fraudsters try to attack these payment tools using various techniques, and credit card fraud transactions have become dangerous. Credit card payment security is becoming an important research topic, and different ways are proposed to overcome this problem. In this article, we will propose a solution that combines the strengths of three methods to secure credit card fraud transactions. The Differential Evolution (DE) algorithm is used to select the best hyperparameters of the XGBoost algorithm (eXtreme Gradient Boosting). Synthetic Minority Oversampling (SMOTE) combined with Edited Nearest Neighbour (ENN) to handle the imbalanced data issues. Finally, we will classify fraud transactions using the optimized XGBoost algorithm. The proposed solution is evaluated using the European data set in terms of Accuracy, Recall, F1-score, and AUC. As a result, the proposed solution generally achieved the best score in terms of all the measurements used in this study. In terms of accuracy, we achieved 99.94%, similarly, we reached the best score in terms of the Precision score, which is 80.68%, in addition, we got 86.02% of recall score, 83.27 of F-measure, and 99.21 of AUC score. Thus, we emphasize the superiority of our proposed method over the competitive machine learning model utilized in this work.

关键词： Fraud Transactions Detection hyperparameters optimization Differential Evolution Algorithm XGBoost algorithm Synthetic Minority Oversampling Edited Nearest Neighbor

来源：评论

学校读者我要写书评

暂无评论

An Automated Hyperparameter Search-Based Deep Learning Model for Highway Traffic Prediction

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2021年第9期22卷 5486-5495页

作者： Yi, Hongsuk Bui, Khac-Hoai Nam Korea Inst Sci & Technol Informat Daejeon 34141 South Korea

Auto machine learning recently has been introduced as a trending technique for learning applications, including smart transportation. In this study, we focus on applying auto-machine learning for hyperparameter tuning to learn traffic datasets at the main regions of highway systems. Particularly, deep learning models have been recently introduced as emergent methods for traffic prediction. However, training deep learning models requires expensive works (e.g., time-consuming and human expertise), especially in terms of determining the configurations of hyperparameters in the models. In this regard, this paper introduces an automated framework for hyperparameter tuning to learn traffic datasets at an ecosystem in terms of reducing time-consuming tasks. Specifically, we first propose the HyperNet framework, using advanced data science techniques (e.g., Bayesian optimization and meta-learning) for the automated hyperparameter search process. Then, a deep learning model with the long short term memory network based on the HyperNet framework has presented for learning the temporal variation of traffic datasets at main regions of highway traffic systems. Regarding the experiment, we take data from the Korean highway system into account as a case study to evaluate the proposed approach. The evaluation indicates promising results of the proposed framework for learning multiple datasets of the traffic highway systems.

关键词： Road transportation Predictive models Training Tuning optimization Bayes methods Deep learning Highway traffic prediction deep learning automated machine learning long-short term memory hyperparameters optimization meta learning

来源：评论

学校读者我要写书评

暂无评论

Immunocomputing-Based Approach for Optimizing the Topologies of LSTM Networks

引用

IEEE ACCESS 2021年 9卷 78993-79004页

作者： Al Bataineh, Ali Kaur, Devinder Univ Toledo Elect Engn & Comp Sci Dept Toledo OH 43606 USA

This paper aims to automatically design optimal LSTM topologies using the clonal selection algorithm (CSA) to solve text classification tasks such as sentiment analysis and SMS spam classification. Designing optimal topologies involves determining the best configuration of hyperparameters that will give the best performance. The current state-of-the-art LSTM topologies are often designed using trial and error approaches which are incredibly time-consuming and require domain experts. Our proposed method, referred to as CSA-LSTM, is evaluated using the Large Movie Review Dataset (IMDB). Furthermore, to verify the robustness of the hyperparameters discovered by CSA for the IMDB dataset, we have used them for the other datasets, viz. the Twitter US Airline Sentiment and the SMS Spam Collection. Additionally, the discovered hyperparameters for the LSTM are combined with pre-determined convolutional neural network (CNN) layers to achieve the same or better results to fast the training time and fewer trainable parameters. For further verification and evaluation of the generalization ability and effectiveness of the proposed approach, it is compared with four machine learning algorithms widely used for text classification tasks: (1) random forest (RF), (2) logistic regression (LR), (3) support vector machine (SVM), and (4) multinomial naive Bayes (NB). The results of our experiments show that the LSTM topologies automatically designed by our CSA method are less expensive, reusable and outperform the machine learning algorithms and other models in the literature evaluated on the same three datasets. Through our proposed method, LSTM's best topology can be self-determined without any human intervention, making CSA-based algorithms a promising approach to automatically design optimal LSTM topologies that provide the best performance for a given task.

关键词： Topology Logic gates Network topology Deep learning Genetic algorithms Training Task analysis Clonal selection algorithm deep learning hyperparameters optimization IMDB immunocomputing long short-term memory

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：