检索结果-内蒙古大学图书馆

Immunocomputing-Based Approach for Optimizing the Topologies of LSTM Networks

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

Comparison of Two Recurrent Neural Networks for Rainfall-Runoff Modeling in the Zou River Basin at Atchérigbé (Bénin)

引用

Journal of Geoscience and Environment Protection 2024年第9期12卷 167-181页

作者： Iboukoun Eliézer Biao Oscar Houessou Pierre Jérôme Zohou Adéchina Eric Alamou National School of Mathematical Engineering and Modeling National University of Sciences Technology Engineering and Mathematics Abomey Benin LaGEA National School of Public Works National University of Sciences Technology Engineering and Mathematics Abomey Benin International Chair of Mathematical Physics and Applications (ICMPA-UNESCO Chair) University of Abomey-Calavi Abomey-Calavi Bnin

Hydrological models are developed to simulate river flows over a watershed for many practical applications in the field of water resource management. The present paper compares the performance of two recurrent neural networks for rainfall-runoff modeling in the Zou River basin at Atchérigbé outlet. To this end, we used daily precipitation data over the period 1988-2010 as input of the models, such as the Long Short-Term Memory (LSTM) and Recurrent Gate Networks (GRU) to simulate river discharge in the study area. The investigated models give good results in calibration (R2 = 0.888, NSE = 0.886, and RMSE = 0.42 for LSTM;R2 = 0.9, NSE = 0.9 and RMSE = 0.397 for GRU) and in validation (R2 = 0.865, NSE = 0.851, and RMSE = 0.329 for LSTM;R2 = 0.9, NSE = 0.865 and RMSE = 0.301 for GRU). This good performance of LSTM and GRU models confirms the importance of models based on machine learning in modeling hydrological phenomena for better decision-making.

关键词： Supervised Learning Modeling Zou Basin Long and Short-Term Memory Gated Recurrent Unit hyperparameters optimization

来源：评论

学校读者我要写书评

暂无评论

Intelligent Traffic Flow Prediction Using Optimized GRU Model

引用

IEEE ACCESS 2021年 9卷 100736-100746页

作者： Hussain, Basharat Afzal, Muhammad Khalil Ahmad, Shafiq Mostafa, Almetwally M. COMSATS Univ Islamabad Wah Dept Comp Sci Wah Cantt 47040 Pakistan King Saud Univ Coll Engn Dept Ind Engn Riyadh 11421 Saudi Arabia King Saud Univ Coll Comp & Informat Sci Dept Informat Syst Riyadh 11421 Saudi Arabia

Facilitating citizens with accurate traffic flow prediction increases the quality of life. Roadside sensors and devices are used to capture live streams of huge data and the Internet of Things (IoT) is becoming popular for the deployment of effective Intelligent Transportation Systems (ITS). Traffic flow prediction from the live datastreams require building a data-driven model. This is a challenging task and has attracted researchers for better interpretation of the traffic characteristics. The core problem in traffic prediction is modeling a diversity of traffic trends and unpredictable flow variations with temporal dependencies. Initially, statistical and shallow neural network models were applied to some extent. Recently, deep learning has come up with proven and promising outcomes. Gated Recurrent Unit (GRU) is a variation of recurrent neural networks used effectively for traffic flow prediction. Like other deep networks, GRU uses hyperparameters and a sliding window time-steps mechanism to prepare and tune the model. Better tuning for hyperparameters and search for optimal window size is a tedious process. In this research work, we present an algorithm for hyperparameters tuning along with sliding window steps optimization. Results obtained on a real-time public traffic dataset show a higher capability of the proposed method to reduce the error and an average gain of the optimized model over the untuned network is 4.5%. Furthermore, we apply the optimal hyperparameters obtained in the experiment to other deep learning models and present that our approach improves prediction accuracy and stability.

关键词： Predictive models Data models Deep learning Logic gates Support vector machines Parametric statistics Recurrent neural networks Traffic flow prediction deep learning gated recurrent unit hyperparameters optimization

来源：评论

学校读者我要写书评

暂无评论

Haulage Cycles Identification for Wheeled Transport in Underground Mine Using Neural Networks

引用

SENSORS 2023年第3期23卷 1331-1331页

作者： Skoczylas, Artur Rot, Artur Stefaniak, Pawel Sliwinski, Pawel KGHM Cuprum Res & Dev Ctr Ltd Gen W Sikorskiego 2-8 PL-53659 Wroclaw Poland Wroclaw Univ Econ & Business Fac Management Komandorska 118-120 PL-53345 Wroclaw Poland KGHM Polska Miedz SA M Sklodowskiej Curie 48 PL-59301 Lubin Poland

The task of ore transportation is performed in all mines, regardless of their type (open pit/underground) or mining process. A substantial number of enterprises utilize wheeled machines to perform ore haulage, especially haul trucks and loaders. These machines' work consists of repeating cycles, and each cycle can be divided into 4 operations: loading, driving with full box/bucket, unloading and driving with empty box/bucket. Monitoring this process is essential to create analytical tools that support foremen and other management crew in achieving effective and optimal production and planning activities. Unfortunately, information gathered regarding the process is frequently based on operators' oral testimony. This process not only allows for abuse but is also a repetitive and tedious task that must be performed by foremen. The time and attention of foremen is valuable as they are responsible for managing practically everything in their current mine section (machines, operators, works, repairs, emergencies, safety, etc.). Therefore, the automatization of the described process of information gathering should be performed. In this article, we present two neural network models (one for haul trucks and one for loaders) build for detecting work cycles of the ore haulage process. Both models were built utilizing a 2-stage approach. In the first stage, the models' structures were optimized, while the second was focused on optimizing hyperparameters for the structure with best performance. Both of the proposed models were trained using data collected from on-board monitoring systems over hundreds of the machines' work hours and utilized the same input features: vehicle speed, fuel consumption, selected gear and engine rotational speed. Models have been subjected to comprehensive testing during which the efficiency and stability of the model responsible for haul trucks was proven. Results for loaders were not as high quality for haul trucks;however, some interesting facts we

关键词： ore transportation artificial intelligence underground mine wheeled transport operational regimes neural networks hyperparameters optimization

来源：评论

学校读者我要写书评

暂无评论

Forecasting long-term stock prices of global indices: A forward-validating Genetic Algorithm optimization approach for Support Vector Regression

引用

APPLIED SOFT COMPUTING 2023年 145卷

作者： Beniwal, Mohit Singh, Archana Kumar, Nand Delhi Technol Univ Delhi Sch Management Delhi 110042 India Delhi Technol Univ Dept Humanities Delhi 110042 India

Predicting long-term stock index prices is a challenging and debatable task. Most of the studies focus on predicting next-day stock prices. However, those are not useful to long-term investors and traders. In this paper, we attempt to predict up to a year's daily prices of global stock indices using daily close prices data. This study fills a gap in the existing literature by focusing on long-term stock index price forecasting, which is crucial for practical applications in the financial markets. Moreover, The empirical analysis highlights the superior performance of a rolling forward-validation approach over cross validation in predicting long-term stock prices. A forward-validating Genetic Algorithm optimization for Support Vector Regression (OGA-SVR) is used to efficiently forecast multi-step ahead long-term global stock indices. Further, the performance of the model is compared with that of Support Vector Regression (SVR), Grid Search based Support Vector Regression (GS-SVR), Genetic algorithm-based Support Vector regression (GA-SVM), and state-of-the-art Long Short-Term Memory (LSTM) algorithms. The models are empirically tested on five global stock indices time series daily data, namely Nifty, Dow Jones Industrial Average (DJIA), DAX performance index (DAX), Nikkei 225 (NI225), and Shanghai Stock Exchange composite index (SSE). Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) are used for the evaluation The result shows the OGA-SVR model outperforms other models in predicting the long-term prices of global indices. Further, the OGA-SVR model has the potential to forecast the long-term underlying future pattern of index prices which can be used to build trading and risk mitigation systems by investors and traders.& COPY;2023 Elsevier B.V. All rights reserved.

关键词： Long-term forecasting Genetic Algorithm Support Vector Regression Stock market prediction Forward validation Multi-step prediction hyperparameters optimization LSTM

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural network architecture search based on fractal decomposition optimization algorithm

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第PartA期213卷

作者： Souquet, Leo Shvai, Nadiya Llanza, Arcadi Nakib, Amir Vinci Autoroutes Nanterre France Univ Paris Est Creteil Lab LISSI 122 Rue Paul Armangot F-94400 Vitry Sur Seine France

This paper presents a new approach to design the architecture and optimize the hyperparameters of a deep convolutional neural network (CNN) via of the Fractal Decomposition Algorithm (FDA). This optimization algorithm was recently proposed to solve continuous optimization problems. It is based on a geometric fractal decomposition that divides the search space while searching for the best solution possible. As FDA is effective in single-objective optimization, in this work we aim to prove that it can also be successfully applied to fine-tuning deep neural network ***, a new formulation based on bi-level optimization is proposed to separate the architecture search composed of discrete parameters from hyperparameters' optimization. This is motivated by the fact that automating the construction of deep neural architecture has been an important focus over recent years as manual construction is considerably time-consuming, error-prone, and requires in-depth knowledge. To solve the bi-level problem thus formulated, a random search is performed aiming to create a set of candidate architectures. Then, the best ones are finetuned using FDA. CIFAR-10 and CIFAR-100 benchmarks were used to evaluate the performance of the proposed approach. The results obtained are among the state of the art in the corresponding class of networks (low number of parameters and chained-structured CNN architectures). The results are emphasized by the fact that the whole process was performed using low computing power with only 3 NVIDIA V100 GPUs. The source code is available at https://***/alc1218/Convolutional-Neural-Network-Architecture-Search-Based-on-Fractal-Decomposition-optimization.

关键词： Neural architecture search hyperparameters optimization Fractal decomposition

来源：评论

学校读者我要写书评

暂无评论

A novel approach based on XGBoost classifier and Bayesian optimization for credit card fraud detection

Cyber Security and Applications

引用

Cyber Security and Applications 2025年 3卷

作者： Tayebi, Mohammed El Kafhali, Said Computer Networks Modeling and Mobility Laboratory (IR2M) Faculty of Sciences and Techniques Hassan First University of Settat Settat 26000 Morocco

Nowadays, detecting fraudulent transactions has become increasingly important due to the rise of online businesses and the increasing use of sophisticated techniques by fraudsters to make fraudulent transactions appear similar to genuine ones. Researchers have explored a lot of machine learning classifiers, such as random forest, decision tree, support vector machine, logistic regression, artificial neural network, and recurrent neural network, to secure these systems. This study proposes an enhanced XGBoost algorithm for detecting fraudulent transactions using an intelligent technique that tunes the hyperparameters of the algorithm through Bayesian optimization. To test the performance of our solution, several experiments are conducted on two credit card datasets consisting of both legitimate and fraudulent transactions. To prevent overfitting on imbalanced datasets, we employed cross-validation, SMOTE, and Random under-sampling techniques. For Data 1, the best performance using SMOTE achieved an accuracy of 0.9996, precision of 0.9406, recall of 0.8740, F-measure of 0.8740, and AUC of 0.9879. For Data 2, the Random Under-sampling technique yielded the highest performance with an accuracy of 0.8325, precision of 0.8294, recall of 0.8378, F-measure of 0.8336, and AUC of 0.9088. Our proposed solution outperforms other machine learning models, as demonstrated by these experimental results. © 2025

关键词： Bayesian optimization Credit card transactions Cross-validation Fraud detection hyperparameters optimization Imbalanced datasets XGBoost algorithm

来源：评论

学校读者我要写书评

暂无评论

Bayesian Hyperparameter optimization of Deep Neural Network Algorithms Based on Ant Colony optimization 16th

Bayesian Hyperparameter Optimization of Deep Neural Network ...

引用

16th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Jlassi, Sinda Jdey, Imen Ltifi, Hela Univ Kairouan Fac Sci & Tech Sidi Bouzid Kairouan Tunisia Univ Sfax Natl Sch Engineers ENIS REs Grp Intelligent Machines BP 1173 Sfax 3038 Tunisia

ISBN: (纸本)9783030863340;9783030863333

Within this paper we proposed a new method named BayesACO, to improve the convolutional neural network based on neural architecture search with hyperparameters optimization. At its essence Bayes ACO in first side uses Ant Colony optimization (ACO) to generate the best neural architecture. In other side, it uses bayesian hyperparameters optimization to select the best hyperparameters. We applied this method on Mnist and FashionMnist datasets. Our proposed method proven competitive results with other methods of convolutional neural network optimization.

关键词： Convolutional neural network Neural architecture search hyperparameters optimization Ant colony optimization Bayesian hyperparameters optimization

来源：评论

学校读者我要写书评

暂无评论

Unveiling the secrets of neural network scaling for ECG classification

引用

Informatics in Medicine Unlocked 2025年 55卷

作者： Lee, Byeong Tak Kwon, Joon-myoung Jo, Yong-Yeon Medical AI Co. Ltd. 13th floor 38 Yeongdong-daero 85-gil Gangnam-gu Seoul 06180 South Korea

We present a new perspective on scaling neural networks for electrocardiograms (ECG). Although ResNet-based models are widely used in ECG classification, the potential benefits of network scaling remain unexplored. Our research investigates the impact of changes in the depth of layers, the number of channels, and the dimensions of the convolution kernels on performance. Contrary to computer vision practices, we found that shallower networks, with more channels and smaller kernels, lead to better performance for ECG classifications. Based on these findings, we provide insights that can guide the efficient development of models in practice. Finally, we explore why scaling hyperparameters affects ECG and computer vision differently. Our findings suggest that the inherent periodicity of the ECG signals plays a crucial role in this difference. © 2025

关键词： Convolutional neural network Deep learning Electrocardiogram hyperparameters optimization Network scaling

来源：评论

学校读者我要写书评

暂无评论

Novel hybrid classification model for multi-class imbalanced lithology dataset

引用

OPTIK 2022年 270卷

作者： Alyasin, Eman Ibrahim Ata, Oguz Mohammedqasim, Hayder Altinbas Univ Inst Sci Dept ECE Istanbul Turkey

Deep learning methods and applications assist geologists in predicting and identifying lithologies in different surveys, hence lowering operational costs and uptime. This allows accurate data analysis and completion of scientific research on data obtained at geologically different places. This study used 4 lithologies datasets with high dimensionality and multiclass imbalance problems for analysis and classification. The imbalance of data classification is one of the most important problems facing current data analysis. Data imbalance can considerably influence classification performance, especially when dealing with other difficulty variables such as the presence of overlapping class distributions. This impact is especially obvious in multi-class conditions when mutual imbalance relations across classes complicate matters even further. Moreover, the problem of high dimensionality can lead to increased computing complexity and overfitting, and thus these issues can affect classification performance. To overcome these problems, we developed a new hybrid deep learning multi-class imbalanced learning method that combines Synthetic Minority Oversampling (SMOTE) to resample the data, and Recursive Feature Elimination (RFE) to identify the most useful predictive features. Finally, we believe that our developments can help improve geology research by providing accurate classification and rapid answers about interpreting data obtained in various study areas.

关键词： Lithology Feature selection hyperparameters optimization Synthetic minority oversampling technique Multi -class imbalanced learning

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：