检索结果-内蒙古大学图书馆

Hybrid deep learning algorithm for smart cities security enhancement through blockchain and internet of things

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第8期83卷 22609-22637页

作者： Mishra, Sourav Chaurasiya, Vijay Kumar Indian Inst Informat Technol Prayagraj 211015 Uttar Pradesh India

Internet of Things (IoT) usage is cherishing nowadays and it is widely used in variety of exciting application such as hospital, industry and cities. Security is found to be a major concern in IoT based application due to advancement made in the field of Information and software technology. Transactions using internet has become significantly in case of smart cities and it is frequently prone to various cyber security threats. For securing various transaction in smart cities hybrid deep learning LSTM-SVM algorithm is developed. Initially, data related to transaction in smart cities is gathered and pre-processed utilizing min-max normalization and weighted average filter. Min-max normalization is employed or normalizing the raw data to a certain range. Then, weighted average filter is used for removing noise in the data. After that, appropriate features from pre-processed data is selected using reptile search algorithm. Using industrial gateway, the selected features are provided to blockchain based distributed network. Function of blockchain is to verify the transaction process using trusted entities. Verifier check whether the transaction is genuine or fake through detecting the presence of attack. In case of genuine transaction request, the transaction is accomplished through creating a block on the blockchain. On the other hand, if an attack is detected the transaction is blocked and further types of attack is predicted using deep learning-based hybrid LSTM- SVM classifier. Simulation analysis on the proposed hybrid deep learning model showed 97% accuracy, 98% specificity, 91% F1 score and 82% sensitivity. Based on this proposed model fake transaction in IoT based blockchain is blocked and paved way for development of secure smart cities environment.

关键词： IoT devices Min-max normalization Weighted average filter reptile search algorithm Block chain network Hybrid LSTM-SVM

来源：评论

学校读者我要写书评

暂无评论

Improved indirect instantaneous torque control based torque sharing function approach of SRM drives in EVs using hybrid technique

引用

ISA TRANSACTIONS 2023年第1期139卷 322-336页

作者： Kannan, R. Rajasekaran, S. Stallon, S. Daison Anand, R. Nehru Inst Engn & Technol Dept Elect & Elect Engn Coimbatore Tamil Nadu India KSR Inst Engn & Technol Dept Elect & Elect Engn Tiruchengode Tamil Nadu India

This manuscript proposes an improved indirect instantaneous torque control (IITC) based torque sharing function (TSF) method of switched reluctance motor (SRM) drives in electric vehicles (EVs) using a hybrid system. The proposed hybrid techniques are joint performance of both reptile search algorithm (RSA) and Honey Badger algorithm (HBA), hence it is named as Enhanced RSA (ERSA) method. Here, an IITC method of SRMs for EVs is utilized. It achieves the requirements of the vehicle, like minimum torque ripple, improved speed range, high effectiveness, and maximal torque per ampere (MTPA). To precisely specify the switched reluctance motor and its magnetic features are measured by the proposed method. The modified Torque sharing function compensates the torque error along with incoming phase, which contains the minimal rate of change of flux linkage. Finally, the ERSA method is implemented to define the best control parameters. Then, the proposed ERSA system is performed on the MATLAB platform and the performance is compared to different existing systems. The MSE for case 1 and case 2 using proposed system attains 0.01093 and 0.01095. The voltage deviation for case 1 and case 2 using proposed system reaches 5 and 5. The power factor for case 1 and case 2 reaches a value of 50 and 40 using the proposed system. & COPY;2023 ISA. Published by Elsevier Ltd. All rights reserved.

关键词： Honey Badger algorithm reptile search algorithm Torque control Electric vehicles Indirect instantaneous torque control

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis of algorithms on concrete at elevated temperatures

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第6期7卷 6191-6205页

作者： Duan, Min Chongqing Coll Finance & Econ Coll Design Chongqing 402160 Peoples R China

Elevated temperatures have a substantial influence on the properties of the materials used in concrete manufacturing, leading to a noticeable decrease in the strength properties of the concrete. Attaining the intended compressive strength of concrete is a demanding and time-consuming pursuit. However, the use of supervised machine learning methods allows for an accurate initial prediction of the intended result. This work demonstrates the utilization of multi-layered perceptron (MLP), support vector regression (SVR), and least squared SVR (LSSVR) for predicting the compressive strength of concrete at elevated temperatures. The prediction models were enhanced by using the reptile search algorithm (RSA) and were trained on a dataset consisting of 207 data points. The investigation included a collection of nine input variables, namely water, cement, coarse aggregate, fine aggregate, fly ash, superplasticizers, silica fume, nano silica, and temperature. The results indicate that all the LSSR, SVRR and MLPR show great potential in accurately predicting the fc of concrete at elevated temperatures with acceptable values of the R2. Regarding the values related to the error-based metrics, the lowest values belonged to the LSSR model with a decline of about 50% with respect to the SVRR and MLPR networks. Turning to uncertainty analysis, it was obvious that in all three training, validating, and testing phases, MLPR resulted in the highest values of uncertainty, compared to SVRR. On the other hand, the most reliable model called LSSR introduced the smallest values of uncertainty at 6.028, 5.98, and 6.52, respectively, which depicted remarkable accuracy and dependability.

关键词： Concrete Elevated temperature Mechanical properties Estimation reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

Elevating Student Performance Prediction using Extra-Trees Classifier and Meta-Heuristic Optimization algorithms

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第2期15卷 434-450页

作者： Li, Yangbo He, Mengfan Henan Inst Technol Dept Comp Sci & Technol Xinxiang 453003 Henan Peoples R China Henan Inst Technol Off President Xinxiang 453003 Henan Peoples R China

In the highly competitive landscape of academia, the study addresses the multifaceted challenge of analyzing voluminous and diverse educational datasets through the application of machine learning, specifically emphasizing dimensionality reduction techniques. This sophisticated approach facilitates educators in making data-informed decisions, providing timely guidance for targeted academic improvement, and enhancing the overall educational experience by stratifying individuals based on their innate aptitudes and mitigating failure rates. To fortify predictive capabilities, the study employs the robust Extra-Trees Classifier (ETC) model for classification tasks. This model is enhanced by integrating the Gorilla Troops Optimizer (GTO) and reptile search algorithm (RSA), cutting-edge optimization algorithms designed to refine decision-making processes and improve predictive precision. This strategic amalgamation underscores the research's commitment to leveraging advanced machine learning and bio-inspired algorithms to achieve more accurate and resilient student performance predictions in the mathematics course, ultimately aiming to elevate educational outcomes. Analyses of G1 and G3 showcase the efficacy of the ETRS model, demonstrating 97.5% Accuracy, F1-Score, and Recall in predicting the G1 values. Similarly, the ETRS model emerges as the premier predictor for G3, attaining 95.3% Accuracy, Recall, and F1-Score, respectively. These outcomes underscore the significant contributions of the proposed models in advancing precision and discernment in student performance prediction, aligning with the overarching goal of refining educational outcomes.

关键词： Student performance mathematics machine learning Extra-Trees Classifier Gorilla Troops Optimizer reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

Research and application of a novel selective stacking ensemble model based on error compensation and parameter optimization for AQI prediction

引用

ENVIRONMENTAL REsearch 2024年 247卷 118176页

作者： Peng, Tian Xiong, Jinlin Sun, Kai Qian, Shijie Tao, Zihan Nazir, Muhammad Shahzad Zhang, Chu Huaiyin Inst Technol Fac Automat Huaian 223003 Peoples R China Huaiyin Inst Technol Jiangsu Permanent Magnet Motor Engn Res Ctr Huaian 223003 Peoples R China

With the ongoing process of industrialization, the issue of declining air quality is increasingly becoming a critical concern. Accurate prediction of the Air Quality Index (AQI), considered as an all-inclusive measure representing the extent of pollutants present in the atmosphere, is of paramount importance. This study introduces a novel methodology that combines stacking ensemble and error correction to improve AQI prediction. Additionally, the reptile search algorithm (RSA) is employed for optimizing model parameters. In this study, four distinct regional AQI data containing a collection of 34864 data samples are collected. Initially, we perform cross -validation on ten commonly used single models to obtain prediction results. Then, based on evaluation indices, five models are selected for ensemble. The results of the study show that the model proposed in this paper achieves an improvement of around 10% in terms of accuracy when compared to the conventional model. Thus, the model introduced in this study offers a more scientifically grounded approach in tackling air pollution.

关键词： Air pollution Stacking ensemble model Error correction reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

A New Signal Denoising algorithm for Low Cost MEMS Gyroscope 3

A New Signal Denoising Algorithm for Low Cost MEMS Gyroscope

引用

3rd International Conference on Sensors and Information Technology (ICSI)

作者： Lv, Ziqiang Si, Tingbo Mu, Wenchao Wang, XiaoMing Nanjing Univ Sci & Technol Sch Mech Engn Nanjing Peoples R China Nanjing Univ Sci & Technol Natl Def Key Lab Intelligent Ammunit Nanjing Peoples R China

ISBN: (纸本)9781510666122;9781510666139

Inertial measurement unit (IMU) has been commonly used in measuring angles, displacement measurement and other fields. However, micro electro-mechanical system (MEMS) gyroscopes have little accuracy of measuring and enormous noise;real signals will be cloaked in the noise. A new denoising algorithm for low cost MEMS gyroscope is offeredin this paper. First, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm is used to decompose the initial-signal which can obtain a limited number of intrinsic mode functions (IMF). Next, use the power spectrum entropy to divide the IMF into noise signals, mixed signals and sound signals. Then, variational mode decomposition (VMD) is choosen to decompose the mixed signal, and using reptile search algorithm (RSA) optimization algorithm optimizes the crucial arguments of VMD. VMD algorithm appropriately dismantles the signal according to the optimized arguments to attain the IMF sections, divided into signal sections and noise sections using the Bhattacharyian distance. The signal sections are furthermore processed by lifting wavelet threshold denoising (LWT), and the valuable signal with denoising is obtained. Finally, all the valuable signals are amalgamated and reestablished into the ending-denoising signal. The effectuality of the algorithm is weighted by Matlab simulation. The static denoising experimentation of the three-axis turntable is put up in the experimental analysis, which exhaustively confirms that the algorithm has clear superiority in denoising and significantly increases the signal quality and the accuracy of the cheap MEMS gyroscope.

关键词： MEMS gyroscope denoising adaptive noise integrated empirical mode decomposition reptile search algorithm lifting wavelet threshold denoising

来源：评论

学校读者我要写书评

暂无评论

A hybridized LSTM-ANN-RSA based deep learning models for prediction of COVID-19 cases in Eastern European countries

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 256卷

作者： Manohar, Balakrishnama Das, Raja Lakshmi, M. Vellore Inst Technol VIT Sch Adv Sci Dept Math Vellore 632014 TamilNadu India Vignans Fdn Sci Technol & Res Sch Appl Sci & Humanities Dept Math & Stat Guntur 522213 Andhra Pradesh India SRM Inst Sci & Technol Dept Math Ramapuram Campus Chennai 600089 Tamil Nadu India

Deep learning models have become essential for managing time-series data across various applications in recent years. COVID-19 case data presents complex time-series patterns with high nonlinearities and dynamic fluctuations. Long short-term memory (LSTM) networks offer a suitable framework for developing prediction models to handle such complexities. However, conventional LSTM networks often have predefined, extensive structures, leading to overfitting issues and difficulties in determining the optimal number of hidden neurons. To address these challenges, we propose Regularized Self-Organizing LSTM (LSTM-ANN-RSA). This method optimizes both the structure and parameters of the network. This study introduces an adaptive learning algorithm with L2-norm regularization to adjust parameters, ensuring prediction accuracy and mitigating overfitting. Additionally, a growing strategy based on hidden neuronal sensitivity automatically determines the LSTM-ANN structure, enhancing compactness and efficiency. The proposed model's efficiency is demonstrated through comparisons with multiple deep learning models (ANN-GD, ANN-LM, ANN-RSA, GRU-ADAM and LSTM-ADAM). The results show that LSTM-ANN-RSA significantly outperformed others in predicting COVID-19 in five countries (Croatia, Greece, Italy, Poland, and Russia), with lower MAPE (2285.018, 64.4903, 205.70, 1611.19, 572.98) and higher R2 (0.99824, 0.99726, 0.99786, 0.9962, 0.99252) values. These findings highlight the proposed model's substantial improvements in predicting the COVID-19 pandemic, enhancing the region's ability to plan for and respond to future epidemics.

关键词： ANN Adaptive learning COVID-19 Gradient descent L2-norm regularization Levenberg-Marquardt LSTM reptile search algorithm

来源：评论

学校读者我要写书评

暂无评论

A forecasting model for optimizing abrasive water jet machining (AWJM) parameters based on the adaptive neuro-fuzzy inference system and meta-heuristic algorithms

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART E-JOURNAL OF PROCESS MECHANICAL ENGINEERING 2023年

作者： Jithendra, Thandra Basha, S. Sharief Vellore Inst Technol Sch Adv Sci Dept Math Vellore Tamil Nadu India Vellore Inst Technol Sch Adv Sci Dept Math Vellore 632014 Tamil Nadu India

Innovative materials have been steadily produced in the machining process, and it has stimulated substantial attention among researchers to assess the ideal parameters for the processing of these materials. In the manufacturing industry, conventional and modern or unconventional machining retains their imprint in delivering quality products. One of the most frequently used contemporary machining processes is abrasive water jet machining (AWJM) for cutting materials. The optimization of parameters, however, is essential to manufacturing high-quality products quickly and affordably. This study focused on optimizing the machining parameters of AWJM using the Adaptive Neuro-Fuzzy Inference System (ANFIS) by encrypting the evolutionary algorithms, including the reptile search algorithm (RSA), beetle antennae search (BAS), and particle swarm optimization (PSO). As a result of the developed methods, the surface roughness of titanium alloy (Ti-6Al-4V) during AWJM machining is predicted by considering inputs such as standoff distance, abrasive flow rate, and traverse speed, which affect the surface roughness. Based on a comparison of the prediction accuracy of the proposed methods, it was found that the combined ANFIS and RSA outperforms the others. In the simulation results, ANFIS-RSA (Adaptive Neuro-Fuzzy Inference System and reptile search algorithm) yielded the most accurate estimates of surface roughness based on the RMSE (0.1241), MAE (0.0961), MAPE (0.0201), and R2 (0.9781) values. In particular, the analysis findings demonstrated that the combination of ANFIS and RSA was the most effective approach for predicting surface roughness on titanium alloy during AWJ machining.

关键词： Abrasive water jet machine surface roughness (Ra) adaptive neuro-fuzzy inference system (ANFIS) reptile search algorithm beetle antennae search and particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Software defects prediction by metaheuristics tuned extreme gradient boosting and analysis based on Shapley Additive Explanations

引用

APPLIED SOFT COMPUTING 2023年 146卷

作者： Zivkovic, Tamara Nikolic, Bosko Simic, Vladimir Pamucar, Dragan Bacanin, Nebojsa Univ Belgrade Sch Elect Engn Bulevar Kralja Aleksandra 73 Belgrade 11000 Serbia Univ Belgrade Fac Transport & Traff Engn Vojvode Stepe 305 Belgrade 11000 Serbia Yuan Ze Univ Coll Engn Dept Ind Engn & Management Yuandong Rd Taoyuan City 320315 Taiwan Univ Belgrade Fac Org Sci Dept Operat Res & Stat Jove Ilica 154 Belgrade 11000 Serbia Singidunum Univ Fac Informat & Comp Danijelova 32 Belgrade 11000 Serbia

Software testing represents a crucial component of software development, and it is usually making the difference between successful and failed projects. Although it is extremely important, due to the fast pace and short deadlines of contemporary projects it is often neglected or not detailed enough due to the lack of available time, leading to the potential loss of reputation, private users' data, money, and even lives in some circumstances. In such situations, it would be vital to have the option to predict what modules are error-prone according to the collection of software metrics, and to focus testing on them, and that task is a typical classification task. Machine learning models have been frequently employed within a wide range of classification problems with significant success, and this paper proposes eXtreme gradient boosting (XGBoost) model to execute the defect prediction task. A modified variant of the well-known reptile search optimization algorithm has been suggested to carry out the calibrating of the XGBoost hyperparameters. The enhanced algorithm was named HARSA and evaluated on the collection of challenging CEC2019 benchmark functions, where it exhibited excellent performance. Later, the introduced XGBoost model that uses the proposed algorithm has been evaluated on two benchmark software testing datasets, and the simulation outcomes have been compared to other powerful swarm intelligence metaheuristics that were used in the identical experimental environment, where the proposed approach attained superior classification accuracy on both datasets. Finally, Shapley Additive Explanations analysis was conducted to discover the impact of various software metrics on the classification results.& COPY;2023 Elsevier B.V. All rights reserved.

关键词： Software testing Software defect prediction XGBoost reptile search algorithm Metaheuristics optimization

来源：评论

学校读者我要写书评

暂无评论

Advanced Air Quality Forecasting Using an Enhanced Temporal Attention-Driven Graph Convolutional Long Short-Term Memory Model With Seasonal-Trend Decomposition

引用

IEEE ACCESS 2024年 12卷 189233-189252页

作者： Boddu, Yuvaraja Manimaran, A. Arunkumar, B. Sucharitha, M. Suresh Babu, J. VIT AP Univ Sch Adv Sci Dept Math Amaravati 522241 Andhra Pradesh India Manipal Acad Higher Educ Manipal Inst Technol Bengaluru Dept Informat Technol Manipal 576104 India VIT AP Univ Sch Elect Engn SENSE Amaravati 522241 Andhra Pradesh India Mohan Babu Univ Dept Comp Applicat Tirupati 517102 Andhra Pradesh India

This study presents the Improved Residual Spatial Attention-Temporal Convolutional Network (IRSA-TCN), an advanced framework for enhancing air quality forecasting across multiple pollutants. By integrating Residual Spatial Attention (RSA) with Graph Convolutional Long Short-Term Memory (GCLSTM) and Seasonal-Trend decomposition using Loess (STL), the IRSA-TCN model effectively captures intricate spatial and temporal patterns inherent in environmental data. The model demonstrates significant improvements in predictive accuracy, achieving reductions of 10-15% in error metrics such as Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) compared to traditional forecasting methods. Specifically, the IRSA-TCN model excels in predicting key pollutants, including nitrogen dioxide (NO2), carbon monoxide (CO), benzene, and nitrogen oxides (NOx), showcasing its capability to account for seasonal variations and complex interdependencies among pollutants. The findings underscore the model's potential as a robust tool for environmental monitoring and management, providing actionable insights for policymakers and stakeholders. Future research will focus on enhancing the model's adaptability through multi-scale spatial attention mechanisms and exploring hybrid architectures with Graph Neural Networks (GNNs) to further refine its applicability in real-time air quality forecasting scenarios. This work significantly contributes to the academic discourse on advanced analytical techniques in environmental science.

关键词： Air quality improved residual spatial attention improved residual spatial attention temporal convolutional network temporal convolutional network seasonal- trend decomposition with loess reptile search algorithm reptile search algorithm

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：