检索结果-内蒙古大学图书馆

GSA-based support vector neural network:a machine learning approach for crop prediction to provision sustainable farming

引用

International Journal of Intelligent Computing and Cybernetics 2023年第1期16卷 1-16页

作者： A.Ashwitha C.A.Latha Department of ISE Ramaiah Institute of TechnologyBangaloreIndia Department of CSE AMCECBangaloreIndia and Vishveshwarya Technical UniversityBelgaumIndia Department of CSE AMC Engineering CollegeBangaloreIndia

Purpose-Automated crop prediction is needed for the following reasons:First,agricultural yields were decided by a farmer’s ability to work in a certain field and with a particular crop *** were not always able to predict the crop and its yield solely on that idea ***,seed firms frequently monitor how well new plant varieties would grow in certain ***,predicting agricultural production is critical for solving emerging food security concerns,especially in the face of global climate *** production forecasts not only assist farmers inmaking informed economic andmanagement decisions but they also aid in the prevention of *** results in farming systems’efficiency and productivity gains,as well as reduced risk from environmental ***/methodology/approach-This research paper proposes a machine learning technique for effective autonomous crop and yield prediction,which makes use of solution encoding to create solutions randomly,and then for every generated solution,fitness is evaluated to meet highest *** focus of the proposed work is to optimize the weight parameter in the input *** algorithm continues until the optimal agent or optimal weight is selected,which contributes to maximum accuracy in automated crop ***-Performance of the proposed work is compared with different existing algorithms,such as Random Forest,support vector machine(SVM)and artificial neural network(ANN).The proposed method support vector neural network(SVNN)with gravitational search agent(GSA)is analysed based on different performance metrics,such as accuracy,sensitivity,specificity,CPU memory usage and training time,and maximum performance is *** limitations/implications-Rather than real-time data collected by Internet of Things(IoT)devices,this research focuses solely on historical data;the proposed work does not impose IoT-based smart farming,which enhances the overall agriculture system by

关键词： Crop yield Support vector machine(SVM) Artificial neural network(ANN) SVNN gravitational search algorithm

来源：评论

学校读者我要写书评

暂无评论

A photovoltaic maximum power point tracking method based on fuzzy improved gravity search algorithm 3

A photovoltaic maximum power point tracking method based on ...

引用

3rd International Conference on Energy and Electrical Power Systems (ICEEPS)

作者： Xing, Zheng Chang, Xiaoheng Bohai Univ Coll Control Sci & Engn Jinzhou Peoples R China

ISBN: (纸本)9798350375145;9798350375138

According to the advantages and disadvantages of the existing maximum power point tracking methods, this paper proposes a new maximum power point tracking method by applying the fuzzy control to the gravitational search algorithm, firstly, improve the optimization speed by taking advantage of the fast convergence speed of the gravitational search algorithm, and secondly, set the index of population maturity, and then set the dynamic adjustment strategy for the flight speed of the particles in the solution space by introducing the fuzzy rule after the population reaches a certain maturity level. After the population reaches a certain maturity, by introducing fuzzy rules, the dynamic adjustment strategy of particle flight speed in the solution space is set up. Finally, a simulation model is established by MATLAB/simulink, and simulation analysis is carried out under different lighting environments, and compared with the traditional gravitational search algorithm, which proves the advantages of the improved algorithm in terms of the searching accuracy and speed, as well as a better effect in solving the problem of local optimization.

关键词： maximum power point tracking fuzzy control gravitational search algorithm local optimization

来源：评论

学校读者我要写书评

暂无评论

A hybrid gravitational search algorithm-Genetic algorithm for neural network training

A hybrid Gravitational Search Algorithm-Genetic Algorithm fo...

引用

21st Iranian Conference on Electrical Engineering (ICEE)

作者： Sheikhpour, Saeide Sabouri, Mahdieh Zahiri, Seyed-Hamid Birzeit Univ Fac Elect Engn Birjand Iran

ISBN: (纸本)9781467356343

Tuning optimum parameter of neural networks, such as weights and biases, has major effects on their performance improvement. Estimation of optimum values for these parameters requires strong and effective training methods, so that the error of the training data reaches its minimum. This paper presents, a suitable training method for optimizing neural networks parameters using a novel hybrid GA-GSA algorithm. Extensive experimental results on different benchmarks show that the hybrid algorithm, performs equal to or better than standard GSA, and backpropagation algorithm.

关键词： neural network gravitational search algorithm genetic algorithm back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Approach for Accurate Prediction of Chronic Diseases

引用

Computer Systems Science & Engineering 2023年第8期46卷 2571-2587页

作者： S.Kavi Priya N.Saranya Mepco Schlenk Engineering College SivakasiTamilnaduIndia

Around the globe,chronic diseases pose a serious hazard to healthcare *** majority of the deaths are due to chronic diseases,and it causes burdens across the *** analyzing healthcare data and extracting patterns healthcare administrators,victims,and healthcare communities will get an advantage if the diseases are early *** majority of the existing works focused on increasing the accuracy of the techniques but didn’t concentrate on other performance ***,the proposed work improves the early detection of chronic disease and safeguards the lives of the patients by increasing the specificity and sensitivity of the classifiers along with the *** proposed work used a hybrid optimization algorithm called the Hybrid gravitational search algorithm and Particle Swarm Optimization algorithm(HGSAPSO)to upgrade the detection of chronic *** classifier parameters with their optimized parameters are compared and *** such as Artificial Neural Network(ANN),Support Vector Machines(SVM),K-Nearest Neighbor(Knn),and Decision tree(DT)are *** care data are obtained from the UCI machine learning repository to evaluate the proposed *** proposed work is assessed on 6 benchmark datasets and the performance metrics such as Accuracy,Specificity,Sensitivity,F-measure,Recall,and Precision are *** experimental results exhibit that the proposed work attains better accuracy on Artificial Neural Network-Hybrid gravitational search algorithm and Particle Swarm Optimization algorithm(ANN-HGSAPSO)classifier compared to other ***-HGSAPSO provides 93%accuracy for Chronic Kidney Disease(CKD),Cardio Vascular Disease(CVD)96%,Diabetes 82%,Hepatitis 94%,Wisconsin Breast Cancer(WBC)91%,and for Liver disease dataset 96%.

关键词： Chronic diseases optimization gravitational search algorithm particle swarm optimization machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

GSA-Inspired Computational Nanobiosensing for Cancer Detection 18th

GSA-Inspired Computational Nanobiosensing for Cancer Detecti...

引用

18th International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA)

作者： Shi, Shaolong Jiang, Zhaoyang Chen, Yifan Univ Elect Sci & Technol China Yangtze Delta Reg Inst Quzhou Quzhou 324003 Peoples R China Univ Elect Sci & Technol China Sch Life Sci & Technol Chengdu 611731 Peoples R China

ISBN: (纸本)9789819722716;9789819722723

We consider the cancer detection procedure (CDP) as the process of the gravitational search algorithm (GSA). Nanorobots coated with protease-sensitive nanomaterials can react with protease which causes unquenching of fluorogenic probes for imaging application. As the protease concentration can induce the different degree of fluorogenic, the strength of fluorogenic can be seen as the tumor-induced biological objective function whose maximum is regarded as the tumor location. The process that employing the externally controllable and trackable nanorobots to detect the tumor in high-risk tissue is treated as using agents to complete the optimization process in the search space. To accomplish the cancer detection procedure using nanorobots with the shortest possible physiological routes and with minimal systemic exposure, it is feasible to adjust the movement of nanorobots according to the information shared by other nanorobots. Following this outline, we consider the mechanism of gravitational search algorithm (GSA) which is more concise and efficient compared with PSO or GA in swarm intelligence field. Every nanorobot in the CDP can be seen as a particle in GSA and the fitness of every nanorobot is associated with the strength of its fluorogenic. To make the reality of the CDP, we should take into account the realistic in vivo propagation scenario of nanorobots swimming in the high-risk tissue to find the tumor location. Finally, we present numerical examples to demonstrate the effective of the CDP in view of GSA.

关键词： cancer detection biosensing swarm optimization gravitational search algorithm nanorobots

来源：评论

学校读者我要写书评

暂无评论

Hyper-heuristic strategies for optimal power flow problem with FACTS devices allocation in wind power integrated system

引用

RESULTS IN CONTROL AND OPTIMIZATION 2024年 14卷

作者： Sulaiman, Mohd Herwan Mustaffa, Zuriani Univ Malaysia Pahang Al Sultan Abdullah UMPSA Fac Elect & Elect Engn Technol Pekan 26600 Pahang Malaysia Univ Malaysia Pahang Al Sultan Abdullah UMPSA Fac Comp Pekan 26600 Pahang Malaysia

This research provides hyper-heuristic methodologies for solving Optimal Power Flow (OPF) issues in power system networks with Flexible AC Transmission Systems (FACTS) devices. OPF can be treated as one of the demanding challenges in the power system operating networks. To address the problems of loss and cost reduction, three types of FACTS devices will be studied in this paper: Static VAR Compensator (SVC), ThyristorControlled Series Compensator (TCSC), and Thyristor-Controlled Phase Shifter (TCPS). Two high level hyper-heuristic (HHH) approaches, called Exponential Monte Carlo with counter (EMCQ) and randomly select-Only Improving (OI), are employed as high-level metaheuristic to select and leverage the effectiveness of four low-level metaheuristics (LLH). These low-level metaheuristics comprise the Moth-Flame Optimizer (MFO), Barnacles Mating Optimizer (BMO), Teaching-Learning Based Optimization (TLBO) and Gradient-Based Optimizer (GBO). The usage of HHH solving the OPF problem is tested on the modified IEEE 30 bus system that integrates the thermal generators with the wind power. Findings of the study demonstrated the promising results by HHH which manages to outperform all the selected LLH algorithms.

关键词： ABC artificial bee colony AGPSO GWO autonomous groups particle swarm and grey wolf optimizers ANN artificial neural network BF bacterial foraging BMO Barnacles Mating Optimizer DE differential evolution DG distributed generation EMCQ exponential Monte Carlo with counter FACTS flexible AC transmission system GBO gradient-based optimizer GSA gravitational search algorithm GOA grasshopper optimization algorithm HBO heap-based optimization HHH high level hyper-heuristic IP interior point LLH low-level heuristic LP linear programming MFO moth flame optimization MLAPO modified lightning attachment procedure optimizer NLP non-linear programming NM Nelder–mead OI randomly select-only improving OPF optimal power flow PSO particle swarm optimization PV photovoltaic QP quadratic programming SSA Salp swarm algorithm SHADE success history based adaptive DE SOS symbiotic organisms search SVC static VAR compensator TCPS thyristor-controlled phase shifter TCSC Thyristor-Controlled Series Compensator TLBO teaching-learning-based optimization

来源：评论

学校读者我要写书评

暂无评论

Minimax Approximation Synthesis in PSS Design by Embedding gravitational search algorithm

Minimax Approximation Synthesis in PSS Design by Embedding G...

引用

International Conference on Advanced Communication Control and Computing Technologies

作者： Akash Saxena Bhanu Pratap Soni Vikas Gupta Dept. of Electrical Engineering Malaviya National Institute of Technology Jaipur India Arya College of Engineering & Information Technology

ISBN: (纸本)9781479939152

This paper presents a new approach to formulate the conventional objective function into multi order polynomials. This work also gives an emphasis on a novel designing and tuning methodology of power system stabilizers (PSSs) over New England System (10 Generator, 39 bus).The intelligent technique based on Newton's Law of gravitation and law of motion, Gravitation search algorithm (GSA) is applied to find the optimal parameters of PSSs. A new minimax approach is employed to design the PSSs, where several run of eigenvalue analysis is performed and in each iteration maximum deviation between ideal phase lag and proposed design is calculated. Approach is to minimize the maximum deviation between both frequency responses. For each set of PSSs parameters, the correlation between settling time, over shoot of the rotor swing curves is formulated by using minimax approach. The efficacy of the proposed design is tested over a wide range of contingencies, perturbation and different system configurations. Comparative analysis of all polynomial designs are presented while solving each with GSA. The results show those polynomials of order one (linear) are found to be the best fit and show a robust response under all operating conditions.

关键词： gravitational search algorithm Power System stabilizer Excitation System Minimax approximation Automatic Voltage Regulators (AVRs)

来源：评论

学校读者我要写书评

暂无评论

A new intrusion detection method for cyber-physical system in emerging industrial IoT

引用

COMPUTER COMMUNICATIONS 2022年 190卷 24-35页

作者： Mittal, Himanshu Tripathi, Ashish Kumar Pandey, Avinash Chandra Alshehri, Mohammad Dahman Saraswat, Mukesh Pal, Raju JIIT Dept Comp Sci & Engn & Informat Technol Noida India MNIT Dept Comp Sci Jaipur India IIITDM Dept Comp Sci Engn Jabalpur India Taif Univ Coll Comp & Informat Technol Dept Comp Sci POB 11099 At Taif 11099 Saudi Arabia

In Industrial Internet-of-Things, data streams across heterogeneous networks which results in several cyber- physical attacks. Moreover, the security of unlabeled data is a challenging task. For the same, this paper presents a new clustering method for intrusion detection. The proposed method employs a novel variant of gravitational search algorithm to obtain optimal clusters. In the proposed variant, Kbest is modified as an exponentially decreasing function with logistic-mapping-based chaotic behavior. To validate the proposed variant, a comparative analysis on IEEE CEC2013 benchmark functions is conducted against five existing algorithms. Experimental results are investigated in terms of mean error value, Wilcoxon rank-sum test, convergence graph, box-plot, and time complexity. It has been observed that proposed variant attained best values for maximum number of times on each dimension, i.e. 10, 13, 15, and 10 on 10, 30, 50, and 90 dimensions, respectively. Further, the efficacy of the proposed clustering method is tested on five Industrial Internet-of-Things datasets. The evaluation is performed in terms of F-measure and computation time. Experiments affirm that the proposed method outperforms considered methods on 80% of the datasets in terms of F-measure and computation time for ensuring security in a real-time Industrial Internet-of-Things environment.

关键词： Intrusion detection Industrial Internet-of-Things Clustering method gravitational search algorithm

来源：评论

学校读者我要写书评

暂无评论

Clustering with a high-performance secure routing protocol for mobile ad hoc networks

引用

JOURNAL OF SUPERCOMPUTING 2022年第6期78卷 8830-8851页

作者： Srinivas, Maganti Patnaik, M. Ramesh Andhra Univ AU Coll Engn Instrument Technol Vishakhapatnam 530003 Andhra Pradesh India VR Siddhartha Engn Coll EIE Vijayawada 520007 Andhra Pradesh India

Mobile ad hoc networks (MANETs) comprise a collection of independent, compact-sized, and inexpensive sensor nodes, which are commonly used to sense the physical parameters in geographical locations and transmit them to base stations (BSs). Since clustering and routing are considered commonly used energy efficient techniques, several metaheuristic algorithms have been employed to determine optimal cluster heads (CHs) and routes to destinations. However, most metaheuristic techniques have failed to achieve effective clustering and routing solutions in a large search space, and the probability of generating optimal solutions is also considerably reduced. To resolve these issues, this paper presents a new metaheuristic quantum worm swarm optimization-based clustering with a secure routing protocol for MANETs, named QGSOC-SRP. The presented QGSOC-SRP technique follows a two-stage process, namely optimal CH selection and route selection. First, the QGSO algorithm derives a fitness function using four variables, the energy, distance, node degree, and trust factor, for the optimal selection of secure CHs. Second, the SRP using the oppositional gravitational search algorithm (OGSA) is applied for the optimal selection of routes to the BS. The traditional GSA is inspired by the law of gravity and interaction among masses. To improve the effectiveness of the GSA, the OGSA is derived based on the opposition-based learning concept for population initialization and generation jumping. To validate the results regarding the effectiveness of the presented OGSOC-SRP technique, a set of experiments was performed, and the results were determined using distinct measures such as the energy consumption, network lifetime, throughput, and end-to-end delay.

关键词： Wireless sensor networks Clustering Routing gravitational search algorithm Glowworm swarm optimization Metaheuristics

来源：评论

学校读者我要写书评

暂无评论

Deterministic and probabilistic occupancy detection with a novel heuristic optimization and Back-Propagation (BP) based algorithm

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022年第2期42卷 779-791页

作者： Fatema, Nuzhat Farkoush, Saeid Gholami Hasan, Mashhood Malik, H. Univ Sultan Zainal Abidin UniSZA Fac Business & Management Terengganu Malaysia Intelligent Prognost Private Ltd Delhi India Yeungnam Univ Elect Engn Dept Gyongsan Gyeongsangbuk D South Korea Jazan Univ Coll Appl Ind Technol Elect Power Engn Technol Jazan Saudi Arabia BEARS NUS Campus Singapore Singapore

In this paper, a novel hybrid approach for deterministic and probabilistic occupancy detection is proposed with a novel heuristic optimization and Back-Propagation (BP) based algorithms. Generally, PB based neural network (BPNN) suffers with the optimal value of weight, bias, trapping problem in local minima and sluggish convergence rate. In this paper, the GSA (gravitational search algorithm) is implemented as a new training technique for BPNN is order to enhance the performance of the BPNN algorithm by decreasing the problem of trapping in local minima, enhance the convergence rate and optimize the weight and bias value to reduce the overall error. The experimental results of BPNN with and without GSA are demonstrated and presented for fair comparison and adoptability. The demonstrated results show that BPNNGSA has outperformance for training and testing phase in form of enhancement of processing speed, convergence rate and avoiding the trapping problem of standard BPNN. The whole study is analyzed and demonstrated by using R language open access platform. The proposed approach is validated with different hidden-layer neurons for both experimental studies based on BPNN and BPNNGSA.

关键词： gravitational search algorithm back-propagation algorithm neural network machine learning optimization occupancy smart building

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：