检索结果-内蒙古大学图书馆

Feature Selection: Binary Harris Hawk Optimizer Based Biomedical Datasets

INTELIGENCIA ARTIFICIAL-IBEROAMERICAN JOURNAL OF ARTIFICIAL INTELLIGENCE 2022年第70期25卷 33-49页

作者： Ibrahim, Hadeel Tariq Mazher, Wamidh Jalil Jassim, Enas Mahmood Univ Thi Qar Coll Educ Women E Learning Unit Thi Qar Iraq Southern Tech Univ Al Shatra Tech Inst Elect Dept Basra Iraq Univ Diyala Coll Basic Educ Comp Sc Dept Diyala Iraq

Feature selection (FS) is an essential preprocessing step in utmost solutions for the high -dimensional problem to reduce the number of features by deleting irrelevant and redundant data that preserve a suitable grade of classification accuracy. Feature selection can be treated as an optimization problem. Heuristic optimization algorithms are hopeful approaches to solve feature selection problems because of their difficulty, especially in high-dimensional data. Binary Harris hawk optimization (BHHO) is one of the lately suggested metaheuristic algorithms that has been demonstrated to be used more efficiently in facing some optimization problems. Support vector machines (SVMs) are a vital technique that are employed competently to resolve classification issues. We modified the BHHO algorithm with SVM classifier to solve the feature selection issue. This study suggests BHHO-FS to fix the feature selection problem in biomedical datasets. We ran the proposed approach BHHO-FS on real biomedical datasets with 17 types of cancer for Iraqi patients in 2010-2012. The experimental results demonstrate the supremacy of the proposed BHHO-FS in terms of three performance metrics: feature selection accuracy, runtime and number of selected features compared to four other state-of-art algorithms: Fire Fly (FF) algorithm, Genetic algorithm (GA), grasshopper optimization algorithm (GOA) and Particle Swarm algorithm (PSO). Comparative experiments designate the importance of the proposed approach in comparison with the other four mentioned algorithms. The implementation of the proposed BHHO-FS approach on 17 datasets for different types of cancers reveals 99.967% average accuracy.

关键词： Feature selection Harris hawk optimizer Fire fly Genetic algorithm grasshopper optimization algorithm Particle swarm

来源：评论

学校读者我要写书评

暂无评论

A Maximum Power Point Tracking Method Based on a Modified grasshopper algorithm Combined with Incremental Conductance

引用

ENERGIES 2020年第17期13卷 4329页

作者： Wijaya, Bustani Hadi Subroto, Ramadhani Kurniawan Lian, Kuo Lung Hariyanto, Nanang Natl Taiwan Univ Sci & Technol Dept Elect Engn 43 Sec 4Keelung Rd Taipei 106 Taiwan Sch Elect Engn & Informat Inst Teknol Bandung Bandung 40116 Indonesia

The partial shading of photovoltaic (PV) modules due to clouds or blocking objects, such as buildings or tree leaves, is a common problem for photovoltaic systems. To address this, maximum power point tracking (MPPT) is implemented to find the global maximum power point (GMPP). In this paper, a new hybrid MPPT is proposed that combines a modified grasshopper optimization algorithm (GOA) with incremental conductance (IC). In the first stage, the proposed modified GOA is implemented to find a suitable tracking area where the GMPP is located. Then the system moves to the second stage by implementing IC to get the correct GMPP. IC is a fast-performing and reliable algorithm. By combining GOA and IC, the proposed method can find the GMPP accurately with a short tracking time. Various experimental results show that the proposed method yields the highest tracking efficiency and lowest tracking time compared to some of the state-of-the-art MPPT algorithms, such as particle swarm and modified firefly optimizations.

关键词： grasshopper optimization algorithm incremental conductance maximum power point tracking PV system

来源：评论

学校读者我要写书评

暂无评论

Federated Convolutional Neural Networks for Predictive Analysis of Traumatic Brain Injury: Advancements in Decentralized Health Monitoring

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第4期15卷 910-923页

作者： Sharma, Tripti Reddy, Desidi Narsimha Kaur, Chamandeep Godla, Sanjiv Rao Salini, R. Gopi, Adapa El-Ebiary, Yousef A. Baker Rungta Coll Engn & Technol Dept Comp Sci & Engn Bhilai Chhattisgarh India Soniks Consulting LLC Dallas TX USA Jazan Univ Dept Comp Sci Jazan Saudi Arabia Aditya Coll Engn & Technol Dept CSE Artificial Intelligence & Machine Learni Surampalem Andhra Pradesh India Panimalar Engn Coll Dept CSE Chennai Tamil Nadu India Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vaddeswaram Andhra Pradesh India UniSZA Univ Fac Informat & Comp Kuala Terengganu Malaysia

Traumatic Brain Injury (TBI) is a significant global health concern, often leading to long-term disabilities and cognitive impairments. Accurate and timely diagnosis of TBI is crucial for effective treatment and management. In this paper, we propose a novel federated convolutional neural network (FedCNN) framework for predictive analysis of TBI in decentralized health monitoring. The framework is implemented in Python, leveraging three diverse datasets: CQ500, RSNA, and CENTER-TBI, each containing annotated brain CT images associated with TBI. The methodology encompasses data preprocessing, feature extraction using gray level co-occurrence matrix (GLCM), feature selection employing the grasshopper optimization algorithm (GOA), and classification using FedCNN. Our approach achieves superior performance compared to existing methods such as DANN, RF and DT, and LSTM, with an accuracy of 99.2%, surpassing other approaches by 1.6%. The FedCNN framework offers decentralized privacy-preserving training across individual networks while sharing model parameters with a central server, ensuring data privacy and decentralization in health monitoring. Evaluation metrics including accuracy, precision, recall, and F1-score demonstrate the effectiveness of our approach in accurately classifying normal and abnormal brain CT images associated with TBI. The ROC analysis further validates the discriminative ability of the FedCNN framework, highlighting its potential as an advanced tool for TBI diagnosis. Our study contributes to the field of decentralized health monitoring by providing a reliable and efficient approach for TBI management, offering significant advancements in patient care and healthcare management. Future research could explore extending the FedCNN framework to incorporate additional modalities and datasets, as well as integrating advanced deep learning architectures and optimization algorithms to further improve performance and scalability in healthcare applications.

关键词： Traumatic brain injury federated learning convolutional neural network grasshopper optimization algorithm health monitoring

来源：评论

学校读者我要写书评

暂无评论

Research on IGOA-LSSVM based fault diagnosis of power transformers

引用

JOURNAL OF VIBROENGINEERING 2022年第7期24卷 1262-1274页

作者： Chen, Yunsheng Guangzhou Huali Sci & Technol Vocat Coll Coll Elect Power & Intelligent Mfg Guangzhou Peoples R China

Power transformer is an important part of power equipment, and its functionality affects the proper operation of the whole power network. In order to diagnose power transformer faults effectively, the authors propose a fault diagnosis strategy based on an improved locust optimization algorithm for least squares vector machines (IGOA-LSSVM). Firstly, it was required to address the problem that the diagnostic prediction accuracy of the least squares vector machine is reduced due to its parameters. So this paper introduces the locust optimization algorithm with simple algorithm structure and good performance for optimizing the parameters. And at the same time, the authors generate an improved locust optimization algorithm with self-learning factors, proportional weight coefficients and Levy flight strategy. Secondly, the improved locust optimization algorithm is used for optimizing the least squares vector machine parameters. Finally, in the simulation experiments, the results of the benchmark test function illustrate that the IGOA algorithm has better performance, and the test results of a fault samples diagnosis of the power transformer equipment illustrate that the IGOA-LSSVM has good prediction effect and improves the fault identification accuracy compared with ACO-LSSVM and PSO-LSSVM in five types of fault diagnosis.

关键词： power transformer fault prediction grasshopper optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Prepositioning and distributing relief items in humanitarian logistics with uncertain parameters

引用

SOCIO-ECONOMIC PLANNING SCIENCES 2021年 74卷 100933-100933页

作者： Abazari, Seyed Reza Aghsami, Amir Rabbani, Masoud Univ Tehran Coll Engn Sch Ind & Syst Engn Tehran Iran KN Toosi Univ Technol Sch Ind Engn Tehran Iran

Humans tackle natural disasters all over the world. Humanitarian supply chain plays an important role to mitigate damages occurred after a disaster. This research formulates a multi-objective Mixed-Integer Non-Linear programming (MINLP) with uncertain parameters considering Relief Centers (RC), Demand Points (DP) in affected areas, transportation methods to deliver Relief Items (RI) and different types of RIs namely, perishable and imperishable. In pre-disaster stage, location and number of RCs with their prepositioned inventory level are determined. After disaster strikes, based on a distribution plan the amount of RIs that should be transported to DPs and number of needed vehicles are determined. The objective functions minimize the total distance traveled by RIs, total costs (including RC establish cost, inventory cost, fixed cost for each vehicle type and acquisition cost for RIs), maximum traveling time between RCs and DPs and number of perished items respectively. The proposed model is solved by GAMS software for small size test problems and grasshopper optimization algorithm (GOA) as a meta-heuristic approach for large size problems. Numerical and computational results are provided to prove the efficiency and feasibility of the presented model. Finally, the developed model is implemented to Iran?s flood in 2019 as a case study.

关键词： Humanitarian supply chain Disaster relief logistics Transportation and distribution planning optimization grasshopper optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Estimation of pile settlement socketed to rock applying hybrid ALO-ANFIS and GOA-ANFIS approaches

引用

淡江理工学刊 2022年第6期25卷 1131-1144页

作者： Dai Yu

Pile settlement (SP) socketed to rock has received substantial attention. Despite introducing some design methods of SP prediction, considering the novel and practical predicting model with satisfactory performance is pivotal. The primary target of the present paper is to find out the applicability of applying two hybrid adaptive neuro-fuzzy inference system (ANFIS) models in predicting the pile settlement (SP) socketed to rock in the Klang Valley Mass Rapid Transit (KVMRT) project constructed in Kuala Lumpur, Malaysia. Two constructive variables of the ANFIS method are tuned using two optimization algorithm named antlion optimization (ALO) and grasshopper optimization algorithm (GOA). Five parameters, including the ratio of length in soil layer to length in the rock layer, total length to diameter, uniaxial compressive strength, standard penetration test, and ultimate bearing capacity, were considered as input variables. The results specify remarkable potential in both the training and testing phases for both hybrid ANFIS models. Comparing the measured settlement with those predicted by ALO-ANFIS and GOA-ANFIS methods demonstrated that the developed models have R^2 larger than 0.9077 for training data and bigger than 0.9387 in the testing phase. ALO-ANFIS has better performance than GOA-ANFIS in all four statistical performance evaluators. Both of the hybrid ANFIS models have a high capability for predicting SP. However, ALO-ANFIS represents the more prominent ability to determine the optimal value of the ANFIS parameters than other ones.

关键词： Pile socketed into rock Pile Settlement Prediction Adaptive Neuro-Fuzzy Inference System Ant lion optimization grasshopper optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative performance assessment of several Fractional Order - Two Degree Freedom controllers tuned using GOA for LFC

引用

Procedia Computer Science 2020年 167卷 2022-2032页

作者： Debasis Tripathy N.B. Dev Choudhury B.K. Sahu Electrical Engineering Department National Institute of Techonology Silchar Silchar-788010 India Electrical Engineering Department Siksha ‘O’ Anusandhan University Bhubaneswar-751030 India

The work puts an earliest effort to compare the performances of different fractional order based feed-forward type two degree of freedom (2DOF-FO) controllers optimized with grasshopper optimization algorithm (GOA) for the study of load frequency control in interconnected system. As fractional order controllers (FOC) are gaining attention of researchers over integer order controller (IOC) in recent era, so the authors’ main motive in this article is to highlight a comparative performance analysis between three different structures of feed-forward type 2DOF-FOC namely 2DOF-FO-proportional-integral-derivative (2DOF-FOPID), 2DOF-FO-integral-derivative (2DOF-FOID) and 2DOF-FOPI. These controllers are optimally designed through GOA technique. The 2DOF-FOPID controller ensured as the best one over other two controllers in GOA framework even in the presence of nonlinearities for a two area and three areas thermal system. Also, the robustness of the controllers is verified for two area system by applying different physical conditions like a random pattern of step load variations, changing the loading condition in area-1 and the system parameters within a range of ± 20%.

关键词： Fractional Order Controller grasshopper optimization algorithm Load Frequency Control Nonlinearities Two Degree of Freedom

来源：评论

学校读者我要写书评

暂无评论

Energy and Cost-Aware Workflow Scheduling in Cloud Computing Data Centers Using a Multi-objective optimization algorithm

引用

JOURNAL OF NETWORK AND SYSTEMS MANAGEMENT 2021年第3期29卷 31-31页

作者： Mohammadzadeh, Ali Masdari, Mohammad Gharehchopogh, Farhad Soleimanian Islamic Azad Univ Dept Comp Engn Shahindezh Branch Shahindezh Iran Islamic Azad Univ Dept Comp Engn Urmia Branch Orumiyeh Iran

A multi-objective optimization approach is suggested here for scientific workflow task-scheduling problems in cloud computing. More frequently, scientific workflow involves a large number of tasks. It requires more resources to perform all these tasks. Such a large amount of computing power can be supported only by cloud infrastructure. To implement complex science applications, more computing energy is expended, so the use of cloud virtual machines in an energy-saving way is essential. However, even today, it is a difficult challenge to conduct a scientific workflow in an energy-aware cloud platform. The hardness of this problem increases even more with several contradictory goals. Most of the existing research does not consider the essential characteristic of cloud and significant issues, such as energy variation and throughput besides makespan and cost. Therefore, a hybridization of the Antlion optimization (ALO) algorithm with the grasshopper optimization algorithm (GOA) was proposed and used multi-objectively to solve the scheduling problems. The novelty of the proposed algorithm was enhancing the search performance by making algorithms greedy and using random numbers according to Chaos Theory on the green cloud environment. The purpose was to minimize the makespan, cost of performing tasks, energy consumption, and increase throughput. WorkflowSim simulator was used for implementation, and the results were compared with the SPEA2 algorithm. Experimental results indicate that based on these metrics, a proposed multi-objective optimization algorithm is better than other similar methods.

关键词： Ant lion optimization grasshopper optimization algorithm Meta-heuristic Workflow scheduling

来源：评论

学校读者我要写书评

暂无评论

Power quality disturbances recognition using adaptive chirp mode pursuit and grasshopper optimized support vector machines

引用

MEASUREMENT 2021年 168卷 108461-108461页

作者： Motlagh, Shayan Z. T. Foroud, Asghar Akbari Semnan Univ Elect & Comp Engn Dept Semnan Iran

This paper presents a new method for identifying different types of power quality disturbances (PQDs). In this article, adaptive chirp mode pursuit (ACMP) is used to extract useful features and the greedy algorithm that uses the similar principles of the matching pursuit method is adopted in the ACMP. Besides, the ACMP takes advantage of the sparse matrices, which reduce the computational cost. The infinite feature selection as the filter-based algorithm is applied for the elimination of improper features. Also, the grasshopper optimization algorithm (GOA) is used to optimize the parameters of the SVM as the classifier. The obtained results of the simulations and real disturbances show the high accuracy and speed of the proposed algorithm, which makes it possible to use it in power quality measuring and analysis devices. Also, the proposed method has noise rejection capability, which is another advantage that justifies its use in measuring and analyzing PQDs.

关键词： Power quality disturbances recognition adaptive chirp mode pursuit (ACMP) support vector machine (SVM) grasshopper optimization algorithm Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Method for Assessing Financial Market Price Behavior: An Analysis of the Shanghai Stock Exchange Index

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第5期15卷 220-231页

作者： Huang, Zhi Li, Jiansheng Nanchang Hangkong Univ Fac Econ & Management Coll Sci & Technol Jiujiang 332020 Jiangxi Peoples R China Dongbei Univ Finance & Econ Sch Business Adm Dalian 116025 Liaoning Peoples R China

A stock market is a venue where the shares of publicly traded companies are available for purchase and sale by individuals. The financial markets exert a substantial influence on various domains, including technology, employment, and business. Given the substantial rewards and risks associated with stock trading, investors are exceedingly concerned with the precision of future stock value forecasts. They modify their investment strategies in an effort to achieve even greater returns. Accurate stock price forecasting can be challenging in the securities industry due to the complex nature of the problem and the requirement for a comprehensive understanding of various interconnected factors. The stock market is influenced by a variety of factors, including politics, society, and economics. A multitude of interrelated factors contribute to these behaviors, and stock price fluctuations are capricious. In order to tackle a range of these difficulties, the present investigation proposes an innovative framework that integrates a grasshopper optimization method with the gated recurrent unit model, a machine-learning approach. The research used data from the Shang Hai Stock Exchange Index for the period of 2015-2023. The proposed hybrid model was also tested on the 2013-2022 S&P 500 and Nikkei 225. The proposed model demonstrated optimal performance, exhibiting a minimal error rate and exceptional effectiveness. The study's findings demonstrate that the proposed model is more suitable for the volatile stock market and surpasses other existing strategies in terms of predictive accuracy.

关键词： Financial market shanghai stock exchange price gated recurrent unit grasshopper optimization 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：