127 research outputs found
Artificial Neural Networks for Stock Market Prediction: A Comprehensive Review
No full textThe forecasting of stock market is known to be a remarkable effort and a great deal of attention, as forecasting stock prices can effectively steer to desirable profits by making sound investment choices. It is a challenging job due to highly non-linear, blaring, and unpredictable data. Currently, a variety of useful methods have been developed to predict stock prices. This chapter provides a thorough analysis of 48 research papers proposing artificial neural networks-based stock price prediction methodologies. Here, the reported research is categorized on the basis of various prediction techniques. Moreover, the studies are evaluated based on databases used, performance assessment indicators, and prediction targets. The collective evidence suggests that stock market prediction involves numerous factors that need to be efficiently and precisely addressed
A Review of Metaheuristic Optimization Algorithms in Wireless Sensor Networks
No full textThe proliferation of wireless sensor network (WSNs) applications span different domains of life, including medicine, engineering, industry, agriculture, and military. A notable part of research pertaining to WSNs relates to metaheuristic algorithms, implemented to address difficulties in the deployment of these networks. Due to robust and cost effective optimization ability, these algorithms efficiently optimize sensor locations for maximum coverage and extended energy consumption. This chapter presents the definitions of metaheuristic intelligence, wireless sensor network, and their respective types. Also, a wide range of scientific research works that include improving the performance of wireless sensor networks in terms of deployment, localization, and energy using optimization algorithms. Finally, the evaluation criteria for deployment and localization in wireless sensor networks are introduced
Green and blue water accounting in the Limpopo and Nile Basins: Implications for food and agricultural policy
No full textGreen water, Blue water, Irrigation, Rainfed, Agriculture, technology, Investment, Impact, Climate change, Water resources,
Particle Swarm Optimization-Enhanced Twin Support Vector Regression for Wind Speed Forecasting
No full textAbstract
Wind energy is considered one of the renewable energy sources that minimize the cost of electricity production. This article proposes a hybrid approach based on particle swarm optimization (PSO) and twin support vector regression (TSVR) for forecasting wind speed (PSO-TSVR). To enhance the forecasting accuracy, TSVR was utilized to forecast the wind speed, and the optimal settings of TSVR parameters were optimized by PSO carefully. Moreover, to estimate the performance of the suggested approach, three wind speed benchmark data of OpenEI were used as a case study. The experimental results revealed that the optimized PSO-TSVR approach is able to forecast wind speed with an accuracy of 98.9%. Further, the PSO-TSVR approach has been compared with two well-known algorithms such as genetic algorithm with TSVR and the native TSVR using radial basis kernel function. The computational results proved that the proposed approach achieved better forecasting accuracy and outperformed the comparison algorithms.</jats:p
Machine Learning and Meta-heuristic Algorithms for Renewable Energy: A Systematic Review
No full textA picture of tariff protection across the World in 2004: MAcMap-HS6, Version 2
No full textMAcMap-HS6v2 is a comprehensive database providing detailed protection data at the 6 digit level of the harmonized system (HS6), i.e. more than 5000 products, for the year 2004. It includes ad valorem equivalents on MFN tariffs for 169 importing countries, as well as bilateral applied protection, together with preferential provisions for 220 partners. Specific and compound tariffs and tariff rate quotasdata are also provided, at the same level of detail. In this paper we present the methodology used for building this new database, paying attention to the consequences from such choices. We then provide evidence on the world applied protection in 2004. Finally we investigate variations in tariffs occurred between 2001 and 2004.Globalization, Markets, trade policies, tariffs, databases, Ad valorem equivalent,
Dynamic Candidate Solution Boosted Beluga Whale Optimization Algorithm for Biomedical Classification
No full textIn many fields, complicated issues can now be solved with the help of Artificial Intelligence (AI) and Machine Learning (ML). One of the more modern Metaheuristic (MH) algorithms used to tackle numerous issues in various fields is the Beluga Whale Optimization (BWO) method. However, BWO has a lack of diversity, which could lead to being trapped in local optimaand premature convergence. This study presents two stages for enhancing the fundamental BWO algorithm. The initial stage of BWO’s Opposition-Based Learning (OBL), also known as OBWO, helps to expedite the search process and enhance the learning methodology to choose a better generation of candidate solutions for the fundamental BWO. The second step, referred to as OBWOD, combines the Dynamic Candidate Solution (DCS) and OBWO based on the k-Nearest Neighbor (kNN) classifier to boost variety and improve the consistency of the selected solution by giving potential candidates a chance to solve the given problem with a high fitness value. A comparison study with present optimization algorithms for single-objective bound-constraint optimization problems was conducted to evaluate the performance of the OBWOD algorithm on issues from the 2022 IEEE Congress on Evolutionary Computation (CEC’22) benchmark test suite with a range of dimension sizes. The results of the statistical significance test confirmed that the proposed algorithm is competitive with the optimization algorithms. In addition, the OBWOD algorithm surpassed the performance of seven other algorithms with an overall classification accuracy of 85.17% for classifying 10 medical datasets with different dimension sizes according to the performance evaluation matrix
Squirrel search algorithm applied to effective estimation of solar PV model parameters: a real-world practice
No full textModel parameters estimation of solar photovoltaic (PV) cells/modules using real current–voltage (I–V) data is a critical task for the performance of PV systems. Therefore, there is a necessity to procure optimal parameters of PV models using proper optimization techniques. For this aim, squirrel search algorithm (SSA) as the recent and powerful tool is employed to accomplish the mentioned task in the single-diode model (SDM) and double-diode model (DDM) of a PV unit. Of course, better parameter values can be obtained by reducing the error between the experimental and model-based estimated data. Analyses are performed under two case studies. The former considers a standard dataset of R.T.C. France silicon solar cell, whereas the latter uses an experimental dataset of a polycrystalline CS6P-220P solar module. The I-V data of this PV module were acquired when it worked under 30 °C and solar radiance of 1000W/m2 at the Engineering Faculty Campus of Düzce University, Turkey. The results of the first case study are compared with those of other prevalent approaches, which demonstrate the superiority of SSA over its competing peers. Moreover, SSA is found to handle the model parameters definition of an industrial PV module located at the university campus. Thus, the new method offers a practical tool beneficial to boost the effectiveness of PV systems. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature
Optimum solution of power flow problem based on search and rescue algorithm
No full textAbstract In order to solve the optimal power flow (OPF) problem, a unique algorithm based on a search and rescue method is applied in this study. For the OPF problem under three objective functions, the SAR offers a straightforward and reliable solution. The three objective functions are used to minimize the fuel cost, power loss and voltage deviation as a single objective function. The OPF problem for benchmark test system, including the IEEE-14 bus, IEEE-30 bus, and IEEE-57 bus, are solved by the Search and Rescue algorithm (SAR) under specific objective functions that are determined by the operational and economic performance indices of the power system. To demonstrate the efficacy and possibilities of the SAR algorithm, SAR is contrasted with alternative optimization techniques such as harmony search algorithm, gradient method, adaptive genetic algorithm, biogeography-based optimization, Artificial bee colony, gravitational search algorithm, particle swarm optimization, Jaya algorithm, enhanced genetic algorithm, modified shuffle frog leaping algorithm, practical swarm optimizer, Moth flam optimizer, whale and moth flam optimizer, grey wolf optimizer, cheap optimization algorithm and differential evolution algorithm. The value of minimum power losses based on SAR technique is equal to 0.459733441487247 MW for IEEE-14 bus. The value of minimum total fuel cost based on SAR technique is equal to 8051.12225602148 /h for IEEE-30 bus. The value of minimum voltage deviation based on SAR technique is equal to 0.0978069572088536 for IEEE-30 bus. The value of minimum total fuel cost based on SAR technique is equal to 38017.7691758245 $/h for IEEE-57 bus. The acquired results for the OPF compared to all competitor algorithms in every case of fitness function demonstrate the superiority of the SAR method
Henry gas solubility optimization: A novel physics-based algorithm
No full textSeveral metaheuristic optimization algorithms have been developed to solve the real-world problems recently. This paper proposes a novel metaheuristic algorithm named Henry gas solubility optimization (HGSO), which mimics the behavior governed by Henry's law to solve challenging optimization problems. Henry's law is an essential gas law relating the amount of a given gas that is dissolved to a given type and volume of liquid at a fixed temperature. The HGSO algorithm imitates the huddling behavior of gas to balance exploitation and exploration in the search space and avoid local optima. The performance of HGSO is tested on 47 benchmark functions, CEC’17 test suite, and three real-world optimization problems. The results are compared with seven well-known algorithms; the particle swarm optimization (PSO), gravitational search algorithm (GSA), cuckoo search algorithm (CS), grey wolf optimizer (GWO), whale optimization algorithm (WOA), elephant herding algorithm (EHO) and simulated annealing (SA). Additionally, to assess the pairwise statistical performance of the competitive algorithms, a Wilcoxon rank sum test is conducted. The experimental results revealed that HGSO provides competitive and superior results compared to other algorithms when solving challenging optimization problems.Full Tex
- …
