optimization techniques
Recently Published Documents


TOTAL DOCUMENTS

5487
(FIVE YEARS 1754)

H-INDEX

75
(FIVE YEARS 14)

2022 ◽  
Vol 20 (3) ◽  
pp. 386-394
Author(s):  
Adelicio Maximiano Sobrinho ◽  
Jose Roberto Camacho ◽  
Rafael Lima de Carvalho ◽  
Sergio Manuel Rivera Sanhueza ◽  
Stefani Carolline Leal de Freitas

Author(s):  
Raveendra Gudodagi ◽  
Rayapur Venkata Siva Reddy ◽  
Mohammed Riyaz Ahmed

Owing to the substantial volume of human genome sequence data files (from 30-200 GB exposed) Genomic data compression has received considerable traction and storage costs are one of the major problems faced by genomics laboratories. This involves a modern technology of data compression that reduces not only the storage but also the reliability of the operation. There were few attempts to solve this problem independently of both hardware and software. A systematic analysis of associations between genes provides techniques for the recognition of operative connections among genes and their respective yields, as well as understandings into essential biological events that are most important for knowing health and disease phenotypes. This research proposes a reliable and efficient deep learning system for learning embedded projections to combine gene interactions and gene expression in prediction comparison of deep embeddings to strong baselines. In this paper we preform data processing operations and predict gene function, along with gene ontology reconstruction and predict the gene interaction. The three major steps of genomic data compression are extraction of data, storage of data, and retrieval of the data. Hence, we propose a deep learning based on computational optimization techniques which will be efficient in all the three stages of data compression.


Author(s):  
Mahmoud Abbas El-Dabah ◽  
Ragab Abdelaziz El-Sehiemy ◽  
Mohamed Ahmed Ebrahim ◽  
Zuhair Alaas ◽  
Mohamed Mostafa Ramadan

This paper proposes the application of a novel metaphor-free population optimization based on the mathematics of the Runge Kutta method (RUN) for parameter extraction of a double-diode model of the unknown solar cell and photovoltaic (PV) module parameters. The RUN optimizer is employed to determine the seven unknown parameters of the two-diode model. Fitting the experimental data is the main objective of the extracted unknown parameters to develop a generic PV model. Consequently, the root means squared error (RMSE) between the measured and estimated data is considered as the primary objective function. The suggested objective function achieves the closeness degree between the estimated and experimental data. For getting the generic model, applications of the proposed RUN are carried out on two different commercial PV cells. To assess the proposed algorithm, a comprehensive comparison study is employed and compared with several well-matured optimization algorithms reported in the literature. Numerical simulations prove the high precision and fast response of the proposed RUN algorithm for solving multiple PV models. Added to that, the RUN can be considered as a good alternative optimization method for solving power systems optimization problems.


Author(s):  
Ahmad AL Smadi ◽  
Atif Mehmood ◽  
Ahed Abugabah ◽  
Eiad Almekhlafi ◽  
Ahmad Mohammad Al-smadi

<p>In computer vision, image classification is one of the potential image processing tasks. Nowadays, fish classification is a wide considered issue within the areas of machine learning and image segmentation. Moreover, it has been extended to a variety of domains, such as marketing strategies. This paper presents an effective fish classification method based on convolutional neural networks (CNNs). The experiments were conducted on the new dataset of Bangladesh’s indigenous fish species with three kinds of splitting: 80-20%, 75-25%, and 70-30%. We provide a comprehensive comparison of several popular optimizers of CNN. In total, we perform a comparative analysis of 5 different state-of-the-art gradient descent-based optimizers, namely adaptive delta (AdaDelta), stochastic gradient descent (SGD), adaptive momentum (Adam), adaptive max pooling (Adamax), Root mean square propagation (Rmsprop), for CNN. Overall, the obtained experimental results show that Rmsprop, Adam, Adamax performed well compared to the other optimization techniques used, while AdaDelta and SGD performed the worst. Furthermore, the experimental results demonstrated that Adam optimizer attained the best results in performance measures for 70-30% and 80-20% splitting experiments, while the Rmsprop optimizer attained the best results in terms of performance measures of 70-25% splitting experiments. Finally, the proposed model is then compared with state-of-the-art deep CNNs models. Therefore, the proposed model attained the best accuracy of 98.46% in enhancing the CNN ability in classification, among others.</p>


Author(s):  
Prince Nathan S

Abstract: Travelling Salesmen problem is a very popular problem in the world of computer programming. It deals with the optimization of algorithms and an ever changing scenario as it gets more and more complex as the number of variables goes on increasing. The solutions which exist for this problem are optimal for a small and definite number of cases. One cannot take into consideration of the various factors which are included when this specific problem is tried to be solved for the real world where things change continuously. There is a need to adapt to these changes and find optimized solutions as the application goes on. The ability to adapt to any kind of data, whether static or ever-changing, understand and solve it is a quality that is shown by Machine Learning algorithms. As advances in Machine Learning take place, there has been quite a good amount of research for how to solve NP-hard problems using Machine Learning. This reportis a survey to understand what types of machine algorithms can be used to solve with TSP. Different types of approaches like Ant Colony Optimization and Q-learning are explored and compared. Ant Colony Optimization uses the concept of ants following pheromone levels which lets them know where the most amount of food is. This is widely used for TSP problems where the path is with the most pheromone is chosen. Q-Learning is supposed to use the concept of awarding an agent when taking the right action for a state it is in and compounding those specific rewards. This is very much based on the exploiting concept where the agent keeps on learning onits own to maximize its own reward. This can be used for TSP where an agentwill be rewarded for having a short path and will be rewarded more if the path chosen is the shortest. Keywords: LINEAR REGRESSION, LASSO REGRESSION, RIDGE REGRESSION, DECISION TREE REGRESSOR, MACHINE LEARNING, HYPERPARAMETER TUNING, DATA ANALYSIS


2022 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Leila Hashemi ◽  
Armin Mahmoodi ◽  
Milad Jasemi ◽  
Richard C. Millar ◽  
Jeremy Laliberté

PurposeIn the present research, location and routing problems, as well as the supply chain, which includes manufacturers, distributor candidate sites and retailers, are explored. The goal of addressing the issue is to reduce delivery times and system costs for retailers so that routing and distributor location may be determined.Design/methodology/approachBy adding certain unique criteria and limits, the issue becomes more realistic. Customers expect simultaneous deliveries and pickups, and retail service start times have soft and hard time windows. Transportation expenses, noncompliance with the soft time window, distributor construction, vehicle purchase or leasing, and manufacturing costs are all part of the system costs. The problem's conceptual model is developed and modeled first, and then General Algebraic Modeling System software (GAMS) and Multiple Objective Particle Swarm Optimization (MOPSO) and non-dominated sorting genetic algorithm II (NSGAII) algorithms are used to solve it in small dimensions.FindingsAccording to the mathematical model's solution, the average error of the two suggested methods, in contrast to the exact answer, is less than 0.7%. In addition, the performance of algorithms in terms of deviation from the GAMS exact solution is pretty satisfactory, with a divergence of 0.4% for the biggest problem (N = 100). As a result, NSGAII is shown to be superior to MOSPSO.Research limitations/implicationsSince this paper deals with two bi-objective models, the priorities of decision-makers in selecting the best solution were not taken into account, and each of the objective functions was given an equal weight based on the weighting procedures. The model has not been compared or studied in both robust and deterministic modes. This is because, with the exception of the variable that indicates traffic mode uncertainty, all variables are deterministic, and the uncertainty character of demand in each level of the supply chain is ignored.Practical implicationsThe suggested model's conclusions are useful for any group of decision-makers concerned with optimizing production patterns at any level. The employment of a diverse fleet of delivery vehicles, as well as the use of stochastic optimization techniques to define the time windows, demonstrates how successful distribution networks are in lowering operational costs.Originality/valueAccording to a multi-objective model in a three-echelon supply chain, this research fills in the gaps in the link between routing and location choices in a realistic manner, taking into account the actual restrictions of a distribution network. The model may reduce the uncertainty in vehicle performance while choosing a refueling strategy or dealing with diverse traffic scenarios, bringing it closer to certainty. In addition, two modified MOPSO and NSGA-II algorithms are presented for solving the model, with the results compared to the exact GAMS approach for medium- and small-sized problems.


2022 ◽  
Vol 9 ◽  
Author(s):  
Zhengxun Guo ◽  
Bo Yang ◽  
Yiming Han ◽  
Tingyi He ◽  
Peng He ◽  
...  

Phase-locked loop (PLL) is a fundamental and crucial component of a photovoltaic (PV) connected inverter, which plays a significant role in high-quality grid connection by fast and precise phase detection and lock. Several novel critical structure improvements and proportional-integral (PI) parameter optimization techniques of PLL were proposed to reduce shock current and promote the quality of grid connection at present. However, the present techniques ignored the differential element of PLL and did not acquire ideal results. Thus, this paper adopts Aquila optimizer algorithm to regulate the proportional-integral-differential (PID) parameters of PLL for smoothing power fluctuation and improving grid connection quality. Three regulation strategies (i.e., PLL regulation, global regulation, and step regulation) are carefully designed to systematically and comprehensively evaluate the performance of the proposed method based on a simulation model in MATLAB/Simulink, namely, “250-kW Grid-Connected PV Array”. Simulation results indicate that PLL regulation strategy can effectively decrease power fluctuation and overshoot with a short response time, low complexity, and time cost. Particularly, the Error(P) and the maximum deviation of output power under optimal parameters obtained by PLL strategy are decreased by 418 W and 12.5 kW compared with those under initial parameters, respectively.


2022 ◽  
Vol 8 (1) ◽  
pp. 12
Author(s):  
Jürgen Hofmann ◽  
Alexander Flisch ◽  
Robert Zboray

This article describes the implementation of an efficient and fast in-house computed tomography (CT) reconstruction framework. The implementation principles of this cone-beam CT reconstruction tool chain are described here. The article mainly covers the core part of CT reconstruction, the filtered backprojection and its speed up on GPU hardware. Methods and implementations of tools for artifact reduction such as ring artifacts, beam hardening, algorithms for the center of rotation determination and tilted rotation axis correction are presented. The framework allows the reconstruction of CT images of arbitrary data size. Strategies on data splitting and GPU kernel optimization techniques applied for the backprojection process are illustrated by a few examples.


2022 ◽  
Author(s):  
Marius Møller Rokstad ◽  
Karel Antonie van Laarhoven

Abstract. Drinking water distribution networks form an essential part of modern-day critical infrastructure. Sectorizing a network into district metered areas is a key technique for pressure management and water loss reduction. Sectorizing an existing network from scratch is, however, an exceedingly complex design task that designs in a well-studied general mathematical problem. Numerical optimization techniques such as evolutionary algorithms can be used to search for near-optimal solutions to such problems, but doing so within a reasonable timeframe remains an ongoing challenge. In this work, we introduce two heuristic tricks that use information of the network structure and information of the operational requirements of the drinking water distribution network to modify the basic evolutionary algorithm used to solve the general problem. These techniques not only reduce the time required to find good solutions, but also ensure that these solutions better match the requirements of drinking water practice. Both techniques were demonstrated by applying them in the sectorization of the actual distribution network of a large city.


Sign in / Sign up

Export Citation Format

Share Document