Search

This paper presents a modified metaheuristic algorithm named the modified Firefly algorithm. Any metaheuristic algorithm will have exploration and exploitation steps, and the goal of modification is to maintain a balance between them. The improvement relies on movement equations, alterations to the algorithm's structure by introducing a single loop, and a selection of movement equations at random. Two movement equations are included in the improved method and are randomly selected. This guarantees both regionally and globally focused solution-finding. This prevents the algorithm from getting stuck at a local minimum. Comparing the modified version to the original Firefly method, just one for loop is used, reducing the algorithm's complexity. The algorithm's performance is evaluated with 35 traditional benchmark test functions and 10 CEC2019 test functions. According to the findings, the suggested method performed optimally in 24 traditional benchmark test functions and best in the six remaining benchmark test functions. The improved algorithm produced the best outcomes in seven of the 10 CEC2019 test functions. In contrast, the Firefly algorithm produced optimal results in 18 classical benchmark test functions and the best results in 6 CEC2019 test functions. The proposed algorithm is compared with other variants of the Firefly algorithm for common test functions in the literature. The results show that the proposed algorithm outperforms other variants in most test functions. [ABSTRACT FROM AUTHOR]

In this paper, two optimized autofocusing metasurfaces (AFMs) with different desired focal distances are designed by using particle swarm optimization (PSO) algorithm. Based on the finite element simulation software COMSOL Multiphysics, the performance of ultrasound transducer (UT) with AFM at different design parameters in Airy distributions (r 0 , ω) and the bottom thickness (d) of AFM are simulated and analyzed. Based on the simulation data, the artificial neural network model is trained to describe the complex relationship between the design parameters of AFM and the performance parameters of UT. Then, the multiobjective optimization function for AFM is determined according to the desired performance parameters of UT, including focal position, lateral resolution, longitudinal resolution and absolute sound pressure. In order to obtain AFMs with the desired performance, PSO algorithm is adopted to optimize the design parameters of AFM according to the multiobjective optimization function, and two AFMs are optimized and fabricated. The experimental results well agree with the simulation and optimization results, and the optimized AFMs can achieve the desired performance. The fabricated AFM can be easily integrated with UT, which has great potential applications in wave field modulation underwater, acoustic tweezers, biomedical imaging, industrial nondestructive testing and neural regulation. [ABSTRACT FROM AUTHOR]

Nowadays, liver cancers are well-known cancers attacking the human body. The larger segment of liver carcinomas is highly affected by alcohol-associated hepatitis as well as cirrhosis circumstances. In order to increase the survival rate of humans, premature and early diagnosis of liver cancer is very vital. Currently, discriminating the tumor and liver segments from medical imaging with the help of entirely automated computer-aided software is a highly difficult task, because the liver tumor may differ from one human being to another human being. Thus, this paper endeavors to present a new liver tumor segmentation and classification approach by incorporating an optimization-enabled deep learning model. Here, the adopted model comprises four stages, pre-processing, liver segmentation, liver tumor detection, and classification. To begin with, the collected images are given to the pre-processing stage using the African vulture's optimization-based adaptive histogram equalization (AVOAHE). The integration of the African vulture's optimization (AVO) concept in adaptive histogram equalization is named AVOAHE. After the image pre-processing phase, the liver region is segmented by utilizing kernel-based fuzzy C-means clustering. Then, the detection of liver tumor is performed using the Swin-Unet. Finally, tumor detection is done by utilizing the deep convolutional neural network (Deep CNN). Moreover, a hybrid optimization approach, called double exponential smoothing (DES)-marine predator algorithm (MPA), is developed by combining DES and MPA, which is used to train Deep CNN and serves as an enhancement. Finally, the experimental analysis has shown that the adopted technique has achieved better results in terms of accuracy, specificity, sensitivity, and precision with values of 0.957, 0.969, 0.941 and 0.915, respectively. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to optimize the thinning of an elliptical cylindrical array (ECA) composed of uniformly stimulated, isotropic antennas with the objective of achieving a directed beam characterized by a significantly reduced relative Sidelobe Level (SLL). The optimization process employs the Novel Particle Swarm Optimization (NPSO) method, which offers a fresh perspective on addressing electromagnetic optimization challenges by its ability to effectively explore solution spaces. By employing the NPSO algorithm, which emulates the collective behavior of swarming particles to search for optimal solutions, this study addresses complex optimization challenges inherent in antenna array design. This study focuses on identifying the optimal combination of ON–OFF components (use the minimum number of ON antenna elements) within the antenna array to produce a radiation pattern exhibiting the greatest decrease in SLL. Additionally, the First Null Beam Width (FNBW) is targeted for optimization without predefined values. The optimization approach also considers the effect of thinned array element spacing on the overall performance metrics. Out of total 36 elements, only 15 elements are switched ON and the remaining of the elements are OFF, so the total reduction or thinning of ECAA is 41.66%. Simulation results demonstrate that the proposed methodology enables a simultaneous reduction of more than half of the antenna array elements while achieving superior SLL minimization. This significant reduction in antenna elements not only contributes to simplifying the array design, but also enhances the array’s beamforming capabilities. [ABSTRACT FROM AUTHOR]

The welding community faces a challenging problem in choosing the best welding methods since they are multi-input processes. Modern manufacturing industries have requirements to get fast and optimum process parameters to utilize complete resources in an optimum way. This work attempts to improve the performance of submerged arc welding (SAW), friction welding (FW), and gas tungsten arc welding (GTAW) processes by optimizing their parameters. The newly developed Rao algorithms and their modified versions known as quasi-oppositional Rao (QO Rao), self-adaptive multi-population elite Rao (SAMPE Rao), and improved Rao (I-Rao) are used. This paper contains four multi-objective optimization case studies of SAW, FW, and GTAW processes. A weighted approach is employed to tackle the multi-objective optimization problems effectively. The outcomes achieved using the Rao, QO Rao, SAMPE Rao, and I-Rao algorithms are compared with those obtained by the established optimization algorithms such as accelerated cuckoo optimization algorithm (ACCOA), cuckoo optimization algorithm (COA), plant propagation algorithm (PPA), teaching–learning-based optimization (TLBO) algorithm, Jaya algorithm, quasi-oppositional Jaya (QO Jaya) algorithm, genetic algorithm (GA), particle swarm optimization (PSO) algorithm, and heat transfer search (HTS) algorithm. The effectiveness of the Rao algorithms and their modified versions has been clearly demonstrated as these algorithms have provided superior solutions while requiring fewer generations to achieve them. [ABSTRACT FROM AUTHOR]

Tuberculosis (TB) stands as the leading cause of death and a significant threat to humanity in the contemporary world. Early detection of TB is crucial for precise identification and treatment, and Chest X-Rays (CXR) serve as a valuable tool in this regard. Computer-Aided Diagnosis (CAD) systems play a vital role in easing the classification process of active and latent TB. This paper uses an approach called the Double Attention Res-U-Net-based Deep Neural Network (DARUNDNN) to enhance TB detection in the lungs. The detection process involves pre-processing, noise removal, image level balancing, the application of the DARUNDNN model and using the Whale Optimization Algorithm (WOA) for improved accuracy. Experimental validation using Montgomery Country (MC), Shenzhen China (SC), and NIH CXR Datasets compares the results with U-Net, AlexNet, GoogleNet, and convolutional neural network (CNN) models. The findings, particularly from the SC dataset, demonstrate the efficiency of the proposed DARUNDNN model with an accuracy of 98.6%, specificity of 96.24%, and sensitivity of 97.66%, outperforming benchmarked deep learning models. Additionally, validation with the MC dataset reveals an excellent accuracy of 98%, specificity of 97.56%, and sensitivity of 98.52%. [ABSTRACT FROM AUTHOR]

Electric Vehicles (EVs) are powered by a battery mounted in the vehicle, which powers the motor and drives the wheels. Most commercial EVs can be charged by plugging them into a charging station. Such conductive recharging has various drawbacks, including physical plugging of the cable, safety concerns, and charging time. Manually charging EVs might be dangerous due to the chance of an electric spark or disaster. Advances in Wireless Power Transfer (WPT) demonstrate the capacity to transfer significant amounts of electricity over short and medium-range distances. The ultimate purpose of this paper is to improve the efficacy of electric car wireless charging systems. Here, a hybrid optimization-based Artificial Neural Network (ANN) model is applied to improve the efficacy of the WPT model in EVs. To optimize the weights of the ANN classifier, a hybrid approach termed as Grasshopper-Assisted Elephant Herd Optimization (GA-EHO) method is proposed. The GA-EHO is derived through the hybridization of Elephant Herd Optimization (EHO) Algorithm and the Grasshopper Optimization Algorithm (GOA) techniques. Finally, the experimental study reveals that at 70% learning rate, the proposed ANN system achieves a minimal MSE value of 0.0528, which is lower than other current classifiers, such as SVM, LSTM, and CNN. [ABSTRACT FROM AUTHOR]

Sine cosine algorithm (SCA) is a recently developed meta-heuristic method based on the characteristics of sine and cosine functions. However, SCA algorithm may suffer premature convergence in solving complex optimization problems. To mitigate this limitation, a modified SCA (MSCA) is developed to achieve an effective balance between exploration and exploitation. Specifically, the conversion parameter can be configured adaptively by using the individual fitness information in the evolution process to guide the individual search behavior. After that, an inertia weight is embedded in the position updating equation to further improve the search accuracy and accelerate the convergence speed. The performance of MSCA algorithm is investigated on 13 benchmark functions and the chaotic time series prediction problem. Experimental results demonstrate that MSCA algorithm is more effective than the other optimization methods. [ABSTRACT FROM AUTHOR]

Blockchain mining pools assist in reducing computational load on individual miner nodes via distributing mining tasks. This distribution must be done in a non-redundant manner, so that each miner is able to calculate block hashes with optimum efficiency. To perform this task, a wide variety of mining optimization methods are proposed by researchers, and most of them distribute mining tasks via statistical request processing models. These models segregate mining requests into non-redundant sets, each of which will be processed by individual miners. But this division of requests follows a static procedure, and does not consider miner specific parameters for set creation, due to which overall efficiency of the underlying model is limited, which reduces its mining performance under real-time scenarios. To overcome this issue, an Incremental & Continuous Q-Learning Framework for generation of miner-specific task groups is proposed in this text. The model initially uses a Genetic Algorithm (GA) method to improve individual miner performance, and then applies Q-Learning to individual mining requests. The Reason for selecting GA model is that it assists in maintaining better speed-to-power (S2P) ratio by optimization of miner resources that are utilized during computations. While, the reason for selecting Q-Learning Model is that it is able to continuously identify miners performance, and create performance-based mining pools at a per-miner level. Due to application of Q-Learning, the model is able to assign capability specific mining tasks to individual miner nodes. Because of this capability-driven approach, the model is able to maximize efficiency of mining, while maintaining its QoS performance. The model was tested on different consensus methods including Practical Byzantine Fault Tolerance Algorithm (PBFT), Proof-of-Work (PoW), Proof-of-Stake (PoS), and Delegated PoS (DPoS), and its performance was evaluated in terms of mining delay, miner efficiency, number of redundant calculations per miner, and energy efficiency for mining nodes. It was observed that the proposed GA based Q-Learning Model was able to reduce mining delay by 4.9%, improve miners efficiency by 7.4%, reduce number of redundant computations by 3.5%, and reduce energy required for mining by 7.1% when compared with various state-of-the-art mining optimization techniques. Similar performance improvement was observed when the model was applied on different blockchain deployments, thus indicating better scalability and deployment capability for multiple application scenarios. [ABSTRACT FROM AUTHOR]

The gait cycle of 25-degree of freedom (DOF) humanoid robot, namely NAO robot, consists of single support phase (SSP) and double support phase (DSP). Both dynamic and stability analyses are carried out for this robot to determine its power consumption and dynamic stability margin, respectively. Constrained single-objective optimization problems are formulated for the SSP and DSP separately and solved using particle swarm optimization (PSO) and genetic algorithms (GA). A performance index, other than the fitness function, consisting of constraint values and maximum swing height, is also considered to compare PSO and GA-obtained optimal solutions. PSO is able to find the trajectories that offer higher swing height for nearly similar power consumption during SSP. A performance assessment of each algorithm based on the best fitness values in each generation across several runs is also carried out. These values are compared using the Wilcoxon rank-sum test, and PSO is found to be statistically better than GA. The optimal solutions from the simulations are tested using the Webots simulator to validate their efficacy on stability. Moreover, an investigation of the influence of gait parameters on power consumption during SSP and DSP reveals that the humanoid robot with a higher hip height, lower swing height, and slow pace consumes less power. The methodology developed in this is generic and can be easily extended to other robots. [ABSTRACT FROM AUTHOR]

Vibration suppression of a simply supported beam under moving loads is investigated by employing a nonlinear energy sink (NES), which is an essential nonlinear (cubic) oscillator with a vanishing linear stiffness. Dynamic equations of the beam-NES coupled system are established and Galerkin method is applied to discretize the equations. By focusing on an energy dissipation index, an optimization procedure is employed and the optimal parameters of the NES are found. The results demonstrate that beam responses with a NES are reduced significantly compared to the case without NES. In particular, the NES can irreversibly transfer and dissipate vibration energy in a wide frequency range, which thus performs better than the classical linear tuned mass damper (TMD) through a further comparison study. [ABSTRACT FROM AUTHOR]