Narrow Results

We present a solution of the multiprocessor scheduling problem based on applying a relatively new metaheuristic called Generalized Extremal Optimization (GEO). GEO is inspired by a simple coevolutionary model known as Bak-Sneppen model. The model assumes existing of an ecosystem consisting of N species. Evolution in this model is driven by a process in which the weakest species in the ecosystem, together with its nearest neighbors is always forced to mutate. This process shows characteristic of a phenomenon called a punctuated equilibrium which is observed in evolutionary biology. We interpret the multiprocessor scheduling problem in terms of the Bak-Sneppen model and apply the GEO algorithm to solve the problem. We show that the proposed optimization technique is simple and yet outperforms both genetic algorithm (GA)-based and particle swarm optimization (PSO) algorithm-based approaches to the multiprocessor scheduling problem.

It is very important to accurately predict the population pattern in the framework of spatial planning in the township development track. In this paper, the basic principle and application field of population forecasting method of urban spatial planning are deeply studied, and the applicability of BP neural network method of genetic evolution to predict population size is described. The study initially used genetic algorithms to refine the initial weights and structure of BP neural networks to improve their proficiency and generalization ability in the interpretation of demographic data. The empirical results show that the method produces superior predictive performance on multiple township demographic data sets, especially when trying to cope with complex population dynamics. In addition, when benchmarked against traditional forecasting models, the technology showed significant enhancements in the accuracy, stability, and adaptability of predictive models. These results suggest that combining GA-driven evolution with BP neural networks provides a more robust and precise tool for population prediction.

In this study, by performing the experimental research, the surface roughness, cutting force and vibration were modeled. The Genetic Algorithms (GAs) were applied to determine the optimal values of external cylindrical grinding conditions to achieve the minimum value of surface roughness and the maximum value of the material removal rate. The optimum values of surface roughness and material removal rate are 0.490 $\mu$m and 3.974 mm²/s, respectively, that were obtained at a feed rate of 0.3 m/min, at a workpiece speed of 164.82 rpm, at a cutting depth of 0.015 mm, and a workpiece Rockwell hardness of 56.32 HRC. The optimal values were successfully verified by experimental results with very promising results.

Today, with real-life problems, modeling is a primary step in organizing, analyzing and optimizing them. Queueing theory is a particular approach used to model this category of issues. Space constraints, feedback, service dependency, etc. are often inseparable from the issues they create. In light of this objective, this research presents a model and analysis of the steady-state behavior of an $M/G/1$ feedback retrial queue with two dependent phases of service under a Bernoulli vacation policy. The service times for the two stages are often independent in normal queueing frameworks. We presume that they are dependent random variables in this case. Indeed, this dependence is one-way (i.e., the service time of the second phase has no effect on the service time of the first phase). Yet, the first phase service time has an impact on the second phase service time. In order to determine the steady-state probabilities and probability-generating functions (PGF) for the different states, the supplementary variable technique (SVT) was utilized. Furthermore, a broad range of performance metrics had been established. The generated metrics are then envisioned and validated with the aid of graphs and tables. Additionally, a nonlinear cost function is constructed, which is subsequently minimized by distinct approaches like particle swarm optimization (PSO), artificial bee colony (ABC) and genetic algorithm (GA). Furthermore, we used certain figures to examine the convergence of these optimization methods. Finally, validation outcomes are compared with neuro-fuzzy results generated with the “adaptive neuro-fuzzy inference system” (ANFIS).

This paper reports an efficient technique of evolving Cellular Automata (CA) as an associative memory model. The evolved CA termed as GMACA (Generalized Multiple Attractor Cellular Automata), acts as a powerful pattern recognizer. Detailed analysis of GMACA rules establishes the fact that the rule subspace of the pattern recognizing CA lies at the edge of chaos — believed to be capable of executing complex computation.

To remove image noise without considering the noise model, a dual-tree wavelet thresholding method (CDOA-DTDWT) is proposed through noise variance optimization. Instead of building a noise model, the proposed approach using the improved chaotic drosophila optimization algorithm (CDOA), to estimate the noise variance, and the estimated noise variance is utilized to modify wavelet coefficients in shrinkage function. To verify the optimization ability of the improved CDOA, the comparisons with basic DOA, GA, PSO and VCS are performed as well. The proposed method is tested to remove addictive noise and multiplicative noise, and denoising results are compared with other representative methods, e.g. Wiener filter, median filter, discrete wavelet transform-based thresholding (DWT), and nonoptimized dual-tree wavelet transform-based thresholding (DTDWT). Moreover, CDOA-DTDWT is applied as pre-processing utilization for tracking roller of mining machine as well. The experiment and application results prove the effectiveness and superiority of the proposed method.

Airfoil optimization algorithm is studied and a hybrid PSO and GA method is proposed in this paper. After function test, it shows that algorithm is well in convergence performance, fast speed, and optimization capability. Then, the airfoil parametric expression theory is analyzed. A new airfoil is obtained after combining CFD and PSO-GA optimization. The aerodynamic of new airfoil is compared with the airfoil optimized by GA-PSO and basic airfoil NACA0018. The results indicate that new airfoil is better than the other two airfoils in lift coefficient, lift-drag ratio, and surface pressure. At last, wing-sail of new airfoil and NACA0018 wing-sail are designed and manufactured. Both of them are applied in land-yacht robot linear motion and steering motion experiment. For the linear motion, in the situation of wind speed being 15m/s and angle of attack being 5, running speed of robot with optimized new wing-sail is 1.853m/s. In steering motion, trajectory with new wing-sail is closer to the real situation and it gets more thrust. The experiments data verify that the simulation results are correct and PSO-GA algorithm is effective.

Error correcting codes (ECCs) are commonly used as a protection against the soft errors. Single error correcting and double error detecting (SEC–DED) codes are generally used for this purpose. Such circuits are widely used in industry in all types of memory, including caches and embedded memory. In this paper, a new genetic design for ECC is proposed to perform SEC–DED in the memory check circuit. The design is aimed at finding the implementation of ECC which consumes minimal power. We formulate the ECC design into a permutable optimization problem and employ special genetic operators appropriate for this formulation. Experiments are performed to demonstrate the performance of the proposed method.

In this paper, the hybrid direct torque control (DTC) technique is proposed for controlling the speed of the induction motor (IM). The hybrid technique is the combination of an enhanced firefly algorithm (FA) and the adaptive neuro fuzzy inference system (ANFIS) technique. The performance of the FA is improved by updating the randomized parameter. Here, the genetic algorithm (GA) is utilized for updating the parameter and improved the performance of the FA. Initially, the actual torque and the change of toque are applied to the input of the enhanced FA and form the electromagnetic torque as a dataset. The output of the enhanced FA is given to the input of the ANFIS which is determined from the output of interference system. The dynamic behavior of the IM is analyzed in terms of the parameters such as the speed, torque, flux, etc. Based on the parameters, the motor speed is controlled by utilizing the proposed technique. Then the output of the ANFIS is translated into the stator voltage which is given to the input of the support vector machine (SVM). After that, the control signal is generated for controlling the speed of the IM. The proposed hybrid technique is implemented in the Matlab/Simulink platform. The performance analysis of the proposed method is demonstrated and contrasted with the existing techniques such as without controller, particle swarm optimization (PSO)-based ANFIS and FA-ANFIS controller.

GPS signals can be affected easily by interference due to the low power of signals and the long way between the satellites and receivers. Interference cancellation is one of the major challenges in using GPS. One of the most common intentional interferences is Continuous Wave Interference (CWI) jamming and the most popular way to reduce the impact of it on the GPS signal is using an Adaptive Notch Filter (ANF). Two kinds of heuristic Evolutionary Algorithms (EAs) are used to design second-order IIR Evolutionary Adaptive Notch Filter (EANF). The first algorithm is the Genetic Algorithm (GA) and the second one is Particle Swarm Optimization (PSO) algorithm. EAs are used to find answers to the problems in which there is no specific solution, and this is exactly what is needed to fix the digital filter design problems. NF is implemented in FPGA hardware according to the obtained filter coefficients. Finally, the efficiency of the proposed methods is compared with similar methods in terms of different evaluation metrics. The simulation results show about 12% SNR improvement by using GA and 97% RMS improvement by using the PSO method for higher than 50-dB JSRs.

In the previous works, a discrete-time microstructure (DTMS) model for financial market was constructed by using identification technology and was successfully applied to dynamic asset allocation based on the identified excess demand. However, the initial value setting of the parameters has a great influence on the estimated results of the DTMS model, which may make the estimated model to describe the dynamic characteristics of the financial time series poor and also affect the investment results indirectly. To overcome the weakness, this paper proposes a global optimization method which combines particle swarm optimization (PSO) and genetic algorithm (GA) to estimate the initial parameters. In the paper, the multi-asset DTMS model is established, and a multi-asset dynamic allocation strategy based on excess demand obtained from the DTMS model is also designed. Furthermore, the paper also discusses the impact of mutual correlation of assets on portfolio. Case studies show that, when a portfolio is composed of several stocks which are weak correlation, its total return of the portfolio is more than the sum of two-asset allocation for each stock; while the correlation between stocks is high, the obtained total return is not better than those of two-asset allocation.

A new fractal interpolation method called PPA (Pointed Point Algorithm) based on IFS is proposed to interpolate the self-affine signals with the expected interpolation error, solving the problem that the ordinary fractal interpolation can't get the value of any arbitrary point directly, which has not been found in the existing literatures. At the same time, a new method to calculate the vertical scaling factors is proposed based on the genetic algorithm, which works together with the PPA algorithm to get the better interpolation performance. Experiments on the theoretical data and real field seismic data show that the proposed interpolation schemes can not only get the expected point's value, but also get a great accuracy in reconstruction of the seismic profile, leading to a significant improvement over other trace interpolation methods.

This study deals with the investigation on the effect of Electrical Discharge Machining (EDM) parameters during machining of hybrid composite (Al 7075/TiC/B₄C). The optimum process parameters of die sinking EDM like pulse current, pulse duration and gap voltage on metal removal rate, tool wear rate and surface finish were investigated. Full factorial experimental design was selected for experiments. Analysis of variance was employed to study the influence of process parameters and their interactions on response variables. Among the process parameters considered, it was observed that the pulse current was found to be more influential in affecting MRR, TWR and SR. The other parameters have little effect on the response variable. Multi-objective optimization study was also performed using genetic algorithm to find the optimum parameter setting for controversial objective function combination such as high MRR and low SR and High MRR and low TWR. Scanning electron microscope study was performed to study the surface characteristics.

In this paper, an effort is made to determine the optimized parameters in laser welding of Hastelloy C-276 using Artificial Neural Network (ANN) and Genetic Algorithm (GA). CO₂ Laser welding was performed on a sheet of thickness 1.6mm based on Taguchi L27 orthogonal array. Laser power, welding speed and shielding gas flow rate were chosen as input parameters and Bead width, depth of Penetration and Microhardness were measured for assessing the weld quality. ANN was applied for modeling the welding process parameters i.e. heat input, welding speed and gas flow rate. Various learning algorithms such as Batch Back Propagation (BBP), Incremental Back Propagation (IBP), Quick Propagation (QP) and Levenberg–Marquardt (LM) were comprehensively tested for estimating the output parameters and a comparison was also made among them, with respect to prediction accuracy. BBP method was found to be the best learning algorithm. Experimental validation test was performed based on the ANN and GA predicted optimized responses and this welding input parameters provided satisfactory weld metal characteristics in terms of penetration depth, bead width and microhardness.

Inconel 617 alloy has been included in the boiler and pressure vessel (BPV) code of the American society of mechanical engineers (ASME) for its effectiveness in nuclear applications due to its ability to maintain strength at elevated temperatures. This study is based on the optimization of process parameters for activated flux tungsten inert gas (A-TIG) welding of 10-mm thick Inconel 617 material. Process parameters considered in this study include weld current (A), weld torch travel speed (mm/min), arc gap (mm) and flux powder (silicon dioxide (SiO${}_2)$ and titanium dioxide (TiO${}_2))$ combination. The bead on plate welding experiment was carried out by varying the combination of process parameters in each experimental trial. The Taguchi L16 orthogonal array was the design matrix used for the design of experiments (DOE). In the bead on plate welding experiment, a total of 16 experimental trials, each having a different set of process parameters was conducted. The weld bead samples corresponding to each trial were prepared for measurement of the responses which were measured from each of the 16 weld bead samples and included depth of penetration (DOP), bead width (BW), depth to width ratio (DWR), weld cross-sectional area (WA), and bead height (BH). The objective of this work was to maximize DOP, DWR, WA, BH and minimize BW. Analysis of variance (ANOVA) was used to identify the significance of process parameters. Optimization techniques including particle swarm optimization (PSO) and genetic algorithm (GA) were used in the study. The optimized process parameters and optimal solutions attained from each optimization technique were compared. It was found from the study that weld current was the most significant process parameter for all responses followed by weld torch travel speed, flux powder combination and arc gap. Optimal process parameters to achieve maximum DOP, DWR and WA were found to be weld current of 290 A, weld torch travel speed of 50mm/min along with an arc gap of 1mm and 100% TiO₂ as flux. The optimal solution for DOP, DWR and WA was found to be 7.04mm, 0.437 and 7.619mm² respectively. The optimal solution for BW and BH was 6.302 and 0.677mm, respectively. A confirmation test was conducted to validate the optimal solution obtained from this study. The results from the confirmation test agreed with the solution obtained by optimization techniques.

This paper proposes an advanced and precise technique for the segmentation of Magnetic Resonance Image (MRI) of the brain. Brain MRI segmentation is to be familiar with the anatomical structure, to recognize the deformities, and to distinguish different tissues which help in treatment planning and diagnosis. Nature’s inspired population-based evolutionary algorithms are extremely popular for a wide range of applications due to their best solutions. Teaching Learning Based Optimization (TLBO) is an advanced population-based evolutionary algorithm designed based on Teaching and Learning process of a classroom. TLBO uses common controlling parameters and it won’t require algorithm-specific parameters. TLBO is more appropriate to optimize the real variables which are fuzzy valued, computationally efficient, and does not require parameter tuning. In this work, the pixels of the brain image are automatically grouped into three distinct homogeneous tissues such as White Matter (WM), Gray Matter (GM), and Cerebro Spinal Fluid (CSF) using the TLBO algorithm. The methodology includes skull stripping and filtering in the pre-processing stage. The outcomes for 10 MR brain images acquired by utilizing the proposed strategy proved that the three brain tissues are segmented accurately. The segmentation outputs are compared with the ground truth images and high values are obtained for the measure’s sensitivity, specificity, and segmentation accuracy. Four different approaches, namely Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Bacterial Foraging Algorithm (BFA), and Electromagnetic Optimization (EMO) are likewise implemented to compare with the results of the proposed methodology. From the results, it can be proved that the proposed method performed effectively than the other.

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.

A novel two-dimensional Quad-stable stochastic resonance (NTDQSR) system is proposed in this paper to address the poor signal detection capability of the original one-dimensional Quad-stable stochastic resonance (ODQSR) system. Firstly, expressions for the equivalent potential function and the steady-state probability density (SPD) function of the system are derived to study the impact of parameters on it. Secondly, the system is simulated numerically, and the performance of NTDQSR system is evaluated under trichotomous noise in this paper, because trichotomous noise exists widely in practical applications. Finally, the genetic algorithm (GA) is used to optimize the system parameters, and NTDQSR system is applied to bearing fault detection. In LDK UER204 ring fault detection, MSNRG in NTDQSR system is 0.9927 dB and 0.4805 dB higher than ODQSR and under-damped Quad-stable stochastic resonance (UQSR) system. In the outer ring experiment on the experimental bench at CWRU, MSNRG in NTDQSR system is 0.7255dB and 0.0734dB higher than the other two systems, while in the inner ring experiment, MSNRG is 0.6535dB and 0.1943dB higher than the other two systems, respectively. NTDQSR system is compared with ODQSR and UQSR systems to verify the good application value of NTDQSR system in practical engineering.

Background: Walking is a complex process that involves rhythmic movement of lower limb along with the coordination of brain, nerves and muscles. If the coordination is disturbed, gait may be effected or disordered. Therefore, it should be treated effectively and efficiently using assistive devices/exoskeletons. The exoskeletons and assistive devices may be embedded with the linkage and other mechanisms to imitate the behavior of human lower limb. However, these mechanisms are synthesized using the complex conventional procedures. Thus, a new gait-inspired algorithm is proposed in this study for synthesizing a four-bar mechanism for exoskeletons.

Methods: This paper presents a design of four-bar linkage for lower limb exoskeleton to support walking. A new gait-inspired algorithm to synthesize four-bar linkage is also proposed which uses two phases of gait, namely, the swing phase and the stance phase, for lower limb exoskeleton. The trajectory is derived for each phase of the gait and is combined with the optimization techniques. The trajectory passes through 10 precision points in each phase giving a total of 20 precision points for one gait cycle. The optimization is performed in two stages. The first stage deals with the minimization of error between the desired and the generated foot trajectories; whereas, the second stage deals with the minimization of error between the desired and generated hip trajectories of the linkage. Besides the gait-inspired four-bar linkage synthesis, a hybrid teaching-learning-particle-swarm-optimization (HTLPSO) technique is also used to solve the problem.

Results: A well-established genetic algorithm (GA) and a new hybrid (HTLPSO) algorithm are used to compare the results of the tracking error of the linkage. It is found that the HTLPSO optimization algorithm performs better in comparison to GA for the problem considered here. Finally, a solid model of the proposed design for lower limb exoskeleton is presented. Moreover, the obtained linkage tracks all the prescribed points accurately and the simulation of designed linkage has been demonstrated using stick diagram for one gait cycle.

Conclusion: The proposed method has simplified the synthesis procedure to a great extent, and a feasible design is obtained using the optimization algorithm. The mechanism obtained using the proposed method can walk smoothly which is validated through stick diagram. The proposed mechanism can be used for exoskeleton, assistive devices, bipeds etc. Moreover, the proposed method may be extended to six- and eight-bar mechanisms.

In the plastic industry for mold making, pocket milling is applied. The surface finish of the mold affects the quality of the plastic product, especially for toys. This can be achieved by minimising the surface roughness of the mold. To get a good quality product with a better production rate, the selection of the best combination of parameters in pocket milling is necessary. Multi-response optimisation can be applied for selecting such parameters which are suited for fulfilling the objective. In this study, one of the toy mold designs is selected as a pocket profile on which, two tool trajectories, viz Follow Periphery (FP) and Zigzag (ZZ), are applied for generation of pocket by varying Speed (S), Feed (F) and Step Over (SO). Box–Behnken Response Surface Methodology is applied to find the experimental runs. Two conflicting objectives minimising Surface Roughness (SR) and maximising Material Removal Rate (MRR) are obtained by applying Artificial Neural Networks (ANN) and Multi-Objective Genetic Algorithm (MOGA). Conformational experiments were conducted for the random set of Pareto results obtained from MOGA for both the tool trajectories to validate the model. From the analysis, it is observed that the FP tool path strategy is well suited to generate the pocket to get minimum SR and maximum MRR as the error percentage between the predicted and test results observed is 0.8085% for SR and 0.9236% for MRR.