Search results

This paper aims to propose a dynamically balanced mechanism for cleaning unit used in agricultural thresher machine using a dynamically equivalent system of point masses.

The cleaning unit works on crank-rocker Grashof mechanism. This mechanism can be balanced by optimizing the inertial properties of each link. These properties are defined by the dynamic equivalent system of point masses. Parameters of these point masses define the shaking forces and moments. Hence, the multi-objective optimization problem with minimization of shaking forces and shaking moments is formulated by considering the point mass parameters as the design variables. The formulated optimization problem is solved using a posteriori approach-based algorithm i.e. the non-dominated sorting Jaya algorithm (NSJAYA) and a priori approach-based algorithms i.e. Jaya algorithm and genetic algorithm (GA) under suitable design constraints.

The mass, center of mass and inertias of each link are calculated using optimum design variables. These optimum parameters improve the dynamic performance of the cleaning unit. The optimal Pareto set for the balancing problem is measured and outlined in this paper. The designer can choose any solution from the set and balance any real planar mechanism.

The efficiency of the proposed approach is tested through the existing cleaning mechanism of the thresher machine. It is found that the NSJAYA is computationally more efficient than the GA and Jaya algorithm. ADAMS software is used for the simulation of the mechanism.

The purpose of this paper is to propose the dynamically balanced mechanism for cleaning unit used in the agricultural thresher machine using the system of point masses.

The cleaning unit works on crank-rocker Grashof mechanism. To balance the mechanism, the shaking forces and shaking moments are minimized by optimizing the mass distribution of links using the dynamically equivalent system of point masses. The point mass parameters are taken as the design variables. Then, the optimization problem is solved using Jaya algorithm and genetic algorithm (GA) under suitable design constraints.

The mass, center of mass and inertias of each link are calculated using optimum design variables. These optimum parameters improve the dynamic performance of the cleaning unit.

The proposed methodology is tested through the standard four-bar mechanism taken from literature and also applied to the existing cleaning mechanism of the thresher machine. It is observed that the Jaya algorithm is computationally more efficient than the GA. The dynamic analysis of the proposed mechanism is simulated using ADAMS software.

This paper aims to present the optimum two-plane discrete balancing procedure for rigid rotor. The discrete two-plane balancing in which rotor is balanced to minimize the residual effects or the reactions on the bearing supports using discrete parameters such as masses and their angular positions on two balancing planes.

Therefore as a multi-objective optimization problem is formulated by considering reaction forces on the bearing supports as a multi objective functions and discrete parameters on each balancing plane as design variables. These multi-objective functions are converted into a single-objective function using appropriate weighting factors. Further, this optimization problem is solved using discrete optimization algorithm, based on Jaya algorithm.

The performance of the discrete Jaya algorithm is compared to genetic algorithm (GA) algorithm. It is found that Jaya algorithm is computationally more efficient than GA algorithm. A number of masses per plane are used to balance the rotor. A comparison of reaction forces using number of masses per plane is investigated.

The effectiveness of the proposed methodology is tested by the balancing problem of rotor available in the literature. The influence of a number of balance masses on bearing forces and objective function are discussed. ADAMS software is used for validation of a developed balancing approach.

The Covid-19 prediction process is more indispensable to handle the spread and death occurred rate because of Covid-19. However early and precise prediction of Covid-19 is more difficult because of different sizes and resolutions of input image. Thus these challenges and problems experienced by traditional Covid-19 detection methods are considered as major motivation to develop JHBO-based DNFN.

The major contribution of this research is to design an effectual Covid-19 detection model using devised JHBO-based DNFN. Here, the audio signal is considered as input for detecting Covid-19. The Gaussian filter is applied to input signal for removing the noises and then feature extraction is performed. The substantial features, like spectral roll-off, spectral bandwidth, Mel-frequency cepstral coefficients (MFCC), spectral flatness, zero crossing rate, spectral centroid, mean square energy and spectral contract are extracted for further processing. Finally, DNFN is applied for detecting Covid-19 and the deep leaning model is trained by designed JHBO algorithm. Accordingly, the developed JHBO method is newly designed by incorporating Honey Badger optimization Algorithm (HBA) and Jaya algorithm.

The performance of proposed hybrid optimization-based deep learning algorithm is estimated by means of two performance metrics, namely testing accuracy, sensitivity and specificity of 0.9176, 0.9218 and 0.9219.

The JHBO-based DNFN approach is developed for Covid-19 detection. The developed approach can be extended by including other hybrid optimization algorithms as well as other features can be extracted for further improving the detection performance.

The proposed Covid-19 detection method is useful in various applications, like medical and so on.

Developed JHBO-enabled DNFN for Covid-19 detection: An effective Covid-19 detection technique is introduced based on hybrid optimization–driven deep learning model. The DNFN is used for detecting Covid-19, which classifies the feature vector as Covid-19 or non-Covid-19. Moreover, the DNFN is trained by devised JHBO approach, which is introduced by combining HBA and Jaya algorithm.

The purpose of this study is to analyze direct current (DC) drive stability, including parameter uncertainty and perturbation in the feedback loop, by computing disk margins.

Although the closed-loop stability analysis of a DC drive has been presented well in the referenced papers, the effect of parameter uncertainty and perturbation in the feedback loop has not yet been discussed well. In this study, the conventional and disk-based stability margins were measured and compared for the nominal parameters of the DC drive. Subsequently, the smallest disk-based margins that destabilize the feedback loop for a given perturbation are computed and compared with normal disk margins.

The disk-based margin offered by the DC drive controlled by the JAYA-PID controller is disk gain margins (DGM) = 8.41 dB and disk phase margin (DPM) = 48.410 and the smallest disk-based margin offered is DGM = 1.51 dB and DPM = 9.950. In addition, the effect of the modeled uncertainty on the disk stability margins was analyzed, and it was observed that the maximum allowable parameter uncertainty with the JAYA controller was 73% of its nominal parameters. The simulation results were validated using an experimental testbed.

This research work is not published anywhere else.

The purpose of this study is to provide a novel portfolio asset prediction by means of the modified deep learning and hybrid meta-heuristic concept. In the past few years, portfolio optimization has appeared as a demanding and fascinating multi-objective problem, in the area of computational finance. Yet, it is accepting the growing attention of fund management companies, researchers and individual investors. The primary issues in portfolio selection are the choice of a subset of assets and its related optimal weights of every chosen asset. The composition of every asset is chosen in a manner such that the total profit or return of the portfolio is improved thereby reducing the risk at the same time.

This paper provides a novel portfolio asset prediction using the modified deep learning concept. For implementing this framework, a set of data involving the portfolio details of different companies for certain duration is selected. The proposed model involves two main phases. One is to predict the future state or profit of every company, and the other is to select the company which is giving maximum profit in the future. In the first phase, a deep learning model called recurrent neural network (RNN) is used for predicting the future condition of the entire companies taken in the data set and thus creates the data library. Once the forecasting of the data is done, the selection of companies for the portfolio is done using a hybrid optimization algorithm by integrating Jaya algorithm (JA) and spotted hyena optimization (SHO) termed as Jaya-based spotted hyena optimization (J-SHO). This optimization model tries to get the optimal solution including which company has to be selected, and optimized RNN helps to predict the future return while using those companies. The main objective model of the J-SHO-based RNN is to maximize the prediction accuracy and J-SHO-based portfolio asset selection is to maximize the profit. Extensive experiments on the benchmark datasets from real-world stock markets with diverse assets in various time periods shows that the developed model outperforms other state-of-the-art strategies proving its efficiency in portfolio optimization.

From the analysis, the profit analysis of proposed J-SHO for predicting after 7 days in next month was 46.15% better than particle swarm optimization (PSO), 18.75% better than grey wolf optimization (GWO), 35.71% better than whale optimization algorithm (WOA), 5.56% superior to JA and 35.71% superior to SHO. Therefore, it can be certified that the proposed J-SHO was effective in providing intelligent portfolio asset selection and prediction when compared with the conventional methods.

This paper presents a technique for providing a novel portfolio asset prediction using J-SHO algorithm. This is the first work uses J-SHO-based optimization for providing a novel portfolio asset prediction using the modified deep learning concept.

This paper aims to get the optimal controller parameters of fractional order proportional integral derivative (FOPID)/proportional integral derivative (PID) i.e. K_p, K_i, K_d, λ and µ for designing controller in automatic voltage regulator (AVR) system.

A novel method is proposed to get the optimal controller parameters for designing controller in AVR system using improved Jaya algorithm (IJA). The time domain objective and regular integral error objectives are used to design the controller to estimate the performance of the AVR system based on optimal tuning FOPID/PID controller.

The proposed method captures time domain objective of the FOPID/PID controller design and demonstrates effective transient response and better control action. The efficient tuning of FOPID controller results in high superiority of control efforts.

The simulations of IJA-based FOPID/PID controller design method are performed in MatLab tool and compared with several methods in the recent state of the art and the same are observed to be robust for the AVR system.

The developed optimal FOPID/PID controller tuning using IJA optimization method is totally a new approach for the AVR system in the literature.

The purpose of this paper is to adopt a three-stage cloud-based management system for optimizing greenhouse gases (GHG) emission and marketing decisions with supplier selection and product family design in a multi-level supply chain with multiple suppliers, one single manufacturer and multiple retailers.

The manufacturer purchases optional components of a certain functionality from his alternative suppliers and customizes a set of platform products for retailers in different independent market segments. To tackle the studied problem, a hierarchical analytical target cascading (ATC) model is proposed, Jaya algorithm is applied and supplier selection and product family design are implemented in its encoding procedure.

A case study is used to verify the effectiveness of the ATC model in solving the optimization problem and the corresponding algorithm. It has shown that the ATC model can not only obtain close optimization results as a central optimization method but also maintain the autonomous decision rights of different supply chain members.

This paper first develops a three-stage cloud-based management system to optimize GHG emission, marketing decisions, supplier selection and product family design in a multi-level supply chain. Then, the ATC model is proposed to obtain the close optimization results as central optimization method and also maintain the autonomous decision rights of different supply chain members.

Machining of curved channels using electrical discharge machining (EDM) is a novel approach. In this study, an experimental setup was designed, developed and mounted on die-sinking EDM to manufacture curve channels in AISI P20 mold steel.

The effect of specific machining parameters such as peak current, pulse on time, duty factor and lift over material removal rate (MRR) and tool wear rate (TWR) were studied. Multi-objective optimization was performed using Taguchi technique and Jaya algorithm.

The experimental results revealed current and pulse on time to have the predominant effect over material removal and tool wear diagnostic parameters with contributions of 39.67, 32.04% and 43.05, 36.52%, respectively. The improvements in material removal and tool wear as per the various optimization techniques were 35.48 and 10.91%, respectively.

Thus, Taguchi method was used for effective optimization of the machining parameters. Further, nature-based Jaya algorithm was implemented for obtaining the optimum values of TWR and MRR.

This paper aims to propose a new upper limb movement classification with two phases like pre-processing and classification. Investigation of human limb movements is a significant topic in biomedical engineering, particularly for treating patients. Usually, the limb movement is examined by analyzing the signals that occurred by the movements. However, only few attempts were made to explore the correlations among the movements that are recognized by the human brain.

The initial process is the pre-processing that is performed for detecting and removing noisy channels. The artifacts are marked by band-pass filtering that discovers the values below and above thresholds of 200 and –200 µV, correspondingly. It also discovers the trials with unusual joint probabilities, and the trials with unusual kurtosis are also determined using this method. After this, the pre-processed signals are subjected to a classification process, where the neural network (NN) model is used. The model finally classifies six movements like “elbow extension, elbow flexion, forearm pronation, forearm supination, hand open, and hand close,” respectively. To make the classification more accurate, this paper intends to optimize the weights of NN by a new hybrid algorithm known as bypass integrated jaya algorithm (BI-JA) that hybrids the concept of rider optimization algorithm (ROA) and JA. Finally, the performance of the proposed model is proved over other conventional models concerning certain measures like accuracy, sensitivity, specificity, and precision, false positive rate, false negative rate, false discovery rate, F₁-score and Matthews correlation coefficient.

From the analysis, the adopted BI-JA-NN model in terms of accuracy was high at 80th population size was 7.85%, 3.66%, 7.53%, 2.09% and 0.52% better than Levenberg–Marquardt (LM)-NN, firefly (FF)-NN, JA-NN, whale optimization algorithm (WOA)-NN and ROA-NN algorithms. On considering sensitivity, the proposed method was 2%, 0.2%, 5.01%, 0.29% and 0.3% better than LM-NN, FF-NN, JA-NN, WOA-NN and ROA-NN algorithms at 50th population size. Also, the specificity of the implemented BI-JA-NN model at 80th population size was 7.47%, 4%, 7.05%, 2.1% and 0.5% better than LM-NN, FF-NN, JA-NN, WOA-NN and ROA-NN algorithms. Thus, the betterment of the presented scheme was proved.

This paper adopts the latest optimization algorithm called BI-JA to introduce a new upper limb movement classification with two phases like pre-processing and classification. This is the first work that uses BI-JA based optimization for improving the upper limb movement detection using electroencephalography signals.