Novel Hybrid Invasive Weed Optimization and Machine Learning Approach for Fault Detection

In this paper, a novel hybrid Invasive Weed Optimization (IWO) and Cuckoo Search (CS) algorithm (IWO/CS) is presented for phase-only pattern synthesis of large array antenna. The hybrid IWO/CS algorithm embeds the Levy flight of CS algorithm into IWO algorithm as a global guide, thereby enhancing the global search ability of the algorithm. At the same time, in order to avoid trapping into the local optimal solution, mutation operator is introduced to enhance search ability of the algorithm. Finally, competitive exclusion operation is improved to maintain the diversity of population. The hybrid algorithm is applied to phase-only beam shaping to achieve main lobe broadening and side lobe depression. Simulation results demonstrate the superiority of the hybrid IWO and CS algorithm.

In view of the traditional numerical method to solve the nonlinear equations exist is sensitive to initial value and the higher accuracy of defects. This paper presents an invasive weed optimization (IWO) algorithm which has population diversity with the heuristic global search of differential evolution (DE) algorithm. In the iterative process, the global exploration ability of invasive weed optimization algorithm provides effective search area for differential evolution; at the same time, the heuristic search ability of differential evolution algorithm provides a reliable guide for invasive weed optimization. Based on the test of several typical nonlinear equations and a circle packing problem, the results show that the differential evolution invasive weed optimization (DEIWO) algorithm has a higher accuracy and speed of convergence, which is an efficient and feasible algorithm for solving nonlinear systems of equations.

The optimal hydropower operation of reservoir systems is known as a complex nonlinear nonconvex optimization problem. This paper presents the application of invasive weed optimization (IWO) algorithm, which is a novel evolutionary algorithm inspired from colonizing weeds, for optimal operation of hydropower reservoir systems. The IWO algorithm is used to optimally solve the hydropower operation problems for both cases of single reservoir and multi reservoir systems, over short, medium and long term operation periods, and the results are compared with the existing results obtained by the two most commonly used evolutionary algorithms, namely, particle swam optimization (PSO) and genetic algorithm (GA). The results show that the IWO is more efficient and effective than PSO and GA for both single reservoir and multi reservoir hydropower operation problems.

Trajectory planning algorithm based on MIWO used for nondestructive testing of EAST divertor

In this paper, a modified invasive weed optimization (IWO) algorithm is presented for optimization of multiobjective flexible job shop scheduling problems (FJSSPs) with the criteria to minimize the maximum completion time (makespan), the total workload of machines and the workload of the critical machine. IWO is a bio-inspired metaheuristic that mimics the ecological behaviour of weeds in colonizing and finding suitable place for growth and reproduction. IWO is developed to solve continuous optimization problems that’s why the heuristic rule the Smallest Position Value (SPV) is used to convert the continuous position values to the discrete job sequences. The computational experiments show that the proposed algorithm is highly competitive to the state-of-the-art methods in the literature since it is able to find the optimal and best-known solutions on the instances studied.

Recommender systems intend to help users find their interested items from among a large number of items. We continue our previous work that emphasizes on approach as an effective approach to increase the quality of the recommendations. Prioritized user-profile is an approach that tries to implement more personalized recommendation by assigning different priority importance to each of the features of the user-profile for different users. In order to find the optimal priorities for each user an optimization algorithm is needed. In this paper, we employ a new optimization algorithm namely invasive weed optimization (IWO) for this purpose. IWO is a relatively new and simple algorithm inspired from the invasive habits of growth of weeds in nature. Experimental results showed that IWO achieved the best accuracy in predicting users' interests compared to two other prioritized approaches which were based on genetic algorithm (GA) and particle swarm optimization (PSO) and to standard user-based Pearson algorithm on a movie dataset.

In this paper, a novel approach is introduced to estimate the North American Aerospace Defense Command (NORAD)-type two-line elements (TLE) data based on the invasive weed optimization (IWO) method, which is a stochastic numerical optimization algorithm inspired by colonizing weeds. Many satellite applications use the NORAD Simplified General Perturbations model 4 (SGP4) for satellite position prediction. The input of SGP4 consists of TLEs which are published via NORAD freely through the worldwide web. Since it is generated irregular, a new TLE which is independent of NORAD is required to access data about the satellite location each time. An alternative to independent computation of TLE can be made feasible by the existing emersion of GPS receivers in the space project and using IWO. Using this stochastic algorithm increases the success probability to find a more accurate TLE. The estimation is performed for six Keplerian orbital elements and SGP4 drag term ( B*) by using the satellite position data achieved from the GPS receiver. Also, the feasibility study of the concept is performed by using the actual GPS data of CHAMP and corresponding NORAD TLE. The time length of the GPS data used in the estimation is studied for practical application purposes. The results show that 500 samples of position data, with 1-min time intervals, are sufficient to keep the position error within 10 km in 3 days after epoch time in orbital elements with known drag term estimation. Moreover, for orbital elements with drag term estimation, 1000 samples of position, with 1-min time intervals, are sufficient to keep the position error within 15 km in 3 days after epoch time. If there is no considerable constraint for position-data time-length or time available for performing numerical computations, the estimated TLE can be more accurate than corresponding NORAD TLE.

The aim of the research work is to propose an integrated optimization technique, established with the integration of the invasive weed optimization (IWO) and Powell’s pattern search (PPS) method. The IWO algorithm has been undertaken as a global search technique, which is inspired from the specific ecological behavior of weeds and has the ability to adapt to the changing environment. The local search PPS method is based upon a conjugate-based search and having excellent exploitation search capability, which helps to improve the solution obtained from IWO technique. The proposed technique is applied to solve optimal power flow (OPF) problem with the flexible AC transmission system devices. The OPF problem is a nonlinear, non-convex optimization problem and consists of continuous and discrete decision variables. The three objective functions comprise total fuel cost, pollutant emission and system transmission loss which are minimized sequentially. The proposed technique is tested on four standard IEEE test systems, and results are compared with the reported results in the literature and found promising. The results illustrate that the proposed technique performs better as compared to IWO technique in terms of the quality of solution and convergence characteristics. Further, t test is performed to validate the statistical performance of the proposed integrated optimization technique.

A chemistry-informed hybrid machine learning approach to predict metal adsorption onto mineral surfaces

This paper explicates hybrid optimization driven Extreme Machine Learning (ELM) strategy is developed with feed forward neural network (FFNN) for the classification of data and improving ELM. The pre-processing of input data is carried for the missing value imputation and transformation of data into numerical value using exponential kernel transform. The significant feature is determined using the Jaro–Winkler distance. The classification of data is done using the FFNN classifier, which is trained with the help of the hybrid optimization algorithm, namely developed modified Cuckoo Search and Invasive Weed Optimization (CSIWO) ELM. The modified CSIWO is devised by integrating the modified Cuckoo search (CS) algorithm and Invasive Weed Optimization (IWO) algorithm. The experimental results proposed in this paper show the feasibility and effectiveness of the developed CSIWO ELM method with encouraging performance compared with other ELM methods.

This paper proposes a hybrid predictive model that adopts both logistic regression and Naive Bayes with the aim of boosting the performance of multiclass classification. Logistic regression presents the most robust linear modeling and good interpretability, while Naïve Bayes is very powerful in probabilistic reasoning with the independent assumptions, which guarantees high computational efficiency and strong performance in classification tasks. Therefore, combining both methods, this hybrid model takes advantage of complementary strengths: interpretability versus accuracy. In the preprocessing stage, the dataset was imputed for missing values, normalizing features and balancing the classes using different resampling techniques. The hybrid framework starts with logistic regression that gives interpretable probability estimates. Further refinement of predictions is facilitated by Naïve Bayes, in which the application of probabilistic reasoning will enhance the classification accuracy. These scores and results from the evaluation, therefore, indicate that for accuracy, the logistic regression model returned 73%, while that of Naïve Bayes was 90%. As a hybrid model, though, it outperformed by yielding an impressive accuracy rate of 93%, hence being both linear and probabilistic at once. This shows the process in making an improvement while capturing both the linearity and non-linearity in any complex dataset. All experiments were conducted in a reproducible Google Colab environment using Python, which guarantees scalability and transparency. The results validate the promise of hybrid machine learning techniques for robust, interpretable, and computationally efficient solutions on a wide variety of realworld classification problems.

Multi-Objective Invasive Weed Optimization – An application to optimal network reconfiguration in radial distribution systems

Heart diseases represent a significant global health concern, characterized by impaired heart function. Unfortunately, it’s predicted that fatalities resulting from heart-related illnesses may escalate dramatically, reaching an astounding 24.2 million by the year 2030.Accurate prognosis and identification of cardiac diseases play a pivotal role in facilitating timely prevention, detection, and therapy. However, existing medical equipment such as electrocardiograms and computerized tomography scans employed for detecting heart disorders often pose difficulties owing to prohibitive costs and operational constraints, making access challenging for many individuals. By harnessing these capabilities, machine learning models can potentially provide more accurate predictions of heart disease risk based on body composition data. The use of machine learning algorithms in healthcare has already shown encouraging results in various applications, including disease diagnosis, treatment planning, and patient outcome prediction. In light of these developments, the study aims to create a hybrid machine learning model that leverages the strengths of multiple algorithms to predict heart disease risk based on body composition data to reduce death rate. This paper proposed six Machine Learning algorithms using body composition dataset, the algorithms are Decision tree model (DTM), XGBOOST, LIGHTGBM, Support Vector Machine (SVM), KNN and Hybrid model. The experimental result indicates that the HHP model outperformed others in precision, recall, F-score, with accuracy of 90.2 %

A new hybrid evolutionary algorithm for multi-objective optimal power flow in an integrated WE, PV, and PEV power system

ABSTRACTIn this paper, Invasive weed optimization (IWO) algorithm is proposed for testing automatic generation control (AGC) of multi-area power systems. Initially, a two-area multi-source power system interconnected by a DC link is considered and IWO is employed to optimize the proportional integral derivative (PID) controller for AGC employing a modified objective function. The superiority of the proposed approach is shown by comparing the results with recently published optimal algorithms for the similar system under study. The comparison is made using various performance criteria such as integral of time multiplied absolute error (ITAE), minimum damping ratio (MDR) of dominant eigenvalues, settling times and maximum overshoots. Furthermore, sensitivity analysis is performed to show the robustness of the proposed approach by varying the system parameters, operating load conditions from their nominal values as well as size and locations of disturbance. The proposed approach is also extended to three area system considering both thermal and hydro units with generation rate constraints (GRC) and the superiority of the proposed approach is shown by comparing the results of Adaptive Neuro Fuzzy Inference System (ANFIS), hybrid Bacteria Foraging Optimization Algorithm with Particle Swarm Optimization (hBFOA–PSO) approaches for the identical interconnected power system.