Heart Disease Prediction Using Artificial Neural Network with ADAM Optimization and Harmony Search Algorithm

This work presents the development of multi-objective harmony search (MOHS) algorithm for optimization problem using self-adaptive improved harmony search (SIHS) algorithm which is a variant of recently developed harmony search algorithm (HS) for single objective optimization. The approach used in this work is decomposing of multiple objectives into several single objective functions which are simultaneously optimized in such a way that a nearly uniform distribution of the solutions along the pareto-front is followed. The algorithm upon testing for standard test functions has shown promising results.KeywordsHarmony SearchMulti-objective optimizationPareto front

Decision-making and optimal design of green energy system based on statistical methods and artificial neural network approaches

Shunt capacitors are broadly applied in distribution systems to scale down power losses, improve voltage profile and boost system capacity. The amount of capacitors added and location of deployment in the system highly determine the advantage of compensation. A novel global harmony search (GHS) algorithm in parallel with the backward/ forward sweep power flow technique and radial harmonic power flow was used to investigate the optimal placement and sizing of capacitors in radial distribution networks for minimizing power loss and total cost by taking account load unbalancing, mutual coupling and harmonics. The optimal capacitor placement outcomes show that the GHS algorithm can reduce total power losses up to 60 kW and leads to more than 18% of cost saving. The results also demonstrate that the GHS algorithm is more effective in minimization of power loss and total costs compared with genetic algorithm (GA), particle swarm optimization (PSO) and harmony search (HS) algorithm. Moreover, the proposed algorithm converges within 800 iterations and is faster in terms of computational time and gives better performance in finding optimal capacitor location and size compared with other optimization techniques.

Heart disease has long been a major threat to human health, causing about one-third of all deaths each year. Therefore, there is a need for accurate and effective prediction of cardiac disease using machine learning techniques. This paper uses data from 1,319 patients with heart disease and applies several machine-learning methods to study the relationship between a total of eight factors. The algorithms used in this paper include neural networks, decision trees, random forests, and so on. The best model was established by the random forest method, with an accuracy of 96.97%, precision of 97.03%, recall of 96.97%, and f1-Score of 0.9. It was found that troponin and CK-MB indicators had the highest influence weights, and the sum of the weights of each model accounted for more than 75% of the total weight, which demonstrated their significance in the prediction of heart disease, and the results could be utilized for the future prediction of heart disease. In addition, it also plays an essential role in the prediction of heart disease. To sum up, this is really important for the prediction of future heart disease.

An improved harmony search algorithm for power economic load dispatch

Harmony search (HS) algorithm is an emerging population oriented stochastic metaheuristic algorithm, which is inspired by the music improvisation process. This paper introduces an Amended harmony search (AHS) algorithm for solving optimization problems. In AHS, an enhanced approach is employed for generating better solution that improves accuracy and convergence speed of harmony search (HS). The effects of various parameters on harmony search algorithm are analyzed in this paper. The proposed approach performs fine tuning of two parameters bandwidth and pitch adjustment rate. The proposed algorithm is demonstrated on complex benchmark functions and results are compared with two recent variants of HS optimization algorithms, improved harmony search (IHS) and highly reliable harmony search (HRHS). Results suggested that the AHS method has strong convergence and has better balance capacity of exploration and exploitation.

Voltage stability is an important issue in power system operation. Flexible AC transmission systems, so-called FACTS devices, help to improve voltage stability and minimize real power losses. The effectiveness of FACTS devices depend on their proper location and rating. This paper presents a method, based on line flow sensitivity factors such as bus voltage stability index and line voltage stability index, to find suitable locations of multi-type FACTS devices. Also this paper proposes an application of particle swarm optimization (PSO) and harmony search algorithm (HSA) in optimizing the rating of FACTS devices. The proposed approaches are evaluated with three different objective functions namely, minimization of real power loss, improvement of voltage profile and enhancement of voltage stability. The performance of proposed methods is analyzed on IEEE 14 bus system by implementing FACTS devices such as static var compensator (SVC), thyristor controlled series capacitor (TCSC) and unified power flow controller (UPFC).The analysis shows that there is a reduction in real power loss and improvement in voltage stability and voltage profile of the system after employing FACTS devices. It also shows that both real power loss and bus voltage stability index (BVSI) have been reduced more with FACTS ratings obtained from PSO than with that from HSA.

A method based on harmony search (HS) algorithm for designing an optical comb generator with excellent flatness is proposed. The comb generator with simple structure consists of four phase modulators with a single laser as the input, single radio frequency (RF) bias with different amplitudes, and DC bias for each modulator. No RF phase shifter, filter, or fiber loop is needed. Instead of following a classic mathematical model for finding the values of RF amplitudes and DC voltages for generating an optical comb, HS algorithm is implemented, which is an intelligent algorithm inspired from the improvisation of music players and seeks for the most harmonized answers corresponding to flat optical combs. The simulation results of generating two sets of optical combs by HS algorithm with 43 and 53 lines with flatness of 0.51 and 0.59 dB and then after inclusion of power conversion efficiency in the objective function of HS algorithm, two other sets of combs with 47 and 55 lines, flatness of 1.64 and 1.77 dB, and power conversion efficiency of 28% and 32% are presented. Such a device can be used in wavelength-division multiplexing systems and many other applications.

In this paper, a new variant of harmony search algorithm called self-adaptive differential harmony search (SADHS) algorithm is proposed to solve the combined economic emission dispatch (CEED) problems. The proposed algorithm is tested on 6- and 40 unit test systems to show the effectiveness. The simulation results obtained by the proposed algorithm are compared with the results of differential harmony search (DHS) algorithm. The results obtained by the proposed algorithm are found to be better than DHS algorithm in terms of quality of solution, speed of convergence and CPU time.

Cardiovascular diseases are one of the most common causes of death in the world. At this point, early diagnosis of heart diseases is critically important. The aim of this study is to predict the heart disease using feature selection, classification and optimization algorithms. Firstly, principal component analysis (PCA) is used to create the feature selection model and to determine the effective attributes. Then, Extreme Gradient Boosting (XGBoost) classification model is proposed to predict the heart disease. Finally, genetic algorithm (GA) is applied to optimize the parameters of XGBoost to improve the classification accuracy. The developed hybrid PCA-XGBoost-GA approach is compared with XGBoost, PCA-XGBoost, XGBoost-GA, artificial neural network (ANN) and support vector machine (SVM). The effectiveness of these approaches is illustrated with a case study with the actual data taken from a university hospital in Turkey. The numerical results show that the proposed PCA-XGBoost-GA model outperforms the other classification models in terms of accuracy rate, recall, precision and F-measure. Moreover, feature selection and parameter optimization improve the classification performance of the XGBoost model.

Several researchers have developed intelligent medical devices to support the systems and further to enhance the ability to diagnose and predict heart diseases. However, there are few studies that look at the capabilities of ensemble methods in developing a heart disease detection and prediction model. In this study, the researchers assessed that how to use ensemble model, which proposes a more stable performance than the use of base learning algorithm and these leads to better results than other heart disease prediction models. The University of California, Irvine (UCI) Machine Learning Repository archive was used to extract patient heart disease data records. To achieve the aim of this study, the researcher developed the meta-algorithm. The ensemble model is a superior solution in terms of high predictive accuracy and diagnostics output reliability, as per the results of the experiments. An ensemble heart disease prediction model is also presented in this work as a valuable, cost-effective, and timely predictive option with a user-friendly graphical user interface that is scalable and expandable. From the finding, the researcher suggests that Bagging is the best ensemble classifier to be adopted as the extended algorithm that has the high prediction probability score in the implementation of heart disease prediction.

One of the most undesirable consequences induced by blasting in open-pit mines and civil activities is flyrock. Furthermore, the production of oversize boulders creates many problems for the continuation of the work and usually imposes additional costs on the project. In this way, the breakage of oversize boulders is associated with throwing small fragments particles at high speed, which can lead to serious risks to human resources and infrastructures. Hence, the accurate prediction of flyrock induced by boulder blasting is crucial to avoid possible consequences and its’ environmental side effects. This study attempts to develop an optimized artificial neural network (ANN) by particle swarm optimization (PSO) and jellyfish search algorithm (JSA) to construct the hybrid models for anticipating flyrock distance resulting in boulder blasting in a quarry mine. The PSO and JSA algorithms were used to determine the optimum values of neurons’ weight and biases connected to neurons. In this regard, a database involving 65 monitored boulders blasting for recording flyrock distance was collected that comprises six influential parameters on flyrock distance, i.e., hole depth, burden, hole angle, charge weight, stemming, and powder factor and one target parameter, i.e., flyrock distance. The ten various models of ANN, PSO–ANN, and JSA–ANN were established for estimating flyrock distance, and their results were investigated by applying three evaluation indices of coefficient of determination (R2), root mean square error (RMSE) and value accounted for (VAF). The results of the calculation of evaluation indicators revealed that R2, values of (0.957, 0.972 and 0.995) and (0.945, 0.954 and 0.989) were determined to train and test of proposed predictive models, respectively. The yielded results denoted that although ANN model is capable of anticipating flyrock distance, the hybrid PSO–ANN and JSA–ANN models can anticipate flyrock distance with more accuracy. Furthermore, the performance and accuracy level of the JSA–ANN predictive model can estimate better compared to ANN and PSO–ANN models. Therefore, the JSA–ANN model is identified as the superior predictive model in estimating flyrock distance induced from boulder blasting. In the final, a sensitivity analysis was conducted to determine the most influential parameters in flyrock distance, and the results showed that charge weight, powder factor, and hole angle have a high impact on flyrock changes.

Inverse kinematics is one of the most important and complicated problems in robotics, and there is almost no exact analytical solution for this problem. Alternatively, with significant growth in machine learning techniques in recent decades, numerical methods are widely being used to solve this problem. This article aims to present a novel application of two powerful meta-heuristic optimization algorithms including cuckoo optimization algorithm and imperialist competitive algorithm to solve robotic manipulators’ inverse kinematics problem for the first time. Recently, these two algorithms have been used to solve several problems in different majors more efficiently in comparison with other well-known algorithms. To validate the efficiency of proposed approaches and suggest them as the preferred numerical methods to solve this problem, a comprehensive study has been done on performance of almost all recently used numerical methods to solve the same problem including genetic algorithm, particle swarm optimization, harmony search and differential evolution algorithms as well as adaptive neuro-fuzzy inference system and two artificial neural networks (multilayer perceptron and radial basis function). Simulations have been performed on an anthropomorphic arm with spherical wrist manipulator case study because of its complex model and degree of freedom. Proposed approach can be included in computer-aided manufacturing packages to increase robotic manipulators’ efficiencies.

In this paper a new method for dynamic parameter adaptation in harmony search (HS) algorithm is proposed. HS is a music inspired metaheuristic optimization algorithm, in particular we refer to jazz improvisation and is applied to solve complex problems. In this paper we propose an improvement to the convergence of the harmony search algorithm using fuzzy logic. Simulation results show that the propose approach improves the performance of HS, and benchmark mathematical functions are used to illustrate the feasibility of the proposed approach.

Software testing is the primary phase, which is performed during software development and it is carried by a sequence of instructions of test inputs followed by expected output.The Harmony Search (HS) algorithm is based on the improvisation process of music.In comparison to other algorithms, the HSA has gain popularity and superiority in the field of evolutionary computation.When musicians compose the harmony through different possible combinations of the music, at that time the pitches are stored in the harmony memory and the optimization can be done by adjusting the input pitches and generate the perfect harmony.The test case generation process is used to identify test cases with resources and also identifies critical domain requirements.In this paper, the role of Harmony search meta-heuristic search technique is analyzed in generating random test data and optimized those test data.Test data are generated and optimized by applying in a case study i.e. a withdrawal task in Bank ATM through Harmony search.It is observed that this algorithm generates suitable test cases as well as test data and gives brief details about the Harmony search method.It is used for test data generation and optimization.