International Journal of Computer and Applications

The statistical approach

Heart diseases are highly ranked among the leading causes of mortality in the world. They have various types including vascular, ischemic, and hypertensive heart disease. A large number of medical features are reported for patients in the Electronic Health Records (EHR) that allow physicians to diagnose and monitor heart disease. We collected a dataset from Medica Norte Hospital in Mexico that includes 800 records and 141 indicators such as age, weight, glucose, blood pressure rate, and clinical symptoms. Distribution of the collected records is very unbalanced on the different types of heart disease, where 17% of records have hypertensive heart disease, 16% of records have ischemic heart disease, 7% of records have mixed heart disease, and 8% of records have valvular heart disease. Herein, we propose an ensemble-learning framework of different neural network models, and a method of aggregating random under-sampling. To improve the performance of the classification algorithms, we implement a data preprocessing step with features selection. Experiments were conducted with unidirectional and bidirectional neural network models and results showed that an ensemble classifier with a BiLSTM or BiGRU model with a CNN model had the best classification performance with accuracy and F1-score between 91% and 96% for the different types of heart disease. These results are competitive and promising for heart disease dataset. We showed that ensemble-learning framework based on deep models could overcome the problem of classifying an unbalanced heart disease dataset. Our proposed framework can lead to highly accurate models that are adapted for clinical real data and diagnosis use.

Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

An enhanced hybrid arithmetic optimization algorithm for engineering applications

This paper introduces a robust model predictive controller (MPC) to operate an automatic voltage regulator (AVR). The design strategy tends to handle the uncertainty issue of the AVR parameters. Frequency domain conditions are derived from the Hermite–Biehler theorem to maintain the stability of the perturbed system. The tuning of the MPC parameters is performed based on a new evolutionary algorithm named arithmetic optimization algorithm (AOA), while the expert designers use trial and error methods to achieve this target. The stability constraints are handled during the tuning process. An effective time-domain objective is formulated to guarantee good performance for the AVR by minimizing the voltage maximum overshoot and the response settling time simultaneously. The results of the suggested AOA-based robust MPC are compared with various techniques in the literature. The system response demonstrates the effectiveness and robustness of the proposed strategy with low control effort against the voltage variations and the parameters’ uncertainty compared with other techniques.

Robust Model Predictive Control Paradigm for Automatic Voltage Regulators against Uncertainty Based on Optimization Algorithms

Feature selection is a well-known prepossessing procedure, and it is considered a challenging problem in many domains, such as data mining, text mining, medicine, biology, public health, image processing, data clustering, and others. This paper proposes a novel feature selection method, called AOAGA, using an improved metaheuristic optimization method that combines the conventional Arithmetic Optimization Algorithm (AOA) with the Genetic Algorithm (GA) operators. The AOA is a recently proposed optimizer; it has been employed to solve several benchmark and engineering problems and has shown a promising performance. The main aim behind the modification of the AOA is to enhance its search strategies. The conventional version suffers from weaknesses, the local search strategy, and the trade-off between the search strategies. Therefore, the operators of the GA can overcome the shortcomings of the conventional AOA. The proposed AOAGA was evaluated with several well-known benchmark datasets, using several standard evaluation criteria, namely accuracy, number of selected features, and fitness function. Finally, the results were compared with the state-of-the-art techniques to prove the performance of the proposed AOAGA method. Moreover, to further assess the performance of the proposed AOAGA method, two real-world problems containing gene datasets were used. The findings of this paper illustrated that the proposed AOAGA method finds new best solutions for several test cases, and it got promising results compared to other comparative methods published in the literature.

Boosting Arithmetic Optimization Algorithm with Genetic Algorithm Operators for Feature Selection: Case Study on Cox Proportional Hazards Model

Improved seagull optimization algorithm using Lévy flight and mutation operator for feature selection

This paper proposes a self-adaptive Equilibrium Optimizer (self-EO) to perform better global, combinatorial, engineering, and multi-objective optimization problems. The new self-EO algorithm integrates four effective exploring phases, which address the potential shortcomings of the original EO. We validate the performances of the proposed algorithm over a large spectrum of optimization problems, i.e., ten functions of the CEC’20 benchmark, three engineering optimization problems, two combinatorial optimization problems, and three multi-objective problems. We compare the self-EO results to those obtained with nine other metaheuristic algorithms (MAs), including the original EO. We employ different metrics to analyze the results thoroughly. The self-EO analyses suggest that the self-EO algorithm has a greater ability to locate the optimal region, a better trade-off between exploring and exploiting mechanisms, and a faster convergence rate to (near)-optimal solutions than other algorithms. Indeed, the self-EO algorithm reaches better results than the other algorithms for most of the tested functions. • An enhanced algorithm called the self-EO that employs three strategies is proposed. • Self-EO efficiency and performance are verified on several benchmarks. • CEC’20 suite and 3 engineering problems are used for algorithm validation. • Two combinatorial problems, and ten CEC’20 multi-objective problems are solved. • Self-EO performance is analyzed with many metrics and compared to 30 algorithms. 

Self-adaptive Equilibrium Optimizer for solving global, combinatorial, engineering, and Multi-Objective problems

Current research on computer-aided diagnosis (CAD) of liver cancer is based on traditional feature engineering methods, which have several drawbacks including redundant features and high computational cost. Recent deep learning models overcome these problems by implicitly capturing intricate structures from large-scale medical image data. However, they are still affected by network hyperparameters and topology. Hence, the state of the art in this area can be further optimized by integrating bio-inspired concepts into deep learning models. This work proposes a novel bio-inspired deep learning approach for optimizing predictive results of liver cancer. This approach contributes to the literature in two ways. Firstly, a novel hybrid segmentation algorithm is proposed to extract liver lesions from computed tomography (CT) images using SegNet network, UNet network, and artificial bee colony optimization (ABC), namely, SegNet-UNet-ABC. This algorithm uses the SegNet for separating liver from the abdominal CT scan, then the UNet is used to extract lesions from the liver. In parallel, the ABC algorithm is hybridized with each network to tune its hyperparameters, as they highly affect the segmentation performance. Secondly, a hybrid algorithm of the LeNet-5 model and ABC algorithm, namely, LeNet-5/ABC, is proposed as feature extractor and classifier of liver lesions. The LeNet-5/ABC algorithm uses the ABC to select the optimal topology for constructing the LeNet-5 network, as network structure affects learning time and classification accuracy. For assessing performance of the two proposed algorithms, comparisons have been made to the state-of-the-art algorithms on liver lesion segmentation and classification. The results reveal that the SegNet-UNet-ABC is superior to other compared algorithms regarding Jaccard index, Dice index, correlation coefficient, and convergence time. Moreover, the LeNet-5/ABC algorithm outperforms other algorithms regarding specificity, F1-score, accuracy, and computational time.

A Novel Bio-Inspired Deep Learning Approach for Liver Cancer Diagnosis

Biodiesel is considered to be a promising alternative option to diesel fuel. The main contribution of the current work is to improve compression ignition engine performance, fueled by several biodiesel blends. Three metrics were used to evaluate the output performance of the compression ignition engine, as follows: brake torque (BT), brake specific fuel consumption (BSFC), and brake thermal efficiency (BTE), by varying two input parameters (engine speed and fuel type). The engine speeds were in the 1200–2400 rpm range. Three biodiesel blends, containing 20 vol.% of vegetable oil and 80 vol.% of pure diesel fuel, were prepared and tested. In all the experiments, pure diesel fuel was employed as a reference for all biodiesel blends. The experimental results revealed the following findings: although all types of biodiesel blends have low calorific value and slightly high viscosity, as compared to pure diesel fuel, there was an improvement in both BT and brake power (BP) outputs. An increase in BSFC by 7.4%, 4.9%, and 2.5% was obtained for palm, sunflower, and corn biodiesel blends, respectively, as compared to that of pure diesel. The BTE of the palm oil biodiesel blend was the lowest among other biodiesel blends. The suggested work strategy includes two stages (modeling and parameter optimization). In the first stage, a robust fuzzy model is created, depending on the experimental results, to simulate the output performance of the compression ignition engine. The particle swarm optimization (PSO) algorithm is used in the second stage to determine the optimal operating parameters. To confirm the distinction of the proposed strategy, the obtained outcomes were compared to those attained by response surface methodology (RSM). The coefficient of determination (R2) and the root-mean-square-error (RMSE) were used as comparison metrics. The average R2 was increased by 27.7% and 29.3% for training and testing, respectively, based on the fuzzy model. Using the proposed strategy in this work (integration between fuzzy logic and PSO) may increase the overall performance of the compression ignition engine by 2.065% and 8.256%, as concluded from the experimental tests and RSM.

https://www.mdpi.com/2227-7390/10/3/420/pdf?version=1644568621

Rania M. Ghoniem

Papers

Boosting Arithmetic Optimization Algorithm with Genetic Algorithm Operators for Feature Selection: Case Study on Cox Proportional Hazards Model

Improved seagull optimization algorithm using Lévy flight and mutation operator for feature selection

Self-adaptive Equilibrium Optimizer for solving global, combinatorial, engineering, and Multi-Objective problems

A Novel Bio-Inspired Deep Learning Approach for Liver Cancer Diagnosis

Modeling and Optimization of a Compression Ignition Engine Fueled with Biodiesel Blends for Performance Improvement