Thamotharan B^1,*, Venkatraman B², Chandrasekaran S³

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 335-340, 2020, DOI:10.31209/2019.100000156

Abstract Accumulation of impurities within cold trap device results in degradation of efficient performance in a nuclear reactor systems. The impurities have to be identified and the device has to be replaced periodically based on the accumulation level. Though there are a few techniques available to identify these impurities from the cold trap device, there are certain limitations in these techniques. In order to overcome these constraints, a new harmless and easy approach for identifying and separating the impurities using the radiographic images of cold traps is proposed in this paper. It includes a new segmentation algorithm to segregate the deposited… More >

Parvathavarthini S^1,*, Karthikeyani Visalakshi N², Shanthi S³, Madhan Mohan J⁴

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 253-260, 2020, DOI:10.31209/2019.100000155

Abstract Intuitionistic fuzzy clustering allows the uncertainties in data to be represented more precisely. Medical data usually possess a high degree of uncertainty and serve as the right candidate to be represented as Intuitionistic fuzzy sets. However, the selection of initial centroids plays a crucial role in determining the resulting cluster structure. Crow search algorithm is hybridized with Intuitionistic fuzzy C-means to attain better results than the existing hybrid algorithms. Still, the performance of the algorithm needs improvement with respect to the objective function and cluster indices especially with internal indices. In order to address these issues, the crow search algorithm… More >

S.Ilangovan^1,*, A. Vincent Antony Kumar²

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 261-268, 2020, DOI:10.31209/2019.100000154

Abstract In this work, a Novel Feature selection framework called SU embedded PSO Feature Selector has been proposed (SU-PSO) towards the selection of optimal feature subset for the improvement of detection performance of classifiers. The feature space ranking is done through the Symmetrical Uncertainty method. Further, memetic operators of PSO include features and remove features are used to choose relevant features and the best of best features are selected using PSO. The proposed feature selector efficiently removes not only irrelevant but also redundant features. Performance metric such as classification accuracy, subset of features selected and running time are used for comparison. More >

Ebtsam Adel¹, Shaker El-sappagh², Mohammed Elmogy³, Sherif Barakat¹, Kyung-Sup Kwak^4,*

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 237-251, 2020, DOI:10.31209/2019.100000151

Abstract Information technology is a beneficial tool for the healthcare industry. Health informatics is concerned with using ICT within the healthcare system. Different electronic health record (EHR) systems independently store large amounts of medical data in various structures and formats. Achieving semantic interoperability in EHR environments will improve the healthcare industry. In our previous studies, we proposed a framework that identifies the different heterogeneous medical data sources. In this paper, we move towards implementing the first module of that framework. We expect our framework to be a step towards improving performance and reducing both human mediation and data losses. More >

Bhavithra Janakiraman^1,*, Saradha Arumugam²

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 269-280, 2020, DOI:10.31209/2019.100000150

Abstract Personalization in recommendation system has been emerging as the most predominant area in service computing. Collaborative filtering and content based approaches are two major techniques applied for recommendation. However, to improve the accuracy and enhance user satisfaction, optimization techniques such as Ant Colony and Particle Swarm Optimization were analyzed in this paper. For theoretical analysis, this paper investigates web page recommender system. For experimentation, Diabetic patient’s health records were investigated and recommendation algorithms are applied to suggest appropriate nutrition for improving their health. Experiment result shows that Particle Swarm Optimization outperforms other traditional methods with improved performance and accuracy. More >

R.V.V. Krishna^1,*, S. Srinivas Kumar²

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 281-290, 2020, DOI:10.31209/2019.100000121

Abstract In this paper, a color image segmentation algorithm is proposed by extracting both texture and color features and applying them to the one -against-all multi class support vector machine (MSVM) classifier for segmentation. Local Binary Pattern is used for extracting the textural features and L*a*b color model is used for obtaining the color features. The MSVM is trained using the samples obtained from a novel soft rough fuzzy c-means (SRFCM) clustering. The fuzzy set based membership functions capably handle the problem of overlapping clusters. The lower and upper approximation concepts of rough sets deal well with uncertainty, vagueness, and incompleteness… More >

Detian Huang¹, Peiting Gu², Hsuan-Ming Feng^3,*, Yanming Lin¹, Lixin Zheng¹

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 313-322, 2020, DOI:10.31209/2019.100000105

Abstract To tackle the problem of illumination sensitive, scale variation, and occlusion in the Kernelized Correlation Filters (KCF) tracker, an improved robust tracking algorithm based on KCF is proposed. Firstly, the color attribute was introduced to represent the target, and the dimension of target features was reduced adaptively to obtain low-dimensional and illumination-insensitive target features with the locally linear embedding approach. Secondly, an effective appearance model updating strategy is designed, and then the appearance model can be adaptively updated according to the Peak-to-Sidelobe Ratio value. Finally, the low-dimensional color features and the HOG features are utilized to determine the target state… More >

Xin Liu^1,*, Yujuan Si^1,2, Di Wang¹

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 341-351, 2020, DOI:10.31209/2019.100000104

Abstract As a biological signal existing in the human living body, the electrocardiogram (ECG) contains abundantly personal information and fulfils the basic characteristics of identity recognition. It has been widely used in the field of individual identification research in recent years. The common process of identity recognition includes three steps: ECG signals preprocessing, feature extraction and processing, beat classification recognition. However, the existing ECG classification models are sensitive to limitations of database type and extracted features dimension, which makes classification accuracy difficult to improve and cannot meet the needs of practical applications. To tackle the problem, this paper proposes to build… More >

He Ni^1,*, Yongqiao Wang¹, Buyun Xu²

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 227-236, 2020, DOI:10.31209/2019.100000068

Abstract The paper presents a probabilistic clustering approach based on self-organizing learning algorithm and recursive Bayesian estimation. The model is built upon the principle that the market data space is multimodal and can be described by a mixture of Gaussian distributions. The model parameters are approximated by a stochastic recursive Bayesian learning: searches for the maximum a posterior solution at each step, stochastically updates model parameters using a “dualneighbourhood” function with adaptive simulated annealing, and applies profile likelihood confidence interval to avoid prolonged learning. The proposed model is based on a number of pioneer works, such as Mixture Gaussian Autoregressive Model,… More >

Omer Berat Sezer^*, Ahmet Murat Ozbayoglu

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 323-334, 2020, DOI:10.31209/2018.100000065

Abstract Even though computational intelligence techniques have been extensively utilized in financial trading systems, almost all developed models use the time series data for price prediction or identifying buy-sell points. However, in this study we decided to use 2-D stock bar chart images directly without introducing any additional time series associated with the underlying stock. We propose a novel algorithmic trading model CNN-BI (Convolutional Neural Network with Bar Images) using a 2-D Convolutional Neural Network. We generated 2-D images of sliding windows of 30-day bar charts for Dow 30 stocks and trained a deep Convolutional Neural Network (CNN) model for our… More >