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 >

Supreet Kaur^*, Vijay Kumar Joshi

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 217-226, 2020, DOI:10.31209/2018.100000064

Abstract Wireless sensor networks (WSNs) are susceptible to safety threats due to cumulative dependence upon transmission, computing, and control mechanisms. Therefore, securing the end-to-end communication becomes a major area of research in WSNs. A majority of existing protocols are based upon signature and recommended-based trust evaluation techniques only. However, these techniques are vulnerable to wormhole attacks that happen due to lesser synchronization between the sensor nodes. Therefore, to handle this problem, a novel hybrid crossover-based ant colony optimization-based routing protocol is proposed. An integrated modified signature and recommendationbased trust evaluation protocol for WSNs is presented. Extensive experiments reveal that the proposed… More >

Uma K.V^1,*, Appavu alias Balamurugan S²

Intelligent Automation & Soft Computing, Vol.26, No.1, pp. 61-70, 2020, DOI:10.31209/2019.100000153

Abstract Real world data consists of lot of impurities. Entropy measure will help to handle impurities in a better way. Here, data selection is done by using Naïve Bayes’ theorem. The sample which has posterior probability value greater than that of the threshold value is selected. C5.0 decision tree classifier is taken as base and modified the Gain calculation function using Tsallis entropy and Association function. The proposed classifier model provides more accuracy and smaller tree for general and Medical dataset. Precision value obtained for Medical dataset is more than that of existing method. More >

PCD Kalaivaani^1,*, Dr. R Thangarajan²

Intelligent Automation & Soft Computing, Vol.26, No.1, pp. 71-79, 2020, DOI:10.31209/2019.100000152

Abstract Web mining is the process of integrating the information from web by traditional data mining methodologies and techniques. Opinion mining is an application of natural language processing to extract subjective information from web. Online reviews require efficient classification algorithms for analysing the sentiments, which does not perform an in–depth analysis in current methods. Sentiment classification is done at document level in combination with topics and sentiments. It is based on weakly supervised Joint Sentiment-Topic mode which extends the topic model Maximum Entropy Discrimination Latent Dirichlet Allocation by constructing an additional sentiment layer. It is assumed that topics generated are dependent… More >

Ayesha Hoor Chaudhry^*, Faisal Bukhari, Waheed Iqbal, Zubair Nawaz, Muhammad Kamran Malik

Intelligent Automation & Soft Computing, Vol.26, No.1, pp. 53-59, 2020, DOI:10.31209/2019.100000149

Abstract Laparoscopic surgery is a relatively new field in developing countries. There is a scarcity of laparoscopically trained doctors due to a lack of training and resources available in hospitals. Training and evaluation of medical professionals to develop laparoscopic surgical skills are important and essential as it improves the success rate and reduces the risk during real surgery. The purpose of this research is to develop a series of training exercises based on virtual reality using HTC Vive headset to emulate real-world training of doctors. This virtual training not only gives the trainee doctors mastery in their profession but also decreases… More >