Journal of Intelligent & Fuzzy Systems - Volume 35, issue 5

Authors: Al-Hitmi, M.A. | Kesraoui, Hichem | Rahman, Khaliqur | Iqbal, Atif

Article Type: Research Article

Abstract: Speed control of synchronous machines using Field Oriented Control (FOC) classically uses Proportional Integral (PI) or Integral Proportional (IP) regulators that allow to achieve satisfactory goals on the dynamics of speed and torque. However, the performance deteriorates with loss of one or more phases in multiphase machines with IP regulator. This paper present comparison between the use of IP regulator and Fuzzy Logic Regulator (FLR) under same conditions applied to Five Phase Permanent Magnet Synchronous Machine (FPSM). First, modeling and performance of the FPSM are presented. In the beginning, the control is ensured in healthy mode with an IP regulator …then in degraded mode when one then two phases are opened. The performances of the FLR are compared to IP ones. Better performance of FLR is established in terms of faster dynamics. Show more

Keywords: Five phase synchronous machine, open phase, fuzzy logic

DOI: 10.3233/JIFS-169802

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5185-5191, 2018

Authors: Bhatia, M.P.S. | Veenu, | Chandra, Pravin

Article Type: Research Article

Abstract: Weight initialization is the most important component which affects the performance of artificial neural network during training the network using Back-propagation algorithm. The initial starting weights have significant effect on the training. If the weights are too large then the sigmoid will saturate, that makes learning slow. If weights are too small then gradients are also too small. In this paper a new weight initialization method has been proposed. The results for the proposed weight initialization technique are compared against the random weight initialization method. In this paper the proposed weight initialization method is statistically analyzed. Ten different data sets …out of which five sets of data are taken from UCI machine learning repository and five sets of data are generated using function approximation problems that are used. Resilient Back Propagation training algorithm is used for training the feed forward artificial neural network. The proposed weight initialization method gives better results when compared with random weight initialization technique. Show more

Keywords: Feed forward artificial neural network - FFANN, Back propagation algorithm - BP, Gradient descent — gd, Weight initialization — WI, Random numbers — rand

DOI: 10.3233/JIFS-169803

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5193-5201, 2018

Authors: Sharma, Rashmi | Saha, Anju

Article Type: Research Article

Abstract: Software testing contributes a strategic role in software development, as it underrates the cost of software development. Software testing can be categorized as: testing via code or white box testing, testing via specification or black box and testing via UML models. To minimize the issues associated with object-oriented software testing, testing via UML models is used. It is a procedure which derives test paths from a Unified Modelling Language (UML) model which describes the functional aspects of Software Under Test (SUT). Thus, test cases have been produced in the design phase itself, which then reduces the corresponding cost and effort …of software development. This early discovery of faults makes the life of software developer much easier. Also, there is a strong need to optimize the generated test cases. The main goal of optimization is to spawn reduced and unique test cases. To accomplish the same, in this research, a nature-inspired meta-heuristic, Moth Flame Optimization Algorithm has been offered for model based testing of software based on object orientation. Also, the generated test cases have been compared with already explored meta-heuristics, namely, Firefly Algorithm and Ant Colony Optimization Algorithm. The outcomes infer that for large object-oriented software application, Moth Flame Optimization Algorithm creates optimized test cases as equated to other algorithms. Show more

Keywords: Ant Colony Optimization, cuckoo search algorithm, firefly algorithm, genetic algorithm, moth flame algorithm, meta-heuristics, object-oriented, state transition diagram

DOI: 10.3233/JIFS-169804

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5203-5215, 2018

Authors: Joshi, Bhagawati Prasad | Kumar, Abhay | Singh, Akhilesh | Bhatt, Pradeep Kumar | Bharti, Bhupender Kumar

Article Type: Research Article

Abstract: This paper presents the opinion of intuitionistic fuzzy parameterized fuzzy soft set (IFP-FS set) by considering the images of approximate function in the fuzzy subsets of the set of universe of discourse rather than to a crisp subset. Some of the desired operations and relations of IFP-FS set are also considered in this study. A decision making approach based on the proposed IFP-FS set is used. Finally, an example is conducted which illustrates that the proposed approach can be use for many real life problems that include ambiguities and uncertainties.

Keywords: Soft-set’s, fuzzy sets (FSs), intuitionistic fuzzy sets (IFSs), intuitionistic FP-soft set

DOI: 10.3233/JIFS-169805

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5217-5223, 2018

Authors: Joshi, Bhagawati Prasad | Singh, Akhilesh | Bhatt, Pradeep Kumar | Vaisla, Kunwar Singh

Article Type: Research Article

Abstract: Yager [1 ] introduced the concept of q- rung orthopair fuzzy sets (q- ROFSs) in which the sum of the q th exponent of the support for membership and the q th exponent of the support against membership is bounded by one. Thus, the q- ROFSs are an important way to express uncertain information in broader space, and they are superior to the intuitionistic fuzzy sets (IFSs) and the Pythagorean fuzzy sets (PFSs). However, in dealing with many real life situations, it is not appropriate for experts to precisely quantify their judgements with a crisp number due to …insufficiency in available information. In such situation it is advisable for decision makers to provide their judgements by the subset of the closed interval [0, 1]. The notion of interval-valued q- rung orthopair fuzzy sets (IVq- ROFSs) is presented in this paper, which allows decision makers to provide their satisfying degrees and non-satisfying degrees to a given set of alternatives by an interval value. Some of its important operations such as: negation, union and intersection are also given. Based on these operations, the aggregation of IVq- ROFSs is also studied. Show more

Keywords: Intuitionistic fuzzy set (IFS), q-rung orthopair fuzzy set, interval-valued, aggregation operator

DOI: 10.3233/JIFS-169806

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5225-5230, 2018

Authors: Anagha, P. | Balasundaram, S. | Meena, Yogendra

Article Type: Research Article

Abstract: Construction of robust regression learning models to fit training data corrupted by noise is an important and challenging research problem in machine learning. It is well-known that loss functions play an important role in reducing the effect of noise present in the input data. With the objective of obtaining a robust regression model, motivated by the link between the pinball loss and quantile regression, a novel squared pinball loss twin support vector machine for regression (SPTSVR) is proposed in this work. Further with the introduction of a regularization term, our proposed model solves a pair of strongly convex minimization problems …having unique solutions by simple functional iterative method. Experiments were performed on synthetic datasets with different noise models and on real world datasets and those results were compared with support vector regression (SVR), least squares support vector regression (LS-SVR) and twin support vector regression (TSVR) methods. The comparative results clearly show that our proposed SPTSVR is an effective and a useful addition in the machine learning literature. Show more

Keywords: Kernel methods, pinball loss, robust support vector regression

DOI: 10.3233/JIFS-169807

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5231-5239, 2018

Authors: Prakash, Choudhary Shyam | Maheshkar, Sushila | Maheshkar, Vikas

Article Type: Research Article

Abstract: Copy-move forgery is one of the famous manipulation technique in digital image. Many block-based techniques have been proposed previously for forgery detection, but most of them have higher computational complexity due to higher number of feature vectors dimension. In this paper, we have tried to reduce the feature vectors dimension. This paper proposes a copy-move forgery detection (CMFD) technique based on circular blocks and discrete cosine transform (DCT) with fewer feature vectors than the prevalent methods. Initially an input image is taken and divided into overlapping blocks. To extract the features from each block, DCT transformation is used on each …block. Then, these features are represented using a circle block to reduce the feature vectors dimension. The extracted feature vectors are then used for matching process to locate the manipulated regions. Experimental results depict the performance of the proposed method and robustness against the post-processing operations. The computational complexity of the proposed method is lower than the existing techniques due to fewer feature vectors dimension. Show more

Keywords: Forensic science, image forensic, forensics photography, regionduplication detection, copy-move forgery.

DOI: 10.3233/JIFS-169808

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5241-5253, 2018

Authors: Arora, Jyoti | Tushir, Meena

Article Type: Research Article

Abstract: Numerous Fuzzy segmentation techniques have been proposed in the literature for Image segmentation. This paper proposes a new Novel Intuitionistic Fuzzy C-means (S-IFCM) incorporated with Spatial information to reduce noise/outliers influence. This new clustering algorithm uses City-block distance to compute the rank between two pixels. Yager’s type fuzzy complement is used to compute non-membership and further hesitation degree is calculated. The new intuitionistic membership obtained is incorporated with spatial information of image for robustness to noise. Experiments are performed on various noisy images including MRI brain image, to assess the performance of the proposed algorithm. Comparison is done with existing …hard, fuzzy and intuitionistic methods on the basis of entropy based segmentation accuracy and validity index. Experimental results show the effectiveness of the proposed method in contrast with other conventional methods. Show more

Keywords: K-means, fuzzy C-means, spatial fuzzy C-means, robust intuitionistic fuzzy C-means

DOI: 10.3233/JIFS-169809

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5255-5264, 2018

Authors: Yadav, Jyotsna | Rajpal, Navin | Mehta, Rajesh

Article Type: Research Article

Abstract: Invariant feature extraction under diverse illuminations is challenging for face recognition. Related face recognition techniques consider that illumination effect is predominant in low frequencies and involve various methods to segregate high frequency information. However, high frequency feature extraction results in loss of salient features that degrades performance. Thus, objective of this work is to extract illumination normalized robust facial features for face recognition under high illumination conditions. First, a new illumination normalization framework is proposed in which homomorphic filtering (HF) is applied for reducing illumination effect along with contrast enhancement and intensity range compression in face images. Then, illumination deviations …are annulled by using reflectance ratio (RR), which yields appropriate texture smoothing and edge preservation. Further, selective feature extraction by discrete wavelet transform (DWT) is performed on HF and RR based face images that discards noise effect. It outcomes in illumination normalized significant facial features, on which subspace analysis (Principal component analysis) is performed to generate small size feature vectors for classification (k-nearest neighbour classifier). Experimental results on benchmark databases such as CMU-PIE, Yale B and Extended Yale B database, demonstrates that proposed face recognition technique yields high performance under diverse illuminations as compared to existing techniques. Show more

Keywords: Face recognition, homomorphic filtering, illumination normalization, reflectance ratio, selective feature extraction

DOI: 10.3233/JIFS-169810

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5265-5277, 2018

Authors: Lamba, Puneet Singh | Virmani, Deepali

Article Type: Research Article

Abstract: Eye blink is a semi-autonomic rapid closing of eyelid. Eye blink is controlled by the autonomic nervous system of human brain. This normal and most important function of human eye can be embedded with some created (abnormal) sequences to indicate any unusual message. In this paper, a real time novel algorithm to reckon number of eye blinks (RT REB) in a video sequence using eye facet correlation (EFC) is proposed. The proposed RT REB approximates the eye landmark positions using EFC- an extricate variable value of eyelids clearly differentiating between opened and closed eyelid in a frame of a video …sequence. The proposed RT REB is classified with existing classifiers SVM, QSVM, KNN and DTREE. Increased accuracy to 99.8% validates the effectiveness and correctness of RT REB. Show more

Keywords: EFC, eye blink, landmark detector, ZJU

DOI: 10.3233/JIFS-169811

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5279-5286, 2018