Journal of Intelligent & Fuzzy Systems - Volume 32, issue 5

Authors: He, Luwei | Lu, Lu | Wang, Qiang

Article Type: Research Article

Abstract: Markov Clustering algorithm provides an effective method for network clustering problem, especially including community problem and bioinformatics. However, the expansion operation is the most time-consuming procedure, since the multiplication of two large-scale phalanxes can cause the time complexity of Θ (n3 ). Considering that each element value calculation is independent from others, expansion and inflation can be parallel-executed on the multi-core GPU. First, a basic parallel implementation of Markov Clustering which needs the whole adjacent matrix is proposed as a traditional method to improve the performance. In addition, the adjacent matrix is usually sparse and sometimes ultra-sparse. Hence, an optimal parallel …implementation working with the CSR*CSC multiplication has been developed, which significantly decreases the space needed to store the matrix and promotes the performance of the expansion to the extent. The experimental results show that Sparse-MCL is more effective than CPU-MCL and P-MCL when dealing with the big scale network. Show more

Keywords: MCL, GPU, sparse matrix, OpenCL

DOI: 10.3233/JIFS-169296

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3609-3617, 2017

Authors: Samuel, Avinash | Sharma, Dilip Kumar

Article Type: Research Article

Abstract: As the number of social networks users has increased day by day so has the user’s dependency for communication on the social networks. Social networks enable people to connect with one another in many different ways. Many social networks such as Twitter provide their users the functionality to tag the user’s current location to the post. This geographical information can be used in various information retrieval processes. Currently many methods are present which cluster the tweets using traditional K-means algorithm in which user has to specify the number of clusters to be formed, and if the tweets do not lie …within those clusters they are then treated as outliers and discarded. This paper presents a framework which focuses on clustering and indexing of tweets on the basis of its geographical and temporal features. The X-means clustering has been used which does not require the cluster number input from the user but rather it takes input from the index of the specified characteristics created from tweets. The indexing mechanism will not only help in ease of searching but will also aid in many retrieval tasks. The experimental analysis shows that the proposed framework generates improved results over traditional tweet clustering methods. Show more

Keywords: Tweet indexing, tweet clustering, microblog information retrieval

DOI: 10.3233/JIFS-169297

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3619-3632, 2017

Authors: Lu, Lu | Li, Cancan | Yang, Yubin

Article Type: Research Article

Abstract: With the development and popularization of virtualization technology, more and more enterprises tend to deploy applications to virtual machines, in order to reduce cost and improve the utilization rate of resources in the meantime. On the basis of the combination method of the comprehensive performance assessment of virtualization, this article aim to find a way to measure the performance percentage of the virtual machine against the physical machine percentage as a whole, which is built on the method of Fuzzy Analytic Hierarchy Process and the principle of maximizing deviations. According to the shortcoming of the Analytic Hierarchy Process, this article presents a way …to calculate weight of the functional layer elements based on the method of Fuzzy Analytic Hierarchy Process. The experimental results show that the conclusions drawn from the comprehensive performance evaluation method for virtualization are consistent with the experimental results. Show more

Keywords: Virtual machine, FAHP, maximizing deviation decision-making method, performance test, LoadRunner

DOI: 10.3233/JIFS-169298

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3633-3640, 2017

Authors: Sehgal, Priti | Goel, Nidhi

Article Type: Research Article

Abstract: Non-destructive techniques such as hyperspectral imaging, backscattering imaging are the advanced techniques used for predicting mechanical properties of horticulture products. They show relatively good performance but at the expense of costly measuring setups. This application-oriented paper investigates the feasibility of employing simple digital color camera imaging for prediction and fuzzy classification of firmness of tomatoes. Images acquired using digital color camera are preprocessed and subject to texture analysis in order to extract the number of features. The proposed approach exploits four texture feature extraction algorithms: three are based on statistical techniques viz. first order statistics (FOS), gray level co-occurrence matrix …(GLCM), gray level run length matrix (GLRLM), and one is based on transform-based technique viz. wavelet-transform. Out of all extracted features, redundant features are eliminated using various attribute selection methods. Subsequently, prediction models are built and analyzed using regression analysis. Sample space has been split into two sets; 80% training and 20% testing data having tomatoes with almost identical formation. Experimental results illustrates that RBF regression gave the lowest RMSE of 0.174 and highest prediction correlation coefficient of 0.929 for wavelet feature set. Grounded on the prediction model, fuzzy rule based classification (FRBC) is proposed to classify tomatoes into three firmness categories soft, medium, and hard. Accuracy statistics of the proposed FRBCS are compared with the state-of-the-art result and highest classification accuracy of 92.68% is achieved by proposed FRBCS. The results exhibit the possibility of using a digital color imaging system for firmness estimation and further for classification. Show more

Keywords: Image texture analysis, Tomato firmness, fuzzy rule based classification system, RBF regression, machinevision

DOI: 10.3233/JIFS-169299

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3641-3653, 2017

Authors: Li, Chen | Yang, Cheng | Jiang, Qin

Article Type: Research Article

Abstract: This paper proposed a cluster algorithm based on the combination of LDA (Latent Dirichlet allocation) probabilistic topic model and VSM (Vector Space Model), with the three-tier framework adopted containing text, topic and feature word. Although LDA alone has the ability to seek out the hidden topic knowledge, it is hard for the low-dimensional model to remain the integrity of the text information, leading to insufficient capacity for distinguishing texts. The paper is set to launch the cluster analysis in turns of feature words and topic through integrating two model above. With a better mix of LDA and VSM, the clustering effect will be …improved, paralleling determining the optimal clustering number K of the K-means algorithms and optimum topic number T of LDA model. In order to design the algorithms more scientifically and effectively, silhouette coefficient and Dunn coefficient have been brought in to make assessments. Show more

Keywords: Text cluster, LDA model, K-means algorithms, VSM model, silhouette coefficient, Dunn coefficient

DOI: 10.3233/JIFS-169300

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3655-3667, 2017

Authors: Mohan, Vijay | Rani, Asha | Singh, Vijander

Article Type: Research Article

Abstract: The main objective of the present work is to stabilize and maintain the angular position of Double Inverted Pendulum (DIP) system at desired position in presence of disturbances and noise. The system is highly coupled, nonlinear, complex and unstable, thereby making it difficult to control. Genetic algorithm tuned Fuzzy Controller (GFC) and adaptive Neuro-Fuzzy Controller (NFC) is proposed for the purpose, wherein the fuzzy parameters are optimized by genetic algorithm and artificial neural network respectively. The adaptive neuro-fuzzy control technique enjoys powerful learning capability of neural network, whereas genetic algorithm discovers the optimum solutions for the problem. Also a suitable …function is proposed for modifying training data set of neuro-fuzzy inference system that leads to Modified Neuro-Fuzzy Controller (MNFC). Linear Quadratic Regulator (LQR) and Fuzzy Logic Controllers (FLC) are also designed for comparative analysis. Intensive simulation studies are carried out to critically examine the performance of designed controllers on the basis of Integral Absolute Error (IAE), settling time, overshoot and steady state error for set-point tracking, disturbance rejection, noise suppression and simultaneous noise & disturbance rejection. The rigorous comparative analysis shows that MNFC exhibits fast and robust control of DIP system in comparison to designed controllers for all cases. Show more

Keywords: Double Inverted Pendulum (DIP), Fuzzy Logic Controller (FLC), Genetic Algorithm (GA), Linear Quadratic Regulator (LQR), GA Tuned Fuzzy Controller (GFC), Modified Neuro-Fuzzy Controller (MNFC)

DOI: 10.3233/JIFS-169301

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3669-3687, 2017

Authors: Allen, Allen D.

Article Type: Research Article

Abstract: Big data have revealed unexpected and statistically significant correlations along with intractable propositions. In order to address this development, an algorithm is introduced that is consistent with Ramsey’s theorem for pairs and Gödel’s incompleteness theorem. The algorithm assigns one of three truth values to a fuzzy proposition in order to update automatic theorem proving. A unique feature of the algorithm is an AI module that selects the multiple axiom sets needed for a proof. A metric for the AI module is the probability that the database of axiom sets is inadequate for the context. The importance of context is illustrated …by a simple analog electrical circuit applied to Fermat’s last theorem as contrasted with a similar exponential equation having positive real numbers for bases. Another algorithm or decision tree is introduced to differentiate risk factors from necessary conditions. A failure to recognize this distinction has impaired the public health sector for centuries and continues to do so. The second algorithm introduced here represents an effort to conserve science in general. The risk that big data pose for science is the misuse of positive, statistically significant correlations to infer causality when the correlations actually reflect risk factors or even rare coincidences. Show more

Keywords: Artificial intelligence, automatic theorem proving, big data, context awareness, knowledge acquisition

DOI: 10.3233/JIFS-169302

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3689-3694, 2017

Authors: Wang, Hua | Wen, Yingyou | Zhao, Dazhe

Article Type: Research Article

Abstract: In this paper, we study the problem of secure localization in Mobile Wireless Sensor Networks (MWSNs) where beacon nodes are not available. The location reference information is obtained from neighboring nodes within the commination rage of the target node, with the help of a relative location map. A Relative Location Map based Robust Positioning Algorithm (RLMRPA) for MWSNs is presented. The location estimate of the localizing node is formulated by constructing a distance measurement error model. Considering limited resources available, the steepest descent, which is fast and easy to implement, is employed to iteratively find the optimal solution. A 3- …Farthest Neighbors Trilateral Localization Algorithm (3FNTLA) is presented to find the initial position. Considering that malicious neighbors tend to cause larger distance measurement errors and the further the neighbor, the larger the measurement error, an attack-resistant distance residue method is developed to neutralize the impact of inconsistent measurements. Our experiments show that the RLMRPA can perform secure location determination, even with some neighbors aiming at making the localization failed. In addition, our simulation results also demonstrate that the RLMRPA is more resistant to attacks and achieves higher localization accuracy than existing methods. Show more

Keywords: Mobile wireless sensor networks, localization, threats, security

DOI: 10.3233/JIFS-169303

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3695-3710, 2017

Authors: Hasnat, Abul | Barman, Dibyendu | Halder, Santanu | Bhattacharjee, Debotosh

Article Type: Research Article

Abstract: The present work proposes a modified vector quantization algorithm to overcome the blocking artifacts problem of the conventional Vector Quantization (VQ) algorithm. Blocking artifacts affects visual appeal of the decompressed images. The Vector Quantization (VQ) algorithm is improvised where the blocking artifact does not appear in the decompressed image. The proposed algorithm is applied on luminance-chrominance color model where luminance channel is compressed using a novel approach. For the luminance channel, eight separate clusters are constructed using the k-means clustering algorithm then for each cluster, fuzzy intensification applied separately; next for each cluster training vectors are formed by taking sixteen …consecutive elements from a cluster to form one vector, next sixteen elements for second vector and so on. For each group of these training vectors, vector quantization is applied to generate the code vectors. For chrominance channels the conventional VQ algorithm is applied. At the time of decompression the reverse process is followed. The modified VQ algorithm has been applied on standard UCID v.2 image database and standard images found in literature where blocking artifacts problem is effectively solved. Experimental result shows that the proposed algorithm successfully avoids the blocking artefacts and the quality of the decompressed image is improved in terms of PSNR and vSNR compared to the conventional VQ algorithm. This article focuses on retaining more original information of the image rather than restoration of the decompressed image where blocking artifacts exists. Show more

Keywords: Lossy image compression, blocking artifacts, Vector Quantization, LBG, luminance, Kmeans clustering, fuzzy intensification, PSNR, vSNR

DOI: 10.3233/JIFS-169304

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3711-3727, 2017

Authors: Li, Cheng-Fan | Liu, Lan | Lei, Yong-Mei | Yin, Jing-Yuan | Zhao, Jun-juan | Sun, Xian-Kun

Article Type: Research Article

Abstract: Feature extraction from hyperspectral remote sensing data is an effective method for object classification, and how to classify the object information from hyperspectral remote sensing image has become one of the core technologies of the remote sensing application. Aiming at the characteristics of space modulated interference hyperspectral image (HSI) hyperspectral remote sensing image, in this article a new remote sensing clustering method is presented on the basis of analyzing the principal component analysis (PCA) and independent component analysis (ICA), which is able both to extract data’s independent features in terms on the second-order statistics and higher-order statistical information. The proposed …method classifies the HSI hyperspectral remote sensing image better than the traditional methods. Firstly, the definition of the feature weighting between PCA and ICA is used in order to calculate the weighted value. Then, similarity measure contains distance similarity and cosine similarity is introduced. Finally, the recognition rule is constructed to classify the hyperspectral remote sensing image. The true HSI hyperspectral remote sensing is used to evaluate the performance of our method. Experimental results indicate that the proposed clustering method outperforms traditional classification methods, and the classification accuracy reaches to 85% under certain conditions with the suitable number of eigenvectors is 12 and weighted values is 0.8. Meanwhile, the image quality of our method is well preserved. Show more

Keywords: Clustering, hyperspectral image, principal component analysis (PCA), independent component analysis (ICA), classification

DOI: 10.3233/JIFS-169305

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3729-3737, 2017

Authors: Lianqiang, Niu | Xin, Chen | Min, Peng | Gang, Zhang

Article Type: Research Article

Abstract: This paper presents an efficient run-based algorithm for labeling connected components in a binary image. By means of two tables called index table and equivalent information table respectively, the algorithm assign labels only to run sets which are composed of a series of runs connected to each other in adjacent scan rows, then the same index in equivalent information table can be assigned to all runs of a set in index table at one time. Further, the algorithm organizes all equivalence information in equivalent information table in a tree structure, and employee the union-find technique to merge connected components rapidly. …The algorithm is very simple, and fewer operations are needed to check and to label runs of a connected branch. Furthermore, it is not necessary to calculate the minimum label while combining two runs, and is able to construct a union-find tree with smaller height. Thus the algorithm is able to provide a high speed to label connected components for general images. Show more

Keywords: Connected components, union-find, labeling algorithm, label equivalent, run length encoding

DOI: 10.3233/JIFS-169306

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3739-3748, 2017

Authors: Zhang, Zhenhua | Hu, Yong | Ma, Chao | Xu, Jinhui | Yuan, Shenguo | Chen, Zhao

Article Type: Research Article

Abstract: By analyzing three parts of interval valued intuition fuzzy sets (IVIFS), we provide a novel framework constructing risk function with IVIFS information for risk analysis of outsourced software project. First, we introduced some risk factors of outsourced software project according to their hierarchical levels, and present a general risk function model. And then, some useful mathematical properties of this risk function are proved. Based on the mathematical properties of general risk function, all these presented specific risk functions are classified into four types: incentive function, punitive function, incentive-punitive function and equilibrium function. Especially, two kinds of incentive-punitive risk functions are …focused on and a construction method for them is proposed. Finally, an application example for the risk assessment of outsourced software project illustrates the use of this decision making method. The simulation results show that these functions are effective in risk prediction. Show more

Keywords: Interval valued intuitionistic fuzzy sets, risk assessment, incentive-punitive risk function, equilibrium risk function, outsourced software project

DOI: 10.3233/JIFS-169307

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3749-3760, 2017

Authors: Kumar, Tarun | Kushwaha, Dharmender Singh

Article Type: Research Article

Abstract: India has shown rapid economic development and this has forced the country to adopt smart traffic management and surveillance process. The intelligent traffic management and surveillance is the basic need for development of smart cities in India. The Intelligent traffic surveillance includes the detection of moving vehicles, estimation of their speed and extracting its registration number. This paper proposes an efficient and novel approach for the detection of moving vehicles as well as estimation of their speeds for detection of any speed limit violation by using a single camera in daylight or properly illuminated environment. The proposed approach detects and …tracks the vehicle passing through the surveillance area and maintains the record of vehicles position. The Region of Interest (ROI) of the approach is the dark shaded area formed under the vehicles road clearance area instead of the vehicles. The average detection accuracy achieved by proposed approach is 93.32%. This is on an average 7.54% higher than other existing approaches. The proposed approach uses cropping operation to minimize the scope of any false positive detection on both sides of road. The average tracking accuracy of the proposed approach is about 92.2%. The tracking accuracy achieved by the proposed approach is on an average 2.2% higher than the other leading approaches. The average speed estimation error in proposed approach is +2.2 km/h which is lower than other existing leading approaches. The proposed approach is also time and space efficient over the existing approaches. Show more

Keywords: Background subtraction, image filtering, thresholding, contours processing, camera calibration, moving object detection

DOI: 10.3233/JIFS-169308

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3761-3773, 2017

Authors: Wang, Bin | Kong, Bin | Ding, Dawen | Wang, Can | Yang, Jing

Article Type: Research Article

Abstract: In this paper, we have proposed a novel traffic sign recognition algorithm based on sparse representation and dictionary learning. In the past period of research and applications of traffic sign recognition, most of the traffic sign recognition algorithms are based on statistical learning, neural networks and template matching algorithm. In these algorithms, they need high-dimensional mapping during classification, resulting in huge amount of calculation. Meanwhile, when the external environment changes, such as illumination, deformation and occlusion, the recognition rate will be further reduced. The proposed sparse representation theory has much better performance to solve the problems of external environment changed …and while we use dictionary learning method to build a traffic sign over-complete redundant dictionary, the experimental results clearly showed that the algorithm we proposed has much better performance than traditional algorithm and also has much higher recognition rates. Show more

Keywords: Compressive sensing, sparse representation, traffic sign recognition, over-complete, dictionary learning

DOI: 10.3233/JIFS-169310

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3775-3784, 2017

Authors: Zhou, Guiliang | Liu, Zhiqiang | Shu, Wanneng | Bao, Tianwen | Mao, Lina | Wu, Dingxin | Feng-Qiu,

Article Type: Research Article

Abstract: Smart city relies on the smart transportation. And the smart savings on private car pooling based on internet of vehicles will greatly facilitate the expansion of smart transportation. The paper puts forward the smart savings scheme for private car pooling, establishes the dynamic relationship of human – vehicle – road during carpooling process basing on internet of vehicles. We applied the route recommendation technology, information matching technology, information notification technology, dynamic information searching technology and collaborative route optimization technology to the carpooling system to improve the real-time, accuracy and efficiency of carpooling process in uncertain dynamic demand market and realize …the smart savings on private car pooling. Finally, we take an area of Huai’an as example to verify the feasibility of the program and technologies. The experimental results show that the carpooling program (TCP) increased 40% on the private car seat utilization, saved 30.7% on the total travel cost and 38.4% on total travel time than the other existing carpooling program (TECP). Show more

Keywords: Internet of vehicles, private car pooling, smart savings, carpool program, carpooling technology research

DOI: 10.3233/JIFS-169311

Citation: Journal of Intelligent & Fuzzy Systems, vol. 32, no. 5, pp. 3785-3796, 2017