Digital Library

Vol. 13, No. 2, Apr. 2017  

1. [EDITORIAL] Advances in Algorithm, Multimedia, and Network for Future IT
   Jong Hyuk Park
   Vol. 13, No. 2, pp. 197-203, Apr. 2017  
   https://doi.org/10.3745/JIPS.00.0004
   Details
   Keywords:
   Show / Hide Abstract

   The Journal of Information Processing Systems (JIPS) is the official international journal of the Korea Information Processing Society (KIPS). As a leading and multidisciplinary journal, JIPS is indexed in ESCI (Emerging Sources Citation Index), SCOPUS, EI COMPENDEX, DOI, DBLP, EBSCO, Google Scholar, and CrossRef. As information processing systems continue to progress at a rapid pace, KIPS is committed to providing researchers and other professionals with the academic information and resources they need to keep abreast of these ongoing developments. JIPS aims to be a leading source that enables researchers and professionals all over the world to promote, share, and discuss all of the major research issues and developments in the field of information processing systems and other related fields


2. Deep Learning in Genomic and Medical Image Data Analysis: Challenges and Approaches
   Ning Yu, Zeng Yu, Feng Gu, Tianrui Li, Xinmin Tian, Yi Pan
   Vol. 13, No. 2, pp. 204-214, Apr. 2017  
   https://doi.org/10.3745/JIPS.04.0029
   Details
   Keywords: Bioinformatics, Deep Learning, Deep Neural Networks, DNA Genome Analysis, Image Data Analysis, Machine Learning, lincRNA
   Show / Hide Abstract

   Artificial intelligence, especially deep learning technology, is penetrating the majority of research areas, including the field of bioinformatics. However, deep learning has some limitations, such as the complexity of parameter tuning, architecture design, and so forth. In this study, we analyze these issues and challenges in regards to its applications in bioinformatics, particularly genomic analysis and medical image analytics, and give the corresponding approaches and solutions. Although these solutions are mostly rule of thumb, they can effectively handle the issues connected to training learning machines. As such, we explore the tendency of deep learning technology by examining several directions, such as automation, scalability, individuality, mobility, integration, and intelligence warehousing.


3. A Hybrid Bacterial Foraging Optimization Algorithm and a Radial Basic Function Network for Image Classification
   Yasmina Teldja Amghar, Hadria Fizazi
   Vol. 13, No. 2, pp. 215-235, Apr. 2017  
   https://doi.org/10.3745/JIPS.01.0014
   Details
   Keywords: Bacterial Foraging Optimization Algorithm, Hybrid, Image Classification, Radial Basic Function
   Show / Hide Abstract

   Foraging is a biological process, where a bacterium moves to search for nutriments, and avoids harmful substances. This paper proposes a hybrid approach integrating the bacterial foraging optimization algorithm (BFOA) in a radial basis function neural network, applied to image classification, in order to improve the classification rate and the objective function value. At the beginning, the proposed approach is presented and described. Then its performance is studied with an accent on the variation of the number of bacteria in the population, the number of reproduction steps, the number of elimination-dispersal steps and the number of chemotactic steps of bacteria. By using various values of BFOA parameters, and after different tests, it is found that the proposed hybrid approach is very robust and efficient for several-image classification


4. Mobility Scenarios into Future Wireless Access Network
   Syed Mushhad Mustuzhar Gilani, Tang Hong, Qiqi Cai, Guofeng Zhao
   Vol. 13, No. 2, pp. 236-255, Apr. 2017  
   https://doi.org/10.3745/JIPS.03.0069
   Details
   Keywords: Access Point (AP), Internet Architecture, Network Function Virtualization (NFV), Seamless Handover, Software-Defined Network (SDN)
   Show / Hide Abstract

   The rapid growth of smart devices demands an enhanced throughput for network connection sustainability during mobility. However, traditional wireless network architecture suffers from mobility management issues. In order to resolve the traditional mobility management issues, we propose a novel architecture for future wireless access network based on software-defined network (SDN) by using the advantage of network function virtualization (NFV). In this paper, network selection approach (NSA) has been introduced for mobility management that comprises of acquiring the information of the underlying networking devices through the OpenFlow controller, percepts the current network behavior and later the selection of an appropriate action or network. Furthermore, mobility-related scenarios and use cases to analyze the implementation aspects of the proposed architecture are provided. The simulation results confirm that the proposed scenarios have obtained a seamless mobility with enhanced throughput at minimum packet loss as compared to the existing IEEE 802.11 wireless network.


5. An Improved Stereo Matching Algorithm with Robustness to Noise Based on Adaptive Support Weight
   Ingyu Lee, Byungin Moon
   Vol. 13, No. 2, pp. 256-267, Apr. 2017  
   https://doi.org/10.3745/JIPS.02.0057
   Details
   Keywords: Adaptive Census Transform, Adaptive Support Weight, Local Matching, Multiple Sparse Windows, Stereo Matching
   Show / Hide Abstract

   An active research area in computer vision, stereo matching is aimed at obtaining three-dimensional (3D) information from a stereo image pair captured by a stereo camera. To extract accurate 3D information, a number of studies have examined stereo matching algorithms that employ adaptive support weight. Among them, the adaptive census transform (ACT) algorithm has yielded a relatively strong matching capability. The drawbacks of the ACT, however, are that it produces low matching accuracy at the border of an object and is vulnerable to noise. To mitigate these drawbacks, this paper proposes and analyzes the features of an improved stereo matching algorithm that not only enhances matching accuracy but also is also robust to noise. The proposed algorithm, based on the ACT, adopts the truncated absolute difference and the multiple sparse windows method. The experimental results show that compared to the ACT, the proposed algorithm reduces the average error rate of depth maps on Middlebury dataset images by as much as 2% and that is has a strong robustness to noise.


6. Dorsal Hand Vein Identification Based on Binary Particle Swarm Optimization
   Sarah Hachemi Benziane, Abdelkader Benyettou
   Vol. 13, No. 2, pp. 268-283, Apr. 2017  
   https://doi.org/10.3745/JIPS.03.0066
   Details
   Keywords: biometrics, BPSO, GPU, Hand Vein, identification, OTSU
   Show / Hide Abstract

   The dorsal hand vein biometric system developed has a main objective and specific targets; to get an electronic signature using a secure signature device. In this paper, we present our signature device with its different aims; respectively: The extraction of the dorsal veins from the images that were acquired through an infrared device. For each identification, we need the representation of the veins in the form of shape descriptors, which are invariant to translation, rotation and scaling; this extracted descriptor vector is the input of the matching step. The optimization decision system settings match the choice of threshold that allows accepting/rejecting a person, and selection of the most relevant descriptors, to minimize both FAR and FRR errors. The final decision for identification based descriptors selected by the PSO hybrid binary give a FAR =0% and FRR=0% as results.


7. DTG Big Data Analysis for Fuel Consumption Estimation
   Wonhee Cho, Eunmi Choi
   Vol. 13, No. 2, pp. 285-304, Apr. 2017  
   https://doi.org/10.3745/JIPS.04.0031
   Details
   Keywords: Big Data Analysis, DTG, Eco-Driving, Fuel Economy, Fuel Consumption Estimation, MapReduce
   Show / Hide Abstract

   Big data information and pattern analysis have applications in many industrial sectors. To reduce energy consumption effectively, the eco-driving method that reduces the fuel consumption of vehicles has recently come under scrutiny. Using big data on commercial vehicles obtained from digital tachographs (DTGs), it is possible not only to aid traffic safety but also improve eco-driving. In this study, we estimate fuel consumption efficiency by processing and analyzing DTG big data for commercial vehicles using parallel processing with the MapReduce mechanism. Compared to the conventional measurement of fuel consumption using the On-Board Diagnostics II (OBD-II) device, in this paper, we use actual DTG data and OBD-II fuel consumption data to identify meaningful relationships to calculate fuel efficiency rates. Based on the driving pattern extracted from DTG data, estimating fuel consumption is possible by analyzing driving patterns obtained only from DTG big data.


8. Self-adaptive and Bidirectional Dynamic Subset Selection Algorithm for Digital Image Correlation
   Wenzhuo Zhang, Rong Zhou, Yuanwen Zou
   Vol. 13, No. 2, pp. 305-320, Apr. 2017  
   https://doi.org/10.3745/JIPS.02.0056
   Details
   Keywords: Digital Image Correlation, Dynamic Subset Size, Image Processing, Information Amount, Self-Adaptive
   Show / Hide Abstract

   The selection of subset size is of great importance to the accuracy of digital image correlation (DIC). In the traditional DIC, a constant subset size is used for computing the entire image, which overlooks the differences among local speckle patterns of the image. Besides, it is very laborious to find the optimal global subset size of a speckle image. In this paper, a self-adaptive and bidirectional dynamic subset selection (SBDSS) algorithm is proposed to make the subset sizes vary according to their local speckle patterns, which ensures that every subset size is suitable and optimal. The sum of subset intensity variation (?) is defined as the assessment criterion to quantify the subset information. Both the threshold and initial guess of subset size in the SBDSS algorithm are self-adaptive to different images. To analyze the performance of the proposed algorithm, both numerical and laboratory experiments were performed. In the numerical experiments, images with different speckle distribution, different deformation and noise were calculated by both the traditional DIC and the proposed algorithm. The results demonstrate that the proposed algorithm achieves higher accuracy than the traditional DIC. Laboratory experiments performed on a substrate also demonstrate that the proposed algorithm is effective in selecting appropriate subset size for each point.


9. A Multi-Objective TRIBES/OC-SVM Approach for the Extraction of Areas of Interest from Satellite Images
   Wafaa Benhabib, Hadria Fizazi
   Vol. 13, No. 2, pp. 321-339, Apr. 2017  
   https://doi.org/10.3745/JIPS.02.0054
   Details
   Keywords: Image Classification, MO-TRIBES, OC-SVM, Remote Sensing
   Show / Hide Abstract

   In this work, we are interested in the extraction of areas of interest from satellite images by introducing a MOTRIBES/OC-SVM approach. The One-Class Support Vector Machine (OC-SVM) is based on the estimation of a support that includes training data. It identifies areas of interest without including other classes from the scene. We propose generating optimal training data using the Multi-Objective TRIBES (MO-TRIBES) to improve the performances of the OC-SVM. The MO-TRIBES is a parameter-free optimization technique that manages the search space in tribes composed of agents. It makes different behavioral and structural adaptations to minimize the false positive and false negative rates of the OC-SVM. We have applied our proposed approach for the extraction of earthquakes and urban areas. The experimental results and comparisons with different state-of-the-art classifiers confirm the efficiency and the robustness of the proposed approach.


10. Discrete Wavelet Transform and a Singular Value Decomposition Technique for Watermarking Based on an Adaptive Fuzzy Inference System
    Salima Lalani, D. D. Doye
    Vol. 13, No. 2, pp. 340-347, Apr. 2017  
    https://doi.org/10.3745/JIPS.03.0067
    Details
    Keywords: DWT, Fuzzy, SVD, watermarking
    Show / Hide Abstract

    A watermark is a signal added to the original signal in order to preserve the copyright of the owner of the digital content. The basic challenge for designing a watermarking system is a dilemma between transparency and robustness. If we want a higher rate of transparency, there has to be a compromise in terms of its robustness and vice versa. Also, until now, watermarking is generalized, resulting in the need for a specialized algorithm to work for a specialized image processing application domain. Our proposed technique takes into consideration the image characteristics for watermark insertion and it optimizes transparency and robustness. It achieved a 99.98% retrieval efficiency for an image blurring attack and counterfeits other attacks. Our proposed technique counterfeits almost all of the image processing attacks.


11. Design of Real-Time CAN Framework Based on Plug and Play Functionality
    Sungheo Kim, Kwang-il Hwang
    Vol. 13, No. 2, pp. 348-359, Apr. 2017  
    https://doi.org/10.3745/JIPS.03.0071
    Details
    Keywords: Controller Area Networks, Plug and Play, real-time
    Show / Hide Abstract

    Nowadays most vehicles are equipped with a variety of electronic devices to improve user convenience as well as its performance itself. In order to efficiently interconnect these devices with each other, Controller Area Network (CAN) is commonly used. However, the CAN requires reconfiguration of the entire network when a new device, which is capable of supporting both of transmission and reception of data, is added to the existing network. In addition, since CAN is based on the collision avoidance using address priority, it is difficult that a new node is assigned high priority and eventually it results in transmission delay of the entire network. Therefore, in this paper we propose a new system component, called CAN coordinator, and design a new CAN framework capable of supporting plug and play functionality. Through experiments, we also prove that the proposed framework can improve real-time ability based on plug and play functionality.


12. Block Sparse Signals Recovery via Block BacktrackingBased Matching Pursuit Method
    Rui Qi, Yujie Zhang, Hongwei Li
    Vol. 13, No. 2, pp. 360-369, Apr. 2017  
    https://doi.org/10.3745/JIPS.04.0030
    Details
    Keywords: Block Sparse Signal, Compressed Sensing, Sparse Signal Reconstruction
    Show / Hide Abstract

    In this paper, a new iterative algorithm for reconstructing block sparse signals, called block backtrackingbased adaptive orthogonal matching pursuit (BBAOMP) method, is proposed. Compared with existing methods, the BBAOMP method can bring some flexibility between computational complexity and reconstruction property by using the backtracking step. Another outstanding advantage of BBAOMP algorithm is that it can be done without another information of signal sparsity. Several experiments illustrate that the BBAOMP algorithm occupies certain superiority in terms of probability of exact reconstruction and running time.


13. Unsupervised Segmentation of Images Based on Shuffled Frog-Leaping Algorithm
    Amel Tehami*, Hadria Fizazi
    Vol. 13, No. 2, pp. 370-384, Apr. 2017  
    https://doi.org/10.3745/JIPS.02.0055
    Details
    Keywords: Image, K-means, Meta-Heuristic, Optimization, SFLA, Unsupervised Segmentation
    Show / Hide Abstract

    The image segmentation is the most important operation in an image processing system. It is located at the joint between the processing and analysis of the images. Unsupervised segmentation aims to automatically separate the image into natural clusters. However, because of its complexity several methods have been proposed, specifically methods of optimization. In our work we are interested to the technique SFLA (Shuffled Frog-Leaping Algorithm). It’s a memetic meta-heuristic algorithm that is based on frog populations in nature searching for food. This paper proposes a new approach of unsupervised image segmentation based on SFLA method. It is implemented and applied to different types of images. To validate the performances of our approach, we performed experiments which were compared to the method of K-means.


14. Fragile Watermarking Based on LBP for Blind Tamper Detection in Images
    Heng Zhang, Chengyou Wang, Xiao Zhou
    Vol. 13, No. 2, pp. 385-399, Apr. 2017  
    https://doi.org/10.3745/JIPS.03.0070
    Details
    Keywords: fragile watermarking, Local Binary Pattern (LBP), Least Significant Bit (LSB), Tamper Detection and Localization
    Show / Hide Abstract

    Nowadays, with the development of signal processing technique, the protection to the integrity and authenticity of images has become a topic of great concern. A blind image authentication technology with high tamper detection accuracy for different common attacks is urgently needed. In this paper, an improved fragile watermarking method based on local binary pattern (LBP) is presented for blind tamper location in images. In this method, a binary watermark is generated by LBP operator which is often utilized in face identification and texture analysis. In order to guarantee the safety of the proposed algorithm, Arnold transform and logistic map are used to scramble the authentication watermark. Then, the least significant bits (LSBs) of original pixels are substituted by the encrypted watermark. Since the authentication data is constructed from the image itself, no original image is needed in tamper detection. The LBP map of watermarked image is compared to the extracted authentication data to determine whether it is tampered or not. In comparison with other state-of-the-art schemes, various experiments prove that the proposed algorithm achieves better performance in forgery detection and location for baleful attacks.


15. Rough Set-Based Approach for Automatic Emotion Classification of Music
    Babu Kaji Baniya, Joonwhoan Lee
    Vol. 13, No. 2, pp. 400-416, Apr. 2017  
    https://doi.org/10.3745/JIPS.04.0032
    Details
    Keywords: Attributes, Covariance, Discretize, Rough Set, Rules
    Show / Hide Abstract

    Music emotion is an important component in the field of music information retrieval and computational musicology. This paper proposes an approach for automatic emotion classification, based on rough set (RS) theory. In the proposed approach, four different sets of music features are extracted, representing dynamics, rhythm, spectral, and harmony. From the features, five different statistical parameters are considered as attributes, including up to the 4th order central moments of each feature, and covariance components of mutual ones. The large number of attributes is controlled by RS-based approach, in which superfluous features are removed, to obtain indispensable ones. In addition, RS-based approach makes it possible to visualize which attributes play a significant role in the generated rules, and also determine the strength of each rule for classification. The experiments have been performed to find out which audio features and which of the different statistical parameters derived from them are important for emotion classification. Also, the resulting indispensable attributes and the usefulness of covariance components have been discussed. The overall classification accuracy with all statistical parameters has recorded comparatively better than currently existing methods on a pair of datasets.


16. A Power Allocation Algorithm Based on Variational Inequality Problem for Cognitive Radio Networks
    Ming-Yue Zhou, Xiao-Hui Zhao
    Vol. 13, No. 2, pp. 417-427, Apr. 2017  
    https://doi.org/10.3745/JIPS.03.0068
    Details
    Keywords: cognitive radio, Power Allocation, Variational Inequality
    Show / Hide Abstract

    Power allocation is an important factor for cognitive radio networks to achieve higher communication capacity and faster equilibrium. This paper considers power allocation problem to each cognitive user to maximize capacity of the cognitive systems subject to the constraints on the total power of each cognitive user and the interference levels of the primary user. Since this power control problem can be formulated as a mixed-integer nonlinear programming (NP) equivalent to variational inequality (VI) problem in convex polyhedron which can be transformed into complementary problem (CP), we utilize modified projection method to solve this CP problem instead of finding NP solution and give a power control allocation algorithm with a subcarrier allocation scheme. Simulation results show that the proposed algorithm performs well and effectively reduces the system power consumption with almost maximum capacity while achieve Nash equilibrium.