Accepted Papers


  • SINE COSINE CROW SEARCH ALGORITHM: A POWERFUL HYBRID META HEURISTIC FOR GLOBAL OPTIMIZATION
    Seyed Hamid Reza Pasandideh and Soheyl Khalilpourazari,Department of Industrial Engineering, Faculty of Engineering, Kharazmi University, Tehran, Iran
    ABSTRACT

    This paper presents a novel hybrid algorithm named Since Cosine Crow Search Algorithm. To propose the SCCSA, two novel algorithms are considered including Crow Search Algorithm (CSA) and Since Cosine Algorithm (SCA). The advantages of the two algorithms are considered and utilize to design an efficient hybrid algorithm which can perform significantly better in various benchmark functions. The combination of concept and operators of the two algorithms enable the SCCSA to make an appropriate trade-off between exploration and exploitation abilities of the algorithm. To evaluate the performance of the proposed SCCSA, seven well-known benchmark functions are utilized. The results indicated that the proposed hybrid algorithm is able to provide very competitive solution comparing to other state-of-the-art meta heuristics.

  • Computer Aided Liver Tumor Detector - CALTD
    Thayalini Piragash,Department of Computing,Informatics Institute of Technology,Sri Lanka
    ABSTRACT

    Computer-aided liver tumor detection can be an assist to the radiologist to detect the liver tumors from the abdominal CT image. This research proposes a software solution to illustrate the automated liver segmentation and tumor detection using artificial intelligent techniques. Evaluate the results of the liver segmentation and tumor detection, in cooperation with the radiologist by using the prototype of the proposed system. This research overcomes the challenges in medical image processing. The 100 samples collected from ten patients and received 90% accuracy rate.

  • LEAN LEVEL OF AN ORGANIZATION ASSESSED BASED ON FUZZY LOGIC
    A. Abreu and J. M. F. Calado,Mechanical Engineering Department, ISEL - Instituto Superior de Engenharia de Lisboa, IPL – Polytechnic Institute of Lisbon Rua Conselheiro Emídio Navarro, 1, 1959-007 Lisboa, Portugal
    ABSTRACT

    To determine the lean level of an organization a methodology was developed. It was based on a qualitative assessment approach, including quantitative basis, whose development was supported using fuzzy logic. Recourse to the use of fuzzy logic is justified by its ability to cope with uncertainty and imprecision on the input data, as well as, could be applied to the analysis of qualitative variables of a system, turning them into quantitative values. A major advantage of the developed approach is that it can be adjusted to any organization regardless of their nature, size, strategy and market positioning. Furthermore, the proposed methodology allows the systematically identification of constraint factors existing in an organization and, thus, provide the necessary information to the manager to develop a holistic plan for continuous improvement. To assess the robustness of the proposed approach, the methodology was applied to a maintenance and manufacturing aeronautical organization.

  • Error Estimates for Multi-Penalty Regularization under General Source Condition
    Abhishake Rastogi,Department of Mathematics,Indian Institute of Technology Delhi,India
    ABSTRACT

    In learning theory, the convergence issues of the regression problem are investigated with the least square Tikhonov regularization schemes in both the RKHS-norm and the L2-norm. We consider the multi-penalized least square regularization scheme under the general source condition with the polynomial decay of the eigenvalues of the integral operator. One of the motivation for this work is to discuss the convergence issues for widely considered manifold regularization scheme. The optimal convergence rates of multi-penalty regularizer is achieved in the interpolation norm using the concept of e ective dimension. Further we also propose the penalty balancing principle based on augmented Tikhonov regularization for the choice of regularization parameters. The superiority of multi-penalty regularization over single-penalty regularization is shown using the academic example and moon data set.

  • AN INTERVAL TYPE-2 FUZZY LOGIC-BASED FRAMEWORK FOR ADMISSION CONTROL IN 4G MOBILE NETWORKS
    Uduak Umoh1, Daniel Asuquo2 and Imoh Eyoh3,1,2Department of Computer Science,3University of Uyo, Akwa Ibom State, Nigeria,3ASAP Research Group, University of Nottingham Nottingham, United Kingdom
    ABSTRACT

    This paper presents a technique to control based on interval type-2 fuzzy logic system (IT2FLS) of Mamdani fuzzy inference, employed to model connection admission control in Fourth Generation (4G) Networks to improve quality of service (QoS). The appropriate parameter selection to achieve connection admission control is also considered based on major system parameters like latency, packet loss, load, signal strength and user mobility. We explore the use of Karnik-Mendel (KM) and Wu-Mendel (WM) approaches in our proposed system. We also implement a T1FLS connection admission control for guaranteed QoS in 4G mobile networks for comparison purposes. The empirical comparison is made on the designed system using 4G network admission control synthetic datasets. Analysis of our results reveal that the presence of additional degrees of freedom in IT2FLS-WM controller tend to reduce the root mean square error (RMSE) of the model compared to IT2FLS-KM and fuzzy type-1 approaches.

  • A LINK PREDICTION IN SOCIAL NETWORKS: A FUZZY COGNITIVE MAP APPROACH
    Upasana Sharma1 and Srishti Kandwal2,1,2Amity Institute of Information Technology, Amity University, Uttar Pradesh, India
    ABSTRACT

    Social Networking web sites are very common way to make the association between the entities. To evaluate the structure of the complex social network is very tedious task due to large number of variable parameters. Online social networks are very dynamic as the new links and nodes are added with time. Link prediction is an important aspect of social network analysis. Various methods have been introduced for link prediction in past. In this paper, we proposed fuzzy cognitive map approach for link prediction. We implemented proposed technique on two real data sets and the experiment shows good performance.

  • DETECTING AND LOCATING PLAGIARISM OF MUSIC MELODIES BY PATH EXPLORATION OVER A BINARY MASK
    Mu-Syuan Sie, Cheng-Chin Chiang, Hsiu-Chun Yang and Yi-Le Liu,Department of Computer Science and Information Engineering,National Dong Hwa University, Taiwan
    ABSTRACT

    To the best of our knowledge, the issues of automatic detection of music plagiarism have never been addressed before. This paper presents the design of an Automatic Music Melody Plagiarism Detection (AMMPD) method to detect and locate the possible plagiarism in music melodies. The key contribution of the work is an algorithm proposed to address the challenging issues encountered in the AMMPD problem, including (1) the inexact matching of noisy and inaccurate pitches of music audio and (2) the fast detection and positioning of similar subsegments between suspicious music audio. The major novelty of the proposed method is that we address the above two issues in temporal domain by means of a novel path finding approach on a binarized 2-D bit mask in spatial domain. In fact, the proposed AMMPD method can not only identify the similar pieces inside two suspicious music melodies, but also retrieve music audio of similar melodies from a music database given a humming or singing query. Experiments have been conducted to assess the overall performance and examine the effects of various parameters introduced in the proposed method.

  • PD-FUZZY CONTROL OF SINGLE LOWER LIMB EXOSKELETON FOR HEMIPLEGIA MOBILITY
    Abdullah K Alshatti1 and M. O. Tokhi2,1Department of Automatic Control and System Engineering, University of Sheffield, United Kingdom,2School of Engineering, London South Bank University, United Kingdom
    ABSTRACT

    This paper presents studies in the design and control of single leg exoskeleton for hemiplegia mobility in simulation environment. The exoskeleton is designed to support the affected side of the hemiplegia patient while the other leg functions normally. Hip, knee and ankle joints for both humanoid leg and exoskeleton of the affected side are controlled using PD-Fuzzy control to obtain the required natural torque to allow the exoskeleton to compensate for the deficiency in affected leg to achieve normal symmetric gait. The controller is implemented in MATLAB, and the system behaviour observed in Visual Nastran 4D (VN4D) during simulation. Simulation results show that the exoskeleton can support the humanoid with the required augmentation using the proposed design and contro

  • TUNING CONCURRENCY OF THE BUSINESS PROCESS BY DYNAMIC PROGRAMMING
    Mehdi Yaghoubi 1*, Morteza Zahedi2, 1,2Computer & IT Engineering Department, Shahrood university of technology, Shahrood, Iran.
    ABSTRACT

    Business process management systems (BPMS) are vital complex information systems to compete in the global market and to increase economic productivity. Workload balancing of resources in BPMS is one of the challenges that researchers have long studied. Workload balancing of resources increases the system stability, improves the efficiency of the resources and enhances the quality of their products. In this paper, Tuning concurrency of the business process is introduced as a problem in BPMS, which is application issues for improvement at workload balance of resources and uniformity in the workload of each resource. To solve this problem, a delay vector is defined, each element of delay vector make the synthetic delay at the first of each business process, then a dynamic optimization algorithm is presented to compute delay vector and the speed of the proposed algorithms is compared with and state-space search algorithm and evolutionary algorithm of PSO. The comparison shows that the speed of the proposed algorithm is 37 hours to 5.8 years compared to the state-space search algorithm, while the POS algorithm solves the same problem in just 3 minutes.

  • A FRAMEWORK FOR IDENTIFYING EXCESSIVE SADNESS IN STUDENTS THROUGH TWITTER AND FACEBOOK IN THE PHILIPPINES
    Hussain Zuorba1, Celine Louise Olan2 and Anthonette Cantara3, 1,2,3Department of Computer and Information Sciences, University of San Carlos,Cebu City, Philippines.

    ABSTRACT

    Natural Language Processing (NLP) can be used to identify a person’s sentiments or emotions. Depression is one such sentiment that researchers have tried to identify through Natural Language Processing with little success. Depression is especially bad with students due to the amount of stress and anxiety they have to go through. While depression is very difficult to identify and treat, excessive sadness, one of the symptoms that leads to depression can be identified early and appropriate action can be taken. Data Mining was performed on Twitter and Facebook and then using Natural Language Processing (NLP) and Sentiment Analysis, a logistics regression model was devised with the use of emotion Lexicons to identify the user’s state. The Latent Dirichlet Allocation (LDA) was then used to identify important topics of each user and cluster the data and make sense out of it.

  • EXPERIMENTS ON DIFFERENT RECURRENT NEURAL NETWORK ARCHITECTURES FOR ENGLISH-HINDI MACHINE TRANSLATION
    Ruchit Agrawal,Indian Institute of Technology, Hyderabad,India.

    ABSTRACT

    Recurrent Neural Networks are a type of Artificial Neural Networks which are adept at dealing with problems which have a temporal aspect to them. These networks exhibit dynamic properties due to their recurrent connections. Most of the advances in deep learning employ some form of Recurrent Neural Networks for their model architecture. RNN’s have proven to be an effective technique in applications like computer vision and natural language processing. In this paper, we demonstrate the effectiveness of RNNs for the task of English to Hindi Machine Translation. We perform experiments using different neural network architectures - employing Gated Recurrent Units, Long Short Term Memory Units and Attention Mechanism and report the results for each architecture. Our results show a substantial increase in translation quality over Rule- Based and Statistical Machine Translation approaches.