Notification:
We are currently experiencing intermittent issues impacting performance. We apologize for the inconvenience.
By Topic

Machine Learning and Cybernetics (ICMLC), 2012 International Conference on

Date 15-17 July 2012

Go

Filter Results

Displaying Results 1 - 25 of 77
  • [Covers]

    Publication Year: 2012 , Page(s): c1 - c4
    Save to Project icon | Request Permissions | PDF file iconPDF (3052 KB)  
    Freely Available from IEEE
  • [Title page]

    Publication Year: 2012 , Page(s): 1 - 2
    Save to Project icon | Request Permissions | PDF file iconPDF (377 KB)  
    Freely Available from IEEE
  • Greetings from the General Chairs

    Publication Year: 2012 , Page(s): I - III
    Save to Project icon | Request Permissions | PDF file iconPDF (250 KB) |  | HTML iconHTML  
    Freely Available from IEEE
  • [Committees]

    Publication Year: 2012 , Page(s): IV - VI
    Save to Project icon | Request Permissions | PDF file iconPDF (247 KB)  
    Freely Available from IEEE
  • List reviewer

    Publication Year: 2012 , Page(s): VII - XI
    Save to Project icon | Request Permissions | PDF file iconPDF (205 KB)  
    Freely Available from IEEE
  • [Blank page]

    Publication Year: 2012 , Page(s): XII
    Save to Project icon | Request Permissions | PDF file iconPDF (162 KB)  
    Freely Available from IEEE
  • Contents

    Publication Year: 2012 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | PDF file iconPDF (231 KB)  
    Freely Available from IEEE
  • Particle swarm optimization algorithms for mini-benchmark problems

    Publication Year: 2012 , Page(s): 1656 - 1661
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (640 KB) |  | HTML iconHTML  

    Simulated annealing, genetic algorithms, evolutionary programming, swarm intelligence, and ant colony optimization are active research areas in Smart and intelligent innovative algorithms. In particular, Particle Swarm Intelligence (PSI) attracts more attentions because of its simplicity and time efficiency. Recent advance on PSI research includes a classification of PSI or Particle Swarm Optimization (PSO) to Standard PSO. A SPSO is supposed to work on most optimization problems (difficult or easy). However, with different problem constraints, no universal SPSO can work for all problems efficiently. Based on the idea of mini-benchmarking proposed by Maurice Clere, specified PSO (SPPSO) algorithms are proposed in this paper to address the four different problems raised in Maurice Clere's work. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A genetic-search model for first-day returns using IPO fundamentals

    Publication Year: 2012 , Page(s): 1662 - 1667
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (659 KB) |  | HTML iconHTML  

    In this paper, we present a study of genetic-based stock selection models using the data of fundamentals of initial public offerings (IPOs). The stock selection model intends to derive the relative quality of the IPOs in order to obtain their relative rankings. Top-ranked IPOs can be selected to form a portfolio. In this study, we also employ Genetic Algorithms (GA) for optimization of model parameters and feature selection for input variables to the stock selection model. We will show that our proposed models deliver above-average first-day returns. Based upon the promising results obtained, we expect our GA-based methodology to advance the research in soft computing for computational finance and provide an effective solution to stock selection for IPOs in practice. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fundus phase congruency based biometrics system

    Publication Year: 2012 , Page(s): 1668 - 1674
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (904 KB) |  | HTML iconHTML  

    This paper presents a novel biometric authentication method using retinal fundus images. Phase congruency is computed on both RGB and YCbCr channel for vessel segmentation and the Fourier components are used to detect edges. By applying pair threshold values on the phase congruent image, retinal blood vessel tree is acquired. Three different features are used and all combinations of the features are experimented to find which combination produces the best authentication accuracy. Two separate experiments are done, EXP-1 using 18 images from 6 individuals and EXP-2 using 18 (authorized) plus 547 (intruder) images, each from a separate individual. For similarity matching, 2-D correlation coefficient measure is used. In EXP-1 and EXP-2, maximum accuracy achieved was 94.44% and 93.4% respectively and both with YCbCr images. YCbCr color space outperformed RGB color space by a small margin. For EXP-l and EXP-2, the average time taken per image was 12.81 and 12.92 seconds respectively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dermatological disease diagnosis using color-skin images

    Publication Year: 2012 , Page(s): 1675 - 1680
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (840 KB) |  | HTML iconHTML  

    This paper presents an automated dermatological diagnostic system. Etymologically, dermatology is the medical discipline of analysis and treatment of skin anomalies. The system presented is a machine intervention in contrast to human arbitration into the conventional medical personnel based ideology of dermatological diagnosis. The system works on two dependent steps - the first detects skin anomalies and the latter identifies the diseases. The system operates on visual input i.e. high resolution color images and patient history. In terms of machine intervention, the system uses color image processing techniques, k-means clustering and color gradient techniques to identify the diseased skin. For disease classification, the system resorts to feedforward backpropagation artificial neural networks. The system exhibits a diseased skin detection accuracy of 95.99% and disease identification accuracy of 94.016% while tested for a total of 2055 diseased areas in 704 skin images for 6 diseases. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A study of appling BPNN to robot speech interface

    Publication Year: 2012 , Page(s): 1681 - 1685
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (618 KB) |  | HTML iconHTML  

    For robot manipulation, it does not only require accuracy but also a fast response if possible. Neural Network has the advantages of high tolerance of error and has the ability of parallelism calculation. When applying to the real time speech recognition system, through one time computation then can get the recognition result immediately, that is different from other methods like VQ, DTW, HMM. So, using Neural Network method to the field for robot speech operation is a good choice. But using Neural Network as the identifier, the dimension of input vector will large, it will occupy more memory storage, and will affect the efficiency of calculation. Therefore, in this paper we raise the concept to combine HMM and BPNN, it can reduce the dimension of input vector to decrease the burden of memory storage; on the other hand, it can also promote the calculating efficiency. For resolving a general BP network problem of slow convergence while training, in this paper we raise the concept of using the recognition rate as a factor to judge whether to stop the training procedure or not, which can save more training time and can also get the required recognition rate. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting emotion model in e-learning system

    Publication Year: 2012 , Page(s): 1686 - 1691
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (696 KB) |  | HTML iconHTML  

    Affective computing is computing that relates to human affects things. In this research, it proposed a teaching model with affective computing. It uses a novel method to detect learner's emotion and adjust emotion when learner's emotion without in positive emotion status. The detecting emotion teaching model uses emotion management module that include the detecting emotion and emotion map functions to detect learner's emotion and record emotion status for learning. This research uses emotion map to record the emotion locus for learning activity. In this detecting emotion teaching model integrates learning activities and emotion locus to create a complete learning portfolio. And it can be applied in analyzing learning status for adjusting learner's situation. By this research detecting emotion teaching model it makes a method that was based on learner's emotion to build a more effective learning environment. The detect emotion teaching model, which is a kind of innovative learning model can be applied in game based learning for continuously developing in the future and it can be used in a variety of teaching environment for increasing study effect. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A power efficient data dissemination scheme for wireless sensor networks with mobile sinks

    Publication Year: 2012 , Page(s): 1692 - 1697
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (524 KB) |  | HTML iconHTML  

    In this paper, we propose a power efficient data dissemination (PEDD) scheme for wireless sensor networks (WSNs) with mobile sinks. A source proactively constructs a grid structure to disseminate data to the mobile sinks. For each grid point, a cost function is applied to choose a dissemination node to serve it. Only the dissemination nodes are in working mode, while the other sensor nodes just fall into sleep mode to conserve energy. A path along grid points is paved from a sink to the source for forwarding queries and disseminating data. To evenly distribute energy load in the WSN, the dissemination node with the most residual energy is selected for the upstream node in the query forwarding path. Simulation results show that PEDD outperforms previous scheme. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A high performance algorithm for puzzle reconstruction problem

    Publication Year: 2012 , Page(s): 1698 - 1703
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1030 KB) |  | HTML iconHTML  

    Since a puzzle solver, for the puzzle reconstruction problem, can be applied to many other real world problems, various studies have focused on improving the end result of the puzzle solvers they proposed for several years. In spite of these efforts, the puzzle reconstruction problem, however, has never fully solved by using a search algorithm with a limited computation time. In this paper, and effective search algorithm is presented for the puzzle reconstruction problem. The proposed algorithm uses ant colony optimization to guide the search directions toward the global optimal solution, the color information to measure the similarity between pairs of puzzles, and an effective reconstruction strategy to improve the end result. To evaluate the performance of the proposed algorithm, we compare it with several state-of-the-art puzzle reconstruction algorithms. The simulations results show that the proposed algorithm out performs all the state-of-the-art algorithm we compared in this paper. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The approach of using fractal dimension and linguistic descriptors in CBIR

    Publication Year: 2012 , Page(s): 1704 - 1707
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (378 KB) |  | HTML iconHTML  

    In this paper we describe a system which uses linguistic expression and fractal dimensions to retrieve images in database. Brodaz texture images are used for our experiment. In addition, Taruma features are used to extract images of the database and several linguistic expressions are used for classified the images. These linguistic expressions, with the help of fractal dimension are more efficient in searching images. By visual inspection, we are satisfied with our experiment results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design a location-time based ethnic advertising recommendation system using degree of memberships

    Publication Year: 2012 , Page(s): 1708 - 1714
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1536 KB) |  | HTML iconHTML  

    Traditional recommendation systems are mostly based on similarity discrimination which requires sufficient data and recommends high correlated items. It becomes very difficult to accurately recommend products when data are not enough. Thus, the research about Cold Start Problem becomes important which emphasizes in effective item recommendation when too little data are provided. In this work, we propose a novel method called Location-Time based Recommendation System (LTRS) to address the Cold Start Problem with location and time as the initial factors together with degree of membership from fuzzy theory to produce more effective and precise item recommendation. From experimental results, LTRS improves the effectiveness of item recommendation, not only in normal situations but also in Cold Start scenarios. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Option moneyness classification using support vector machine

    Publication Year: 2012 , Page(s): 1715 - 1720
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (545 KB) |  | HTML iconHTML  

    Determining the theoretical price for an option, or option pricing, is regarded as one of the most important issues in financial research. In recent years, linear and non-linear GARCH (Generalized AutoRegressive Conditional Heteroskedasticity) models were used to estimate volatility. However, the empirical analysis of various different volatility model estimations has not achieved consistent results. This study construct an Taiwan's existing tech index options price classification with various a values to determine the moneyness (at-the-money, in-the-money, out-the-money) of option price. This study tested 140 models, the combinations included 4 types of the kernel function in multi-SVM (Linear, Polynomial, RBF, Sigmoid), 7 types of volatility estimation (historical volatility, implied volatility, GARCH, IGARCH, GJR-CARCH, EGARCH, TBGARCH) and 5 types of α (2%, 4%,5%,6%,8%). Finally, the classification result shows that using α=2%, polynomial function multi-SVM with the three types of volatility estimation methods of TBGARCH, EGARCH and GJR-GARCH would yield better classification performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A mashup-based adaptive learning system

    Publication Year: 2012 , Page(s): 1721 - 1726
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1012 KB) |  | HTML iconHTML  

    This study aims to build, using Felder and Silverman's Learning Style Theory and Mashup technology, an adaptive learning system to help students improve their learning effect. In this system, Felder and Silverman's Learning Style Theory is used to gain an understanding of students' learning styles to enable them to engage in adaptive learning according to their respective learning styles. Additionally, this learning system also allows learners to use a Mashup search engine to search for related supplementary teaching materials to achieve better learning results. After its completion, the learning system was used to conduct an experiment on the freshmen of two computer programming classes in the university's Information Management Department to compare the difference in students' learning effect. Moreover, a questionnaire was designed based on Technology Acceptance Model to carry out qualitative and quantitative analyses. The results showed that compared with the control group, students in the experiment group made more significant improvement in their academic performance and all of them had a positive evaluation for the learning system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An intersection-based coverage algorithm for PEGASIS architecture in Wireless sensor networks

    Publication Year: 2012 , Page(s): 1727 - 1731
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (547 KB) |  | HTML iconHTML  

    In Wireless sensor networks (WSNs), the energy of sensor node is finite, it's an important issue that how to reduce the energy consumption and extend the lifetime of entire network. In power-efficient gathering in sensor information systems (pEGASIS) topology architecture, the energy consumption of each sensor node is fewer and more average than low-energy adaptive clustering hierarchy (LEACH). Accordingly, we combine the PEGASIS topology architecture and intersection-based coverage algorithm (IBCA) to decrease the energy consumption. First of all, we find out the redundant sensor nodes to enter to the sleep mode by means of IBCA. Then, it builds the PEGASIS topology architecture by active sensor nodes which are not chosen to enter to sleep mode by IBCA. Through a series of simulations, the performances of our novel scheme outperform LEACH with PBCA in terms of energy consumption, number of alive nodes and sensing areas. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A sound-source localization system using three-microphone array and crosspower spectrum phase

    Publication Year: 2012 , Page(s): 1732 - 1736
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (567 KB) |  | HTML iconHTML  

    A sound source localization system is implemented that uses only three microphones to input sound signals. This system can estimate the azimuth and elevation of a sound source in real-time and in sufficient accuracy. We add a SNR measure besides spectra entropy to help detect voiced frames. Next, synchronous FFT phase copying is adopted, and cross-power spectrum phase is calculated to estimate TDOA (time delay of arrival) for each frame. Also, to enhance the accuracy of TDOA, parabolic interpolation is adopted. Then, by comparing the estimated TDOA values with theoretic ones, the azimuth and elevation of a sound source can be determined. Since a pair of azimuth and elevation is estimated from each voiced frame, these estimated values are thereafter summed with a weighting method to give one final answer of azimuth and elevation. According to the experiment results, the average errors in estimating azimuth and elevation are 4.02 and 2.18 degrees, respectively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent systems on the cloud for the early detection of chronic kidney disease

    Publication Year: 2012 , Page(s): 1737 - 1742
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (542 KB) |  | HTML iconHTML  

    This paper aims to construct intelligence models by applying the technologies of artificial neural networks including back-propagation network (BPN), generalized feed forward neural networks (GRNN), and modular neural network (MNN) are developed respectively for the early detection of chronic kidney disease (CKD). The comparison of accuracy, sensitivity, and specificity among three models is subsequently performed. The model of best performance is chosen for system development. The system developed aligned with the best model is deployed to the Google cloud platform by leveraging Google Application Engine. By doing so, the result can more efficiently provide CKD physicians an alter native way to detect chronic kidney diseases in early stage of a patient. Meanwhile, it may also be used by publics for self-detecting the risk of contracting CKD. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast exemplar-based image inpainting approach

    Publication Year: 2012 , Page(s): 1743 - 1747
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1233 KB) |  | HTML iconHTML  

    This paper presents a way to improve the computation efficiency of exemplar-based inpainting approach in [4]. Note that the inpainting approach in [4] has computation redundancy in searching optimal patches in source region and updating fill front. A scheme to reduce source region and a modified scheme to update fill front are proposed. With the two schemes, better computation efficiency is expected. Several examples are given to justify the proposed fast inpainting approach and used to compare with the approach in [4]. The results indicate that the proposed approach has better computation efficiency than the approach in [4], as expected. Interesting enough, better visual quality of inpainted images is achieved by the proposed approach as well. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A stack-based Markov model in web page navigability measure

    Publication Year: 2012 , Page(s): 1748 - 1753
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (441 KB) |  | HTML iconHTML  

    Usability is critical to the success of a website and good navigability enhances the usability. Hence the navigability is the most important issue in designing websites. Many navigability measures have been proposed with different aspects. Applying information theory, a stack-based Markov model is proposed to represent the structure of a website and to include more surfing behavior. The dynamic users' log data is used to evaluate navigability of a web page. The entropy ratio is proposed to represent the navigability of web pages. Experimental results show the relation between entropy ratio and characteristic of a web page is quit close. Applying the entropy ratio of a web page, the web page can be recognized as a type of page which is good or not. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applying layered multi-population genetic programming on learning to rank for information retrieval

    Publication Year: 2012 , Page(s): 1754 - 1759
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1258 KB) |  | HTML iconHTML  

    Information retrieval (IR) returns a relative ranking of documents with respect to a user query. Learning to rank for information retrieval (LR4IR) employs supervised learning techniques to address this problem, and it aims to produce a ranking model automatically for defining a proper sequential order of related documents based on the query. The ranking model determines the relationship degree between documents and the query. In this paper an improved version of RankGP is proposed. It uses layered multi-population genetic programming to obtain a ranking function which consists of a set of IR evidences and particular predefined operators. The proposed method is capable to generate complex functions through evolving small populations. In this paper, LETOR 4.0 was used to evaluate the effectiveness of the proposed method and the results showed that the method is competitive with other LR4IR Algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.