By Topic

System Science and Engineering (ICSSE), 2012 International Conference on

Date June 30 2012-July 2 2012

Filter Results

Displaying Results 1 - 25 of 126
  • [Front cover]

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (321 KB)  
    Freely Available from IEEE
  • [Title page]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (126 KB)  
    Freely Available from IEEE
  • Proceedings 2012 international conference on system science and engineering (icsse) [copyright notice]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (222 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): i - viii
    Save to Project icon | Request Permissions | PDF file iconPDF (63 KB)  
    Freely Available from IEEE
  • Image-based intelligent attendance logging system

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1065 KB) |  | HTML iconHTML  

    This paper proposes an extension of the surveillance camera's function as an intelligent attendance logging system. The system works as a time recorder within two phases; learning phase and monitoring phase. By placing a camera inside a working room, the sytem enters the learning phase by locating the sitting area automatically based on the camera's images. The learning phase has a defined time duration to complete a working map. Next, the system switches to the monitoring phase to report each occupant's working hour corresponding to their sitting area in the working map. The system detects the entering occupant, the leaving occupant, the sitting occupant, and the standing occupant from their seat. The system also tracks the occupants. The working hours of the occupant will be counted as how long they sit in their desk. When the occupant sits at his/her seat, a start time is given. Later, after he/she leaves from their seat, a stop time is generated. The experimental setup has been done in our laboratory. The result shows that the system can achieve a good result. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent Video Car Recorder systems

    Page(s): 7 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (748 KB) |  | HTML iconHTML  

    Video Car Recorder embedded into intelligent mobile devices is considered in this study. That is, the Lead Management System (LMS) is developed. The features of the LMS include recording instant car traveling screen, displaying the current location map, and capturing the current location data; namely, comprises latitude, longitude, speed, altitude and directional acceleration. Besides, the prominent feature of the entire application is that the system can be embedded into intelligent mobile devices for a variety of the iOS System. Because the iOS mobile devices with GPS and camera which is widely used, the Video Car Recorder application is not limited to the problems of hardware-integration. At the same time, the iOS SDK, Google Map API, Objective-C, and Xcode platform are applied to develop the application of intelligent mobile devices with Video Car Recorder. Consequently, the proposed application is a widely used and saving costs system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the information transmission ability measurement of neurons via fuzzy method

    Page(s): 13 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (613 KB) |  | HTML iconHTML  

    Information processing is an important characteristic of biological neurons. Here, we proposed a method to measure the information transmission ability of neurons. Due to the nonlinear dynamics of neuron, which is experimentally verified, we have to solve the Hamilton-Jacobi inequalities (HJIs) to get the information transmission ability of neuron. Instead of directly solving HJIs, fuzzy interpolation method was employed to help us to systematically measure information transmission ability by solving a set of linear matrix inequalities (LMIs). The information transmission ability measurement method will provide an insight into the mechanism of information processing in neurons. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust back propagation learning algorithm based on near sets

    Page(s): 19 - 23
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (354 KB) |  | HTML iconHTML  

    The traditional robust learning algorithms are based on the estimated errors, which is not correct in the early stage of the training process. Therefore, the use of those approaches still cannot provide very decent learning performance in face of outliers unless a set of good initial weights is used. In this paper, a novel approach, termed as NRBP (Near set based Robust Back Propagation learning algorithm) is proposed. In this learning algorithm, the training (estimated) data sets are separated into overlapping (or nonoverlapping) subsets of those data. It uses the set error measure instead of one-step error in robust back propagation based on near set. The set error measure is an estimated error measure between a subset of training data set and corresponding subset of estimated data set. Its benefit is it includes error messages and also reduces the outlier effect. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Driving force analysis of the carrier of the multiple flexible wheeled suspension mobile manipulator

    Page(s): 24 - 29
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (375 KB) |  | HTML iconHTML  

    In this paper, the multiple flexible wheeled suspension mobile manipulator has been carried on research. The elastic deformation of the manipulator and the elastic damping of the wheeled mobile carrier have been synthetically considered. Combined with the constraint equations of the system, the independent coordinate variables and the associated coordinate variables have been extracted for the first time. It makes the configuration of the wheeled suspension mobile manipulator more concise. On the basis of it, the driving force model containing the elastic variable of the flexible manipulator components of the wheeled suspension mobile carrier has been calculated with Newton-Euler method. Finally the simulation analysis has been proved the rationality of the model and the necessity of considering flexible factors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive fuzzy balance controller for two-wheeled robot

    Page(s): 30 - 33
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (516 KB) |  | HTML iconHTML  

    An adaptive fuzzy sliding-mode balance controller (AFSMBC) for a two-wheeled robot is developed in this study. In the proposed balance controller, a novel sliding surface is adopted as the input variable of fuzzy system to outstanding its merit of insensitivity to uncertainties. In the fuzzy membership function, the translation width is utilized to reduce the chattering phenomena. Moreover, consider the parametric variation, external disturbance and nonlinear friction for the practical wheeled robot motions, the transient and unmodelled uncertainty will be occurred. An adaptive tuner, which is derived in the sense of Lyapunov stability theorem, is added into the fuzzy controller to reduce the accumulated error and to ascend the stability. The hardware of whole control system includes a microcontroller, gyroscope, accelerometer, and two autonomous motors. The effectiveness is verified by simulated and experimental results, and the performance is compared with conventional PD control scheme for the same wheeled robot. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The previous step CMAC for online tuning robust fuzzy controllers

    Page(s): 34 - 39
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (409 KB) |  | HTML iconHTML  

    The previous step CMAC for online tuning robust fuzzy controllers is proposed in this paper. There are two processes in the proposed schemes: one is the robust fuzzy controller and the other is the previous step CMAC learning algorithm. The robust fuzzy controller can achieve a certain goal without concern for instability of the controlled system in the presence of significant plant uncertainties, if the nominal parameter is roughly estimated. In order to improve the performance of robust fuzzy controller, the nominal parameter should be adjusted. Thus, a previous step CMAC learning algorithm under the robust fuzzy control structure is employed for online tuning the nominal parameter. Finally, simulation results demonstrate the excellent capability of the proposed schemes for improving the output performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy based hand-shake compensation for image stabilization

    Page(s): 40 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (700 KB) |  | HTML iconHTML  

    The paper proposed a way of dealing with optical image stabilization in solving blurring images caused by hand shake. The idea is to determine the hand-shake situation and then to correct blurring image through position compensation. This method directly detects motion signals to distinguish the hand shake situations from normal camera movement. In the process, fuzzy rule mechanism is employed to have more accurate decision. If a hand-shake situation is determined, the corresponding correction signal is generated to correct the image in a real-time fashion. In order to demonstrate the effectiveness of the proposed approach, in our implementation, the system directly moves the camera mounted on an X-Y platform to compensate the hand shake effect. From our experiments, it is clearly evident that this method indeed can have better image quality. The average shake without using this method is 73.8 pixels, the average shake with this method is 33.4667 pixels, the average shake reduction is 40.333 pixels and the average percentage of shake reduction is 54.64%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Radar target classification using intelligent cerebellar model articulation controller

    Page(s): 45 - 49
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (262 KB) |  | HTML iconHTML  

    This paper proposed a radar emitter identification method based on cerebellar model articulation controller(CMAC), the controller inputs are radar emitter's characteristic like radio frequency(RF), pulse repetition interval(PRI) and pulse width(PW) etc. The CMAC has to train to be by training data. After training, input the unknown radar characteristic, the network may appropriately identify the emitter types. The simulation results show that CMAC can quickly and accurately classify and identify the emitter types. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent space system oriented to the home service robot

    Page(s): 50 - 54
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (616 KB) |  | HTML iconHTML  

    Intelligent space technology is applied to robot in order to provide more autonomous, accurate and intelligent home service work in an unknown or semi-unknown dynamic environment. There are some key technologies in the study of Intelligent space, such as: wireless sensor network, information management. In this paper, an intelligent space system oriented to home service robot is constructed; some key technologies in this system are proposed; based on the intelligent space system, the smart and agilely home service provided by home service robot is introduced in detail. Combined with the intelligent space technology, a home service robot can obtain more comprehensive environmental information, perceive human and objects in space more completely. Many tasks in the complex environment can be accomplished by robot with “light-packs”, devices in intelligent space, such as air condition can be controlled autonomously. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new dynamic optimal learning rate for a two-layer neural network

    Page(s): 55 - 59
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (393 KB) |  | HTML iconHTML  

    The learning rate is crucial for the training process of a two-layer neural network (NN). Therefore, many researches have been done to find the optimal learning rate so that maximum error reduction can be achieved in all iterations. However, in this paper, we found that the best learning rate can be further improved. In saying so, we have revised the direction to search for a new dynamic optimal learning rate, which can have a better convergence in less iteration count than previous approach. There exists a ratio k between out new optimal learning rate and the previous one after the first iteration. In contrast to earlier approaches, the new optimal learning rate of the two-layer NN has a better performance in the same experiment. So we can conclude that our new dynamic optimal learning rate can be a very useful one for the applications of neural networks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic lumbar motion analysis based on particle filtering

    Page(s): 60 - 63
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (275 KB) |  | HTML iconHTML  

    Spinal motion is produced by complex coordination of nerves and muscles and is constrained by vertebral structure. The observation and measurement of lumbar motion is of great value for clinical diagnosis and surgical plan of lumbar disorders. Digitalized Video Fluoroscopy (DVF) is the most suitable one to image the spine motion but it is quite time consuming. This paper proposes an automatic lumbar motion analysis system (ALMAS) with particle filtering technology. The automatically vertebral tracking for motion analysis was utilized with a friendly-interface, which provides a window for users to process the acquired DVF sequence and to analyze the tracking results. A set of simulation vertebra image were used to evaluate the performance and accuracy of this system. In simulated sequence, the maximal difference is 1.3 mm in translation and 1° in rotation angle. The error is small in x- and y-translation (fiducial error: 2.4%, repeatability error: 0.5%) and in rotation angle (fiducial error: 1.0%, repeatability error: 0.7%). The ALMAS can still track the sequence contaminated by noise with the density ≤ 0.5. Besides, the results demonstrate that the data from the auto-tracking algorithm shows a strong correlation with the actual measurement and that the ALMAS is highly repetitive. Results from this study showed that ALMAS based on particle filtering are relatively robust and accurate for automatic lumbar motion analysis. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple models fusion for pattern classification on noise data

    Page(s): 64 - 68
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (323 KB) |  | HTML iconHTML  

    An important characteristic of real-world learning process is that the data frequently contains uncertainties. The uncertainties in the datasets deteriorate the learning process. Hence, to properly represent and handle the uncertainty problem is one of the key issues in the decision learning system. This paper offers a multiple models fusion method to address the uncertainty problem, by conducting the fusion of two models, Bayesian classifier and Probabilistic based Noise Aware Support Vector Machine. Specifically, we take the advantage of noise-insensitive characteristic of the Naïve Bayesian classifier, to enhance the noise-tolerant ability of probabilistic information based Support Vector Machine. The method fuses the probabilistic decision information obtained from the two classifiers in a flexible way to give the final decision. Furthermore, the multiple models fusion method is evaluated on an artificial dataset for a classification task. The experiment results show good performance when compared with using only one learning technique in the noise environment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new chaotic system for image encryption

    Page(s): 69 - 73
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1890 KB) |  | HTML iconHTML  

    With the increasing demand of providing security for images/videos with private information, chaos-based cryptosystems have played an important role in image encryption because of their excellent random properties and encryption performance. However, existing chaos-based systems have the security defect due to small key space or other security weakness. This paper introduces a new chaotic system using a combination of three conventional chaotic maps. The proposed chaotic system shows excellent chaotic behaviors. To demonstrate its application in image processing, a new image encryption scheme using the proposed chaotic system is also introduced. Computer simulation and security analysis demonstrate that the proposed image encryption scheme shows excellent encryption performance, high sensitivity to the security keys, and a sufficiently large key space to resist the brute attack. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Thermal modeling for vehicle battery system: A brief review

    Page(s): 74 - 78
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (358 KB) |  | HTML iconHTML  

    Thermal management of battery system plays an important role in vehicle industry. An accurate yet time efficient model of the battery system thermal dynamics is essential for design, temperature monitoring and control process. In this paper, a brief review of the advances in thermal modeling of vehicle battery system is given. Based on the review results, the future challenges for vehicle battery system thermal modeling are presented; and a multi-domain, multi-level intelligent modeling procedure for thermal dynamics of vehicle battery system is then proposed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting drivable space in traffic scene understanding

    Page(s): 79 - 84
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (667 KB) |  | HTML iconHTML  

    Traffic scene understanding and perception is an important issue for intelligent vehicles and autonomous mobile robots. Especially in dynamic environments, the determination of drivable space and moving obstacles are fundamental requirement for road scene understanding. In this paper, we propose a vision-based approach combining road geometry and color features to percept road and moving obstacles in a dynamic environment from the camera mounted on the host vehicle. In the approach, a free road surface is detected first based on feature similarity search using statistical feature analysis (SFA) combined with a breadth-first search (BFS) algorithm to segment different intensity similarity regions in a road image. Then, the similarity between the road model (its color distribution) and the road region candidates is expressed by a metric derived from the Bhattacharyya distance. With the free road surface, the relative distance of preceding obstacles can easily be estimated using the obstacle scanning mechanism (OSM) and online camera calibration scheme. The experimental results have shown that the proposed approach can detect the drivable region and estimate the relative distance of preceding obstacles in real traffic scenes. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two-degree-of-freedom control using recurrent fuzzy neural networks for a class of nonlinear discrete-time time-delay systems

    Page(s): 85 - 90
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (364 KB) |  | HTML iconHTML  

    This paper presents a novel two-degrees-of-freedom control for a class of nonlinear discrete-time time-delay systems. The controller combines a TSK-type recurrent fuzzy neural network (TRFNN) adaptive inverse model feedforward controller with a stochastic adaptive model reference predictive controller (SAMRPC). The former is used to provide command-feedforward control and to improve transient performance, while the SAMRPC controller is employed to eliminate any error caused by disturbances or uncertainties. Numerical simulations for controlling a highly nonlinear process reveal disturbance rejection and set-point tracking performance of the proposed control method. The results clearly indicate effectiveness and merit of the proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prediction of Mammalian microRNA binding sites using Random Forests

    Page(s): 91 - 95
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (240 KB) |  | HTML iconHTML  

    In biological systems, microRNAs involve in the regulation of their target genes by degrading the targeted binding mRNAs or by repressing the corresponding protein products. MicroRNAs are shown to play important roles in numerous biological processes, such as disease formation, especially in cancer. Predicting the target binding site of microRNA can help to identify the novel miroRNA target genes. Either microRNAs or its target genes can be recognized as biomarkers for diagnosis of diseases, prediction of prognosis, or even therapy decision. In this study, first we apply support vector machines (SVMs), neural networks and decision tree-based approaches to select a set of useful features, which represent important characteristics for the determination of the interaction between microRNA and its target binding mRNA sequence. Next, these selected features are used in two classifiers, SVM and Random Forests, to perform prediction of microRNA target sites. The features that are selected by Random Forests itself exhibit the best performance for predicting the binding site of microRNA. Its prediction accuracy can reach about 75%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel attribute-weighted fuzzy c-means algorithm for clustering

    Page(s): 96 - 101
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (115 KB) |  | HTML iconHTML  

    Due to energy and bandwidth constraints, traditional data clustering approaches are challenging when the communication to a central processing unit is discouraged in Wireless Sensor Networks. In this paper, a new parallel attribute-weighted fuzzy c-means (PWFCM) algorithm is proposed, in which parallel clustering solution can be achieved by exchanging the centroid messages among single-hop neighbours only. At the same time, the important features can be extracted based on the attribute weight entropy regularization. Experiments on real and synthetic datasets have demonstrated the suitability and efficiency of the presented algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Defining transcriptional network by combining expression data with multiple sources of prior knowledge

    Page(s): 102 - 106
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (359 KB) |  | HTML iconHTML  

    Quantitative estimation of the regulatory relationship between transcription factors and genes is a fundamental stepping stone when trying to develop models of cellular processes. In this paper, a transcriptional regulation model is proposed to quantify the transcriptional regulatory network. Multiple quantities, including binding affinity and the activity level of transcription factor (TF) are incorporated into a general learning model. The model relies on a continuous time, differential equation description of transcriptional dynamics where transcription factors are treated as latent on/off variables and are modeled using a switching stochastic process. Experimental results show that the proposed model can effectively identify the parameters and the activity level of TF. Moreover, the kinetic parameters introduced in the proposed model can reveal more biological sense than some previous models can do. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimized set-point model of grinding process based on case-based reasoning method

    Page(s): 107 - 111
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (367 KB) |  | HTML iconHTML  

    The grinding process is a typical complex nonlinear multivariable industrial production system with strongly coupling and large time delays. Based on the technological characteristics and system control requirements, a set-point optimization control strategy based on the case-based reasoning (CBR) method is proposed for obtaining the optimized velocity set-point of ore feed and pump water feed in the controlled loops of the grinding process, whose four key functional modules of CBR (case retrieve, case reuse, case revision and case retain) are described in details. The statistics results of the industrial experiments show that the set-point control strategy based on the CBR method realizes the on-line optimization of the grinding granularity and ore discharge ratio and lays solid foundations for the intelligent control of grinding process. View full abstract»

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