By Topic

Intelligent Signal Processing (WISP), 2011 IEEE 7th International Symposium on

Date 19-21 Sept. 2011

Filter Results

Displaying Results 1 - 25 of 40
  • [Front cover]

    Publication Year: 2011 , Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (303 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2011 , Page(s): ii
    Save to Project icon | Request Permissions | PDF file iconPDF (43 KB)  
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2011 , Page(s): iii - vii
    Save to Project icon | Request Permissions | PDF file iconPDF (93 KB)  
    Freely Available from IEEE
  • Welcome message from the chairpersons

    Publication Year: 2011 , Page(s): viii - ix
    Save to Project icon | Request Permissions | PDF file iconPDF (71 KB) |  | HTML iconHTML  
    Freely Available from IEEE
  • Monitoring workers through wearable transceivers for improving work safety

    Publication Year: 2011 , Page(s): 1 - 3
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (327 KB) |  | HTML iconHTML  

    In this paper we present a wireless monitoring system for increasing work safety of people working alone. The main component of the system is a wearable transceiver including movement sensors, the so called GALILE device. GALILE detects potential emergency situations automatically and sends an alert to an emergency monitoring center. The worker carrying GALILE is also given the option to trigger an alarm by pressing a button placed on the device. For wireless communication, ZigBee standards are considered. A Zigbee network consisting of several routers and a gateway are collecting GALILE data and forwarding these data to the security center, where it is visualized through an application software providing a visual interface. The system also gives vital information about the location of the worker in emergency. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Indoor location system based on ZigBee devices and Metric Description Graphs

    Publication Year: 2011 , Page(s): 1 - 5
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (937 KB) |  | HTML iconHTML  

    This paper proposes a way to improve the position estimates in an indoor location systems (ILS) based on readings from the power levels (RSSI) of an ad hoc ZigBee network. A mobile object, also equipped with a ZigBee device, can be located, positioned, and tracked by the system. The initial estimate of the mobile node position is extracted from IC devices from Texas Instruments, equipped with a specific hardware module for this function called Location Engine; it computes its position from RSSI readings of the signals coming from a set of reference beacons. Positioning of the blind nodes is enhanced by a post-filtering of the initial estimates by adjusting them into a Metric Description Graph (MDG) of the building, which includes information on distances and connectivity among the various enclosures of the coverage area of the ILS. The system has been experimentally verified in localization tasks of pedestrians in indoor environments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementation of an intelligent sensor for measurement and prediction of solar radiation and atmospheric temperature

    Publication Year: 2011 , Page(s): 1 - 6
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4278 KB) |  | HTML iconHTML  

    The aim of this study was to develop an intelligent sensor for acquiring temperature, solar radiation data and estimate cloudiness indexes, and use these measured values to predict temperature and solar radiation in a close future. The prototype produced can ultimately be used in systems related to thermal comfort in buildings and to the efficient and intelligent use of solar energy. To incorporate these functionalities, a small and portable prototype was developed, which consisted in: a CCTV camera with a fish-eye lens, for sky images acquisition; a computer of format mini-itx with a Linux operative system, for data acquisition and processing; a GPS, to enable automatic use, independent of the system's geographical position; a pyranometer, for regular measurements of solar radiation; a temperature probe, for regular measurements of outdoor temperature; a shadow band, to eliminate the sun's flare effect on sky images; Arduino, an open source electronics prototyping platform that acquires data from the temperature and solar radiation sensors, as well as processing the data provided by the GPS and controlling the shadow band; neural networks of the type NARX, which use the acquired data to forecast the cloudiness index, solar radiation and temperature, in the next four hours period. The system was programmed to acquire data, both from the sensors and the camera, every five minutes. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design of a sensor network based security system

    Publication Year: 2011 , Page(s): 1 - 5
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2010 KB) |  | HTML iconHTML  

    In this paper a wireless distributed building safety and security framework will be introduced. The main design goals of the system are completely distributed operation, flexibility, robustness, fast response time, and energy efficiency. The framework uses low duty cycle TDMA-based communication scheme, where the scheduling is the result of optimization, based on network discovery measurements. The hardware and software architecture of a prototype system is introduced. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison and improvement of Dempster-Shafer models

    Publication Year: 2011 , Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (724 KB) |  | HTML iconHTML  

    In this paper, a performance comparison of different classification algorithms based on the evidence theory of Dempster-Shafer will be presented. The comparison is illustrated on Landsat Multispectral Scanner (Landsat MSS) data whose ground truth is provided. A modification of the Denoeux's model [1] is proposed showing better and more stable classification results of the Landsat MSS data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An add-on solution to take measures automatically from critical care urine meters

    Publication Year: 2011 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2581 KB) |  | HTML iconHTML  

    Critical care patients have most of their physiological parameters automatically sensed by sophisticated commercial monitoring devices. These devices can also supervise whether the values of each parameter lie within a preestablished normal range, and warn of deviations from this range by triggering audible alarms. Automation of the sensing and supervision of physiological parameters discharges the healthcare staff of a considerable workload. Furthermore, it avoids human errors, which are common in repetitive and monotonous tasks. However, there is still a very relevant physiological parameter that is sensed and supervised manually by the healthcare staff: urine output. In this paper we present a patent-pending addon solution that can be easily incorporated into commercial urine meters to transform these manual measuring devices into automated measuring devices. The solution is based on capacitive sensors capable of taking continuous measurements of the height of the column of liquid accumulated in the various chambers that make up a commercial urine meter. An electronic unit sends the measures of the capacitive sensors via Bluetooth to a PC which calculates the urine output from this information and supervises the achievement of therapeutic goals. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Is the average duration of apneas, hypopneas and desaturations useful in the diagnosis of SAHS?

    Publication Year: 2011 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (662 KB) |  | HTML iconHTML  

    Sleep Apnea-Hypopnea Syndrome (SAHS) is usually diagnosed by polysomnography, a test that consists of the registration of a wide range of physiological parameters while the patient is asleep. The commercial monitoring devices used in the polysomnography generate a report summarizing the test. Some of the information presented to the clinicians in these reports, such as the Apnea-Hypopnea Index, has been the target of comprehensive clinical studies, and there are detailed clinical guidelines to interpret it. However, these reports also contain other data such as mean and maximum values of the descriptors of various pathological events recorded in the polysomnogram; e.g., the mean and maximum duration of the apneas, hypopneas and desaturations that the patient has experienced. These features have not been studied in the literature. Therefore, guidelines for their interpretation do not exist. This paper attempts to evaluate the usefulness of this information in the diagnosis of SAHS. It also tries to provide guidelines for clinicians on how to interpret it. To this end, we have calculated these features for 210 patients who underwent polysomnographic testing, and we have analyzed their capability to discriminate between healthy and SAHS patients, as well as to stratify the patients according to their severity. Our results suggest that most of them have little or no utility for diagnosing SAHS patients. Therefore, they could be omitted from the reports without significant loss of information. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enhancing time-frequency parameters estimation for Doppler Ultrasound blood-flow signals

    Publication Year: 2011 , Page(s): 1 - 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (994 KB) |  | HTML iconHTML  

    Doppler Ultrasound (DU) blood flow signals, particularly when collected under intra-operative conditions are noisy; accurate extraction of clinical parameters from their spectra becomes a difficult task. The spectral center frequency and bandwidth were estimated using two estimators with alternative time-frequency resolutions: a fixed resolution method, the Short-Time Fourier Transform (STFT) and the multi-resolution Continuous Wavelet Transform (CWT). Their performance was also assessed when the DU signals were pre-processed by a recently proposed Noise Cancellation Technique (NCTech). The NCTech algorithm enables quantification of the magnitude of the canceled noise in the form of percentage, called Cancellation Level (CL). Quantitative comparisons have been performed in terms of bias of the estimators when four signal-to-noise (SNRs) on DU simulated signals are employed: infinity, 20 dB, 10 dB and 5 dB. Results prove that CWT produced spectral parameters estimates with less bias than STFT; however these estimates were less consistent than the STFT ones. When NCTech is primarily applied to the signal, the STFT is the method to benefit most from this pre-processing technique. The CWT combined with NCTech produced estimates of both spectral parameters with better accuracy over the majority of the cardiac cycle, except where the frequency varies within a small range of frequencies during a short period of time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Solving practical issues of a portable Doppler Ultrasound system for blood flow assessment during coronary graft surgery

    Publication Year: 2011 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4604 KB) |  | HTML iconHTML  

    This paper presents some practical issues regarding the development of a dedicated Doppler Ultrasound system (DUS) for the assessment of blood flow signal on coronary grafts during heart surgery. The DUS is composed of several processing units. This paper concentrates on front-end units: the transducer and a particular issue of the software interface for clinical evaluation, the noise cancellation technique (NCTech). The experimental set-up implemented to evaluate the transducer response is presented. The procedure employed to eliminate the noise components embedded in the DUS data is described. Each of these units was primarily tested in laboratory. Results show their effectiveness in achieving their specific goals. Comments on the overall system's performance are presented denoting the usefulness of such dedicated DUS during bypass assessment at heart surgery. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Activity monitoring and emergency warning with location information of the user

    Publication Year: 2011 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1264 KB) |  | HTML iconHTML  

    Recent advances in communications technologies and embedded systems have allowed the development of remote health monitoring systems. There are different approaches depending on the available measurements and the communication system used. In this paper an activity monitoring system is proposed in order to detect falls and/or faints of the user. The feature that distinguishes this system from other activity monitoring systems is the ability of auto-localization in both outdoor and indoor environments as well as the ability to automatically generate alarms to alert the medical personnel if there is any emergency situation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards a more analytical training of neural networks and neuro-fuzzy systems

    Publication Year: 2011 , Page(s): 1 - 6
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (852 KB) |  | HTML iconHTML  

    When used for function approximation purposes, neural networks belong to a class of models whose parameters can be separated into linear and nonlinear, according to their influence in the model output. In this work we extend this concept to the case where the training problem is formulated as the minimization of the integral of the squared error, along the input domain. With this approach, the gradient-based non-linear optimization algorithms require the computation of terms that are either dependent only on the model and the input domain, and terms which are the projection of the target function on the basis functions and on their derivatives with respect to the nonlinear parameters. These latter terms can be numerically computed with the data provided. The use of this functional approach brings at least two advantages in comparison with the standard training formulation: firstly, computational complexity savings, as some terms are independent on the size of the data and matrices inverses or pseudo-inverses are avoided; secondly, as the performance surface using this approach is closer to the one obtained with the true (typically unknown) function, the use of gradient-based training algorithms has more chance to find models that produce a better fit to the underlying function. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploiting the functional training approach in Radial Basis Function networks

    Publication Year: 2011 , Page(s): 1 - 6
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3563 KB) |  | HTML iconHTML  

    This paper investigates the application of a novel approach for the parameter estimation of a Radial Basis Function (RBF) network model. The new concept (denoted as functional training) minimizes the integral of the analytical error between the process output and the model output [1]. In this paper, the analytical expressions needed to use this approach are introduced, both for the back-propagation and the Levenberg-Marquardt algorithms. The results show that the proposed methodology outperforms the standard methods in terms of function approximation, serving as an excellent tool for RBF networks training. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved back-propagation algorithm for neural network training

    Publication Year: 2011 , Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (893 KB) |  | HTML iconHTML  

    Recently, Artificial Neural Networks (ANNs) have become popular because they can learn complex mappings from the input/output data and are relatively easy to implement in any application. Although, a disadvantageous aspect of their usage is that they need (usually a significant amount of) time to be trained, which scales with the structural parameters of the networks and with the quantity of the input data. However, the training can be done offline; it has a non-negligible cost and further, can cause a delay in the operation. Fuzzy Neural Networks (FNNs) are the combinations of ANNs and fuzzy logic in order to incorporate the advantages of both methods (the learning ability of ANNs and the thinking ability of fuzzy logic). FNNs have fuzzy values in their weight parameters and in the output of each neuron. Circular Fuzzy Neural Networks (CFNNs) are FNNs with their topology realigned to a circular topology and the connections between the input layer and hidden layer trimmed. This may result in a dramatic reduction in the training time, while the precision and accuracy of the network are not affected. To further increase the speed of the training of the ANNs, FNNs, or CFNNs used for classification, a new training procedure is introduced in this paper: instead of directly using the training data in the training phase, the data is first clustered and the neural networks are trained by using only the centers of the obtained clusters. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Genetic algorithm for searching a Doppler resilient multilevel complementary waveform

    Publication Year: 2011 , Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4764 KB) |  | HTML iconHTML  

    This work proposes the use of Genetic Algorithms (GAs) to search a Doppler resilient multilevel complementary pair of sequences. The fitness function deals with the desired ambiguity function to be fit, while it minimizes the crest factor of the resulting sequences. The simulated results show how the waveform obtained has a better performance than that achieved with binary sequences. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A solution for delivery problem based on HIMS model and service science

    Publication Year: 2011 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (911 KB) |  | HTML iconHTML  

    A solution for the delivery problem (vehicle routing, scheduling, and dispatching problem with single depot) is proposed to bridge the gap between conventional methods and complex situations in the real world. The HIMS model (a computational model with Hierarchical Multiplex Structure) is also applied for solving the delivery problem. The HIMS model contains 3 layers: Atomic layer (system cost can be controlled by a heuristic method), Molecular layer (system state can be adjusted by a heuristic method and an optimal calculation), and Individual layer (a system balance can be modified based on information technology service). Experiments with two cases (full or minimum working vehicles) are performed. The experimental results and the evaluations by experts show that the solution provides a feasible and efficient tool to solve the delivery problem in the real world. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent IP traffic matrix estimation by neural network and genetic algorithm

    Publication Year: 2011 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (655 KB) |  | HTML iconHTML  

    Rapid growth of computer network scales has made traffic matrix estimation essential in network management. It can be used in load balancing, traffic detecting and so on. Since traffic should be considered temporally and spatially, prediction is complicated. Tracking dynamic changes of traffic, reducing estimation errors and increasing robustness to noise are factors which should be considered in estimation. In this paper, we propose a novel method to estimate traffic matrix. This approach combines artificial neural network and evolutionary algorithms. It uses autoregressive model with exogenous inputs (ARX) joined with genetic algorithm (GA) which we call it ARXGEN. GA is used in gaining optimized weights and biases. To evaluate our method, we did our simulations on Abilene data. Results prove that it can well track dynamic nature of traffic and has lower estimation errors. It is also more robust to noise. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experimental analyses of mutual shadowing effect for multiple target tracking by UWB radar

    Publication Year: 2011 , Page(s): 1 - 4
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1534 KB) |  | HTML iconHTML  

    Ultra wideband (UWB) radars have appeared as the suitable technology for detection and tracking of moving persons in critical situations and environments. The experimental results of handheld UWB radar application for multiple moving persons tracking have shown that for such scenarios the target located nearby the radar antennas is very often visible only. The other targets can be also detected but with less reliability than that of the target located the most closely to the radar antennas. In this paper, we will outline an origin of this effect as the impact of the mutual shadowing of targets at the multiple persons tracking scenario. This explanation will be confirmed by the experimental measurements. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MMSE speech enhancement based on GMM and solving an over-determined system of equations

    Publication Year: 2011 , Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (740 KB) |  | HTML iconHTML  

    A new and effective algorithm is proposed in this paper based on Gaussian Mixture Modelling (GMM) and Minimum Mean Square Error (MMSE) criterion for speech enhancement where no assumption is made on the nature or stationarity of the noise. No Voice Activity Detection (VAD) or any other means is used to estimate the input Signal to Noise Ratio (SNR). The mean vectors of the mixture models of spectral magnitudes derived from models of speech and different noise sources power spectra are used to form sets of over-determined system of equations, as many as noise source candidates, whose solutions lead to the MMSE estimations of speech and additive noise spectral magnitudes. The corresponding power spectra are then used for noise suppression by applying Wiener filtering carried out on overlapping frames. The input SNR is estimated and the nature of the noise involved is determined as by-products of the method used. Results are compared with codebook constrained methods that have shown very good results but suffer from long processing times. It is shown that, at the cost of a slight lower improvement in SNR and PESQ score, the new algorithm reduces the computation time to one fifth which makes it suitable for practical applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the use of NMF for onset detection in poliphonic piano music

    Publication Year: 2011 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (737 KB) |  | HTML iconHTML  

    Recently the use of non-negative matrix factorization (NMF) for music onset detection has been proposed. In this paper we present the results of an experimental evaluation of NMF for onset detection of piano music. The test results, concerning a publicly available dataset of piano music, show a good performance of NMF, almost invariant from the factorization rank. However, better results have been obtained using simplified onset detection techniques, with lower computational complexity of implementation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Chaos synchronization in Duffing systems with Robust Fixed Point Transformations

    Publication Year: 2011 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (873 KB) |  | HTML iconHTML  

    Nowadays Lyapunov's second method is the most prevailing solution in adaptive control problems. Despite of the idea being splendid, recently other solutions have come up which seem to be more beneficial in some cases. One of these methods is the family of Robust Fixed Point Transformations (RFPT) which proved to be effective in several areas, for example in Classical Mechanical Systems, Electromechanical Systems and in the frames of Model Reference Adaptive Controllers (MRAC). In this paper a novel application of RFTP, the synchronization of two chaotic Duffing systems is shown. Numerical simulations illustrate and confirm the usefulness of the procedure. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pitfalls in using Dual Tree Complex Wavelet Transform for texture featuring: A discussion

    Publication Year: 2011 , Page(s): 1 - 6
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1136 KB) |  | HTML iconHTML  

    Dual Tree Complex Wavelet Transforms (DTCWT) have arisen a lot of interest in the last decade. With the possibility of computing characteristics which are rotation invariable and respond well to oscillations around singularities, shift variance, aliasing and the lack of directionality, DTCWT is an interesting tool to be analyzed and employed in a lot of stages of image processing, (among them being texture featuring). Characteristics that are well observable with the human eye, have to be scaled and transformed, in order to be compared and measured under the similarity aspects. A discussion and technical remarks on these aspects are presented, to well understand them, avoiding strange pitfalls. View full abstract»

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