By Topic

Signal Processing and Information Technology(ISSPIT), 2013 IEEE International Symposium on

Date 12-15 Dec. 2013

Filter Results

Displaying Results 1 - 25 of 87
  • KnowYourColors: Visual dashboards for blood metrics and healthcare analytics

    Page(s): 000002 - 000008
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2838 KB) |  | HTML iconHTML  

    The understanding of medical test results is markedly improved through the use of visual analytics. While traditional theorists in the field of healthcare analytics seek to improve decision making through data mining and machine learning, Visual Analytics augments that intelligence by providing an interface to integrate all of the data in a composite image. KnowYourColors™ is a visual analytics interface providing many dashboards to help the healthcare and insurance providers make better decisions in treatment and spending. This paper discusses many of the visualizations that are used in those applications. This includes new visualizations focused around polar area diagrams that are designed for showing blood metrics and visualizations of prior research work that help in the decision making process. This paper also demonstrates the effectiveness of the application and the reactions of physicians and patients. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Teleassistance outdoor system for the elderly based on Android devices

    Page(s): 000009 - 000014
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (821 KB) |  | HTML iconHTML  

    This article presents a work in progress system for helping people who are suffering from disorientation episodes outside their houses, such as with their family. This is a WIP (Work In Progress). The system is based on modern smartphones and their capacity, using GPS, to locate the user on a map, as well as featuring computing power and Internet connection via 3G. The caregivers also have a web-based application to monitor and configure the alarms that are triggered. The web application contains maps in order to define secure zones, send instant messages to the mobile application, and set events in a calendar and a log with all events that have occurred in the system. Piloting is being undertaken by Osatek and BetiOn, the Basque country teleassistance service. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Increasing security in wireless e-health systems

    Page(s): 000015 - 000020
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (201 KB) |  | HTML iconHTML  

    In this paper, we identify the security and privacy issues specific to wireless health monitoring devices and describe solutions for protecting wireless communications against side channel attacks and in particular traffic analysis attacks. This process takes place by means of data obfuscation and modifications of communication protocol architectures in order to limit exposed information of system architecture to potential attackers. Initial network simulations of the proposed methods show the feasibility of these methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Welcome message from the general co-chairs

    Page(s): 000021
    Save to Project icon | Request Permissions | PDF file iconPDF (48 KB)  
    Freely Available from IEEE
  • Final program

    Page(s): 000022 - 000033
    Save to Project icon | Request Permissions | PDF file iconPDF (6119 KB)  
    Freely Available from IEEE
  • Developing time constraints in Petri net models of biochemical processes via computation structure modeling

    Page(s): 000034 - 000039
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (649 KB) |  | HTML iconHTML  

    Computation structure modeling can be applied to a model of a biochemical process. We present an application of computation structure model analysis to a published Petri net model of part of an inflammation process. From this computation structure model and published experimental data we develop a timing constraint. Because the number of possible biochemical reactions in the human cell is distressingly large, recognizing existing constraints upon what reactions can occur, such as when potential reactants are sequestered in different compartments, or steric constraints prohibit docking, provides needed reduction of these possibilities. Modeling with networks, including Petri nets, is common in systems biology and constraint application can be visualized acting upon these graphs, pruning subtrees from a network of possibilities. The technique is complementary to stochastic simulations algorithms and to T and P-invariant analysis of Petri nets. We apply the modeling technique to spliceosome acting on C9ORF72 intronic hexanucleotide repeats, to illustrate one effect of this repeat on splicing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic Connection Strategies (DyConS) for spoken Malay speech recognition

    Page(s): 000040 - 000045
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (870 KB) |  | HTML iconHTML  

    This paper presents the fusion of artificial intelligence (AI) learning algorithms that are genetic algorithms (GA) and conjugate gradient (CG) methods. Both methods are used to find the optimum weights for the hidden and output layers of feedforward artificial neural network (ANN) model. Each algorithm is presented in separate module and we proposed three different types of Dynamic Connection Strategies (DyConS) for combining both algorithms to improve the recognition performance of spoken Malay speech recognition. Two different GA techniques are used in this research: a mutated GA technique is proposed and compared with the standard GA technique. One hundred experiments with 5000 words are conducted using the proposed DyConS. Owing to previous facts, GA combined with ANN proved to attain certain advantages with sufficient recognition performance. Thus, from the results, it was observed that the performance of mutated GA algorithm when combined with CG is better than standard GA and CG models. Integrating the GA with feed-forward network improved mean square error (MSE) performance and with good connection strategy by this two stage training scheme, the recognition rate is increased up to 99%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel approach on hybrid Support Vector Machines into optimal portfolio selection

    Page(s): 000046 - 000051
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2036 KB) |  | HTML iconHTML  

    The efficient representation of the accurate corporate value on the stock price is vital to investors and fund managers that desire to optimize the net worth of the overall stock portfolio. Although Efficient Market Hypothesis sets limits, the practice of markets is an ideal place of manipulation, and corruption on prices. The accounting statements, evaluated by Support Vector Machines and the SVM Hybrids under Genetic Algorithms provide excellence in portfolio selection. A specific Neuro-genetic Hybrid SVM outperformed all examined SVM models being a powerful tool in financial analysis. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance analysis of mobile communication networks in the presence of composite fading, noise and interference

    Page(s): 000052 - 000057
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1728 KB) |  | HTML iconHTML  

    In this paper, the effects of interference on composite fading environments, where multipath fading coexists with shadowing, are investigated. More specifically, important statistical metrics of a single receiver output signal to interference and noise ratio (SINR) are studied, including the probability density function and the cumulative distribution function. Our analysis is also extended to multi-channel receivers and in particular to selection diversity (SD) receivers. For all scenarios, simplified expressions are also provided for the interference limited cases, where the influence of thermal noise is ignored. The derived expressions are used to analyze the performance, in terms of the average bit error probability and the outage probability. The analysis is accompanied by numerical evaluated results, clearly demonstrating the usefulness of the proposed theoretical framework. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applying event-driven architecture to mobile computing

    Page(s): 000058 - 000063
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (524 KB) |  | HTML iconHTML  

    Complex event processing (CEP) has been an area of intensive research in recent years. Similarly, mobile devices such as smartphones, tablets and laptops are widespread nowadays. Consequently, the integration of CEP into mobile computing is a natural idea. In this paper, we present MetaXA, an event-driven architecture (EDA) with CEP specifically designed for mobile devices, along with its application scenarios in mobile computing: notification distribution and theft detection. Among the main enhancements of MetaXA over previously published work are enabling CEP on mobile devices and leveraging a lightweight yet still platform-independent communication protocol (viz., XMPP). In addition, MetaXA features real-time communication patterns and a publish-subscribe mechanism. MetaXA is implemented on different mobile platforms: Android and Windows Phone. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Effects of different prediction schemes on lossless invisible watermarking

    Page(s): 000064 - 000068
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (603 KB) |  | HTML iconHTML  

    In view of high data embedding capacity and many real time applications, we have proposed a reversible invisible watermarking algorithm. The technique is used to embed a set of watermark data in an image using a one pass embedding process and later recovering the original image without any loss, after the extraction of watermark. Main motivation behind this work is the usage of two different prediction schemes-Weighted Causal Average and Context Based Image Compression Algorithm, to obtain two images similar to the original image, and using the error pattern resulted from the two predicted images to embed data depending upon the nature of image. Based on this error pattern, binary data is embedded in an image using two different embedding schemes- Bijective Mirror Mapping technique and Histogram Shifting Algorithm, resulting in better embedding capacity or payload capacity and better PSNR than other reversible one-pass watermarking algorithms mentioned in literature. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An algorithm based on Google Trends' data for future prediction. Case study: German elections

    Page(s): 000069 - 000073
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (566 KB) |  | HTML iconHTML  

    The analysis of the high volume of statistics generated by web search engines worldwide on a daily basis, allow researchers to examine the relation between the user's search preferences and future facts. This analysis can be applied to various areas of society such as sales, epidemics, unemployment and elections. The paper investigates whether prediction of election results is possible by analyzing the behavior of potential voters before the date of the elections. In particular, the proposed algorithm is applied on the three more recent German elections. The results of this analysis show that a strong correlation exists between the search preferences of potential voters before the date of the election race and the actual elections results. It also demonstrates the fact that search preferences are influenced by various social events that may take place concurrently to the election race. The effect of such events has to be filtered out as noise in order to arrive at a successful estimation of the final results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enhanced quality adaptation strategies for Scalable Video

    Page(s): 000074 - 000079
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (915 KB) |  | HTML iconHTML  

    Technology today favors tightly compressed, but still extremely high quality video transmitted wireless to mobile devices. Users want to access the video data anytime, anywhere, which sets challenges in the highly-loaded network to provide best possible video quality for the end user. Naturally, in the era of high-definition, users want to experience high quality from their mobile devices even when the channel capacity fluctuates drastically due to congestion. Video adaptation to bandwidth fluctuations plays an important role in modern video transmission in order to maximize the best available video quality, but again to use available bandwidth efficiently. In this paper, we aim to find the best strategy for how the adaptation should be performed, to find sufficient adaptation period and number of layers that maximize the compression efficiency, usage of channel resources and objective quality in video streaming. For the compression, we utilize Scalable Video Coding (SVC), which provides layered video structure and enables video adaptation to bandwidth fluctuations. The results indicate that long adaptation period with complex content encoded for two enhancement layers brings essential channel savings while also maintaining the compression efficiency and objective quality in adequate level. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparative analysis of classification techniques for building block extraction using aerial imagery and LiDAR data

    Page(s): 000080 - 000085
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (435 KB) |  | HTML iconHTML  

    Building detection has been a prominent area in the area of image classification. Most of the research effort is adapted to the specific application requirements and available datasets. In this paper we present a comparative analysis of different classification techniques for building block extraction. Our dataset includes aerial orthophotos (with spatial resolution 20cm), a DSM generated from LiDAR (with spatial resolution 1m and elevation resolution 20 cm) and DTM (spatial resolution 2m) from an area of Athens, Greece. The classification methods tested are unsupervised (K-Means, Mean Shift), and supervised (Feed Forward Neural Net, Radial-Basis Functions, Support Vector Machines). We evaluated the performance of each method using a subset of the test area. We present the classified images, and statistical measures (confusion matrix, kappa coefficient and overall accuracy). Our results demonstrate that the top unsupervised method is the Mean Shift that performs similarly to the best supervised methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative image auto-annotation

    Page(s): 000086 - 000091
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (464 KB) |  | HTML iconHTML  

    The image annotation is an effective technology for improving the Web image retrieval. Many works have been proposed to increase the image auto-annotation performance. The annotation quality depends on many factors: segmentation, choice of visual features...etc.. An image contains several visuals information (color, texture, shape....) but the best choice of these parameters is a difficult problem. The main focus of this paper is two-fold. First, we compare between image annotations in latent space and textual space. Second, we survey influence of visual features choice on image annotation. For that, we developed two image auto-annotation systems (AIA-LSA, AIA-WLSA). For each one, we propose three prototypes based on different visual descriptors; such as: texture, color and fusion of both parameters. Corel data set is used to experiment our prototypes, the results show that the annotation by latent space is more efficient than the annotation by textual space and the best choice of visual features is a persistent problem in general images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance and power trade-offs for cryptographic applications in embedded processors

    Page(s): 000092 - 000095
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (579 KB) |  | HTML iconHTML  

    Cryptographic operations are resource-intensive in terms of computational power and energy consumption. Typical approaches towards secure embedded systems employ dedicated modules, such as ASICs, co-processors, and accelerators, to implement these functions and optimize these hardware modules for the adopted algorithms. In our work, we analyze performance and power trade-offs of typical cryptographic algorithms (DES, AES, and RSA) when executed in processing elements that constitute typical embedded processors. Our goal is to characterize and optimize, performance-wise and power-wise, the sources of inefficiency when the encryption/decryption operations are executed in general purpose embedded processors with different processing and caching capabilities. Our analysis focuses on three major parameters: the parallelism of the core (issue width and size of execution window), voltage and frequency switching in the core, and size of the last-level cache (LLC). Those parameters constitute the major power-consumption contributors in all modern embedded general purpose processors. Our results demonstrate that cryptographic operations can be performed efficiently, in terms of both performance and power consumption, for specific values of the analyzed parameters, indicating that reconfigurable approaches can dynamically optimize processor organization and ameliorate the reported performance and power figures in the context of general purpose embedded processors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Phone classification using HMM/SVM system and normalization technique

    Page(s): 000096 - 000101
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (159 KB) |  | HTML iconHTML  

    Support vector machines (SVM) were originally developed for binary classification and extended for multi-class classification. Due to their powerfulness and adaptation to hard classification problems, we have chosen them for automatic speech recognition (ASR). The aim of this paper is to investigate the use of SVM multi-class classification coupled with HMM for TIMIT phones. SVM requires that all data samples for training and test to have the same features vector size. Due to the variability in length of phone signals even for the same phone, we have used a normalization technique: zero padding and resampling on all data samples to get them have features vector with the same size. After mapping the 61 TIMIT phones in 46 phones and conducting tests using LibSVM and HTK, we have obtained a classification accuracy rate of 91.26% with the hybrid HMM/SVM system and 71.41% with the HMM-based system. These results show that the hybrid HMM/SVM system using the normalization technique overcomes an HMM-based system and improves the recognition accuracy by 19.8%. Therefore, our experiments result encouraged us to use this hybrid system and normalization technique for the next work in the context of spoken dialogue system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploiting metropolitan optical networks for high speed interconnections at schools

    Page(s): 000102 - 000107
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1568 KB) |  | HTML iconHTML  

    This work presents the interconnection scheme for Greek School Network that is heavily relied on well-established metropolitan optical networks. The case of the metropolitan optical network located at the Municipality of Kalamata is analyzed and the potential large-scale deployment of this networking scheme is examined. Also, critical security aspects are briefly discussed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The analysis of an NMF-based perceptual image hashing scheme

    Page(s): 000108 - 000112
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (408 KB) |  | HTML iconHTML  

    This paper analyzes a recently introduced perceptual image hashing scheme. This scheme uses non-negative matrix factorization (NMF) as the feature of the image on the secondary image obtained by the ring partitioning of the original one. The image hash is rotation-invariant with arbitrary degree but it is robust against acceptable content-preserving image modifications. We re-visit the algorithm and show that the algorithm tolerates some serious security flaws. Ignoring specific areas of the image in the feature extraction stage and invariance against individual ring rotation are two existing drawbacks. Practical experiments show the mentioned weaknesses and some solutions will be proposed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Empirical channel models for optimized communications in a network of unmanned ground vehicles

    Page(s): 000113 - 000118
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2756 KB) |  | HTML iconHTML  

    Extensive research has been conducted on unmanned ground vehicles (UGVs), used for critical applications, such as military or search and rescue operations. As all those unmanned vehicles use wireless communications due to mobility constraints, it is therefore important to further define the limits of high reliability communication links in operational environments. The practical importance of this study relates to applications where antennas are located very close to plane surfaces e.g. small, unmanned, vehicles used for exploration, monitoring or rescue purposes in confined spaces. An empirical channel model allows better understanding of the RF propagation mechanisms and enables optimisation of the sensor network with certain reliability levels. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Content management and protection in Smart Cities IP - Based backbone Wireless Sensors Networks

    Page(s): 000119 - 000123
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (561 KB) |  | HTML iconHTML  

    Nowadays in modern and ubiquitous computing environments, it is imperative more than ever, the necessity for deployment of Wireless Sensor Networks, which can be used as backbone networks in order to convey different types of digital contents that are locally generated by public utility application servers. Such environments must be developed satisfying the basic security requirements for real-time, secure data communication, and protection of data and measurements, data integrity and confidentiality. In this work, we argue that the MPEG-21 Intellectual Property Management and Protection components can be used in order to achieve protection of transmitted information, since there is selective and controlled access to data that sent towards the central servers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A lightweight anonymity & location privacy service

    Page(s): 000124 - 000129
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (801 KB) |  | HTML iconHTML  

    As embedded systems, in their various forms, become ubiquitous, new types of services are offered, aiming to enhance every aspect of the everyday life and allowing users to enjoy pervasive and personalized access to information. Along with the benefits come considerable threats to users' privacy, as these enhanced services operate on private sensitive information, such as the true identity and location of users. This paper proposes a lightweight, distributed anonymity and location privacy service which can be deployed on mobile embedded systems (e.g. smart clothing, smart phones), even heterogeneous in nature, allowing users to form communities which help them hide their identities and exact location. Acting as a proxy the proposed service can sanitize users' requests prior to forwarding them to a location-based service (LBS). The deployment of this type of information sanitization proxy would facilitate the wider adoption of the new generation of enhanced reality applications and services, alleviating the justified concerns regarding users' privacy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance of CA-CFAR receivers in alpha-stable clutter

    Page(s): 000130 - 000134
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (692 KB) |  | HTML iconHTML  

    We analyze the performance of a cell averaging constant false alarm rate (CA-CFAR) receiver that operates in a heavy-tailed clutter environment that is modeled by an alpha-stable distribution. Stable distributions are usually characterized with known characteristic function but their probability distribution are not known in closed form except for some special cases of the characteristic exponent α. Therefore, previous performance studies of CFAR in alpha-stable clutter have been limited to only some very special cases of α that correspond to the Gaussian, Cauchy and Pearson distributions, for which the statistical distribution of the clutter is available in closed-form. In this paper, we derive the distribution of the receiver output for arbitrary values of α in terms of the Fox's H-function. The derived statistical distribution is useful in evaluating the false alarm and detection probabilities of the system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The weakest link on the network: Exploiting ADSL routers to perform cyber-attacks

    Page(s): 000135 - 000139
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (283 KB) |  | HTML iconHTML  

    ADSL routers are an integral part of today's home and small office networks. Typically, these devices are provided by a user's ISP and are, usually, managed by people who do not have any special technical knowledge. Often poorly configured and vulnerable, such devices are an easy target for network-based attacks, allowing cyber-criminals to quickly and easily gain control over a network. In this paper, we systematically evaluate the security of ADSL routers and identify the potential of attacks, which attempt to compromise the vulnerabilities of their web interface. More specifically, we present common vulnerabilities and attacks that occur in websites on the Internet, and project them on the special characteristics of the web management interface of ADSL routers. To put this analysis into a practical context, we investigate the security of a popular ADSL router provided by a Greek ISP. In this security assessment, we have discovered two 0-day vulnerabilities in the web management interface of the tested router. In particular, we discovered an operating system (OS) command injection and stored Cross-Site Scripting (XSS) attack. A malicious may exploit these vulnerabilities to perform several large-scale attacks. Specifically, he/she can perform DNS hijacking attack and redirect the users to fake web sites for phishing; mount a Distributed Denial of Service (DDoS) attack using the compromised routers as zombie machines; or even spread a malware. Finally, we discuss some well-known security practices that should be followed from developers and users to enhance the security of ADSL routers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic countermeasure against the Zero Power Analysis

    Page(s): 000140 - 000147
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (874 KB) |  | HTML iconHTML  

    Elliptic Curve Cryptography can be vulnerable to Side-Channel Attacks, such as the Zero Power Analysis (ZPA). This attack takes advantage of the occurrence of special points that bring a zero-value when computing a doubling or an addition of points. This paper consists in analysing this attack. Some properties of the said special points are explicited. A novel dynamic countermeasure is described. The elliptic curve formulæ are updated depending on the elliptic curve and the provided base point. View full abstract»

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