Data hiding based on image texture classification

In this paper, a new pattern-based fragile, semi-blind, spatial domain data hiding scheme is proposed. The Local Binary Pattern texture classification approach is used, in order to transparently and securely embed secret data into an image. Pixel values are modified in such a way that the texture satisfies the message requirements. The method is thoroughly studied and compared to other techniques in spatial domain in terms of capacity and image quality. The scheme performs well in images with smooth areas and can be used for authentication, tamper proofing, and secret communications.     

OPC-SMS: a wireless gateway to OPC-based data sources

This paper describes OPC-SMS gateway, a platform that integrates IP networks with the Short Message Service (SMS), in order to deliver an integrated service for access to data sources conforming to Object Linking and Embedding for Process Control (OPC) standard specifications, through SMS-enabled mobile devices. The gateway supports pull and push services in order to support both request-based and alarm/scheduled-based notifications, respectively. The proposed architecture is based entirely on the ubiquitous HyperText Transport Protocol (HTTP), Simple Object Access Protocol (SOAP), Extensible Markup Language (XML) protocols, and the Global System for Mobile communication (GSM) network and thus exploits the network infrastructure already in place. The capability of accessing different types of OPC data sources (real-time and historical) by any SMS-enabled device consists of a highly flexible service, supporting mobility and event-based notification. A pilot implementation of our approach has been tested in a large-scale installation for accessing OPC data sources of several automation subsystems in a hospital.     

Input Feature Extraction for Multilayered Perceptrons Using Supervised Principal Component Analysis

A method is proposed for constructing salient features from a set of features that are given as input to a feedforward neural network used for supervised learning. Combinations of the original features are formed that maximize the sensitivity of the network's outputs with respect to variations of its inputs. The method exhibits some similarity to Principal Component Analysis, but also takes into account supervised character of the learning task. It is applied to classification problems leading to improved generalization ability originating from the alleviation of the curse of dimensionality problem.     

Skin color-based video segmentation under time-varying illumination

A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin-color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and predictions of the Markov model. The evolution of the skin-color distribution at each frame is parameterized by translation, scaling, and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and resampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using Maximum Likelihood Estimation and also evolve over time. The accuracy of the new dynamic skin color segmentation algorithm is compared to that obtained via a static color model. Segmentation accuracy is evaluated using labeled ground-truth video sequences taken from staged experiments and popular movies. An overall increase in segmentation accuracy of up to 24 percent is observed in 17 out of 21 test sequences. In all but one case, the skin-color classification rates for our system were higher, with background classification rates comparable to those of the static segmentation.     

The Wave & Probe Communication Mechanisms

This paper is motivated by the modifications recently suggested to enhance TCP performance over wireless channels. We argue that TCP end-to-end error-control mechanism lacks the functionality to respond appropriately in situations where errors vary in nature, frequency, or duration. As a result, this mechanism could, under some circumstances, yield zero throughput achievements at high energy-cost, or degrade throughput performance without conserving energy. This incompetent behavior with respect to the energy/throughput tradeoff puts in question TCP's suitability as a universal, reliable transport protocol of choice, especially for battery-powered mobile devices for which energy is a critical resource and congestion is not the exclusive cause of errors.We propose Wave and Probing communication and control mechanisms that permit end-to-end protocols to detect congestion without necessarily experiencing packet drops, to distinguish random and burst errors from congestion, and, as conditions vary, to rapidly adjust the transmission window upwards or downwards depending on the nature of the error. We report extensively on the performance of these new mechanisms to demonstrate their energy-conserving and high-throughput capabilities.     

Context-based caching and routing for P2P web service discovery

In modern heterogeneous environments, such as mobile, pervasive and ad-hoc networks, architectures based on web services offer an attractive solution for effective communication and inter-operation. In such dynamic and rapidly evolving environments, efficient web service discovery is an important task. Usually this task is based on the input/output parameters or other functional attributes, however this does not guarantee the validity or successful utilization of retrieved web services. Instead, non-functional attributes, such as device power features, computational resources and connectivity status, that characterize the context of both service providers and consumers play an important role to the quality and usability of discovery results. In this paper we introduce context-awareness in web service discovery, enabling the provision of the most appropriate services at the right location and time. We focus on context-based caching and routing for improving web service discovery in a mobile peer-to-peer environment. We conducted a thorough experimental study, using our prototype implementation based on the JXTA framework, while simulations are employed for testing the scalability of the approach. We illustrate the advantages that this approach offers, both by evaluating the context-based cache performance and by comparing the efficiency of location-based routing to broadcast-based approaches. Recommended by: Zakaria Maamar     

On the properties of an additive increase rate accelerator

We propose AIRA, an Additive Increase Rate Accelerator. AIRA extends AIMD functionality towards adaptive increase rates, depending on the level of network contention and bandwidth availability. In this context, acceleration grows when resource availability is detected by goodput/throughput measurements and slows down when increased throughput does not translate into increased goodput as well. Thus, the gap between throughput and goodput determines the behavior of the rate accelerator.We study the properties of the extended model and propose, based on analysis and simulation, appropriate rate decrease and increase rules. Furthermore, we study conditional rules to guarantee operational success even in the presence of symptomatic, extra-ordinary events. We show that analytical rules can be derived for accelerating, either positively or negatively, the increase rate of AIMD in accordance with network dynamics. Indeed, we find that the “blind”, fixed Additive Increase rule can become an obstacle for the performance of TCP, especially when contention increases. Instead, sophisticated, contention-aware additive increase rates may preserve system stability and reduce retransmission effort, without reducing the goodput performance of TCP.     

Less Impact Better Service (LIBS)

We discuss a new packet service paradigm, called “Less Impact Better Service” (LIBS). In simple terms, LIBS primarily schedules packets based on the delay they cause and cancels service differentiation policies when the cumulative delay due to prioritization becomes significant for non-prioritized packets. Based on LIBS, we evaluate different service policies that prioritize small packets using different service boundaries and we show that, by and large, LIBS satisfies better a number of applications with diverse demands in delay and throughput. We emphasize on Voice over IP applications, which are delay-sensitive but also utilize small packets and rates. Among other traditional performance measures, we also measure fairness in the context of LIBS, that is, we address the question whether the delay experienced per flow is proportional to the delay caused by that flow. We obtained very promising simulation results.