Abstract Automated text classification is a fundamental research topic within the legal domain as it is the foundation for building many intelligent legal solutions. There is a scarcity of publicly available legal training data and these classification algorithms struggle to perform in low data scenarios. Text augmentation techniques have been proposed to enhance classifiers through artificially synthesised training data. In this paper we present and evaluate a combination of rule-based and advanced generative text augmentation methods designed to create additional training data for the task of classification of legal contracts. We introduce a repurposed CUAD contract dataset, modified for the task of document level classification, and compare a deep learning distilBERT model with an optimised support vector machine baseline for useful comparison of shallow and deep strategies. The deep learning model significantly outperformed the shallow model on the full training data (F1-score of 0.9738 compared to 0.599). We achieved promising improvements when evaluating the combined augmentation techniques on three reduced datasets. Augmentation caused the F1-score performance to increase by 66.6%, 17.5% and 2.6% for the 25%, 50% and 75% reduced datasets respectively, compared to the non-augmented baseline. We discuss the benefits augmentation can bring to low data regimes and the need to extend augmentation techniques to preserve key terms in specialised domains such as law.

Strategic investment(s) in vehicle automation technologies led to the rapid development of technology that revolutionised transport services and reduced fatalities on a scale never seen before. Technological advancements and their integration in Connected Autonomous Vehicles (CAVs) increased uptake and adoption and pushed firmly for the development of highly supportive legal and regulatory and testing environments. However, systemic threats to the security and privacy of technologies and lack of data transparency have created a dynamic threat landscape within which the establishment and verification of security and privacy requirements proved to be an arduous task. In CAVs security and privacy issues can affect the resilience of these systems and hinder the safety of the passengers. Existing research efforts have been placed to investigate the security issues in CAVs and propose solutions across the whole spectrum of cyber resilience. This paper examines the state-of-the-art in security and privacy solutions for CAVs. It investigates their integration challenges, drawbacks and efficiencies when coupled with distributed technologies such as Blockchain. It has also listed different cyber-attacks being investigated while designing security and privacy mechanism for CAVs.

Summary Image segmentation plays a crucial role in many image processing and understanding applications. Despite the huge number of proposed image segmentation techniques, accurate segmentation remains a significant challenge in image analysis. This article investigates the viability of using echo state network (ESN), a biologically inspired recurrent neural network, as features extractor for efficient color image segmentation. First, an ensemble of initial pixel features is extracted from the original images and injected into the ESN reservoir. Second, the internal activations of the reservoir neurons are used as new pixel features. Third, the new features are classified using a feed forward neural network as a readout layer for the ESN. The quality of the pixel features produced by the ESN is evaluated through extensive series of experiments conducted on real world image datasets. The optimal operating range of different ESN setup parameters for producing competitive quality features is identified. The performance of the proposed ESN‐based framework is also evaluated on a domain‐specific application, namely, blood vessel segmentation in retinal images where experiments are conducted on the widely used digital retinal images for vessel extraction (DRIVE) dataset. The obtained results demonstrate that the proposed method outperforms state‐of‐the‐art general segmentation techniques in terms of performance with an F‐score of 0.92 ± 0.003 on the segmentation evaluation dataset. In addition, the proposed method achieves a comparable segmentation accuracy (0.9470) comparing with reported techniques of segmentation of blood vessels in images of retina and outperform them in terms of processing time. The average time required by our technique to segment one retinal image from DRIVE dataset is 8 seconds. Furthermore, empirically derived guidelines are proposed for adequately setting the ESN parameters for effective color image segmentation.

People are interacting increasingly with systems through voice assistants and chatbots sectors such as banking and financial are adopting them to create more responsive customer services. This project aimed to implement a web-based chatbot to assist with online banking, using tools that expose artificial intelligence methods such as natural language understanding. The chatbot allows users to view all their personal banking information from within the chatbot. The system was tested across a range of devices such as Google Home and Assistant on android devices to outline the key differences between the two modes of interaction, spoken and text dialog. These tests showed that chatbots can enhance accessibility, reaffirming that they are more than just a passing fad and have a viable use.

Location‐aware services enable location intelligence which provides many benefits such as personalisation of communications, consumer analytics, locating a fireman in a burning building or classifying daily activities in the home among numerous other services. Active localisation technology is where a person carries a device such as a phone or beacon which communicates with a nearby wireless access point, whereas passive localisation is where a person does not carry any electronic device but their presence in a room causes a nearby monitoring device to detect them. This is the holy grail of tracking people as they do not need to carry tracking devices. A hybrid tracking approach is where both active and passive tracking techniques can be used to complement each other in tracking individuals indoors. This study provides an overview of an indoor location framework which allows the plugging in of multiple active tracking solutions such as Bluetooth beacons in addition to facilitating passive localisation techniques to provide a flexible hybrid indoor tracking solution for pinpointing individuals in locations and accordingly classify their activities. The authors demonstrate the practicalities of such a technique when used to classify everyday activities of daily life within a typical home environment.

Identification of persons by way of biometric features is an emerging phenomenon. Over the years, biometric recognition has received much attention due to its need for security. Amongst the many existing biometrics, fingerprints are considered to be one of the most practical ones. Techniques such as watermarking and steganography have been used in attempt to improve security of biometric data. Watermarking is the process of embedding information into a carrier file for the protection of ownership/copyright of music, video or image files, whilst steganography is the art of hiding information. This paper presents an overview of steganography techniques applied in the protection of biometric data in fingerprints. It is novel in that we also discuss the strengths and weaknesses of targeted and blind steganalysis strategies for breaking steganography techniques.

OBJECTIVE: Current methods of assessing the affect patients' health has on their daily lives are extremely limited. The aim of this paper is to develop a sensor-based approach to health status measurement in order to objectively measure health status. METHODS: Techniques to generate human behavior profiles, derived from the smartphone accelerometer and gyroscope sensors, are proposed. Experiments, using SVM regression models, are then conducted in order to evaluate the use of the proposed behavior profiles as a predictor of health status. RESULTS: Experiments were conducted on data from 171 participants, with an average of 114 h of data per participant. Regression models were trained and tested on the 10 SF-36 self-ratings. Results showed that the eight individual SF-36 scales and two component scores could be predicted with an average correlation of 0.683 and 0.698, respectively. General health was predicted with an average correlation of 0.752. CONCLUSION: Research shows that the clinically important difference for SF-36 self-ratings are approximately 10 points. Health status prediction errors in this study were 11.7 points on average. While the problem has not been fully solved, this paper presents a hugely promising direction for health status prediction. SIGNIFICANCE: Using the proposed techniques, health status could be measured using unobtrusive, inexpensive, and already available hardware. It could provide a means for clinicians to accurately and objectively assess the daily life benefits of treatments on an individual patient basis.

Image segmentation refers to the process of dividing an image into multiple regions which represent meaningful areas. Image segmentation is an essential step for most image analysis tasks such as object recognition and tracking, pattern recognition, content-based image retrieval, etc. In recent years, a large number of image segmentation algorithms have been developed, but achieving accurate segmentation still remains a challenging task. Recently, reservoir computing (RC) has drawn much attention in machine learning as a new model of recurrent neural networks (RNN). Echo State Network (ESN) represents one efficient realization of RC, which is initially designed to facilitate learning in Recurrent Neural Networks. In this paper we investigate the viability of ESN as feature extractor for pixel classification based colour image segmentation. Extensive experiments are conducted on real world colour image datasets and the global ESN reservoir parameters are varied to identify their operating ranges that allow the use of the reservoir nodes internal activations as new pixel features for the colour image segmentation task. A simple feed forward neural network is used to realize the ESN readout function and classify these new features. The experimental results show that the proposed method achieves high performance image segmentation comparing with state-of-the-art techniques. In addition, a set of empirically derived guidelines for setting the reservoir global parameters are proposed.

Abstract The benefits of Cloud computing include reduced costs, high reliability and the immediate availability of additional computing resources as needed. Despite such advantages, Cloud Service Provider (CSP) consumers need to be aware that the Clouds poses its own set of unique risks that are not typically associated with storing and processing one's own data internally using privately owned infrastructure. New techniques such as Searchable Encryption are being deployed to enable data to be encrypted online. Despite being a relatively obscure form of Cryptography, Searchable Encryption is now at the point that it can be deployed and used within the Cloud. Searchable Encryption can allow CSP customers to store their data in encrypted form, while retaining the ability to search that data without disclosing the associated decryption key(s) to CSPs. Searchable Encryption is a diverse subject that exists in many forms. Searchable Symmetric Encryption (SSE) which has its roots in plaintext searching is one such form. Although symmetrically encrypted ciphertext cannot be searched in the same manner; nonetheless, many of the principles that apply to plaintext searching also apply to SSE. In its most basic form, SSE is nothing more than an Inverted Index—a mechanism that has been used in plaintext Information Retrieval (IR) for decades—that has been modified and adapted for use with ciphertext. We implement an SSE scheme and evaluate the efficiency of storing and retrieving data from the cloud. The results showed that carrying out a task using SSE is directly proportional to the amount of information involved. In the case of constructing an IR Inverted Index, the results show that the time taken to generate an IR Inverted Index is directly proportional to the number of Terms contained in the underlying Document Collection. Converting the same IR Inverted Index to an SSE Inverted Index is directly proportional to the number of Postings contained within the IR Inverted Index, while the time taken to encrypt the underlying Document Collection is directly proportional to the number of Terms contained within the Document Collection. In relation to searching in SSE, the time taken to identify and decrypt the set of Postings associated with a given Lexicon Term is directly proportional to the number of Postings. We believe that SSE is efficient enough to be deployed in a Cloud environment especially when results only have to be returned to the user in small quantities. When applied to large Sets, SSE querying can become inefficient as its search time is directly proportional to the number of matching. SSE however is designed to achieve efficient search speeds whilst maintaining Data Privacy. Copyright © 2016 John Wiley & Sons, Ltd.

The concept of devices cooperatively assisting with the localization of other devices in either the indoor or outdoor arena is not a new phenomenon. The primary focus of research into such a theory is however, limited to solving the problem of localization accuracy. In this work, the motivation is to provide a solution to the current range limitations of an Indoor Position System (IPS) in the form of a framework “Cooperatively Applied Positioning Techniques Utilizing Range Extension (CAPTURE)”. These range limitations are the culmination of well documented difficulties of localizing using wireless signals in such Non-Line of Sight (NLOS) environments. The coverage of a localization solution is still a new and challenging issue in the indoor environment. In this paper we implement a version of CAPTURE that uses Wi-Fi Direct and Bluetooth Low Energy (Bluetooth LE 4.0) that take advantage of mobile devices at the outer limits of an IPS to help extend its reach into blind spots, where devices cannot be currently located. CAPTURE is evaluated using a live test environment, where range estimations are recorded between cooperating devices. These range estimations are filtered before being placed into a positioning algorithm to locate lost devices. Finally the accuracy of CAPTURE is presented, demonstrating the achievable benefits of implementing CAPTURE as a solution to the problem of coverage in an Indoor environment.

None of the early internet designers has ever foreseen the pervasiveness of its involvement in everyday life. That is why we have so many security and privacy issues today. The landscape is moving all the time with new smartphones hitting the market and new features being rolled out almost weekly. The standard desktop operating system is quickly being overtaken by computing on mobile devices however many of us are unaware of the security vulnerabilities on mobile devices. This paper highlights the security mechanisms deployed to make mobile devices safe for use. Such mechanisms include the choice of mobile device by the user, encryption, authentication, remote wipe capabilities, lost phone hotline, firewalls, utilisation of third party software, intrusion prevention software, anti-virus software and finally Bluetooth.

Purpose – The interoperability of cloud data between web applications and mobile devices has vastly improved over recent years. The popularity of social media, smartphones and cloud-based web services have contributed to the level of integration that can be achieved between applications. This paper investigates the potential security issues of OAuth, an authorisation framework for granting third-party applications revocable access to user data. OAuth has rapidly become an interim de facto standard for protecting access to web API data. Vendors have implemented OAuth before the open standard was officially published. To evaluate whether the OAuth 2.0 specification is truly ready for industry application, an entire OAuth client server environment was developed and validated against the speciation threat model. The research also included the analysis of the security features of several popular OAuth integrated websites and comparing those to the threat model. High-impacting exploits leading to account hijacking were identified with a number of major online publications. It is hypothesised that the OAuth 2.0 specification can be a secure authorisation mechanism when implemented correctly. Design/methodology/approach – To analyse the security of OAuth implementations in industry a list of the 50 most popular websites in Ireland was retrieved from the statistical website Alexa (Noureddine and Bashroush, 2011). Each site was analysed to identify if it utilised OAuth. Out of the 50 sites, 21 were identified with OAuth support. Each vulnerability in the threat model was then tested against each OAuth-enabled site. To test the robustness of the OAuth framework, an entire OAuth environment was required. The proposed solution would compose of three parts: a client application, an authorisation server and a resource server. The client application needed to consume OAuth-enabled services. The authorisation server had to manage access to the resource server. The resource server had to expose data from the database based on the authorisation the user would be given from the authorisation server. It was decided that the client application would consume emails from Google’s Gmail API. The authorisation and resource server were modelled around a basic task-tracking web application. The client application would also consume task data from the developed resource server. The client application would also support Single Sign On for Google and Facebook, as well as a developed identity provider “MyTasks”. The authorisation server delegated authorisation to the client application and stored cryptography information for each access grant. The resource server validated the supplied access token via public cryptography and returned the requested data. Findings – Two sites out of the 21 were found to be susceptible to some form of attack, meaning that 10.5 per cent were vulnerable. In total, 18 per cent of the world’s 50 most popular sites were in the list of 21 OAuth-enabled sites. The OAuth 2.0 specification is still very much in its infancy, but when implemented correctly, it can provide a relatively secure and interoperable authentication delegation mechanism. The IETF are currently addressing issues and expansions in their working drafts. Once a strict level of conformity is achieved between vendors and vulnerabilities are mitigated, it is likely that the framework will change the way we access data on the web and other devices. Originality/value – OAuth is flexible, in that it offers extensions to support varying situations and existing technologies. A disadvantage of this flexibility is that new extensions typically bring new security exploits. Members of the IETF OAuth Working Group are constantly refining the draft specifications and are identifying new threats to the expanding functionality. OAuth provides a flexible authentication mechanism to protect and delegate access to APIs. It solves the password re-use across multiple accounts problem and stops the user from having to disclose their credentials to third parties. Filtering access to information by scope and giving the user the option to revoke access at any point gives the user control of their data. OAuth does raise security concerns, such as defying phishing education, but there are always going to be security issues with any authentication technology. Although several high impacting vulnerabilities were identified in industry, the developed solution proves the predicted hypothesis that a secure OAuth environment can be built when implemented correctly. Developers must conform to the defined specification and are responsible for validating their implementation against the given threat model. OAuth is an evolving authorisation framework. It is still in its infancy, and much work needs to be done in the specification to achieve stricter validation and vendor conformity. Vendor implementations need to become better aligned in order to provider a rich and truly interoperable authorisation mechanism. Once these issues are resolved, OAuth will be on track for becoming the definitive authentication standard on the web.

Streaming media on the Internet can be unreliable. Services such as audio-on-demand drastically increase the loads on networks; therefore, new, robust, and highly efficient coding algorithms are necessary. One method overlooked to date, which can work alongside existing audio compression schemes, is that which takes into account the semantics and natural repetition of music. Similarity detection within polyphonic audio has presented problematic challenges within the field of music information retrieval. One approach to deal with bursty errors is to use self-similarity to replace missing segments. Many existing systems exist based on packet loss and replacement on a network level, but none attempt repairs of large dropouts of 5 seconds or more. Music exhibits standard structures that can be used as a forward error correction (FEC) mechanism. FEC is an area that addresses the issue of packet loss with the onus of repair placed as much as possible on the listener's device. We have developed a server--client-based framework (SoFI) for automatic detection and replacement of large packet losses on wireless networks when receiving time-dependent streamed audio. Whenever dropouts occur, SoFI swaps audio presented to the listener between a live stream and previous sections of the audio stored locally. Objective and subjective evaluations of SoFI where subjects were presented with other simulated approaches to audio repair together with simulations of replacements including varying lengths of time in the repair give positive results.

The most commonly implemented Indoor Location Based Solution uses existing Wi-Fi network components to locate devices within its range. While this technique offers obvious economic rewards by utilizing a preinstalled infrastructure, these network topologies were typically designed to provide network coverage to mobile devices rather than deliver an Indoor Location Based Solution. Large areas without coverage are common in these networks because network designers were not typically concerned about providing 100% coverage for mobile data. Hallways, toilet areas or other general purpose areas that ordinarily would not require network coverage did not get dedicated WAPs installed. Transient users navigating these areas of the network were un-locatable using this infrastructure. Furthermore the indoor arena is an especially noisy atmosphere, being home to other wireless devices such as Bluetooth Headsets, Cordless Phones and Microwave Ovens. Considering users spend more time in an indoor environment, over 88%, the need for a solution is obvious. Therefore, we propose a solution to resolve the issue of restricted coverage of Indoor Location Based solutions, using a cooperative localization technique - Cooperatively Applied Positioning Techniques Utilizing Range Extension (CAPTURE). CAPTURE offers a method of locating devices that are beyond the range of the current in-house location based solution. It presents a unique contribution to research in this field by offering the ability to utilize devices that know their location within a Location Based Solution (LBS), to evaluate the position of unknown devices beyond the range capacity of the LBS. This effectively extends the locating distances of an Indoor LBS by utilizing the existing mobile infrastructure without the need for any additional hardware. The proliferation of smart phones and the tablet form factor, bundled with Wi-Fi, Bluetooth and gyroscopes - technologies currently used to track position, provide a fertile community for CAPTURE to cooperatively deliver a location solution.

The number of Resource-Limited Wireless Devices utilized in many areas of IT is growing rapidly. Some of the applications of these devices pose real security threats that can be addressed using authentication and cryptography. Many of the available authentication and encryption software solutions are predicated on the availability of ample processing power and memory. These demands cannot be met by the majority of ubiquitous computing devices, thus there is a need to apply lightweight cryptography primitives and lightweight authentication protocols that meet these demands in any application of security to devices with limited resources. A security framework is presented here that combines aspects of the Gossamer protocol and the Scalable Encryption Algorithm (SEA) to provide an implementation of inter-device security. The Gossamer Protocol is additionally used as a means of exchanging session keys for use with the SEA encryption protocol. Our system performed well with the code space requirements smaller than 600 bytes (excluding shared libraries) and a performance of 27 milliseconds per one 96-bit block of data.

PeopleN EURODEGENERATIVE diseases are progressive and difficult to diagnose in their early stages.Progressive impairment in the activities of daily living, as well as cognitive deterioration, leads to an increase in patient's dependence.Neuropsychiatric symptoms are common features and include psychosis (delusions and hallucinations), depressive mood, anxiety, irritability/lability, apathy, euphoria, disinhibition, agitation/aggression, aberrant motor activities, sleep disturbance, and eating disorders.Additionally, patients have a tendency to wander and misplace objects in their environment.Therefore, cognitive impaired patients need constant monitoring to ensure their wellbeing, and that they do not harm themselves.Ambient intelligence (AmI) is the computing paradigm that can provide support both for cognitive impaired people within their domestic environments and for clinicians to collect data needed to assess the disease.A novel class of applications can potentially emerge from the specialization of AmI technologies to the special domain of cognitive impaired users.However, such applications must be able to deal with peculiarities due to irrational and abnormal behaviors of cognitive impaired people within their environments, and their general attitude to not accepting wearable technologies.Several technical challenges remain to be solved before effective, intelligent, secure, and reliable AmI applications for the support of cognitive impaired people can be deployed trustfully into real environments.In this special section, the paper "The role of Virtual Motor Rehabilitation.A quantitative analysis between Acute and Chronic Patients with acquired brain injury," concerning acquired brain injury, compares the evolution of chronic patients with acute patients in a virtual rehabilitation program.For this study authors have developed a "Vestibular Virtual Rehabilitation" system.Results have shown a similar recovery for chronic and acute patients during the period of intervention.It has also been shown that chronic patients stop their improvement when they finish the training encouraging the migration of such rehabilitation technologies to home.In the contribution "An Adaptable and Flexible Framework for Assistive Living of Cognitively Impaired People" describes guidelines and an adaptable framework for the dynamic integration of assistive services with their related sensing technologies and interaction devices.The paper on "Statistical Anomaly Detection for Individuals with Cognitive Impairments" focuses on the identification of anomalies for users' routes, which may be useful to assist the impaired in case of losing one's way or to alert caregivers in case of wandering.The proposed approach relies on the exploitation Digital Object

Rheumatoid Arthritis (RA) is a disease which attacks the synovial tissue lubricating skeletal joints. This systemic condition affects the musculoskeletal system, including bones, joints, muscles and tendons that contribute to loss of function and Range of Motion (ROM). Traditional measurement of arthritis requires labour intensive personal examination by medical staff which through their objective measures may hinder the enactment and analysis of arthritis rehabilitation. This paper presents the development of a smart glove to facilitate this rehabilitative process through the integration of sensors, processors and wireless technology to empirically measure ROM. The Tyndall/University of Ulster glove uses a combination of 20 bend sensors, 16 tri-axial accelerometers and 11 force sensors to detect joint movement. All sensors are placed on a flexible PCB to provide high levels of flexibility and sensor stability. The system operation means that the glove does not require calibration for each glove wearer.

Rheumatoid Arthritis (RA) is a disease which attacks the synovial tissue lubricating skeletal joints. This systemic condition affects the musculoskeletal system, including bones, joints, muscles and tendons that contribute to loss of function and Range of Motion (ROM). Traditional measurement of arthritis requires labour intensive personal examination by medical staff which through their objective measures may hinder the enactment and analysis of arthritis rehabilitation. This paper presents the development of a smart glove to facilitate this rehabilitative process through the integration of sensors, processors and wireless technology to empirically measure ROM. The Tyndall/University of Ulster glove uses a combination of 20 bend sensors, 16 tri-axial accelerometers and 11 force sensors to detect joint movement. All sensors are placed on a flexible PCB to provide high levels of flexibility and sensor stability. The system operation means that the glove does not require calibration for each glove wearer.

Indoor radio frequency tracking systems are generally quite expensive and can vary in accuracy due to interference, equipment quality or other environmental factors. Due to these limiting factors of the technology, many businesses today find it hard to justify investing in RFID tracking technologies to improve the safety, efficiency and security of their working environments. The aim of this project was to provide a budget RFID tracking system that was capable of tracking a person or object through an indoor environment. To minimize the cost of the RFID tracking system, the components of the system were built from existing electronic equipment and hardware. The software was also written to minimize licensing and support fees allowing a cost effective budget RFID tracking system to be developed. The tracking system consists of a tag, reader nodes and a PC reader which utilize synapse RF 100 engines with python scripts embedded on to the chips.

Enjoyment of audio has now become about flexibility and personal freedom. Digital audio content can be acquired from many sources and wireless networking allows digital media devices and associated peripherals to be unencumbered by wires. However, despite recent improvements in capacity and quality of service, wireless networks are inherently unreliable communications channels for the streaming of audio, being susceptible to the effects of range, interference, and occlusion. This time-varying reliability of wireless audio transfer introduces data corruption and loss, with unpleasant audible effects that can be profound and prolonged in duration. Traditional communications techniques for error mitigation perform poorly and in a bandwidth inefficient manner in the presence of such large-scale defects in a digital audio stream. A novel solution that can complement existing techniques takes account of the semantics and natural repetition of music. Through the use of self-similarity metadata, missing or damaged audio segments can be seamlessly replaced with similar undamaged segments that have already been successfully received. We propose a technology to generate relevant self-similarity metadata for arbitrary audio material and to utilize this metadata within a wireless audio receiver to provide sophisticated and real-time correction of large-scale errors. The primary objectives are to match the current section of a song being received with previous sections while identifying incomplete sections and determining replacements based on previously received portions of the song. This article outlines our approach to Forward Error Correction (FEC) technology that is used to “repair” a bursty dropout when listening to time-dependent media on a wireless network. Using self-similarity analysis on a music file, we can “automatically” repair the dropout with a similar portion of the music already received thereby minimizing a listener's discomfort.

In this paper, the concept of object-oriented embedding (OOE) is introduced into information hiding in general and particularly to steganography which is the science that involves undetectable communication of secret data in an appropriate multimedia carrier. The proposal takes advantage of computer vision to orient the embedding process. Although, any existing algorithm can benefit from this technique to enhance its performance against steganalysis attacks, however this work also considers a new embedding algorithm in the wavelet domain using the Binary Reflected Gray Code (BRGC). In the realm of information hiding, one wing focuses on robustness, i.e., watermarking, and another wing focuses on imperceptibility, i.e., steganography. This work advocates for a new steganographic model that meets both robustness as well as imperceptibility. Resilience against common steganalysis attacks including the 274-D merged Markov and DCT features while surviving various image processing manipulations are reported. A neural network classifier was trained with features derived from 400 images. Comparisons with existing systems will also be highlighted.

This paper presents a novel dynamic threshold approach to discriminate skin pixels and non-skin pixels in color images. Fixed decision boundaries (or fixed threshold) classification approaches are successfully applied to segment human skin. These fixed thresholds mostly failed in two situations as they only search for a certain skin color range: 1) any non-skin object may be classified as skin if non-skin objects's color values belong to fixed threshold range. 2) any true skin may be mistakenly classified as non-skin if that skin color values do not belong to fixed threshold range. Therefore in this paper, instead of predefined fixed thresholds, novel online learned dynamic thresholds are used to overcome the above drawbacks. The experimental results show that our method is robust in overcoming these drawbacks.

The majority of existing methods have one thing in common which is the de-correlation of luminance from the considered colour channels. It is believed that the luminance is underestimated here since it is seen as the least contributing colour component to skin colour detection. This work questions this claim by showing that luminance can be useful in separating skin and non-skin clusters. To this end, this work uses a new colour space which contains error signals derived from differentiating the grayscale map and the non-encoded-red grayscale version. The advantages of this approach are the reduction of space dimensionality from 3D to 1D space and the construction of a rapid classifier necessary for real time applications. This method is meant to assist digital image steganography to orient the embedding process since skin information is deemed to be psycho-visually redundant.

Previous studies have shown that Steganography tools such as the S-Tools application outperforms counterpart tools in hiding data in the spatial domain. Another tool called F5 is identified as a robust tool in implementing Steganography in the frequency domain. This paper presents a Steganographic system which exploits the YCbCr colour space. YCbCr is intended to take advantage of human colour-response characteristics. Results show that our algorithm outperforms both F5 and S-Tools. Moreover, our system demonstrates improved performance in retrieving the hidden data after applying image processing attacks in the form of additive artificial noise. As a performance measurement for image distortion Peak-Signal-to-Noise Ratio (PSNR), which is classified under the difference distortion metrics, can be applied to the Stego images. This study also shows that by adopting an object oriented Steganography mechanism, in the sense that we track skin tone objects in video frames, we get a higher PSNR value.

Irresponsible and inaccessible web design causes unnecessary problems to certain website users. By applying the web content accessibility guidelines to a website the amount of possible users who can successfully view the content of that site will increase especially for those who are in the disabled and older adult categories of online users. We present the results of assessing the compliance of a selection of websites with guidelines set out by the Web Accessibility Initiative (WAI). It was found that most sites evaluated were inaccessible to those with disabilities. Only one of the selected sites passed all three priority levels set out by the WAI. In many cases, minor modifications to sites will make them accessible to people with disabilities. Therefore it can only be speculated that the reasons for lack of conformance may vary from lack of awareness of the issue, time constraints or the general stress of having to keep up with new technologies. Companies who overlook users with disabilities however may be doing so at long-term risk to their legal position, public image and ultimately business success.

Media monitoring is a function carried out by larger organisations who wish to track items in the news which refer to their organisation. Of late, media monitoring organisations are increasingly finding that a large number of their sources are online news articles. These articles similar to paper based articles must be sourced and archived for future purposes. Tools to assist with this can lead to improved productivity. This research presents the results of a prototype media monitoring tool which crawls the web for search terms, retrieves all relevant documents, archives them and presents search trends in a graphical manner.

Viewing video on the Internet can be troublesome as once a link is clicked on, there inevitably follows a delay while the stream is being buffered. Rich Site Summary (RSS) technology is a web content syndication format commonly used to organise news and the content of news-like sites. RSS has been extended to include tags known as RSS enclosures which allow audio and video to be described in terms of location, duration and size. Once data about each element is established in an RSS format, a program called an aggregator can check the feed frequently for changes and updates and act accordingly. This paper documents a scheduled RSS Multimedia prototype which utilises idle computer time (at night) to subscribe to media RSS channels in order to download audio and video content.

Global positioning systems have enabled the accurate measurement of very large distances and in conjunction with ubiquitous wifi hotspots have enabled the widespread adoption of location based tourism applications which utilise online mapping services to provide users with accurate directions. This paper documents an ‘E-Local Advisor’ application which provides street maps, directions and location of local services. The application works by receiving GPS signals which interact with online mapping services through outdoor wifi hotspots. Tourists can locate places of interest, find out where they are and query the system for exact directions from one location to another.

Purpose Seeks to demonstrate how, with regard to viewing video on the internet, the delay experienced, whilst the stream is being buffered, can be virtually eradicated. Design/methodology/approach Documents a scheduled rich site summary (RSS) multimedia prototype which utilizes idle computer time (at night) to subscribe to media RSS channels in order to download audio and video content. Findings Finds that, a part from involving zero display, the quality of the operation is controlled only by the size of the hard disk not by the capacity of the connection. Originality/value The system documented here will serve users at either end of the RSS feed chain.

This paper presents the latest research into a mobile intelligent multimedia presentation system called TeleMorph which can dynamically generate a multimedia presentation using output modalities that are determined by the bandwidth available on a mobile device's wireless connection. To demonstrate the effectiveness of this research TeleTuras, a tourist information guide will implement the solution provided by TeleMorph, thus demonstrating its effectiveness. This paper highlights issues surrounding such a system & introduces the architecture.

Chameleon is 100% Java middleware for multimedia streaming to heterogeneous mobile clients, which allows the dynamic configuration of protocols with respect to application requirements and available network resources. We evaluate the dynamic reconfigurability of the middleware in order to demonstrate runtime adaptation. We specially concentrate on the secondary quality transformation technique (SQT) of the middleware which enables clients to not only subscribe to media groups in accordance with available resources and network capacity but to also adapt media quality within each quality group dynamically in accordance to resource constraints.

Web Intelligence is a fascinating area in the very early stages of research and development. It combines the interaction of the human mind and artificial intelligence with networks and technology. How will the next generation Web mature? With the imminent growth of Web intelligence what expectations do users have? Users will expect more from the Web than for it to merely pass raw data between people via search engines. We attempt to define and summarise the concept of Web Intelligence, highlight the key elements of Web Intelligence, and explore the topic of Web information retrieval with particular focus on multimedia/information retrieval and intelligent agents.

Fixed end-system protocols are unable to support the wide range of applications requirements on top of current networks without adding overhead in the form of unnecessary functionality for multiple combinations of application requirements and networks. The Real-time Wide Area Network Dissemination Architecture (RWANDA) protocol paradigm dynamically configures protocol stacks to support a wide range of application requirements and to increase performance. RWANDA provides an asynchronous foundation that is necessary for developing reliable large-scale Internet applications requiring timely guarantees such as remote surgery, teleconferencing and Internet telephony.