Vassilis Kolias

Design and implementation of a VoiceXML-driven wiki application for assistive environments on the web

In this paper, we describe the design and implementation of an audio wiki application accessible via both the Public Switched Telephone Network and the Internet. The application exploits mature World Wide Web Consortium standards, such as VoiceXML, Speech Synthesis Markup Language, and Speech Recognition Grammar Specification toward achieving our goals. The purpose of such an application is to assist visually impaired, technologically uneducated, and underprivileged people in accessing information originally intended to be accessed visually via a personal computer (PC). Users may access wiki content via fixed or mobile phones, or via a PC using a Web Browser or a Voice over IP service. This feature promotes pervasiveness to collaboratively created content to an extremely large population, i.e., those who simply own a telephone line.

A pervasive wiki application based on VoiceXML

In this paper, we describe the design and implementation of an audio wiki application accessible via the Public Switched Telephone Network (PSTN) and the Internet for educational purposes. The application exploits mature World Wide Web Consortium standards such as VoiceXML, Speech Synthesis Markup Language (SSML) and Speech Recognition Grammar Specification (SRGS). The purpose of such an application is to assist visually impaired, technologically uneducated, and underprivileged people in accessing information originally intended to be accessed visually via a Personal Computer. Users may access wiki content via wired or mobile phones, or via a Personal Computer using a Web Browser or a Voice over IP service. This feature promotes pervasiveness to educational material to an extremely large population, i.e. those who simply own a telephone line.

TermID: a distributed swarm intelligence-based approach for wireless intrusion detection

With the mushrooming of wireless access infrastructures, the amount of data generated, transferred and consumed by the users of such networks has taken enormous proportions. This fact further complicates the task of network intrusion detection, especially when advanced machine learning (ML) operations are involved in the process. In wireless environments, the monitored data are naturally distributed among the numerous sensor nodes of the system. Therefore, the analysis of data must either happen in a central location after first collecting it from the sensors or locally through collaboration by viewing the problem through a distributed ML perspective. In both cases, concerns are risen regarding the requirements of this demanding task in matters of required network resources and achieved security/privacy. This paper proposes TermID, a distributed network intrusion detection system that is well suited for wireless networks. The system is based on classification rule induction and swarm intelligence principles to achieve efficient model training for intrusion detection purposes, without exchanging sensitive data. An additional achievement is that the produced model is easily readable by humans. While these are the main design principles of our approach, the accuracy of the produced model is not compromised by the distribution of the tasks and remains at competitive levels. Both the aforementioned claims are verified by the results of detailed experiments withheld with the use of a publicly available security-focused wireless dataset.

Enhancing User Privacy in Adaptive Web Sites with Client-Side User Profiles

Web personalization is an elegant and flexible process of making a web site responsive to the unique needs of each individual user. Data that reflects user preferences and likings, comprising therefore a user profile, are gathered to an adaptive web site in a non transparent manner. This situation however raises serious privacy concerns to the end user. When browsing aweb site, users are not aware of several important privacy parameters i.e., which behavior will be monitored and logged, how it will be processed, how long it will be kept, and with whom it will be shared in the long run. In this paper we propose an abstract architecture that enhances user privacy during interaction with adaptive web sites. This architecture enables users to create and update their personal privacy preferences for the adaptive web sites they visit by holding their (user) profiles in the client side instead of the server side. By doing so users will be able to self-confine the personalization experience the adaptive sites offer, thus enhancing privacy.

Integrating RFID on event-based hemispheric imaging for internet of things assistive applications

Automatic surveillance of a scene in a broad sense comprises one of the core modules of pervasive applications. Typically, multiple cameras are installed in an area to identify events through image processing techniques, which however present limitations in terms of object occlusion, noise, lighting conditions, image resolution and computational cost. To overcome such limitations and increase recognition accuracy, the video sensor output can be complemented by Radio Frequency Identification technology, which is ideal for the unique identification of objects. In this paper we examine the feasibility of integrating RFID with hemispheric imaging video cameras. After a brief description and discussion of related research regarding RFID location, video surveillance and their integration, we examine the factors that would render such a system feasible in terms of hardware, software and their environments. The advantages and limitations of each technology and their integration are also presented to conclude that their combination could lead to a robust detection of objects and their interactions within an environment. Finally, this work ends with the presentation of some possible applications of such integration.

Remote experiments in education: A survey over different platforms and application fields

Distance education as well as remote experimentation, is a modern field that aims to deliver education to students who are not physically present on their class or their testbed instrumentation. Nowadays, more and more students and educators/instructors rather than attending courses in person, communicate with the educational material at times of their own through Internet-based technologies and services that allows them to interact in real time or in an asynchronous mode. Remote access is simplified, since Internet allows computer users to connect to other computers and information is stored and processed easily, wherever they may be across the world. This paper provides a straightforward categorization of remote experimentations in education according to the platform used as the medium for conducting the experiments and the scientific field in which they apply to. This contribution aims to be a starting point to those interested in entering the world of remote experiments, by presenting work from 2005 up to date.

RuleMR: Classification rule discovery with MapReduce

The vast amounts of data generated, exchanged and consumed on a daily basis by contemporary networks and devices renders their analysis a cumbersome procedure with inherent difficulties. On the one hand, the need for efficient Machine Learning algorithms and tools that scale on large datasets is continuously growing. On the other, parallel or distributed solutions have proven to conceal many pitfalls. The MapReduce programming model has quickly emerged as the de facto model for executing simple algorithmic tasks over huge volumes of data, since it is simple, highly abstract and efficient. However, due to its unidirectional communication model and the inherent lack of support for iterative execution, few Machine Learning algorithms can easily be implemented on MapReduce. In this paper, we present a classification rule discovery algorithm, namely RuleMR, which despite its iterative nature, can capitalize on MapReduce. In order to construct quality rules in less iterations, the algorithm exploits the distributed nature of MapReduce to explore only the promising areas in the search space. We conduct a series of experimental evaluations which indicate that the proposed approach not only scales well with respect to the size of the training dataset, but also, in many cases, the resulting model is comparable to many well known algorithms in matters of accuracy.

A Covering Classification Rule Induction Approach for Big Datasets

With the ever increasing production of data from various heterogeneous sources in modern information societies, the need for scalable data-intensive processing is increasing. MapReduce quickly became the de facto framework for large scale data analysis, due to its simple and abstract programming model and its efficient underlying execution system. However, this simplicity comes with a price: its unidirectional communication model and the lack of support for iterations, makes repeated querying of datasets difficult and imposes limitations in many fields including Machine Learning. In this paper we describe the implementation of a classification rule induction algorithm based on MapReduce, with the aim of building a classification model within as few iterations as possible. After a thorough description of the algorithm, we evaluate its performance from three perspectives: its accuracy, its parallel performance and the communication costs. The evaluations indicate that the approach is scalable and since it produces a comprehensive human-readable model it can be proven valuable for a wide range of applications.

A Speech-Enabled Assistive Collaborative Platform for Educational Purposes with User Personalization

With the proliferation of Web 2.0 applications, collaborative learning has gathered a lot of attention due its potentiality in the e-learning field. Forums, Wikis and Blogs for example are only some of the applications that exploit the collaborative nature of e-learning. However, these applications are originally designed for access from desktop systems and access to them when on the move can prove a challenging task. This paper elaborates on the design and implementation of an assistive collaborative platform for educational purposes that can be accessed by heterogeneous hardware platforms such as PCs, PDAs, mobile or traditional phones due to its capability of representing data in vocal manner. Its main purpose is to provide a platform for collaboration between university students and teachers in away that enhances students¿ access to educational resources and their overall learning experience. This is achieved by personalizing its content at least to some degree. Furthermore, its acoustic/vocal characteristics may also prove valuable for learners with visual or kinetic impairments.

A Client-Side Privacy Framework for Web Personalization

Personalization of web applications is the complex process of dynamically rendering the application responsive to the unique needs of individual users. Nevertheless, the information required for achieving the personalization procedures is usually gathered and stored beyond the user’s control. This is a situation that raises serious privacy concerns to the end-users and may drive them to reject the application. For example, when browsing an adaptive e-commerce website, users are not aware which behavior will be monitored and logged, how it will be processed, how long it will be stored, and with whom it will be shared in the long run, thus they may hesitate to visit the website. In this chapter after an introduction to the state of the art in privacy preserving personalized web applications we present an abstract architecture that enables users to fine-tune their privacy level (and in result their personalization experience) according to the trust they put on different applications. Since the data is stored on the client side, this approach by definition enhances user privacy.