Dimitrios Tsolis

Ionian Music Archive: Application of digitization, management and dissemination technologies for musical cultural heritage

This paper presents the design and implementation of a web-based application aiming at the digitization, management, long term preservation and dissemination of musical cultural heritage. The architecture of the application is modular consisting of a digitization layer that provides all the necessary digitization services to the expert and an information system layer that supports multimedia management and dissemination services along with system administration services. The architecture is expandable due to the dynamic nature of a musical heritage archive. The application is safeguarding folklore music of Greek Ionian islands and provides services and tools to the internet user as well as the curator of the musical archive.

A multimedia application for watermarking digital images based on a content based image retrieval technique

The current work is focused on the implementation of a robust multimedia application for watermarking digital images, which is based on an innovative spread spectrum analysis algorithm for watermark embedding and on a content-based image retrieval technique for watermark detection. The existing highly robust watermark algorithms are applying “detectable watermarks” for which a detection mechanism checks if the watermark exists or not (a Boolean decision) based on a watermarking key. The problem is that the detection of a watermark in a digital image library containing thousands of images means that the watermark detection algorithm is necessary to apply all the keys to the digital images. This application is non-efficient for very large image databases. On the other hand “readable” watermarks may prove weaker but easier to detect as only the detection mechanism is required. The proposed watermarking algorithm combine’s the advantages of both “detectable” and “readable” watermarks. The result is a fast and robust multimedia application which has the ability to cast readable multibit watermarks into digital images. The watermarking application is capable of hiding 214 different keys into digital images and casting multiple zero-bit watermarks onto the same coefficient area while maintaining a sufficient level of robustness.

Large Scale Implementations for Twitter Sentiment Classification

Sentiment Analysis on Twitter Data is indeed a challenging problem due to the nature, diversity and volume of the data. People tend to express their feelings freely, which makes Twitter an ideal source for accumulating a vast amount of opinions towards a wide spectrum of topics. This amount of information offers huge potential and can be harnessed to receive the sentiment tendency towards these topics. However, since no one can invest an infinite amount of time to read through these tweets, an automated decision making approach is necessary. Nevertheless, most existing solutions are limited in centralized environments only. Thus, they can only process at most a few thousand tweets. Such a sample is not representative in order to define the sentiment polarity towards a topic due to the massive number of tweets published daily. In this work, we develop two systems: the first in the MapReduce and the second in the Apache Spark framework for programming with Big Data. The algorithm exploits all hashtags and emoticons inside a tweet, as sentiment labels, and proceeds to a classification method of diverse sentiment types in a parallel and distributed manner. Moreover, the sentiment analysis tool is based on Machine Learning methodologies alongside Natural Language Processing techniques and utilizes Apache Spark’s Machine learning library, MLlib. In order to address the nature of Big Data, we introduce some pre-processing steps for achieving better results in Sentiment Analysis as well as Bloom filters to compact the storage size of intermediate data and boost the performance of our algorithm. Finally, the proposed system was trained and validated with real data crawled by Twitter, and, through an extensive experimental evaluation, we prove that our solution is efficient, robust and scalable while confirming the quality of our sentiment identification.

Digital watermarking in peer to peer networks

As a general and effective protection measure for copyright violations which occur with the use of digital technologies including peer to peer (P2P) networks, copyright owners often use digital watermarking techniques so as to encrypt copyright information to the content or otherwise restrict or even block access to the digital content through the Internet and the P2P infrastructure. This paper claims that DRM and P2P can be quite complementary. Specifically, a P2P infrastructure is presented which allows broad digital content exchange while on the same time supports copyright protection and management through watermarking technologies for digital images.

A P2P cultural multimedia network - maximizing cultural dissemination and supporting copyright protection and management

This paper presents a novel implementation for the distribution of cultural heritage digital images via a Peer-to-Peer network. This implementation consists of a Peer-to-Peer (P2P) network for the distribution of cultural heritage digital images and Digital Rights Management (DRM) technologies for the copyright protection of these digital images. In this approach, we design and implement a software in which each peer of P2P network performs the functionalities of three basic entities of a typical DRM system. That is, each peer of P2P network acting as Content Owner, as Trusted Third Party and as User, simultaneously. The Content Owner uploads cultural heritage images to P2P network, these images are at protected format. The protection of digital images is achieved with watermarking techniques and encryption techniques. The License Broker controls the usage of digital images and detects the infringement of copyright. The User performs a search to a list with the available cultural heritage images. Then, the User downloads the images that chooses and uses these images with the terms of usage license. The purpose of this implementation is the legitimate distribution of cultural heritage digital images in a P2P network. The legitimate distribution achieved with the use of DRM technologies. Finally, we are trying to achieve a distributed DRM and P2P architecture for our implementation.

(A)kNN Query Processing on the Cloud: A Survey

A k-nearest neighbor (kNN) query determines the k nearest points, using distance metrics, from a given location. An all k-nearest neighbor (AkNN) query constitutes a variation of a kNN query and retrieves the k nearest points for each point inside a database. Their main usage resonates in spatial databases and they consist the backbone of many location-based applications and not only. Although (A)kNN is a fundamental query type, it is computationally very expensive. During the last years a multiplicity of research papers has focused around the distributed (A)kNN query processing on the cloud. This work constitutes a survey of research efforts towards this direction. The main contribution of this work is an up-to-date review of the latest (A)kNN query processing approaches. Finally, we discuss various research challenges and directions of further research around this domain.

Ionian music archive: application of digitisation, management, protection and dissemination technologies for musical cultural heritage

This paper presents the design and implementation of a web-based application aiming at the digitisation, management and dissemination of musical cultural heritage. The architecture of the application is modular consisting of a digitisation layer that provides all the necessary digitisation services to the expert and an information system layer that supports multimedia management, protection through watermarking and dissemination services along with system administration services. The architecture is expandable due to the dynamic nature of a musical heritage archive. The application is safeguarding folklore music of Greek Ionian islands and provides services and tools to the internet user as well as the curator of the musical archive.

Secure mobile services for on-going archaeological excavations management and dissemination

This paper presents the design of an information system that offers secure mobile services for management, long term preservation and dissemination of archaeological content originated from an on-going excavation. The proposed system is safeguarding archaeological relics discovered in the excavation and provides services and mobile tools to the internet user as well as the director of the archaeological excavation aiming at the efficient dissemination of the excavation findings and their significance.

Development of a Clinical Decision Support System Using AI, Medical Data Mining and Web Applications

The need of an advanced hospital information system is imminent as it supports electronic patient record management and use of decision support leading to effective diagnosis and treatment. Data mining algorithms and techniques are playing a key role to this process, enhancing access to critical data by the medical personnel and optimizing functionality for the decision support services. In addition, web services make access to critical information feasible from any place, at any time and from any device. In the current paper, DEUS, a clinical decision support system is proposed and presented which combines efficient data mining, artificial intelligence and web services so as to support diagnosis and treatment planning. The system is tested throughout two case studies a) thyroid cancer and b) hepatitis.

Web services for digital rights management and copyright protection in digital media

The paper focuses on the implementation of an advanced digital rights management (DRM) system which supported by web services offers copyright protection and management of digital media. The main components of the DRM system are a digital image library, which offers specialized services for storing and searching and a copyright protection and digital rights management subsystem for the digitized media based on innovative watermarking and web technologies.