Search results

Currently, electronic election is one of the most popular issues of e-democracy. This has led to the development of applications and several security mechanisms to address such necessity. The problem that arises is that such applications are created either on demand for a specific election process, or experimentally for scientific purposes. The purpose of this study is to present a new e-voting system, called VOTAN. The VOTAN system involves a combination of new features with basic advantages, the implementation as open source software, its modular organization covering the functional requirements of a typical electronic voting system (EVS) and the capability of data analysis of candidates and voters.

VOTAN stands for VOTes Analyzer. It is a secure application for the conduct of electronic elections through the internet based on its own security protocol. It also includes a data analysis component which analyzes the election results and investigates the factors that play a crucial role. The major advantages of the system are that it is an open source and includes a data analysis module that can distinguish important variables from the elections and help make predictions for the outcome based on the selected variables. It is a practical solution to the existing e-voting applications and is ideal for small communities such as organizations, universities and chambers.

Its main advantage, compared to similar e-voting systems, is the integration of the data analysis component. The analysis of the data produced from elections is considered a critical process to fully comprehend the outcome of the elections and its correlation to specific attributes/variables of the election process. The data analysis module is a unique feature of VOTAN. It facilitates the selection of the most important attributes that influence the outcome of elections and creates a mathematical model to predict the outcome of an election based on the selected attributes. The method used in the module is the LDA.

The originality of the paper derives from the data analysis component and its security protocol/schema that fulfils several requirements.

A huge amount of data are produced in the agriculture sector. Due to the huge number of these datasets it is necessary to use data analysis techniques in order to comprehend the data and extract useful information. The purpose of this paper is to measure, archetype and mine olea europaea production data.

This work applies three different data mining techniques to data about Olea europaea var. media oblonga from the island of Thassos, at the northern part of Greece. The data were from 1,063 farmers from three different municipalities of Thassos, namely Kallirachi, Limenaria and Prinos and concerned the year 2010. They were analysed using the classification algorithm OneR, the clustering algorithm k‐means and the association rule mining algorithm, Apriori from the WEKA data mining package. Also, new measures which quantify the performance of the productions of olives and oil are applied. Finally, archetypal analysis is applied in order to distinguish the most typical/stereotype farms for each region and describe their specific characteristics.

The results indicate that organic cultivation could improve the production of olives and olive oil. Furthermore, the climate differences among the three municipalities seems to be a factor involved in production efficacy.

It is the first time that data from the island of Thassos have been analysed systematically using a variety of data mining methods. Also, the measures proposed in the paper in order to analyse the data are new. Furthermore, archetypal analysis is proposed as a method to extract sterotypes/representative farms from the dataset.