Announcement:

Τhe application procedure for excellence scholarships and scholarships based on Law 4485/2017 for the acad. year 2019-20 was completed on 24/10/2019

Ανακοίνωση:

Η διαδικασία υποβολής αιτήσεων για υποτροφίες αριστείας και υποτροφίες στο πλαίσιο του ν. 4485/2017 για το ακαδ. έτος 2019-20 ολοκληρώθηκε στις 24/10/2019

**IHU Students' Success Stories**
 

We are very proud that Dimosthenis Beleveslis MSc in Data Science , at the School of Science & Technology, under the supervision of Asst. Prof. Christos Tjortjis, and in collaboration with Dimitris Psaradelis and Dimitris Nikoglou of InfiLab GmbH had his paper on: “A Hybrid Method for Sentiment Analysis of Election Related Tweets”, accepted by the 4th IEEE SE Europe Design Automation, Computer Engineering, Computer Networks, and Social Media Conf. ( EEDA-CECNSM 2019).

Also, Dimitrios Tasios, MSc in Data Science , at the School of Science & Technology, under the supervision of Asst. Prof. Christos Tjortjis, and in collaboration with Asst. Prof. Andreas Gregoriades of the Cyprus University of Technology, had his paper on: “Mining Traffic Accident Data for Hazard Causality Analysis”, accepted by the 4 th IEEE SE Europe Design Automation, Computer Engineering, Computer Networks, and Social Media Conf. ( EEDA-CECNSM 2019 ).

Figure 1: Number of tweets per class



Figure 2: Accident Frequency per age group

You can find more ‘IHU Students’ Stories’ here .

Mr. D. Beleveslis

Mr. D. Tasios
**IHU Students' Success Stories**
 

We are very proud that Paraskevas Koukaras MSc in ICT Systems graduate, and Dimitris Rousidis, both PhD candidates at the School of Science & Technology, under the supervision of Asst. Prof. Christos Tjortjis, had their paper on: “Social Media Types: Introducing a Data Driven Taxonomy”, accepted by the prestigious international peer reviewed journal Computing , published by Springer.

You can find more ‘IHU Students’ Stories’ here .

Mr. P. Koukaras

Mr. D. Rousidis
**IHU Students' Success Stories**
 

We are very proud that Konstantinos Christantonis and Konstantinos Apostolou, both MSc in Data Science students, supervised by Asst. Prof. Christos Tjortjis had their respective papers on:

· “Data Mining for Smart Cities: Predicting Electricity Consumption by Classification”, and

· “Sports Analytics algorithms for performance prediction”,


accepted by the IEEE 10th International Conference on Information, Intelligence, Systems and Applications ( IISA 19).

You can find more ‘IHU Students’ Stories’ here .

Mr. K. Christantonis

Mr. K. Apostolou

Research Seminar 9/5: “A combinatorial approach to entity matching for products”

School of Science and Technology
International Hellenic University

Thursday 9 May 2019
17:00-18:00

International Hellenic University, Lecture Room B1

Seminar Title

A combinatorial approach to entity matching for products”

Dr Leonidas Akritidis

Speaker information:
Leonidas Akritidis is a post-doctoral researcher at the Data Structuring and Engineering (DaSE) Lab of the Department of Electrical & Computer Engineering, University of Thessaly, Greece. He is also an MSc studies instructor in the same Department, teaching Data Structures, Algorithms and World Wide Web technologies. He obtained his PhD degree in 2013, and his BSc from the Department of Electrical & Computer Engineering of the Aristotle University of Thessaloniki, Greece, in 2003. His research interests include Data Mining, Machine Learning, Large-scale Data Processing, Big Data Engineering, and Information Retrieval.

Presentation at a glance:
The continuous growth of the e-commerce industry has rendered the problem of product retrieval particularly important. As more enterprises move their activities on the Web, the volume and the diversity of the product-related information increase quickly. These factors make it difficult for the users to identify and compare the features of their desired products. Recent studies proved that the standard similarity metrics cannot effectively identify identical products, since similar titles often refer to different products and vice-versa. Other studies employed external data sources (search engines) to enrich the titles; these solutions are rather impractical since the process of fetching external data is inefficient. In this presentation we will review the state-of-the-art approaches to entity matching and we will introduce UPM, an unsupervised algorithm for matching products by their titles. UPM is independent of any external sources and consists of three stages: during the first stage, the algorithm analyzes the titles and extracts combinations of words out of them. These combinations are evaluated in stage 2 according to several criteria, and the most appropriate of them are selected to form the initial clusters. The third phase is a post-processing verification stage which performs a refinement of the initial clusters by correcting the erroneous matches. This stage is designed to operate in combination with all clustering approaches, especially when the data possess properties which prevent the co-existence of two data points within the same cluster. We shall also present experimental results which demonstrate the superiority of the algorithm against multiple string similarity metrics and clustering methods.

https://www.ihu.edu.gr/index.php/news-events/item/https://www.ihu.edu.gr/index.php/news-events/item/1570-scholarships-by-the-george-and-victoria-karelia-foundation.html

https://www.ihu.edu.gr/index.php/news-events/item/1567-helmepa-2019-20-scholarships-for-master’s-studies.html

**IHU Students' Success Stories**
 

Congratulations to Ioannis Schoinas, IHU MSc in Mobile and Web Computing student, for his paper: Ι. Schoinas, C. Tjortjis, “MuSIF: A Product Recommendation System Based on Multi-source Implicit Feedback”, accepted by the 15th Int’l Conf. on Artificial Intelligence Applications and Innovations http://www.aiai2019.eu/ to be published by the Springer IFIP AICT (LNCS) Series.

The paper reports on MuSIF, a recommendation system equipped with a new method to increase the accuracy of matrix factorization algorithms via initialization of factor vectors, which is tested for the first time in an implicit model-based Collaborative Filtering approach. Moreover, it includes methods for addressing data sparsity. Evaluation shows that MuSIF can benefit customers and e-shop owners with personalization in real world scenarios.

You can find more ‘IHU Students’ Stories’ here .

https://www.ihu.edu.gr/index.php/vacancies.html

Page 1 of 6