Special Issue "Humanistic Data Mining: Tools and Applications"

A special issue of Algorithms (ISSN 1999-4893).

Deadline for manuscript submissions: 31 October 2018

Special Issue Editors

Guest Editor
Dr. Phivos Mylonas

Image, Video and Multimedia Systems Laboratory [IVML] Zografou Campus, Iroon Polytechneioy 9, PC 15773 ECE Building - 1st Floor - Room 11.23
Website | E-Mail
Interests: Knowledge-assisted multimedia analysis; Multimedia information retrieval; Multimedia personalization; User adaptation; User modeling; User profiling; Visual context representation and analysis; Human-computer interaction
Guest Editor
Dr. Katia Lida Kermanidis

Department of Informatics, Ionian University, Greece
Website | E-Mail
Interests: artificial intelligence; natural language processing, grammar development; information retrieval; linguistic data mining; ontology extraction
Guest Editor
Dr. Christos Makris

Department of Computer Engineering & Informatics, University of Patras, Greece
Website | E-Mail
Interests: data structures; information retrieval; data mining; bioinformatics; string algorithmic; computational geometry; multimedia data bases; internet technologies
Guest Editor
Dr. Spyros Sioutas

Department of Informatics, Ionian University, Greece
Website | E-Mail
Interests: algorithmic data management; spatio-temporal database systems; distributed data structures and P2P overlays; cloud infrastructures; indexing; query processing and query optimization
Guest Editor
Dr. Vasileios Megalooikonomou

Computer Engineering & Informatics Department, University of Patras, Greece
Website | E-Mail
Interests: database and knowledge-based systems; intelligent information systems; data mining; pattern recognition; data compression; biomedical informatics; multimedia

Special Issue Information

Dear Colleagues,

Digital data mining could be described as one of the most important, computationally intensive and challenging tasks of our era. As this observation applies both to the research community, which is faced with enormous challenges derived from (big-)data management as well as new emerging disciplines like, for instance, precision agriculture, and the applied world, in terms, for instance, of social data handling and related social apps, it is becoming evident that new approaches have to be followed and new tools and applications have to invented in order to efficiently handle the vast amounts of information.

The aim of the “Mining Humanistic Data Workshop”, and by association of the proposed Special Issue, is formed around two main pillars. The first pillar focuses on the primitive information and knowledge analysis, as well as the extraction of the inherited knowledge. The task here is to achieve a better understanding of human activities associated to the respective computational tasks. The second pillar aims to exploit the extracted knowledge by incorporating it into smart tools and applications; the latter will ultimately make the life of involved users easier with respect to their everyday life.

This Special Issue aims to bring together interdisciplinary approaches that focus on the application of innovative as well as existing humanistic data mining and knowledge discovery and management methodologies. Since humanistic data typically are dominated by semantic heterogeneity and are quite dynamic in nature, computer science researchers are obliged and encouraged to develop new suitable algorithms, tools and applications to efficiently tackle them, whereas existing ones need to be adapted to the individual special characteristics using traditional methodologies, such as decision rules, decision trees, association rules, ontologies and alignments, clustering, filtering, learning, classifier systems, neural networks, support vector machines, preprocessing, post processing, feature selection and visualization techniques. The Special Issue is devoted to the exploitation of the multiple facets of the above research fields and will explore the current related state-of-the-art. Its topics of interest cover the scope of the MHDW 2018 workshop (https://conferences.cwa.gr/mhdw2018/). Extended versions of papers presented at MHDW 2018 are sought, but this Call for Papers is also fully open to all who want to contribute by submitting a relevant research manuscript.

Dr. Phivos Mylonas
Dr. Katia Lida Kermanidis
Dr. Christos Makris
Dr. Spyros Sioutas
Dr. Vasileios Megalooikonomou
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Algorithms is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 850 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • humanistic sciences
  • data mining
  • knowledge discovery
  • knowledge representation and management
  • artificial intelligence
  • information retrieval
  • context
  • social data analytics

Published Papers (2 papers)

View options order results:
result details:
Displaying articles 1-2
Export citation of selected articles as:

Research

Open AccessArticle LSTM Accelerator for Convolutional Object Identification
Algorithms 2018, 11(10), 157; https://doi.org/10.3390/a11100157
Received: 4 August 2018 / Revised: 10 October 2018 / Accepted: 12 October 2018 / Published: 17 October 2018
PDF Full-text (492 KB) | HTML Full-text | XML Full-text
Abstract
Deep Learning has dramatically advanced the state of the art in vision, speech and many other areas. Recently, numerous deep learning algorithms have been proposed to solve traditional artificial intelligence problems. In this paper, in order to detect the version that can provide
[...] Read more.
Deep Learning has dramatically advanced the state of the art in vision, speech and many other areas. Recently, numerous deep learning algorithms have been proposed to solve traditional artificial intelligence problems. In this paper, in order to detect the version that can provide the best trade-off in terms of time and accuracy, convolutional networks of various depths have been implemented. Batch normalization is also considered since it acts as a regularizer and achieves the same accuracy with fewer training steps. For maximizing the yield of the complexity by diminishing, as well as minimizing the loss of accuracy, LSTM neural net layers are utilized in the process. The image sequences are proven to be classified by the LSTM in a more accelerated manner, while managing better precision. Concretely, the more complex the CNN, the higher the percentages of exactitude; in addition, but for the high-rank increase in accuracy, the time was significantly decreased, which eventually rendered the trade-off optimal. The average improvement of performance for all models regarding both datasets used amounted to 42 % . Full article
(This article belongs to the Special Issue Humanistic Data Mining: Tools and Applications)
Figures

Figure 1

Open AccessArticle An Auto-Adjustable Semi-Supervised Self-Training Algorithm
Algorithms 2018, 11(9), 139; https://doi.org/10.3390/a11090139
Received: 19 July 2018 / Revised: 23 August 2018 / Accepted: 10 September 2018 / Published: 14 September 2018
PDF Full-text (325 KB) | HTML Full-text | XML Full-text
Abstract
Semi-supervised learning algorithms have become a topic of significant research as an alternative to traditional classification methods which exhibit remarkable performance over labeled data but lack the ability to be applied on large amounts of unlabeled data. In this work, we propose a
[...] Read more.
Semi-supervised learning algorithms have become a topic of significant research as an alternative to traditional classification methods which exhibit remarkable performance over labeled data but lack the ability to be applied on large amounts of unlabeled data. In this work, we propose a new semi-supervised learning algorithm that dynamically selects the most promising learner for a classification problem from a pool of classifiers based on a self-training philosophy. Our experimental results illustrate that the proposed algorithm outperforms its component semi-supervised learning algorithms in terms of accuracy, leading to more efficient, stable and robust predictive models. Full article
(This article belongs to the Special Issue Humanistic Data Mining: Tools and Applications)
Figures

Figure 1

Back to Top