Search

In recent years and after continuous training of educators, the design of flexible educational scenarios is gradually evolving and being integrated into the teaching practice, which is related to the proposed ways of implementing pre-selected modules from the curriculum of a subject and can be applied to distance learning. In this context and during the development of the "BYRON" and "MON REPO" projects, educational scenarios were designed and implemented in practice. These are based on the serious games design principles and follow existing and modern pedagogical theories. In particular, the aim of designing educational scenarios is to reflect the latest research on the integration and utilization of serious games in the teaching of History and through distance learning. Furthermore, the activities aim at highlighting the role of ICT in teaching strategies, which support the playful way of approaching knowledge, with particular emphasis on supporting and promoting transitions from frontal teaching, group teaching and in collaborative learning, transforming the form of teaching from teacher-centered to student-centered, by deploying specific educational scenarios. The structure of the scenarios, their supported activities and the evaluation process, are closely intertwined with the plot of the digital educational serious game "BYRON", as well as the on-site project "MON REPO".

The problem of human activity recognition (HAR) has been increasingly attracting the efforts of the research community, having several applications. It consists of recognizing human motion and/or behavior within a given image or a video sequence, using as input raw sensor measurements. In this paper, a multimodal approach addressing the task of video-based HAR is proposed. It is based on 3D visual data that are collected using an RGB + depth camera, resulting to both raw video and 3D skeletal sequences. These data are transformed into six different 2D image representations; four of them are in the spectral domain, another is a pseudo-colored image. The aforementioned representations are based on skeletal data. The last representation is a “dynamic” image which is actually an artificially created image that summarizes RGB data of the whole video sequence, in a visually comprehensible way. In order to classify a given activity video, first, all the aforementioned 2D images are extracted and then six trained convolutional neural networks are used so as to extract visual features. The latter are fused so as to form a single feature vector and are fed into a support vector machine for classification into human activities. For evaluation purposes, a challenging motion activity recognition dataset is used, while single-view, cross-view and cross-subject experiments are performed. Moreover, the proposed approach is compared to three other state-of-the-art methods, demonstrating superior performance in most experiments.

Trust is a fundamental sociotechnological mainstay of the Web today. There is substantial evidence about this since netizens implicitly or explicitly agree to trust virtually every Web service they use ranging from Web-based mail to e-commerce portals. Moreover the methodological framework for trusting individual netizens, primarily their identity and communications, has considerably progressed. Nevertheless, the core of fact checking for human generated content is still far from being substantially automated as most proposed smart algorithms capture inadequately fundamental human traits. One such case is the evaluation of the profile trustworthiness of LinkedIn members based on publicly available attributes available from the platform itself. A trusted profile may indirectly indicate a more suitable candidate since its contents can be easily verified. In this article a first order graph search mechanism for discovering LinkedIn trusted profiles based on a random walker is extended to higher order ranking based on a combination of functional and connectivity patterns. Results are derived for the same benchmark dataset and the first- and higher-order approaches are compared in terms of accuracy.

There is a significant number of agricultural systems with rich and special biodiversity, characterized as high-nature-value farming systems (HNV) in the Ionian Islands region. These agro-ecosystems cover a significant area in this region and are divided in olive groves and vineyards which, in some cases, cover a significant part of the protected areas (Natura 2000 and SPA). There are solid olive groves but also a large number of scattered trees or clusters, as well as vineyards, which are largely identified as high-quality wine producers. Finally, there are smaller but extremely important examples of HNV, such as the Englouvi plateau in Lefkada. In this study, we propose a method to survey the spread of Ailanthus altissima in olive groves and vineyards (HNV areas) with the scope of evaluating the considered agro-ecosystems, based on the importance of ecosystems and ecosystem services they provide, and preparing a management plan for HNV areas.

In the current paper, we propose a machine learning forecasting model for the accurate prediction of qualitative weather information on winter precipitation types, utilized in Apache Spark Streaming distributed framework. The proposed model receives storage and processes data in real-time, in order to extract useful knowledge from different sensors related to weather data. In following, the numerical weather prediction model aims at forecasting the weather type given three precipitation classes namely rain, freezing rain, and snow as recorded in the Automated Surface Observing System (ASOS) network. For depicting the effectiveness of our proposed schema, a regularization technique for feature selection so as to avoid overfitting is implemented. Several classification models covering three different categorization methods namely the Bayesian, decision trees, and meta/ensemble methods, have been investigated in a real dataset. The experimental analysis illustrates that the utilization of the regularization technique could offer a significant boost in forecasting performance.

The proliferation of smart things and the subsequent emergence of the Internet of Things has motivated the deployment of intelligent spaces that provide automated services to users. Context-awareness refers to the ability of the system to be aware of the virtual and physical environment, allowing more efficient personalization. Context modeling and reasoning are two important aspects of context-aware computing, since they enable the representation of contextual data and inference of high-level, meaningful information. Context-awareness middleware systems integrate context modeling and reasoning, providing abstraction and supporting heterogeneous context streams. In this work, such a context-awareness middleware system is presented, which integrates a proposed context model based on the adaptation and combination of the most prominent context categorization schemata. A hybrid reasoning procedure, which combines multiple techniques, is also proposed and integrated. The proposed system was evaluated in a real-case-scenario cultural space, which supports preventive conservation. The evaluation showed that the proposed system efficiently addressed both conceptual aspects, through means of representation and reasoning, and implementation aspects, through means of performance.

Mining social web text has been at the heart of the Natural Language Processing and Data Mining research community in the last 15 years. Though most of the reported work is on widely spoken languages, such as English, the significance of approaches that deal with less commonly spoken languages, such as Greek, is evident for reasons of preserving and documenting minority languages, cultural and ethnic diversity, and identifying intercultural similarities and differences. The present work aims at identifying, documenting and comparing social text data sets, as well as mining techniques and applications on social web text that target Modern Greek, focusing on the arising challenges and the potential for future research in the specific less widely spoken language.

Stock markets prediction is considered a considerably demanding task due to its notable returns as well as due to the high randomness within the stock market. Moreover, stock price alternations are primarily related to the capital circumstances and hot occasions/events. Nowadays, researchers have sufficiently improved prediction accuracy by taking into consideration news and social media. However, the existing strategies do not employ the different impacts that events may pose. Streaming data proves to be a perpetual real-time source of data analysis as information from different web sources can be carried. In this paper, we explore whether estimations, in terms of sentiment analysis derived from Twitter posts, can be correlated to the stock market prices. Initially, the daily Twitter posts are analyzed and different n-grams along with two strategies that are utilized to increase the accuracy of the classification, are applied. Spark streaming has been employed for the processing of Twitter data, while Apache Flume has been utilized for the analysis.

At the dawn of the 10V or big data data era, there are a considerable number of sources such as smart phones, IoT devices, social media, smart city sensors, as well as the health care system, all of which constitute but a small portion of the data lakes feeding the entire big data ecosystem. This 10V data growth poses two primary challenges, namely storing and processing. Concerning the latter, new frameworks have been developed including distributed platforms such as the Hadoop ecosystem. Classification is a major machine learning task typically executed on distributed platforms and as a consequence many algorithmic techniques have been developed tailored for these platforms. This article extensively relies in two ways on classifiers implemented in MLlib, the main machine learning library for the Hadoop ecosystem. First, a vast number of classifiers is applied to two datasets, namely Higgs and PAMAP. Second, a two-step classification is ab ovo performed to the same datasets. Specifically, the singular value decomposition of the data matrix determines first a set of transformed attributes which in turn drive the classifiers of MLlib. The twofold purpose of the proposed architecture is to reduce complexity while maintaining a similar if not better level of the metrics of accuracy, recall, and F 1 . The intuition behind this approach stems from the engineering principle of breaking down complex problems to simpler and more manageable tasks. The experiments based on the same Spark cluster indicate that the proposed architecture outperforms the individual classifiers with respect to both complexity and the abovementioned metrics.

How online cultural content is chosen based on conscious or subconscious criteria is an central question across a broad spectrum of sciences and for the entertainment industry, including content providers and distributors. To this end, a number of tailored analytics forming the backbone of recommendation engines specialized for retrieving cultural content are proposed. Their strength derives directly from well-established principles of cognitive science and behavioral economics, both scientific fields exploring aspects of human decision making. Another novel contribution of this conference paper is that these analytics are implemented in Neo4j expressed as Cypher queries. Various aspects of the cultural content and digital consumers can be naturally represented by appropriately configured vertices, whereas edges represent various connections indicating content delivery preferences. Early experiments conducted over a synthetic dataset mimicking the distributions of preferences and ratings of well-known movie datasets are encouraging as the proposed analytics outperformed the baseline of a multilayer feedforward neural network of various configurations. The synthetic dataset contains enriched preferences of mobile digital consumers of cultural content regarding literature of the Greek region of Ionian Islands.

It took some time indeed, but the research evolution and transformations that occurred in the smart agriculture field over the recent years tend to constitute the latter as the main topic of interest in the so-called Internet of Things (IoT) domain. Undoubtedly, our era is characterized by the mass production of huge amounts of data, information and content deriving from many different sources, mostly IoT devices and sensors, but also from environmentalists, agronomists, winemakers, or plain farmers and interested stakeholders themselves. Being an emerging field, only a small part of this rich content has been aggregated so far in digital platforms that serve as cross-domain hubs. The latter offer typically limited usability and accessibility of the actual content itself due to problems dealing with insufficient data and metadata availability, as well as their quality. Over our recent involvement within a precision viticulture environment and in an effort to make the notion of smart agriculture in the winery domain more accessible to and reusable from the general public, we introduce herein the model of an aggregation platform that provides enhanced services and enables human-computer collaboration for agricultural data annotations and enrichment. In principle, the proposed architecture goes beyond existing digital content aggregation platforms by advancing digital data through the combination of artificial intelligence automation and creative user engagement, thus facilitating its accessibility, visibility, and re-use. In particular, by using image and free text analysis methodologies for automatic metadata enrichment, in accordance to the human expertise for enrichment, it offers a cornerstone for future researchers focusing on improving the quality of digital agricultural information analysis and its presentation, thus establishing new ways for its efficient exploitation in a larger scale with benefits both for the agricultural and the consumer domains.

Digital influence and trust are central research topics in social media analysis with a plethora of applications ranging from social login to geolocation services and community structure discovery. In the evolving and diverse microblogging sphere of Twitter verified accounts reinforce digital influence through trust. These typically correspond either to an organization or to a person of high social status or to netizens who have been consistently proven to be highly influential. This conference paper presents a framework for estimating the probability that the next mention of any account will be to a verified account, an important metric of digital influence. At the heart of this framework lies a convolutional neural network (CNN) implemented in keras over TensorFlow. The training features are extracted from a dataset of tweets regarding the presentation of the Literature Nobel prize to Bob Dylan collected with the Twitter Streaming API and stored in MongoDB. In order to demonstrate the performance of the CNN, the results obtained by applying logistic regression to the same training features are shown in the form of statistical metrics computed from the corresponding contingency matrices, which are obtained using the pandas Python library.

Multimedia content sharing within social networks has become one of the most interesting and trending research fields over the last few years. This undoubted emerge of related research works is rather twofold, namely it includes both the analysis and management techniques of the content itself, as well as new ways for its accompanied meaningful interpretation and exploitation. In this paper, we review the recent advances in the above fields in the humanistic framework of the popular Flickr social network. In addition, the major research challenges in the area are demonstrated and discussed, which include current state-of-the-art approaches with respect to interesting humanistic data collection and interpretation research fields, such as multimedia information retrieval, (semi-) automatic tag manipulation, travel applications, semantic knowledge extraction, human activity tracking, as well as related benchmarking efforts. At the end of this survey, we also discuss the main challenges and propose a number of future research directions for interested fellow researchers to continue investigation in the field.

Recent advances in big data systems and databases have made it possible to gather raw unlabeled data at unprecedented rates. However, labeling such data constitutes a costly and timely process. This is especially true for video data, and in particular for human activity recognition (HAR) tasks. For this reason, methods for reducing the need of labeled data for HAR applications have drawn significant attention from the research community. In particular, two popular approaches developed to address the above issue are data augmentation and domain adaptation. The former attempts to leverage problem-specific, hand-crafted data synthesizers to augment the training dataset with artificial labeled data instances. The latter attempts to extract knowledge from distinct but related supervised learning tasks for which labeled data is more abundant than the problem at hand. Both methods have been extensively studied and used successfully on various tasks, but a comprehensive comparison of the two has not been carried out in the context of video data HAR. In this work, we fill this gap by providing ample experimental results comparing data augmentation and domain adaptation techniques on a cross-viewpoint, human activity recognition task from pose information.

Biomolecular computation is the scientific field focusing on the theory and practice of encoding combinatorial problems in ordinary DNA strands and applying standard biology lab operations such as cleansing and complementary sequence generation to them in order to compute an exact solution. The primary advantage offered by this computational paradigm is massive parallelism as the solution space is simultaneously searched. On the other hand, factors that need to addressed under this model are the DNA volume growth and computational errors attributed to inexact DNA matching. Biomolecular computation additionally paves the way for two- and three-dimensional self assemblying biological tiles which are closely linked at a theoretical level to a Turing machine, establishing thus its computational power. Applications include medium sized instances of TSP and the evaluation of the output of bounded fan-out Boolean circuits.

The current paper provides an overview on how user modeling, context awareness and content adaptation in Smart Home environments may be handled formally in order to capture the semantics that emerge from a newly introduced user experience: SandS is in fact a complete ecosystem of users within a social network, creating and exchanging content in the form of so-called recipes and developing a collective intelligence which adapts its operation through appropriate feedback provided by the user. The authors will approach SandS from the user's perspective and illustrate how users and their relationships can be modeled through a number of fuzzy stereotypical profiles. Additionally, context modeling in pervasive computing systems and especially in the Smart Home paradigm will be examined through appropriate representation of context cues in the overall interaction. Finally, the authors will investigate how users and system services although using languages of different semantic expressiveness can inter-operate successfully thanks to appropriate knowledge-based expert mappings.

We live in an era where typical measures towards the mitigation of environmental degradation follow the identification and recording of natural parameters closely associated with it. In addition, current scientific knowledge on the one hand may be applied to minimize the environmental impact of anthropogenic activities, whereas informatics on the other, playing a key role in this ecosystem, do offer new ways of implementing complex scientific processes regarding the collection, aggregation and analysis of data concerning environmental parameters. Furthermore, another related aspect to consider is the fact that almost all relevant data recordings are influenced by their given spatial characteristics. Taking all aforementioned inputs into account, managing such a great amount of complex and remote data requires specific digital structures; these structures are typically deployed over the Web on an attempt to capitalize existing open software platforms and modern developments of hardware technology. In this paper we present an effort to provide a technical solution based on sensing devices that are based on the well-known Arduino platform and operate continuously for gathering and transmitting of environmental state information. Controls, user interface and extensions of the proposed project rely on the Android mobile device platform (both from the software and hardware side). Finally, a crucial novel aspect of our work is the fact that all herein gathered data carry spatial information, which is rather fundamental for the successful correlation between pollutants and their place of origin. The latter is implemented by an interactive Web GIS platform operating oversight in situ and on a timeline basis.

Emotion recognition from speech may play a crucial role in many applications related to human–computer interaction or understanding the affective state of users in certain tasks, where other modalities such as video or physiological parameters are unavailable. In general, a human’s emotions may be recognized using several modalities such as analyzing facial expressions, speech, physiological parameters (e.g., electroencephalograms, electrocardiograms) etc. However, measuring of these modalities may be difficult, obtrusive or require expensive hardware. In that context, speech may be the best alternative modality in many practical applications. In this work we present an approach that uses a Convolutional Neural Network (CNN) functioning as a visual feature extractor and trained using raw speech information. In contrast to traditional machine learning approaches, CNNs are responsible for identifying the important features of the input thus, making the need of hand-crafted feature engineering optional in many tasks. In this paper no extra features are required other than the spectrogram representations and hand-crafted features were only extracted for validation purposes of our method. Moreover, it does not require any linguistic model and is not specific to any particular language. We compare the proposed approach using cross-language datasets and demonstrate that it is able to provide superior results vs. traditional ones that use hand-crafted features.

The term intelligent agriculture, or smart farming, typically involves the incorporation of computer science and information technologies into the traditional notion of farming. The latter utilizes plain machinery and equipment used for many decades and the only significant improvement made over the years has been the introduction of automation in the process. Still, at the beginning of the new century, there are ways and room for further vast improvements. More specifically, the low cost of rather advanced sensors and small-scale devices, now even connected to the Internet of Things (IoT), allowed them to be introduced in the process and used within agricultural production systems. New and emerging technologies and methodologies, like the utilization of cheap network storage, are expected to advance this development. In this sense, the main goals of this paper may be summarized as follows: (a) To identify, group, and acknowledge the current state-of-the-art research knowledge about intelligent agriculture approaches, (b) to categorize them according to meaningful data sources categories, and (c) to describe current efficient data processing and utilization aspects from the perspective of the main trends in the field.

Part 10: Mining Humanistic Data Workshop (MHDW); International audience; Living in the era of social networking, coupled together with great advances in digital multimedia user-generated content, motivated us to focus our research work on humanistic data generated by such activities towards new, more efficient ways of extracting semantically meaningful information in the process. More specifically, the herein proposed approach aims to extract areas of interest in urban areas, utilizing the increasing socially-generated knowledge from social networks. A part of the area of interest is selected, then split into “tiles” and processed with an iterative merging approach whose goal is to extract larger, “homogeneous” areas which are of special (e.g., tourist) interest. In this work generated areas of interest focus on interesting points from the humanistic point of view, thus covering in general main touristic attractions and places of interest. In order to achieve our goals, we exploit two types of metadata, namely location-based information (geo-tags) geo-tags and simple user-generated tags.

Time-based online media, such as video, has been growing in importance. Still, there is limited research on information retrieval of time-coded media content. This work elaborates on the idea of extracting feature characteristics from time-based online content by means of users' interactions analysis instead of analyzing the content itself. Accordingly, a time series of users’ activity in online media is constructed and shown to exhibit rich temporal dynamics. Additionally it is demonstrated that is also possible to detect characteristic patterns in collective activity while accessing time-based media. Pattern detection of collective activity, as well as feature extraction of the corresponding pattern, is achieved by means of a time series clustering approach. This is demonstrated with the proposed approach featuring information-rich videos. It is shown that the proposed probabilistic algorithm effectively detects distinct shapes of the users’ time series, predicting correctly popularity dynamics, as well as their scale characteristics.

New applications are emerging every day exploiting the huge data volume in community photo collections. Most focus on popular subsets, e.g., images containing landmarks or associated to Wikipedia articles. In this work we are concerned with the problem of accurately finding the location where a photo is taken without needing any metadata, that is, solely by its visual content. We also recognize landmarks where applicable, automatically linking them to Wikipedia. We show that the time is right for automating the geo-tagging process, and we show how this can work at large scale. In doing so, we do exploit redundancy of content in popular locations--but unlike most existing solutions, we do not restrict to landmarks. In other words, we can compactly represent the visual content of all thousands of images depicting e.g., the Parthenon and still retrieve any single, isolated, non-landmark image like a house or a graffiti on a wall. Starting from an existing, geo-tagged dataset, we cluster images into sets of different views of the same scene. This is a very efficient, scalable, and fully automated mining process. We then align all views in a set to one reference image and construct a 2D scene map. Our indexing scheme operates directly on scene maps. We evaluate our solution on a challenging one million urban image dataset and provide public access to our service through our online application, VIRaL.

The ability to learn robust, resizable feature representations from unlabeled data has potential applications in a wide variety of machine learning tasks. One way to create such representations is to train deep generative models that can learn to capture the complex distribution of real-world data. Generative adversarial network (GAN) approaches have shown impressive results in producing generative models of images, but relatively little work has been done on evaluating the performance of these methods for the learning representation of natural language, both in supervised and unsupervised settings at the document, sentence, and aspect level. Extensive research validation experiments were performed by leveraging the 20 Newsgroups corpus, the Movie Review (MR) Dataset, and the Finegrained Sentiment Dataset (FSD). Our experimental analysis suggests that GANs can successfully learn representations of natural language texts at all three aforementioned levels.