Search

The presence of occlusion in human activity recognition (HAR) tasks hinders the performance of recognition algorithms, as it is responsible for the loss of crucial motion data. Although it is intuitive that it may occur in almost any real-life environment, it is often underestimated in most research works, which tend to rely on datasets that have been collected under ideal conditions, i.e., without any occlusion. In this work, we present an approach that aimed to deal with occlusion in an HAR task. We relied on previous work on HAR and artificially created occluded data samples, assuming that occlusion may prevent the recognition of one or two body parts. The HAR approach we used is based on a Convolutional Neural Network (CNN) that has been trained using 2D representations of 3D skeletal motion. We considered cases in which the network was trained with and without occluded samples and evaluated our approach in single-view, cross-view, and cross-subject cases and using two large scale human motion datasets. Our experimental results indicate that the proposed training strategy is able to provide a significant boost of performance in the presence of occlusion.

Microblogging has become an extremely popular communication tool among Internet users worldwide. Millions of users daily share a huge amount of information related to various aspects of their lives, which makes the respective sites a very important source of data for analysis. Bitcoin (BTC) is a decentralized cryptographic currency and is equivalent to most recurrently known currencies in the way that it is influenced by socially developed conclusions, regardless of whether those conclusions are considered valid. This work aims to assess the importance of Twitter users’ profiles in predicting a cryptocurrency’s popularity. More specifically, our analysis focused on the user influence, captured by different Twitter features (such as the number of followers, retweets, lists) and tweet sentiment scores as the main components of measuring popularity. Moreover, the Spearman, Pearson, and Kendall Correlation Coefficients are applied as post-hoc procedures to support hypotheses about the correlation between a user influence and the aforementioned features. Tweets sentiment scoring (as positive or negative) was performed with the aid of Valence Aware Dictionary and Sentiment Reasoner (VADER) for a number of tweets fetched within a concrete time period. Finally, the Granger causality test was employed to evaluate the statistical significance of various features time series in popularity prediction to identify the most influential variable for predicting future values of the cryptocurrency popularity.

Exploring a community is an important aspect of social network analysis because it can be seen as a crucial way to decompose specific graphs into smaller graphs based on interactions between users. The process of discovering common features between groups of users, entitled “community detection”, is a fundamental feature for social network analysis, wherein the vertices represent the users and the edges their relationships. Our study focuses on identifying such phenomena on the Twitter graph of posts and on determining communities, which contain users with similar features. This paper presents the evaluation of six established community-discovery algorithms, namely Breadth-First Search, CNM, Louvain, MaxToMin, Newman–Girvan and Propinquity Dynamics, in terms of four widely used graphs and a collection of data fetched from Twitter about man-made and physical data. Furthermore, the size of each community, expressed as a percentage of the total number of vertices, is identified for the six particular algorithms, and corresponding results are extracted. In terms of user-based evaluation, we indicated to some students the communities that were extracted by every algorithm, with a corresponding user and their tweets in the grouping and considered three different alternatives for the extracted communities: “dense community”, “sparse community” and “in-between”. Our findings suggest that the community-detection algorithms can assist in identifying dense group of users.

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.

Computer games play an increasingly important role in cultural heritage preservation. They keep tradition alive in the digital domain, reflect public perception about historical events, and make history, and even legends, vivid, through means such as advanced storytelling and alternative timelines. In this context, understanding the respective underlying player base is a major success factor as different game elements elicit various emotional responses across players. To this end, player profiles are often built from a combination of low- and high-level attributes. The former pertain to ordinary activity, such as collecting points or badges, whereas the latter to the outcome of strategic decisions, such as participation in in-game events such as tournaments and auctions. When available, annotations about in-game items or player activity supplement these profiles. In this article, we describe how such annotations may be integrated into different player profile clustering schemes derived from a template Simon–Ando iterative process. As a concrete example, the proposed methodology was applied to a custom benchmark dataset comprising the player base of a cultural game. The findings are interpreted in the light of Bartle taxonomy, one of the most prominent player categorization. Moreover, the clustering quality is based on intra-cluster distance and cluster compactness. Based on these results, recommendations in an affective context for maximizing engagement are proposed for the particular game player base composition.

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.

Cognitive maps are high level representations of the key topological attributes of real or abstract spatial environments progressively built by a sequence of noisy observations. Currently such maps play a crucial role in cognitive sciences as it is believed this is how clusters of dedicated neurons at hippocampus construct internal representations. The latter include physical space and, perhaps more interestingly, abstract fields comprising of interconnected notions such as natural languages. In deep learning cognitive graphs are effective tools for simultaneous dimensionality reduction and visualization with applications among others to edge prediction, ontology alignment, and transfer learning. Fuzzy cognitive graphs have been proposed for representing maps with incomplete knowledge or errors caused by noisy or insufficient observations. The primary contribution of this article is the construction of cognitive map for the sixteen Myers-Briggs personality types with a tensor distance metric. The latter combines two categories of natural language attributes extracted from the namesake Kaggle dataset. To the best of our knowledge linguistic attributes are separated in categories. Moreover, a fuzzy variant of this map is also proposed where a certain personality may be assigned to up to two types with equal probability. The two maps were evaluated based on their topological properties, on their clustering quality, and on how well they fared against the dataset ground truth. The results indicate a superior performance of both maps with the fuzzy variant being better. Based on the findings recommendations are given for engineers and practitioners.

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.

Short-term property rentals are perhaps one of the most common traits of present day shared economy. Moreover, they are acknowledged as a major driving force behind changes in urban landscapes, ranging from established metropolises to developing townships, as well as a facilitator of geographical mobility. A geolocation ontology is a high level inference tool, typically represented as a labeled graph, for discovering latent patterns from a plethora of unstructured and multimodal data. In this work, a two-step methodological framework is proposed, where the results of various geolocation analyses, important in their own respect, such as ghost hotel discovery, form intermediate building blocks towards an enriched knowledge graph. The outlined methodology is validated upon data crawled from the Airbnb website and more specifically, on keywords extracted from comments made by users of the said platform. A rather solid case-study, based on the aforementioned type of data regarding Athens, Greece, is addressed in detail, studying the different degrees of expansion & prevalence of the phenomenon among the city’s various neighborhoods.

In recent years, following the tremendous growth of the Web, extremely large amounts of digital multimedia content are being produced every day and are shared online mainly through several newly emerged channels, such as social networks [...]

In this paper we present an approach towards real-time hand gesture recognition using the Kinect sensor, investigating several machine learning techniques. We propose a novel approach for feature extraction, using measurements on joints of the extracted skeletons. The proposed features extract angles and displacements of skeleton joints, as the latter move into a 3D space. We define a set of gestures and construct a real-life data set. We train gesture classifiers under the assumptions that they shall be applied and evaluated to both known and unknown users. Experimental results with 11 classification approaches prove the effectiveness and the potential of our approach both with the proposed dataset and also compared to state-of-the-art research works.

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.

It is noteworthy nowadays that monitoring and understanding a human’s emotional state plays a key role in the current and forthcoming computational technologies. On the other hand, this monitoring and analysis should be as unobtrusive as possible, since in our era the digital world has been smoothly adopted in everyday life activities. In this framework and within the domain of assessing humans’ affective state during their educational training, the most popular way to go is to use sensory equipment that would allow their observing without involving any kind of direct contact. Thus, in this work, we focus on human emotion recognition from audio stimuli (i.e., human speech) using a novel approach based on a computer vision inspired methodology, namely the bag-of-visual words method, applied on several audio segment spectrograms. The latter are considered to be the visual representation of the considered audio segment and may be analyzed by exploiting well-known traditional computer vision techniques, such as construction of a visual vocabulary, extraction of speeded-up robust features (SURF) features, quantization into a set of visual words, and image histogram construction. As a last step, support vector machines (SVM) classifiers are trained based on the aforementioned information. Finally, to further generalize the herein proposed approach, we utilize publicly available datasets from several human languages to perform cross-language experiments, both in terms of actor-created and real-life ones.

Ubiquitous Computing is moving the interaction away from the human-computer paradigm and towards the creation of smart environments that users and things, from the IoT perspective, interact with. User modeling and adaptation is consistently present having the human user as a constant but pervasive interaction introduces the need for context incorporation towards context-aware smart environments. The current article discusses both aspects of the user modeling and adaptation as well as context awareness and incorporation into the smart home domain. Users are modeled as fuzzy personas and these models are semantically related. Context information is collected via sensors and corresponds to various aspects of the pervasive interaction such as temperature and humidity, but also smart city sensors and services. This context information enhances the smart home environment via the incorporation of user defined home rules. Semantic Web technologies support the knowledge representation of this ecosystem while the overall architecture has been experimentally verified using input from the SmartSantander smart city and applying it to the SandS smart home within FIRE and FIWARE frameworks.

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.

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 % .

After many decades of flourishing computer science it is now rather evident that in a world dominated by different kinds of digital information, both applications and people are forced to seek new, innovative structures and forms of data management and organization. Following this blunt observation, researchers in informatics have strived over the recent years to tackle the non-unique and rather evolving notion of context, which aids significantly the data disambiguation process. Motivated by this environment, this work attempts to summarize and organize in a researcher-friendly tabular manner important or pioneer related research works deriving from diverse computational intelligence domains: Initially, we discuss the influence of context with respect to traditional low-level multimedia content analysis and search, and retrieval tasks and then we advance to the fields of overall computational context-awareness and the so-called human-generated contextual elements. In an effort to provide meaningful information to fellow researchers, this brief survey focuses on the impact of context in modern and popular computing undertakings of our era. More specifically, we focus to the presentation of a short review of visual context modeling methods, followed by the depiction of context-awareness in modern computing. Works dealing with the interpretation of context by human-generated interactions are also discussed herein, as the particular domain gains an ever-increasing proportion of related research nowadays. We then conclude the paper by providing a short discussion on (i) the motivation behind the included context type categorization into three main pillars; (ii) the findings and conclusions of the survey for each context category; and (iii) a couple of brief advices derived from the survey for both interested developers and fellow researchers.

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.

Living in the “era of social networking”, we are experiencing a data revolution, generating an astonishing amount of digital information every single day. Due to this proliferation of data volume, there has been an explosion of new application domains for information mined from social networks. In this paper, we leverage this “socially-generated knowledge” (i.e., user-generated content derived from social networks) towards the detection of areas-of-interest within an urban region. These large and homogeneous areas contain multiple points-of-interest which are of special interest to particular groups of people (e.g., tourists and/or consumers). In order to identify them, we exploit two types of metadata, namely location-based information included within geo-tagged photos that we collect from Flickr, along with plain simple textual information from user-generated tags. We propose an algorithm that divides a predefined geographical area (i.e., the center of Athens, Greece) into “tile”-shaped sub-regions and based on an iterative merging procedure, it aims to detect larger, cohesive areas. We examine the performance of the algorithm both in a qualitative and quantitative manner. Our experiments demonstrate that the proposed geo-clustering algorithm is able to correctly detect regions that contain popular tourist attractions within them with very promising results.

Abstract  This paper presents a video analysis approach based on concept detection and keyframe extraction employing a visual thesaurus representation. Color and texture descriptors are extracted from coarse regions of each frame and a visual thesaurus is constructed after clustering regions. The clusters, called region types, are used as basis for representing local material information through the construction of a model vector for each frame, which reflects the composition of the image in terms of region types. Model vector representation is used for keyframe selection either in each video shot or across an entire sequence. The selection process ensures that all region types are represented. A number of high-level concept detectors is then trained using global annotation and Latent Semantic Analysis is applied. To enhance detection performance per shot, detection is employed on the selected keyframes of each shot, and a framework is proposed for working on very large data sets. [ABSTRACT FROM AUTHOR]

Abstract  In this paper we present a framework for unified, personalized access to heterogeneous multimedia content in distributed repositories. Focusing on semantic analysis of multimedia documents, metadata, user queries and user profiles, it contributes to the bridging of the gap between the semantic nature of user queries and raw multimedia documents. The proposed approach utilizes as input visual content analysis results, as well as analyzes and exploits associated textual annotation, in order to extract the underlying semantics, construct a semantic index and classify documents to topics, based on a unified knowledge and semantics representation model. It may then accept user queries, and, carrying out semantic interpretation and expansion, retrieve documents from the index and rank them according to user preferences, similarly to text retrieval. All processes are based on a novel semantic processing methodology, employing fuzzy algebra and principles of taxonomic knowledge representation. The first part of this work presented in this paper deals with data and knowledge models, manipulation of multimedia content annotations and semantic indexing, while the second part will continue on the use of the extracted semantic information for personalized retrieval. [ABSTRACT FROM AUTHOR]