This page has only limited features, please log in for full access.
Graph signal processing has recently emerged as a field with applications across a broad spectrum of fields including brain connectivity networks, logistics and supply chains, social media, computational aesthetics, and transportation networks. In this paradigm, signal processing methodologies are applied to the adjacency matrix, seen as a two-dimensional signal. Fundamental operations of this type include graph sampling, the graph Laplace transform, and graph spectrum estimation. In this context, topology similarity metrics allow meaningful and efficient comparisons between pairs of graphs or along evolving graph sequences. In turn, such metrics can be the algorithmic cornerstone of graph clustering schemes. Major advantages of relying on existing signal processing kernels include parallelism, scalability, and numerical stability. This work presents a scheme for training a tensor stack network to estimate the topological correlation coefficient between two graph adjacency matrices compressed with the two-dimensional discrete cosine transform, augmenting thus the indirect decompression with knowledge stored in the network. The results from three benchmark graph sequences are encouraging in terms of mean square error and complexity especially for graph sequences. An additional key point is the independence of the proposed method from the underlying domain semantics. This is primarily achieved by focusing on higher-order structural graph patterns.
Georgios Drakopoulos; Eleanna Kafeza; Phivos Mylonas; Lazaros Iliadis. Transform-based graph topology similarity metrics. Neural Computing and Applications 2021, 1 -13.
AMA StyleGeorgios Drakopoulos, Eleanna Kafeza, Phivos Mylonas, Lazaros Iliadis. Transform-based graph topology similarity metrics. Neural Computing and Applications. 2021; ():1-13.
Chicago/Turabian StyleGeorgios Drakopoulos; Eleanna Kafeza; Phivos Mylonas; Lazaros Iliadis. 2021. "Transform-based graph topology similarity metrics." Neural Computing and Applications , no. : 1-13.
Database deployment is a complex task depending on a multitude of operational parameters such as anticipated data scaling trends, expected type and volume of queries, uptime requirements, replication policies, available budget, and personnel training and experience. Thus, enterprise database administrators eventually rely on various performance metrics in conjunction to existing company policies in order to determine the best possible solution under these constraints. The recent advent of NoSQL databases, including graph databases such as Neo4j and document stores like MongoDB, added another degree of freedom in database selection since for a number of years relational databases such as PostgreSQL were the only available technology. In this work the scaling characteristics of a representative set of social queries executed on virtual machine installations of PostgreSQL and MongoDB are evaluated on a large volume of political tweets regarding Brexit. Moreover, Wiener filters for predicting the execution time of social query windows of fixed length over both databases are designed.
Michael Marountas; Georgios Drakopoulos; Phivos Mylonas; Spyros Sioutas. Recommending Database Architectures for Social Queries: A Twitter Case Study. Collaboration in a Hyperconnected World 2021, 715 -728.
AMA StyleMichael Marountas, Georgios Drakopoulos, Phivos Mylonas, Spyros Sioutas. Recommending Database Architectures for Social Queries: A Twitter Case Study. Collaboration in a Hyperconnected World. 2021; ():715-728.
Chicago/Turabian StyleMichael Marountas; Georgios Drakopoulos; Phivos Mylonas; Spyros Sioutas. 2021. "Recommending Database Architectures for Social Queries: A Twitter Case Study." Collaboration in a Hyperconnected World , no. : 715-728.
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.
Georgios Drakopoulos; Yorghos Voutos; Phivos Mylonas. Annotation-Assisted Clustering of Player Profiles in Cultural Games: A Case for Tensor Analytics in Julia. Big Data and Cognitive Computing 2020, 4, 39 .
AMA StyleGeorgios Drakopoulos, Yorghos Voutos, Phivos Mylonas. Annotation-Assisted Clustering of Player Profiles in Cultural Games: A Case for Tensor Analytics in Julia. Big Data and Cognitive Computing. 2020; 4 (4):39.
Chicago/Turabian StyleGeorgios Drakopoulos; Yorghos Voutos; Phivos Mylonas. 2020. "Annotation-Assisted Clustering of Player Profiles in Cultural Games: A Case for Tensor Analytics in Julia." Big Data and Cognitive Computing 4, no. 4: 39.
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.
Georgios Drakopoulos; Andreas Kanavos; Phivos Mylonas Mylonas; Panagiotis Pintelas. Extending Fuzzy Cognitive Maps With Tensor-Based Distance Metrics. Mathematics 2020, 8, 1898 .
AMA StyleGeorgios Drakopoulos, Andreas Kanavos, Phivos Mylonas Mylonas, Panagiotis Pintelas. Extending Fuzzy Cognitive Maps With Tensor-Based Distance Metrics. Mathematics. 2020; 8 (11):1898.
Chicago/Turabian StyleGeorgios Drakopoulos; Andreas Kanavos; Phivos Mylonas Mylonas; Panagiotis Pintelas. 2020. "Extending Fuzzy Cognitive Maps With Tensor-Based Distance Metrics." Mathematics 8, no. 11: 1898.
Self organizing maps (SOMs) are neural networks designed to be in an unsupervised way to create connections, learned through a modified Hebbian rule, between a high- (the input vector space) and a low-dimensional space (the cognitive map) based solely on distances in the input vector space. Moreover, the cognitive map is segmentwise continuous and preserves many of the major topological features of the latter. Therefore, neurons, trained using a Hebbian learning rule, can approximate the shape of any arbitrary manifold provided there are enough neurons to accomplish this. Moreover, the cognitive map can be readily used for clustering and visualization. Because of the above properties, SOMs are often used in big data pipelines. This conference paper focuses on a multilinear distance metric for the input vector space which adds flexibility in two ways. First, clustering can be extended to higher order data such as images, graphs, matrices, and time series. Second, the resulting clusters are unions of arbitrary shapes instead of fixed ones such as rectangles in case of \(\ell _1\) norm or circles in case of \(\ell _2\) norm. As a concrete example, the proposed distance metric is applied to an anonymized and open under the Creative Commons license cognitive multimodal dataset of fMRI images taken during three distinct cognitive tasks. Keeping the latter as ground truth, a subset of these images is clustered with SOMs of various configurations. The results are evaluated using the corresponding confusion matrices, topological error rates, activation set change rates, and intra-cluster distance variations.
Georgios Drakopoulos; Ioanna Giannoukou; Phivos Mylonas; Spyros Sioutas. On Tensor Distances for Self Organizing Maps: Clustering Cognitive Tasks. Transactions on Petri Nets and Other Models of Concurrency XV 2020, 195 -210.
AMA StyleGeorgios Drakopoulos, Ioanna Giannoukou, Phivos Mylonas, Spyros Sioutas. On Tensor Distances for Self Organizing Maps: Clustering Cognitive Tasks. Transactions on Petri Nets and Other Models of Concurrency XV. 2020; ():195-210.
Chicago/Turabian StyleGeorgios Drakopoulos; Ioanna Giannoukou; Phivos Mylonas; Spyros Sioutas. 2020. "On Tensor Distances for Self Organizing Maps: Clustering Cognitive Tasks." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 195-210.
Does a tweet with specific emotional content posted by an influential account have the capability to shape or even completely alter the opinions of its readers? Moreover, can other influential accounts further enhance its original emotional potential by retweeting it and, thus, letting their followers read it? Real Twitter conversations seem to imply an affirmative answer to both questions. If this is indeed the case, then what is the key for not only successfully reaching to a large number of accounts but also for convincingly offering an alternative perspective via affective means, therefore triggering a large scale opinion change in an ongoing Twitter conversation? This work primarily focuses on determining which tweets cause multiple sentiment polarity alternations to occur based on a window segmentation approach. Moreover, an offline framework for discovering affective pivot points in a conversation based on its Hilbert–Huang spectrum, which has close ties to the Fourier transform, is introduced. Finally, given that it is highly desirable to track the sentiment shifts of a Twitter conversation while it unfolds, an adaptive scheme is presented for approximating the window sizes obtained by the offline methodology. As a concrete example, the abovementioned methodologies are applied to three recent long Twitter discussions and the results are analyzed.
Georgios Drakopoulos; Andreas Kanavos; Phivos Mylonas; Spyros Sioutas. Discovering sentiment potential in Twitter conversations with Hilbert–Huang spectrum. Evolving Systems 2020, 12, 3 -17.
AMA StyleGeorgios Drakopoulos, Andreas Kanavos, Phivos Mylonas, Spyros Sioutas. Discovering sentiment potential in Twitter conversations with Hilbert–Huang spectrum. Evolving Systems. 2020; 12 (1):3-17.
Chicago/Turabian StyleGeorgios Drakopoulos; Andreas Kanavos; Phivos Mylonas; Spyros Sioutas. 2020. "Discovering sentiment potential in Twitter conversations with Hilbert–Huang spectrum." Evolving Systems 12, no. 1: 3-17.
Blockchain is a linearly linked, distributed, and very robust data structure. Originally proposed as part of the Bitcoin distributed stack, it can be applied in a number of fields, most notably in smart contracts, social media, secure IoT, and cryptocurrency mining. It ensures data integrity by distributing strongly encrypted data in widely redundant segments. Each new insertion requires verification and approval by the majority of the users of the blockchain. Both encryption and verification are computationally intensive tasks which cannot be solved with ordinary off-the-shelf CPUs. This has resulted in a renewed scientific interest in secure distributed communication and coordination protocols. Mobile health applications are growing progressively popular and have the enormous advantage of timely diagnosis of certain conditions. However, privacy concerns have been raised as mobile health applications by default have access to highly sensitive personal data. This chapter presents concisely how blockchain can be applied to mobile health applications in order to enhance privacy.
Georgios Drakopoulos; Michail Marountas; Xenophon Liapakis; Giannis Tzimas; Phivos Mylonas; Spyros Sioutas. Blockchain for Mobile Health Applications Acceleration with GPU Computing. Advances in Experimental Medicine and Biology 2020, 1194, 389 -396.
AMA StyleGeorgios Drakopoulos, Michail Marountas, Xenophon Liapakis, Giannis Tzimas, Phivos Mylonas, Spyros Sioutas. Blockchain for Mobile Health Applications Acceleration with GPU Computing. Advances in Experimental Medicine and Biology. 2020; 1194 ():389-396.
Chicago/Turabian StyleGeorgios Drakopoulos; Michail Marountas; Xenophon Liapakis; Giannis Tzimas; Phivos Mylonas; Spyros Sioutas. 2020. "Blockchain for Mobile Health Applications Acceleration with GPU Computing." Advances in Experimental Medicine and Biology 1194, no. : 389-396.
Mobile health applications are steadily gaining momentum in the modern world given the omnipresence of various mobile or Wi-Fi connections. Given that the bandwidth of these connections increases over time, especially in conjunction with advanced modulation and error-correction codes, whereas the latency drops, the cooperation between mobile applications becomes gradually easier. This translates to reduced computational burden and heat dissipation for each isolated device but at the expense of increased privacy risks. This chapter presents a configurable and scalable edge computing architecture for cooperative digital health mobile applications.
Georgios Drakopoulos; Phivos Mylonas; Spyros Sioutas. An Architecture for Cooperative Mobile Health Applications. Advances in Experimental Medicine and Biology 2020, 1194, 23 -29.
AMA StyleGeorgios Drakopoulos, Phivos Mylonas, Spyros Sioutas. An Architecture for Cooperative Mobile Health Applications. Advances in Experimental Medicine and Biology. 2020; 1194 ():23-29.
Chicago/Turabian StyleGeorgios Drakopoulos; Phivos Mylonas; Spyros Sioutas. 2020. "An Architecture for Cooperative Mobile Health Applications." Advances in Experimental Medicine and Biology 1194, no. : 23-29.
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.
Georgios Drakopoulos; Ioanna Giannoukou; Phivos Mylonas; Spyros Sioutas. The Converging Triangle of Cultural Content, Cognitive Science, and Behavioral Economics. Collaboration in a Hyperconnected World 2020, 200 -212.
AMA StyleGeorgios Drakopoulos, Ioanna Giannoukou, Phivos Mylonas, Spyros Sioutas. The Converging Triangle of Cultural Content, Cognitive Science, and Behavioral Economics. Collaboration in a Hyperconnected World. 2020; ():200-212.
Chicago/Turabian StyleGeorgios Drakopoulos; Ioanna Giannoukou; Phivos Mylonas; Spyros Sioutas. 2020. "The Converging Triangle of Cultural Content, Cognitive Science, and Behavioral Economics." Collaboration in a Hyperconnected World , no. : 200-212.
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.
Athanasios Alexopoulos; Georgios Drakopoulos; Andreas Kanavos; Phivos Mylonas; Gerasimos Vonitsanos. Two-Step Classification with SVD Preprocessing of Distributed Massive Datasets in Apache Spark. Algorithms 2020, 13, 71 .
AMA StyleAthanasios Alexopoulos, Georgios Drakopoulos, Andreas Kanavos, Phivos Mylonas, Gerasimos Vonitsanos. Two-Step Classification with SVD Preprocessing of Distributed Massive Datasets in Apache Spark. Algorithms. 2020; 13 (3):71.
Chicago/Turabian StyleAthanasios Alexopoulos; Georgios Drakopoulos; Andreas Kanavos; Phivos Mylonas; Gerasimos Vonitsanos. 2020. "Two-Step Classification with SVD Preprocessing of Distributed Massive Datasets in Apache Spark." Algorithms 13, no. 3: 71.
In communication networks resilience or structural coherency, namely the ability to maintain total connectivity even after some data links are lost for an indefinite time, is a major design consideration. Evaluating resilience is a computationally challenging task since it often requires examining a prohibitively high number of connections or of node combinations, depending on the structural coherency definition. In order to study resilience, communication systems are treated in an abstract level as graphs where the existence of an edge depends heavily on the local connectivity properties between the two nodes. Once the graph is derived, its resilience is evaluated by a tensor stack network (TSN). TSN is an emerging deep learning classification methodology for big data which can be expressed either as stacked vectors or as matrices, such as images or oversampled data from multiple-input and multiple-output digital communication systems. As their collective name suggests, the architecture of TSNs is based on tensors, namely higher-dimensional vectors, which simulate the simultaneous training of a cluster of ordinary multilayer feedforward neural networks (FFNNs). In the TSN structure the FFNNs are also interconnected and, thus, at certain steps of the training process they learn from the errors of each other. An additional advantage of the TSN training process is that it is regularized, resulting in parsimonious classifiers. The TSNs are trained to evaluate how resilient a graph is, where the real structural strength is assessed through three established resiliency metrics, namely the Estrada index, the odd Estrada index, and the clustering coefficient. Although the approach of modelling the communication system exclusively in structural terms is function oblivious, it can be applied to virtually any type of communication network independently of the underlying technology. The classification achieved by four configurations of TSNs is evaluated through six metrics, including the F1 metric as well as the type I and type II errors, derived from the corresponding contingency tables. Moreover, the effects of sparsifying the synaptic weights resulting from the training process are explored for various thresholds. Results indicate that the proposed method achieves a very high accuracy, while it is considerably faster than the computation of each of the three resilience metrics. Concerning sparsification, after a threshold the accuracy drops, meaning that the TSNs cannot be further sparsified. Thus, their training is very efficient in that respect.
Georgios Drakopoulos; Phivos Mylonas. Evaluating graph resilience with tensor stack networks: a Keras implementation. Neural Computing and Applications 2020, 32, 4161 -4176.
AMA StyleGeorgios Drakopoulos, Phivos Mylonas. Evaluating graph resilience with tensor stack networks: a Keras implementation. Neural Computing and Applications. 2020; 32 (9):4161-4176.
Chicago/Turabian StyleGeorgios Drakopoulos; Phivos Mylonas. 2020. "Evaluating graph resilience with tensor stack networks: a Keras implementation." Neural Computing and Applications 32, no. 9: 4161-4176.
Georgios Drakopoulos; Evaggelos Spyrou; Yorghos Voutos; Phivos Mylonas. A semantically annotated JSON metadata structure for open linked cultural data in Neo4j. Proceedings of the 23rd Pan-Hellenic Conference on Informatics 2019, 81 -88.
AMA StyleGeorgios Drakopoulos, Evaggelos Spyrou, Yorghos Voutos, Phivos Mylonas. A semantically annotated JSON metadata structure for open linked cultural data in Neo4j. Proceedings of the 23rd Pan-Hellenic Conference on Informatics. 2019; ():81-88.
Chicago/Turabian StyleGeorgios Drakopoulos; Evaggelos Spyrou; Yorghos Voutos; Phivos Mylonas. 2019. "A semantically annotated JSON metadata structure for open linked cultural data in Neo4j." Proceedings of the 23rd Pan-Hellenic Conference on Informatics , no. : 81-88.
Blockchain is a prime example of disruptive technology in multiple levels. With the advent of blockchains becomes obsolete the need for a mutually trusted third party acting as intermediary between agents which do not necessarily trust each other in transactions of any kind, including political or shareholder voting, crowdfunding, financial deals, logistics and supply chain management, and contract formulation. An integral part of the blockchain stack is the proof system, namely the mechanism efficiently verifying the claims of various blockchain stakeholders. Thus, trust is effectively established in a literally trustless environment with purely computational means. This is especially critical in the digital formulation of smart contracts where clauses are to be strictly upheld by intelligent agents. The most prominent proof systems recently proposed in the scientific literature are reviewed. Additionally, the applications of blockchain technology to smart contracts is discussed. The latter allows clause re-negotiation, increasing thus the flexibility factor in transactions. As a concrete example, a simple smart contract written in Solidity, a high level language for the Ethereum Virtual Machine, is presented.
Georgios Drakopoulos; Eleanna Kafeza; Haseena Al Katheeri. Proof Systems In Blockchains: A Survey. 2019 4th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM) 2019, 1 -6.
AMA StyleGeorgios Drakopoulos, Eleanna Kafeza, Haseena Al Katheeri. Proof Systems In Blockchains: A Survey. 2019 4th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM). 2019; ():1-6.
Chicago/Turabian StyleGeorgios Drakopoulos; Eleanna Kafeza; Haseena Al Katheeri. 2019. "Proof Systems In Blockchains: A Survey." 2019 4th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM) , no. : 1-6.
Smart agriculture is increasingly becoming a paramount financial sector with important implications on a global scale. The real time weather and soil status monitoring as well as the desired higher food quality are major drivers behind this technological, ecological, and financial trend. This work explores the enticing prospect of combining IoT and smart contract technologies with smart agriculture in order to deliver not only higher quality agricultural products, but also improving the associated supply chain and agricultural logistics, thus resulting in multiple benefits for all the parties involved. Emphasis is placed on deriving similarity metrics for tuples describing soil and climate conditions based on numerical and possibly categorical data. Moreover, a sample implementation of one such metric is given in Solidity, a high level language for formulating smart contracts designed for the Ethereum Virtual Machine is also provided as a concrete example. Finally, aspects of agricultural asset digitization, a crucial step for smart contracts relying on physical objects are also discussed.
Yorghos Voutos; Georgios Drakopoulos; Phivos Mylonas. Smart Agriculture: An Open Field For Smart Contracts. 2019 4th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM) 2019, 1 -6.
AMA StyleYorghos Voutos, Georgios Drakopoulos, Phivos Mylonas. Smart Agriculture: An Open Field For Smart Contracts. 2019 4th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM). 2019; ():1-6.
Chicago/Turabian StyleYorghos Voutos; Georgios Drakopoulos; Phivos Mylonas. 2019. "Smart Agriculture: An Open Field For Smart Contracts." 2019 4th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM) , no. : 1-6.
Non-linear system identification is a challenging problem with a plethora of engineering applications including digital telecommunications, adaptive control of biological systems, assessing integrity of mechanical constructs, and geological surveys. Various approaches have been proposed in the scientific literature, including Volterra and multivariate Taylor series, fuzzy neural networks, state space models, and wavelets. This conference paper proposes a succinct model of a non-linear system with memory based on a third order tensor whose coefficients are trained in an LMS-like way. Moreover, two variants deriving from sign LMS and batch LMS algorithms respectively are also implemented in TensorFlow. The results of applying the three training algorithms to this system are compared in terms of the mean square error in validation phase, the convergence rate of the coefficients, and the convergence rate of the Euclidean norm of the local gradients of the system model.
Georgios Drakopoulos; Phivos Mylonas; Spyros Sioutas. A Case of Adaptive Nonlinear System Identification with Third Order Tensors in TensorFlow. 2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA) 2019, 1 -6.
AMA StyleGeorgios Drakopoulos, Phivos Mylonas, Spyros Sioutas. A Case of Adaptive Nonlinear System Identification with Third Order Tensors in TensorFlow. 2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA). 2019; ():1-6.
Chicago/Turabian StyleGeorgios Drakopoulos; Phivos Mylonas; Spyros Sioutas. 2019. "A Case of Adaptive Nonlinear System Identification with Third Order Tensors in TensorFlow." 2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA) , no. : 1-6.
Tensor algebra is the next evolutionary step of linear algebra to more than two dimensions. Its plethora of applications include signal processing, big data, deep learning, multivariate numerical analysis, information retrieval, and social media analysis. As is precisely the case with data matrices, decompositions and factorizations with special properties reveal inherent but latent patterns which are not immediately discernible. Alternatively, for large tensors direct clustering can yield similar patterns. Once identified, said patterns can pave the way for other operations commonly found in a knowledge mining pipeline such as compression, outlier discovery, and higher order statistics. This survey concisely presents the key tensor clustering techniques as well as their applications. Additionally, deep learning frameworks which natively support tensors such as TensorFlow, Breeze, Spark MLlib, and Tensor Toolbox are presented.
Georgios Drakopoulos; Evaggelos Spyrou; Phivos Mylonas. Tensor Clustering: A Review. 2019 14th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP) 2019, 1 -6.
AMA StyleGeorgios Drakopoulos, Evaggelos Spyrou, Phivos Mylonas. Tensor Clustering: A Review. 2019 14th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP). 2019; ():1-6.
Chicago/Turabian StyleGeorgios Drakopoulos; Evaggelos Spyrou; Phivos Mylonas. 2019. "Tensor Clustering: A Review." 2019 14th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP) , no. : 1-6.
Fibonacci numbers appear in numerous engineering and computing applications including population growth models, software engineering, task management, and data structure analysis. This mandates a computationally efficient way for generating a long sequence of successive Fibonacci integers. With the advent of GPU computing and the associated specialized tools, this task is greatly facilitated by harnessing the potential of parallel computing. This work presents two alternative parallel Fibonacci generators implemented in TensorFlow, one based on the well-known recurrence equation generating the Fibonacci sequence and one expressed on inherent linear algebraic properties of Fibonacci numbers. Additionally, the question of using lookup tables in conjunction with spline interpolation or direct computation within a parallel context for the computation of the powers of known quantities is explored. Although both parallel generators outperform the baseline serial implementation in terms of wallclock time and FLOPS, there is no clear winner between them as the results rely on the number of integers generated. Additionally, replacing computations with a lookup table degrades performance, which can be attributed to the frequent access to the shared memory.
Georgios Drakopoulos; Xenophon Liapakis; Evaggelos Spyrou; Giannis Tzimas; Phivos Mylonas; Spyros Sioutas. Computing Long Sequences of Consecutive Fibonacci Integers with TensorFlow. Lecture Notes in Control and Information Sciences 2019, 150 -160.
AMA StyleGeorgios Drakopoulos, Xenophon Liapakis, Evaggelos Spyrou, Giannis Tzimas, Phivos Mylonas, Spyros Sioutas. Computing Long Sequences of Consecutive Fibonacci Integers with TensorFlow. Lecture Notes in Control and Information Sciences. 2019; ():150-160.
Chicago/Turabian StyleGeorgios Drakopoulos; Xenophon Liapakis; Evaggelos Spyrou; Giannis Tzimas; Phivos Mylonas; Spyros Sioutas. 2019. "Computing Long Sequences of Consecutive Fibonacci Integers with TensorFlow." Lecture Notes in Control and Information Sciences , no. : 150-160.
Tensor clustering is a knowledge management technique which is well known as a major algorithmic and technological driver behind a broad applications spectrum. The latter ranges from multimodal social media analysis and geolocation processing to analytics tailored for large omic data. However, known exact tensor clustering problems when reduced to tensor factorization are provably NP hard. This is attributed in part to the volume of data contained in a tensor, proportional to the product of its dimensions, as well as to the increased interdependency between the tensor entries across its dimensions. One well studied way to circumvent this inherent difficulty is to resort to heuristics. This article presents an enhanced version of a genetic algorithm tailored for community discovery structure in tensors containing spatiosocial data, namely linguistic and geolocation data. The objective function as well as the chromosome fitness functions by design take into account elements of linguistic propagation models. The genetic operators of selection, crossover, and mutation as well as the newly added double mutation operator work directly on the community level. Moreover, various policies for maintaining gene variability across generations are studied in an extensive simulation powered by Google TensorFlow. As with its predecessor, the proposed genetic algorithm has been applied to a dataset consisting of a large number of Tweets and their associated geolocations from the Grand Duchy of Luxembourg, a historically and de facto trilingual country. The results are compared with those obtained from the original genetic algorithm and their differences are interpreted.
Georgios Drakopoulos; Foteini Stathopoulou; Andreas Kanavos; Michael Paraskevas; Giannis Tzimas; Phivos Mylonas; Lazaros Iliadis. A genetic algorithm for spatiosocial tensor clustering. Evolving Systems 2019, 11, 491 -501.
AMA StyleGeorgios Drakopoulos, Foteini Stathopoulou, Andreas Kanavos, Michael Paraskevas, Giannis Tzimas, Phivos Mylonas, Lazaros Iliadis. A genetic algorithm for spatiosocial tensor clustering. Evolving Systems. 2019; 11 (3):491-501.
Chicago/Turabian StyleGeorgios Drakopoulos; Foteini Stathopoulou; Andreas Kanavos; Michael Paraskevas; Giannis Tzimas; Phivos Mylonas; Lazaros Iliadis. 2019. "A genetic algorithm for spatiosocial tensor clustering." Evolving Systems 11, no. 3: 491-501.
Georgios Drakopoulos; George Pikramenos; Evaggelos Spyrou; Stavros Perantonis. Emotion Recognition from Speech: A Survey. Proceedings of the 15th International Conference on Web Information Systems and Technologies 2019, 432 -439.
AMA StyleGeorgios Drakopoulos, George Pikramenos, Evaggelos Spyrou, Stavros Perantonis. Emotion Recognition from Speech: A Survey. Proceedings of the 15th International Conference on Web Information Systems and Technologies. 2019; ():432-439.
Chicago/Turabian StyleGeorgios Drakopoulos; George Pikramenos; Evaggelos Spyrou; Stavros Perantonis. 2019. "Emotion Recognition from Speech: A Survey." Proceedings of the 15th International Conference on Web Information Systems and Technologies , no. : 432-439.
Ioanna Kyriazidou; Georgios Drakopoulos; Andreas Kanavos; Christos Makris; Phivos Mylonas. Towards Predicting Mentions to Verified Twitter Accounts: Building Prediction Models over MongoDB with Keras. Proceedings of the 15th International Conference on Web Information Systems and Technologies 2019, 25 -33.
AMA StyleIoanna Kyriazidou, Georgios Drakopoulos, Andreas Kanavos, Christos Makris, Phivos Mylonas. Towards Predicting Mentions to Verified Twitter Accounts: Building Prediction Models over MongoDB with Keras. Proceedings of the 15th International Conference on Web Information Systems and Technologies. 2019; ():25-33.
Chicago/Turabian StyleIoanna Kyriazidou; Georgios Drakopoulos; Andreas Kanavos; Christos Makris; Phivos Mylonas. 2019. "Towards Predicting Mentions to Verified Twitter Accounts: Building Prediction Models over MongoDB with Keras." Proceedings of the 15th International Conference on Web Information Systems and Technologies , no. : 25-33.