Search

Regression algorithms are regularly used for improving the accuracy of satellite precipitation products. In this context, satellite precipitation and topography data are the predictor variables, and gauged-measured precipitation data are the dependent variables. Alongside this, it is increasingly recognised in many fields that combinations of algorithms through ensemble learning can lead to substantial predictive performance improvements. Still, a sufficient number of ensemble learners for improving the accuracy of satellite precipitation products and their large-scale comparison are currently missing from the literature. In this study, we work towards filling in this specific gap by proposing 11 new ensemble learners in the field and by extensively comparing them. We apply the ensemble learners to monthly data from the PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks) and IMERG (Integrated Multi-satellitE Retrievals for GPM) gridded datasets that span over a 15-year period and over the entire contiguous United States (CONUS). We also use gauge-measured precipitation data from the Global Historical Climatology Network monthly database, version 2 (GHCNm). The ensemble learners combine the predictions of six machine learning regression algorithms (base learners), namely the multivariate adaptive regression splines (MARS), multivariate adaptive polynomial splines (poly-MARS), random forests (RF), gradient boosting machines (GBM), extreme gradient boosting (XGBoost) and Bayesian regularized neural networks (BRNN), and each of them is based on a different combiner. The combiners include the equal-weight combiner, the median combiner, two best learners and seven variants of a sophisticated stacking method. The latter stacks a regression algorithm on top of the base learners to combine their independent predictions. Its seven variants are defined by seven different regression algorithms, specifically the linear regression (LR) algorithm and the six algorithms also used as base learners. The results suggest that sophisticated stacking performs significantly better than the base learners, especially when applied using the LR algorithm. It also beats the simpler combination methods. [ABSTRACT FROM AUTHOR]

An important issue in performing dance analysis is the automatic extraction of its choreographic patterns, since these elements provide an abstract representation of the semantics of the dance and encode the overall dance storytelling. However, application of conventional video summarization algorithms on dance sequences cannot appropriately retrieve their choreographic patterns, since a dance is composed of an ordered set of sequential elements which are often repeated in time. Additionally, 3D geometry is lost using color information. For this reason, in this paper we propose a new dance summarization scheme of 3D motion captured data (in the form of skeleton joints coordinates) recorded using the Vicon motion capture system. The proposed key frame extraction method implements a hierarchical scheme that exploits spatio-temporal variations of dance features. Initially, global holistic descriptors are extracted to localize the key choreographic steps of a dance (coarse representation). Then, each segment is further decomposed into finer sub-segments to improve dance representativity (fine representation). The abstraction scheme exploits the concepts of a Sparse Modeling Representative Selection (SMRS) appropriately modified to enable spatio-temporal modelling of the dance sequences through a hierarchical decomposition algorithm. Our approach is evaluated on thirty folkloric dance sequences recorded at the Aristotle University of Thessaloniki under the framework of Terpsichore project representing five different choreographies and on publicly available datasets from Carnegie–Mellon University, which depict performances on theatrical kinesiology. Comparisons with other traditional video summarization methods indicate a clear superiority of the proposed hierarchical spatio-temporal decomposition scheme. [ABSTRACT FROM AUTHOR]

Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure, advantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future directions in designing deep learning schemes for computer vision problems and the challenges involved therein. [ABSTRACT FROM AUTHOR]

A system designed and developed for the three-dimensional (3-D) reconstruction of cultural heritage (CH) assets is presented. Two basic approaches are presented. The first one, resulting in an "approximate" 3-D model, uses images retrieved in online multimedia collections; it employs a clustering-based technique to perform content-based filtering and eliminate outliers that significantly reduce the performance of 3-D reconstruction frameworks. The second one is based on input image data acquired through terrestrial laser scanning, as well as close range and airborne photogrammetry; it follows a sophisticated multistep strategy, which leads to a "precise" 3-D model. Furthermore, the concept of change history maps is proposed to address the computational limitations involved in four-dimensional (4-D) modeling, i.e., capturing 3-D models of a CH landmark or site at different time instances. The system also comprises a presentation viewer, which manages the display of the multifaceted CH content collected and created. The described methods have been successfully applied and evaluated in challenging real-world scenarios, including the 4-D reconstruction of the historic Market Square of the German city of Calw in the context of the 4-D-CH-World EU project. [ABSTRACT FROM AUTHOR]

We present a S imultaneous P recise L ocalization A nd C lassification architecture employing a U-Net model (called SPLAC U-Net) for an automated simultaneous detection/localization of corrosion and recognition of rust grade from RGB images on metal structures. The proposed architecture is compatible with the innovative idea of automated maintenance and prefabrication since (i) rust detection is carried out at pixel level accuracy in a highly precise manner and (ii) localization/classification is performed simultaneously. Prior works on corrosion identification tend to focus either on localizing defected regions with bounding boxes, with low therefore localization precision, or on only visual inspection or classification and thus they are incompatible with the prefabrication concept. The proposed scheme consists of three layers. In the first layer, we utilize a lightweight deep U-Net model for semantically localizing corroded regions in images. In the second layer, we adopt a novel data projection scheme for refining the contours of the detected objects (i.e., defected regions) of the first layer, enhancing, therefore, localization precision. We find that the network after the boundary refinement process exceeds the typical deep learning methods performance on the accuracy, F1-score, and Intersection over Union (IoU) metrics. In the third and final layer of SPLAC U-Net, we extend the U-Net model by adding residual attention modules to efficiently classify multiple rust grades based on the ISO 8501-1 taxonomy. Experimental results using objective evaluation criteria, such as accuracy, precision, recall, F1-score, IoU, and Receiver Operating Characteristic Curve (ROC) show the outperformance of the proposed SLPAC U-Net in simultaneous detecting/localizing and classifying rust regions compared to other state-of-the-art methods exploiting either color distribution properties or traditional deep learning models. Lastly, a comparison of the computational performance shows that the total required time of the proposed SPLAC U-Net model (segmentation + projection refinement) is less than solely segmenting an image by using traditional deep learning models. • Corrosion localization and rust grade classification based on the ISO 8501-1 taxonomy, using a 3-layered U-Net architecture. • Projection-based boundary refinement to promote robotic-driven maintenance and prefabrication. • Comparison with color distribution methods shows an error reduction of 37% (F1-score) and 32% (IoU) in localizing corrosion. • Comparison with other deep learning methods shows an error reduction of 14% (F1-score) and 13% (IoU) in localizing corrosion. • Comparison with a conventional U-Net shows an error reduction of 28% (F1-score) and 22% (IoU) in classifying rust grades. [ABSTRACT FROM AUTHOR]

The current technological evolutions enter 3D geo-informatics into their digital age, enabling new potential applications in the field of virtual tourism, pleasure, entertainment and cultural heritage. It is argued that 3D information provides the natural way of navigation. However, personalization is a key aspect in a navigation system, since a route that incorporates user preferences is ultimately more suitable than the route with the shortest distance or travel time. Usually, user's preferences are expressed as a set of weights that regulate the degree of importance of the scene metadata on the route selection process. These weights, however, are defined by the users, setting the complexity to the user's side, which makes personalization an arduous task. In this paper, we propose an alternative approach in which metadata weights are estimated implicitly and transparently to the users, transferring the complexity to the system side. This is achieved by introducing a relevance feedback on-line learning strategy which automatically adjusts metadata weights by exploiting information fed back to the system about the relevance of user's preferences judgments given in a form of pair-wise comparisons. Practically implementing a relevance feedback algorithm presents the limitation that several pair-wise comparisons (samples) are required to converge to a set of reliable metadata weights. For this reason, we propose in this paper a weight rectification strategy that improves weight estimation by exploiting metadata interrelations defined through an ontology. In the sequel, a genetic optimization algorithm is incorporated to select the most user preferred routes based on a multi-criteria minimization approach. To increase the degree of personalization in 3D navigation, we have also introduced an efficient algorithm for estimating 3D trajectories around objects of interest by merging best selected 2D projected views that contain faces which are mostly preferred by the users. We have conducted simulations and comparisons with other approaches either in the field of on-line learning or route selection using objective metrics in terms of precision and recall values. The results indicate that our system yields on average a 13.76 % improvement of precision as regards the learning strategy and an improvement of 8.75 % regarding route selection. In addition, we conclude that the ontology driven weight rectification strategy can reduce the number of samples (pair-wise comparisons) required of 76 % to achieve the same precision. Qualitative comparisons have been also performed using a use case route scenario in the city of Athens. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new algorithm for fair scheduling, and we compare it to other scheduling schemes such as the Earliest Deadline First (EDF) and the First Come First Served (FCFS) schemes. Our algorithm uses a max-min fair sharing approach for providing fair access to users. When there is no shortage of resources, the algorithm assigns to each task enough computational power for it to finish within its deadline. When there is congestion, the main idea is to fairly reduce the CPU rates assigned to the tasks so that the share of resources that each user gets is proportional to the user's weight. The weight of a user may be defined as the user's contribution to the infrastructure or the price he is willing to pay for services or any other socioeconomic consideration. In our algorithms, all tasks whose requirements are lower than their fair share CPU rate are served at their demanded CPU rates. However, the CPU rates of tasks whose requirements are larger than their fair share CPU rate are reduced to fit the total available computational capacity in a fair manner. Three different versions of fair scheduling are adopted in this paper: the Simple Fair Task Order (SFTO), which schedules the tasks according to their respective fair completion times, the Adjusted Fair Task Order (AFTO), which refines the SFTO policy by ordering the tasks using the adjusted fair completion time, and the Max-Min Fair Share (MMFS) scheduling policy, which simultaneously addresses the problem of finding a fair task order and assigning a processor to each task based on a max-min fair sharing policy. Experimental results and comparisons with traditional scheduling schemes such as the EDF and the FCFS are presented using three different error criteria. Validation of the simulations using real experiments of tasks generated from 3D image- rendering processes is also provided. The three proposed scheduling schemes can be integrated into existing Grid computing architectures. [ABSTRACT FROM AUTHOR]

Abstract: Multimedia content modeling, i.e., identification of semantically meaningful entities, is an arduous task mainly due to the fact that (a) humans perceive the content using high-level concepts and (b) the subjectivity of human perception, which often interprets the same content in a different way at different times. For this reason, an efficient content management system has to be adapted to current user''s information needs and preferences through an on-line learning strategy based on users’ interaction. One adaptive learning strategy is relevance feedback, originally developed in traditional text-based information retrieval systems. In this way, the user interacts with the system to provide information about the relevance of the content, which is then fed back to the system to update its performance. In this paper, we evaluate and investigate three main types of relevance feedback algorithms; the Euclidean, the query point movements and the correlation-based approaches. In the first case, we examine heuristic and optimal techniques which are based either on the weighted or the generalized Euclidean distance. In the second case, we survey single and multipoint query movement schemes. As far as the third type is concerned, two different ways for parametrizing the normalized cross-correlation similarity metric are proposed. The first scales only the elements of the query feature vector and called query-scaling strategy, while the second scales both the query and the selected samples (query-sample scaling strategy). All the examined algorithms are evaluated using both subjective and objective criteria. Subjective evaluation is performed by depicting the best retrieved images as response of the system to a user''s query. Instead, objective evaluation is obtained using standard criteria, such as the precision–recall curve and the average normalized modified retrieval rank (ANMRR). Furthermore, a newly objective criterion, called average normalized similarity metric distance is introduced which exploits the difference among the actual and ideal similarity measure among all best retrievals. Discussions and comparisons of all the aforementioned relevance feedback algorithms are presented. [Copyright &y& Elsevier]

Abstract: In this paper, a multiscale content-based video decomposition scheme is presented for efficient non-linear (non-sequential) organization of the video visual content. In particular, each video file is analyzed in a multiscale structure of different “content resolution levels”, creating a hierarchy from the lowest (coarse) to the highest (fine) resolution. The scheme resembles the progressive transmission of still images, where instead of transmitting the image sequentially at a full resolution, by scanning it line by line, a lower image resolution is first delivered and then, the image quality gradually enhances so that the user is able at any time to see a preview of the image content. The proposed video decomposition is represented as a graph structure, each level of which corresponds to a particular content resolution, while the graph-nodes the respective regions that the content is analyzed at this level. Transitions among nodes of the same level are also permitted. The number of nodes at a given level expresses the degree of detail that the content at this level is analyzed. This number is estimated by minimizing the average transmitted information, required for localizing a video segment of interest and also takes into account the content complexity. Quality criteria are introduced to evaluate the efficiency of the proposed scheme. The efficiency of the organization is maximized if multiscale content decomposition is performed using content representatives and constructing content classes. Content representatives are estimated in our approach as the ones of the maximum dissimilarity, expressed by a distance metric. The optimization is conducted by incorporating a stochastic algorithm of logarithmically reduced searching area (stochastic logarithmic). Experimental results on real-life video sequences show that the proposed multiscale video organization enables users to detect content of interest much faster, compared to the conventional sequential video scanning or other video decomposition/summarization methods, resulting in a better organization efficiency as measured by the quality criteria. [Copyright &y& Elsevier]

In this paper, an interactive framework for navigating video sequences is presented using an optimal content-based video decomposition scheme. In particular, each video sequence is analyzed at different content resolution levels, creating a hierarchy from the lowest (coarse) to the highest (fine) resolution. This content hierarchy is represented as a tree structure, each level of which corresponds to a particular content resolution, while the tree nodes indicate the temporal video segments that the sequence content is partitioned at a given resolution. A criterion is introduced to measure the efficiency of the proposed scheme in organizing the video visual content and to compare it with other hierarchical video content representations and navigation schemes. The efficiency is measured as the difficulty for a user to locate a video segment of interest, while moving through different levels of hierarchy. In our case, video is decomposed so that the best efficiency is accomplished. However, the efficiency of a nonlinear video decomposition scheme depends on: 1) the number of paths required for a user to locate a relevant video segment and 2) the number of shot/frame classes (i.e., content representatives) extracted to represent the visual content. Both issues are addressed in this paper. In the first case, the probability of selecting a relevant video segment in the first path is maximized by extracting optimal content representatives through a minimization of a cross-correlation criterion. For the minimization, a genetic algorithm (GA) is adopted, since application of an exhaustive search to obtain the minimum value is too large to be implemented. The cross-correlation criterion is evaluated on the feature domain by extracting appropriate global and object-based descriptors for each video frame so that a better representation of the visual content is achieved. The second aspect (e.g., the number of content representatives) is addressed by minimizing the average transmitted information and simultaneously taking into consideration the temporal video segment complexity. More content representatives are extracted for video segments of high complexity, whereas a low number is required for low-complexity segments. In addition, a degree of interest is assigned to each video shot (or frame) to address the fact that, from the user's perception, the visual content of a set of shots (frames) satisfies his/her information needs. Finally, a computationally efficient algorithm is proposed to regulate the degree of detail (i.e., the number of shot/frames representatives) in case the visual content is not efficiently represented from the user's perceptive view. Experimental results on real-life video sequences indicate the performance of the proposed GA-based video decomposition scheme compared to other hierarchical video organization methods. [ABSTRACT FROM AUTHOR]

In this paper, a novel relevance feedback algorithm is proposed for improving the performance of inter active content-based retrieval systems. The algorithm recursively estimates the similarity measure, which is used for data ranking in description environments where similarity-based queries are applied, using a set of relevant/irrelevant samples feedback by the user to the system so that the adjusted response is a better approximation of the current user's information needs and preferences. In particulars using concepts of functional analysis, the similarity measure is expressed as a parametric form of known monotone increasing functional components. Then, the contribution of each functional component to the similarity measure is estimated through a recursive and efficient on-line learning algorithm so that: 1) the current user's needs and preferences, as indicated by a set of selected relevant/Irrelevant samples, are satisfied as much as possible, while simultaneously 2) a minimal modification of the already estimated similarity measure is accomplished. Experimental Salts on a large real-life database using objective evaluation criteria, such as the precision-recall curve and the average normalized modified retrieval rank (ANMRR), indicate that the proposed scheme outperforms the compared ones. In addition, the proposed algorithm requires low computational complexity and it can be implemented in a recursive way. [ABSTRACT FROM AUTHOR]

Proposes an unsupervised video object segmentation and tracking algorithm based on an adaptable neural-network architecture. Neural-network retraining strategy; Unsupervised retraining set estimation in videoconference sequences; Specifications of the decision mechanism; Experimental results; Conclusion.

The performance of a Content-Based Image Retrieval System (CBIR) depends on (a) the system's adaptability to the user's information needs, which permits different types of indexing and simultaneously reduces the subjectivity of human perception for the interpretation of the image visual content and (b) the efficient organization of the extracted descriptors, which represent the rich visual information. Both issues are addressed in this paper. Descriptor organization is performed using a fuzzy classification scheme fragmented into multidimensional classes, instead of the previous works where fuzzy histograms were created in one dimension using, for example, the feature vector norm. Multidimensionality relates the descriptors with one another and thus allows a compact and meaningful visual representation by mapping the elements of the resulted feature vectors with a physical visual interpretation. Furthermore, fuzzy classification is applied for all visual content descriptors, in contrast to the previous approaches where only color information is exploited. Two kinds of content descriptors are extracted in our case; global-based and region-based. The first refers to the global image characteristics, while the second exploits the region-based properties. Regions are obtained by applying a multiresolution implementation of the Recursive Shortest Spanning Tree (RSST) algorithm, called M-RSST in this paper. The second issue is addressed by proposing a computationally efficient relevance feedback mechanism based on an optimal weight updating strategy. The scheme relies on the cross-correlation measure, instead of the Euclidean distance which is mainly used in most relevance feedback algorithms. Crosscorrelation is a normalized measure, which expresses how similar the two feature vectors are and thus it indicates a metric of their content similarity. The proposed scheme can be recursively implemented in the case of multiple feedback iterations, instead of the previous... [ABSTRACT FROM AUTHOR]

Presents information on a study which described a neural network architecture for recursive nonlinear traffic prediction and modeling of MPEG video sources. Investigation of the problem of online traffic modeling; Implementation of the neural network architecture; Results and discussion; Conclusions.

In this paper, a combined neural network and an evolutionary programming scheme is proposed to improve the quality of wound core distribution transformers in an industrial environment by exploiting information derived from both the construction and transformer design phase. In particular, the neural network architecture is responsible for predicting transformer iron losses prior to their assembly, based on several actual core measurements, transformer design parameters and the specific core assembling. A genetic algorithm is applied to estimate the optimal core arrangement, (i.e. the way of core assembling) that yields a set of three-phase transformers of minimal iron losses. The minimization is performed by exploiting information derived from the neural network model resulting in a synergetic neural network-genetic algorithm scheme. After the transformer construction, the prediction accuracy of the neural network model is evaluated. If accuracy is poor, a weight adaptation algorithm is applied to improve the prediction performance. For the weight updating, both the current and the previous network knowledge are taken into account. Application of the proposed neural network-genetic algorithm scheme to our industrial environment indicates a significant reduction in the variation between the actual and the designed transformer iron losses. This further leads to a reduction of the production cost since a smaller safety margin can be used for the transformer design. [ABSTRACT FROM AUTHOR]

Presents a method to reduce the iron losses of wound core distribution transformers based on a combined neural network-genetic algorithm approach. Iron loss reduction problem; Feasibility and practicality of the approach; Neural networks for predicting iron losses; Genetic algorithms for reducing iron losses.

Deals with a study which proposed an algorithm for non-sequential video content representation. Depiction of the feature-based video representation; Description of the fuzzy classification of feature vectors; Presentation of experimental results using real life video sequences; Concluding remarks.

This paper presents an efficient technique for unsupervised content-based segmentation in stereoscopic video sequences by appropriately combined different content descriptors in a hierarchical framework. Three main modules are involved in the proposed scheme; extraction of reliable depth information, image partition into color and depth regions and a constrained fusion algorithm of color segments using information derived from the depth map. In the first module, each stereo pair is analyzed and the disparity field and depth map are estimated. Occlusion detection and compensation are also applied for improving the depth map estimation. In the following phase, color and depth regions are created using a novel complexity-reducing multiresolution implementation of the Recursive Shortest Spanning Tree algorithm (M-RSST). While depth segments provide a coarse representation of the image content, color regions describe very accurately object boundaries. For this reason, in the final phase, a new segmentation fusion algorithm is employed which projects color segments onto depth segments. Experimental results are presented which exhibit the efficiency of the proposed scheme as content-based descriptor, even in case of images with complicated visual content. [ABSTRACT FROM AUTHOR]

Features an efficient technique for summarization of stereoscopic video sequences which extracts a small but meaningful set of video frames using a content-based sampling algorithm. Capability of browsing digital stereoscopic video sequences; Efficient content-based queries and indexing; Recursive Shortest Spanning Tree algorithm; Multidimensional fuzzy classification of segment.

Proposes the layer modeling of Motion Picture Experts Group (MPEG)-1 coded video streams and statistical analysis of their characteristics at each layer. Basic characteristics of MPEG-1 encoders; Encoding algorithm; Study of autocorrelation function; Traffic model of frame layer; Intermediate layer modeling; Buffer configuration scheme; Prediction of video activity.

Presents information on a study which described an approach for improving the performance of neural-network classifiers in image recognition, segmentation or coding applications based on a retraining algorithm. Formulation of the problem; Optimal selection of the network retraining data; Decision mechanism for network retraining; Conclusions.

Presents an adaptive algorithm for extracting foreground objects from background in videophone or videoconference applications. Neural network architecture; Incorporation of the algorithm in motion-compensated discrete cosine transform-based coding schemes; Simulation results.

Modeling ionospheric variability throughout a proper total electron content (TEC) parameter estimation is a demanding, however, crucial, process for achieving better accuracy and rapid convergence in precise point positioning (PPP). In particular, the single-frequency PPP (SF-PPP) method lacks accuracy due to the difficulty of dealing adequately with the ionospheric error sources. In order to apply ionosphere corrections in techniques, such as SF-PPP, external information of global ionosphere maps (GIMs) is crucial. In this article, we propose a deep learning model to efficiently predict TEC values and to replace the GIM-derived data that inherently have a global character, with equal or better in accuracy regional ones. The proposed model is suitable for predicting the ionosphere delay at different locations of receiver stations. The model is tested during different periods of time, under different solar and geomagnetic conditions and for stations in various latitudes, providing robust estimations of the ionospheric activity at the regional level. Our proposed model is a hybrid model comprising of a 1-D convolutional layer used for the optimal feature extraction and stacked recurrent layers used for temporal time series modeling. Thus, the model achieves good performance in TEC modeling compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we present WaterSpy, a project developing an innovative, compact, cost-effective photonic device for pervasive water quality sensing, operating in the mid-IR spectral range. The approach combines the use of advanced Quantum Cascade Lasers (QCLs) employing the Vernier effect, used as light source, with novel, fibre-coupled, fast and sensitive Higher Operation Temperature (HOT) photodetectors, used as sensors. These will be complemented by optimised laser driving and detector electronics, laser modulation and signal conditioning technologies. The paper presents the WaterSpy concept, the requirements elicited, the preliminary architecture design of the device, the use cases in which it will be validated, while highlighting the innovative technologies that contribute to the advancement of the current state of the art. [ABSTRACT FROM AUTHOR]

Deep learning techniques are used for capturing intricate structures of large-scale data by employing computational models of multiple processing layers that can learn and represent data with multiple levels of abstraction. Such methods can include Convolutional Neural Networks, stacked auto-encoders and Long-Short Term Memory (LSTM) architectures. LSTM networks are suitable for dealing with time-dependent data through mapping input to output sequences as, for instance, in language modeling and speech recognition. One application that has recently attracted considerable attention within the geodetic community is the possibility of applying these techniques to account for the adverse effects of the ionospheric delays on the GNSS satellite signals. Ionospheric delay depend on three main factors: (i) the total electron content (TEC), (ii) the frequency of the GNSS signals, and (iii) the angle at which the signal enters the ionospheric layer. The combination of multi-frequency GNSS measurements allows us to remove most of the ionospheric effects. However, ionospheric prediction models have to be applied for single-frequency ionospheric estimation in order to remove this effect. This can be done using Global Ionospheric Maps (GIMs) available from the International GNSS Service (IGS) and evaluating the TEC effect via a mapping function involving the azimuth and elevation angles of the GNSS signals. This paper deals with a modeling approach suitable for predicting the ionospheric delay at different locations of the IGS network stations using the LSTM networks. We also incorporate a Bayesian optimization method for selecting the best configuration parameters of the LSTM network, thus improving network's performance. LSTM architecture models long-range dependencies in time series, making it appropriate for ionospheric modeling in GNSS positioning. As experimental data we used actual GNSS observations from the global IGS network stations participating in the MGEX project that provides various satellite signals from the currently available multiple navigation satellite systems. Slant TEC data (STEC) were obtained using the available GPS/GLONASS/Galileo signals after processing with various techniques, such as Precise Point Positioning (PPP). The combination of multi-GNSS signals in PPP, allows us to investigate additional biases such as Differential Code Biases (DCBs) that are closely related to the ionospheric delays. Consequently, a basic LSTM network structure is created, having as minimum inputs the following: time epoch, GNSS signal azimuth and elevation angle, ionospheric delays for the previous and present observation epochs. The sequential GNSS observations are fed one by one in a chain-like structure, in a way that a single state is stored in a unique node with a single activation function in the network at one timestep and then is propagated to the next timestep. In this way, the LSTM algorithm is able to predict future ionospheric delay values. Topics to be discussed in the paper include the design of the LSTM network structure, the Bayesian optimization strategy, the training methods exploiting steepest descent algorithms, data analysis, as well as preliminary testing results of the ionospheric delay predictions as compared, for instance, with the IGS ionosphere products and the widely used Klobuchar model. [ABSTRACT FROM AUTHOR]

Recently, several educational game platforms have been proposed in the literature for choreographic training. However, their main limitation is that they fail to provide a quantitative assessment framework of a performing choreography against a groundtruth one. In this paper, we address this issue by proposing a machine learning framework exploiting deep learning paradigms. In particular, we introduce a long short-term memory network with the main capability of analyzing 3D captured skeleton feature joints of a dancer into predefined choreographic postures. This pose identification procedure is capable of providing a detailed (fine) evaluation score of a performing dance. In addition, the paper proposes a choreographic summarization architecture based on sparse modeling representative selection (SMRS) in order to abstractly represent the performing choreography through a set of key choreographic primitives. We have modified the SMRS algorithm in a way to extract hierarchies of key representatives. Choreographic summarization provides an efficient tool for a coarse quantitative evaluation of a dance. Moreover, hierarchical representation scheme allows for a scalable assessment of a choreography. The serious game platform supports advanced visualization toolkits using Labanotation in order to deliver the performing sequence in a formal documentation. [ABSTRACT FROM AUTHOR]

Serious games are receiving increasing attention in the field of cultural heritage (CH) applications. A special field of CH and education is intangible cultural heritage and particularly dance. Machine learning (ML) tools are necessary elements for the success of a serious game platform since they introduce intelligence in processing and analysis of users' interactivity. ML provides intelligent scoring and monitoring capabilities of the user's progress in a serious game platform. In this article, we introduce a deep learning model for motion primitive classification. The model combines a convolutional processing layer with a bidirectional analysis module. This way, RGB information is efficiently handled by the hierarchies of convolutions, while the bidirectional properties of a long short term memory (LSTM) model are retained. The resulting convolutionally enhanced bidirectional LSTM (CEBi-LSTM) architecture is less sensitive to skeleton errors, occurring using low-cost sensors, such as Kinect, while simultaneously handling the high amount of detail when using RGB visual information. [ABSTRACT FROM AUTHOR]

In this paper, we present tensor-based linear and nonlinear models for hyperspectral data classification and analysis. By exploiting the principles of tensor algebra, we introduce new classification architectures, the weight parameters of which satisfy the rank-1 canonical decomposition property. Then, we propose learning algorithms to train both linear and nonlinear classifiers. The advantages of the proposed classification approach are that: 1) it significantly reduces the number of weight parameters required to train the model (and thus the respective number of training samples); 2) it provides a physical interpretation of model coefficients on the classification output; and 3) it retains the spatial and spectral coherency of the input samples. The linear tensor-based model exploits the principles of logistic regression, assuming the rank-1 canonical decomposition property among its weights. For the nonlinear classifier, we propose a modification of a feedforward neural network (FNN), called rank-1 FNN, since its weights satisfy again the rank-1 canonical decomposition property. An appropriate learning algorithm is also proposed to train the network. Experimental results and comparisons with state-of-the-art classification methods, either linear (e.g., linear support vector machine) or nonlinear (e.g., deep learning), indicate the outperformance of the proposed scheme, especially in the cases where a small number of training samples is available. [ABSTRACT FROM AUTHOR]

In this study, we propose a tensor-based learning model to efficiently detect abnormalities on digital mammograms. Due to the fact that the availability of medical data is limited and often restricted by GDPR (general data protection regulation) compliance, the need for more sophisticated and less data-hungry approaches is urgent. Accordingly, our proposed artificial intelligence framework utilizes the canonical polyadic decomposition to decrease the trainable parameters of the wrapped Rank-R FNN model, leading to efficient learning using small amounts of data. Our model was evaluated on the open source digital mammographic database INBreast and compared with state-of-the-art models in this domain. The experimental results show that the proposed solution performs well in comparison with the other deep learning models, such as AlexNet and SqueezeNet, achieving 90% ± 4% accuracy and an F1 score of 84% ± 5%. Additionally, our framework tends to attain more robust performance with small numbers of data and is computationally lighter for inference purposes, due to the small number of trainable parameters. [ABSTRACT FROM AUTHOR]

Non-intrusive load monitoring (NILM) is the task of disaggregating the total power consumption into its individual sub-components. Over the years, signal processing and machine learning algorithms have been combined to achieve this. Many publications and extensive research works are performed on energy disaggregation or NILM for the state-of-the-art methods to reach the desired performance. The initial interest of the scientific community to formulate and describe mathematically the NILM problem using machine learning tools has now shifted into a more practical NILM. Currently, we are in the mature NILM period where there is an attempt for NILM to be applied in real-life application scenarios. Thus, the complexity of the algorithms, transferability, reliability, practicality, and, in general, trustworthiness are the main issues of interest. This review narrows the gap between the early immature NILM era and the mature one. In particular, the paper provides a comprehensive literature review of the NILM methods for residential appliances only. The paper analyzes, summarizes, and presents the outcomes of a large number of recently published scholarly articles. Furthermore, the paper discusses the highlights of these methods and introduces the research dilemmas that should be taken into consideration by researchers to apply NILM methods. Finally, we show the need for transferring the traditional disaggregation models into a practical and trustworthy framework. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has affected many aspects of human life around the world, due to its tremendous outcomes on public health and socio-economic activities. Policy makers have tried to develop efficient responses based on technologies and advanced pandemic control methodologies, to limit the wide spreading of the virus in urban areas. However, techniques such as social isolation and lockdown are short-term solutions that minimize the spread of the pandemic in cities and do not invert long-term issues that derive from climate change, air pollution and urban planning challenges that enhance the spreading ability. Thus, it seems crucial to understand what kind of factors assist or prevent the wide spreading of the virus. Although AI frameworks have a very efficient predictive ability as data-driven procedures, they often struggle to identify strong correlations among multidimensional data and provide robust explanations. In this paper, we propose the fusion of a heterogeneous, spatio-temporal dataset that combine data from eight European cities spanning from 1 January 2020 to 31 December 2021 and describe atmospheric, socio-economic, health, mobility and environmental factors all related to potential links with COVID-19. Remote sensing data are the key solution to monitor the availability on public green spaces between cities in the study period. So, we evaluate the benefits of NIR and RED bands of satellite images to calculate the NDVI and locate the percentage in vegetation cover on each city for each week of our 2-year study. This novel dataset is evaluated by a tree-based machine learning algorithm that utilizes ensemble learning and is trained to make robust predictions on daily cases and deaths. Comparisons with other machine learning techniques justify its robustness on the regression metrics RMSE and MAE. Furthermore, the explainable frameworks SHAP and LIME are utilized to locate potential positive or negative influence of the factors on global and local level, with respect to our model's predictive ability. A variation of SHAP, namely treeSHAP, is utilized for our tree-based algorithm to make fast and accurate explanations. [ABSTRACT FROM AUTHOR]

COVID-19 evolution imposes significant challenges for the European healthcare system. The heterogeneous spread of the pandemic within EU regions elicited a wide range of policies, such as school closure, transport restrictions, etc. However, the implementation of these interventions is not accompanied by the implementation of quantitative methods, which would indicate their effectiveness. As a result, the efficacy of such policies on reducing the spread of the virus varies significantly. This paper investigates the effectiveness of using deep learning paradigms to accurately model the spread of COVID-19. The deep learning approaches proposed in this paper are able to effectively map the temporal evolution of a COVID-19 outbreak, while simultaneously taking into account policy interventions directly into the modelling process. Thus, our approach facilitates data-driven decision making by utilizing previous knowledge to train models that predict not only the spread of COVID-19, but also the effect of specific policy measures on minimizing this spread. Global models at the EU level are proposed, which can be successfully applied at the national level. These models use various inputs in order to successfully model the spatio-temporal variability of the phenomenon and obtain generalization abilities. The proposed models are compared against the traditional epidemiological and Autoregressive Integrated Moving Average (ARIMA) models. [ABSTRACT FROM AUTHOR]

Non-Intrusive Load Monitoring (NILM) describes the process of inferring the consumption pattern of appliances by only having access to the aggregated household signal. Sequence-to-sequence deep learning models have been firmly established as state-of-the-art approaches for NILM, in an attempt to identify the pattern of the appliance power consumption signal into the aggregated power signal. Exceeding the limitations of recurrent models that have been widely used in sequential modeling, this paper proposes a transformer-based architecture for NILM. Our approach, called ELECTRIcity, utilizes transformer layers to accurately estimate the power signal of domestic appliances by relying entirely on attention mechanisms to extract global dependencies between the aggregate and the domestic appliance signals. Another additive value of the proposed model is that ELECTRIcity works with minimal dataset pre-processing and without requiring data balancing. Furthermore, ELECTRIcity introduces an efficient training routine compared to other traditional transformer-based architectures. According to this routine, ELECTRIcity splits model training into unsupervised pre-training and downstream task fine-tuning, which yields performance increases in both predictive accuracy and training time decrease. Experimental results indicate ELECTRIcity's superiority compared to several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we provide the results of ongoing work in Magnet Beyond project, regarding social networking services. We introduce an integrated social networking framework through the definition or the appropriate notions and metrics. This allows one to run an evaluation study of three widely used clustering methods (-means, hierarchical and spectral clustering) in the scope of social groups assessment and in regard to the cardinality of the profile used to assess users’ preferences. Such an evaluation study is performed in the context of our service requirements (i.e. on the basis of equal-sized group formation and of maximization of interests’ commonalities between users within each social group). The experimental results indicate that spectral clustering, due to the optimization it offers in terms of normalized cut minimization, is applicable within the context of Magnet Beyond socialization services. Regarding profile’s cardinality impact on the system performance, this is shown to be highly dependent on the underlying distribution that characterizes the frequency of user preferences appearance. Our work also incorporates the introduction of a heuristic algorithm that assigns new users that join the service into appropriate social groups, once the service has been initialized and the groups have been assessed using spectral clustering. The results clearly show that our approach is able to adhere to the service requirements as new users join the system, without the need of an iterative spectral clustering application that is computationally demanding. [Copyright &y& Elsevier]

In this paper, we propose a Stack Auto-encoder (SAE)-Driven and Semi-Supervised (SSL)-Based Deep Neural Network (DNN) to extract buildings from relatively low-cost satellite near infrared images. The novelty of our scheme is that we employ only an extremely small portion of labeled data for training the deep model which constitutes less than 0.08% of the total data. This way, we significantly reduce the manual effort needed to complete an annotation process, and thus the time required for creating a reliable labeled dataset. On the contrary, we apply novel semi-supervised techniques to estimate soft labels (targets) of the vast amount of existing unlabeled data and then we utilize these soft estimates to improve model training. Overall, four SSL schemes are employed, the Anchor Graph, the Safe Semi-Supervised Regression (SAFER), the Squared-loss Mutual Information Regularization (SMIR), and an equal importance Weighted Average of them (WeiAve). To retain only the most meaning information of the input data, labeled and unlabeled ones, we also employ a Stack Autoencoder (SAE) trained under an unsupervised manner. This way, we handle noise in the input signals, attributed to dimensionality redundancy, without sacrificing meaningful information. Experimental results on the benchmarked dataset of Vaihingen city in Germany indicate that our approach outperforms all state-of-the-art methods in the field using the same type of color orthoimages, though the fact that a limited dataset is utilized (10 times less data or better, compared to other approaches), while our performance is close to the one achieved by high expensive and much more precise input information like the one derived from Light Detection and Ranging (LiDAR) sensors. In addition, the proposed approach can be easily expanded to handle any number of classes, including buildings, vegetation, and ground. [ABSTRACT FROM AUTHOR]

The necessity of predicting the spatio-temporal phenomenon of ionospheric variability is closely related to the requirement of many users to be able to obtain high accuracy positioning with low cost equipment. The Precise Point Positioning (PPP) technique is highly accepted by the scientific community as a means for providing high level of position accuracy from a single receiver. However, its main drawback is the long convergence time to achieve centimeter-level accuracy in positioning. Hereby, we propose a deep learning-based approach for ionospheric modeling. This method exploits the advantages of Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNN) for timeseries modeling and predicts the total electron content per satellite from a specific station by making use of a causal, supervised deep learning method. The scope of the proposed method is to compare and evaluate the between-satellites ionospheric delay estimation, and to aggregate the Total Electron Content (TEC) outcomes per-satellite into a single solution over the station, thus constructing regional TEC models, in an attempt to replace Global Ionospheric Maps (GIM) data. The evaluation of our proposed recurrent method for the prediction of vertical total electron content (VTEC) values is compared against the traditional Autoregressive (AR) and the Autoregressive Moving Average (ARMA) methods, per satellite. The proposed model achieves error lower than 1.5 TECU which is slightly better than the accuracy of the current GIM products which is currently about 2.0–3.0 TECU. [ABSTRACT FROM AUTHOR]

Accurate prediction of the seawater intrusion extent is necessary for many applications, such as groundwater management or protection of coastal aquifers from water quality deterioration. However, most applications require a large number of simulations usually at the expense of prediction accuracy. In this study, the Gaussian process regression method is investigated as a potential surrogate model for the computationally expensive variable density model. Gaussian process regression is a nonparametric kernel-based probabilistic model able to handle complex relations between input and output. In this study, the extent of seawater intrusion is represented by the location of the 0.5 kg/m3 iso-chlore at the bottom of the aquifer (seawater intrusion toe). The initial position of the toe, expressed as the distance of the specific line from a number of observation points across the coastline, along with the pumping rates are the surrogate model inputs, whereas the final position of the toe constitutes the output variable set. The training sample of the surrogate model consists of 4000 variable density simulations, which differ not only in the pumping rate pattern but also in the initial concentration distribution. The Latin hypercube sampling method is used to obtain the pumping rate patterns. For comparison purposes, a number of widely used regression methods are employed, specifically regression trees and Support Vector Machine regression (linear and nonlinear). A Bayesian optimization method is applied to all the regressors, to maximize their efficiency in the prediction of seawater intrusion. The final results indicate that the Gaussian process regression method, albeit more time consuming, proved to be more efficient in terms of the mean absolute error (MAE), the root mean square error (RMSE), and the coefficient of determination (R²). [ABSTRACT FROM AUTHOR]

Detection of moving objects in videos is a crucial step toward successful surveillance and monitoring applications. A key component for such tasks is called background subtraction and tries to extract regions of interest from the image background for further processing or action. For this reason, its accuracy and real-time performance are of great significance. Although effective background subtraction methods have been proposed, only a few of them take into consideration the special characteristics of thermal imagery. In this paper, we propose a background subtraction scheme, which models the thermal responses of each pixel as a mixture of Gaussians with unknown number of components. Following a Bayesian approach, our method automatically estimates the mixture structure, while simultaneously it avoids over-/underfitting. The pixel density estimate is followed by an efficient and highly accurate updating mechanism, which permits our system to be automatically adapted to dynamically changing operation conditions. We propose a reference implementation of our method in reconfigurable hardware achieving both adequate performance and low-power consumption. Adopting a high-level synthesis design and demanding floating point arithmetic operations are mapped in reconfigurable hardware, demonstrating fast prototyping and on-field customization at the same time. [ABSTRACT FROM AUTHOR]

Detection of outliers in radar signals is a considerable challenge in maritime surveillance applications. High-Frequency Surface-Wave (HFSW) radars have attracted significant interest as potential tools for long-range target identification and outlier detection at over-the-horizon (OTH) distances. However, a number of disadvantages, such as their low spatial resolution and presence of clutter, have a negative impact on their accuracy. In this paper, we explore the applicability of deep learning techniques for detecting deviations from the norm in behavioral patterns of vessels (outliers) as they are tracked from an OTH radar. The proposed methodology exploits the nonlinear mapping capabilities of deep stacked autoencoders in combination with density-based clustering. A comparative experimental evaluation of the approach shows promising results in terms of the proposed methodology’s performance. [ABSTRACT FROM AUTHOR]

Resource allocation and scheduling are fundamental issues in a Workflow Management System (WfMS). Effective resource management in WfMS should examine resource allocation together with task scheduling since these problems impose mutual constraints. Optimization of the one factor is subject to the other constraints and vice versa. Thus, an ideal algorithm should take into account not only performance metrics of the infrastructure, such as the number of resources and their utilization, but also quality criteria such as the percentage of tasks undergone violation in their temporal restrictions. In this paper, we propose an innovative algorithm which jointly optimizes the two aforementioned contradictory criteria. The algorithm, called Resource Conflicts Joint Optimization (Re.Co.Jo.Op.), minimizes resource conflicts subject to temporal constraints and simultaneously optimizes throughput or utilization subject to resources constraints. To achieve the optimization, the two factors are formulated in a matrix form and the optimal solution is found by applying concepts of the generalized eigenvalue analysis. A rough outline of an agent-based architecture is proposed to achieve runtime integration of our algorithm into a functional WfMS, while experimental results under different load environments and tasks assumption reveal the superiority of the proposed strategy than the other conventional approaches. [ABSTRACT FROM AUTHOR]

The primary aim of GridLab is to provide users and application developers with a simple and robust environment enabling them to produce applications that can exploit the full power and possibilities of the Grid. The GridLab project brings together computer scientists with computational scientists from various application areas to design and implement a Grid Application Toolkit (GAT), together with a set of Grid services, in a production grid environment. The GAT will provide functionality through a carefully constructed set of generic high-level APIs, through which an application will be able to call the underlying Grid services. The project will demonstrate the benefits of the GAT by developing and implementing real application scenarios, illustrating compelling new uses of the Grid. The development of the OAT is accompanied by the establishment of a pan-European testbed and by the development of Grid services of varying complexity, tailored to the needs of user community. These services are designed to complement and complete the existing Grid infrastructure, and to provide functionality needed by the GridLab applications in order to be usefully deployed in such environment.

Recent studies indicate that detecting radiographic patterns on CT chest scans can yield high sensitivity and specificity for COVID-19 identification. In this paper, we scrutinize the effectiveness of deep learning models for semantic segmentation of pneumonia-infected area segmentation in CT images for the detection of COVID-19. Traditional methods for CT scan segmentation exploit a supervised learning paradigm, so they (a) require large volumes of data for their training, and (b) assume fixed (static) network weights once the training procedure has been completed. Recently, to overcome these difficulties, few-shot learning (FSL) has been introduced as a general concept of network model training using a very small amount of samples. In this paper, we explore the efficacy of few-shot learning in U-Net architectures, allowing for a dynamic fine-tuning of the network weights as new few samples are being fed into the U-Net. Experimental results indicate improvement in the segmentation accuracy of identifying COVID-19 infected regions. In particular, using 4-fold cross-validation results of the different classifiers, we observed an improvement of 5.388 ± 3.046% for all test data regarding the IoU metric and a similar increment of 5.394 ± 3.015% for the F1 score. Moreover, the statistical significance of the improvement obtained using our proposed few-shot U-Net architecture compared with the traditional U-Net model was confirmed by applying the Kruskal-Wallis test (p-value = 0.026). [ABSTRACT FROM AUTHOR]

This paper proposes a 3D object recognition method for non-coloured point clouds using point features. The method is intended for application scenarios such as Inspection, Maintenance and Repair (IMR) of industrial sub-sea structures composed of pipes and connecting objects (such as valves, elbows and R-Tee connectors). The recognition algorithm uses a database of partial views of the objects, stored as point clouds, which is available a priori. The recognition pipeline has 5 stages: (1) Plane segmentation, (2) Pipe detection, (3) Semantic Object-segmentation and detection, (4) Feature based Object Recognition and (5) Bayesian estimation. To apply the Bayesian estimation, an object tracking method based on a new Interdistance Joint Compatibility Branch and Bound (IJCBB) algorithm is proposed. The paper studies the recognition performance depending on: (1) the point feature descriptor used, (2) the use (or not) of Bayesian estimation and (3) the inclusion of semantic information about the objects connections. The methods are tested using an experimental dataset containing laser scans and Autonomous Underwater Vehicle (AUV) navigation data. The best results are obtained using the Clustered Viewpoint Feature Histogram (CVFH) descriptor, achieving recognition rates of 51.2 % , 68.6 % and 90 % , respectively, clearly showing the advantages of using the Bayesian estimation ( 18 % increase) and the inclusion of semantic information ( 21 % further increase). [ABSTRACT FROM AUTHOR]

The usage of VR gear in mixed reality applications demands a high position and orientation accuracy of all devices to achieve a satisfying user experience. This paper investigates the system behaviour of the VR system HTC Vive Pro at a testing facility that is designed for the calibration of highly accurate positioning instruments like geodetic total stations, tilt sensors, geodetic gyroscopes or industrial laser scanners. Although the experiments show a high reproducibility of the position readings within a few millimetres, the VR system has systematic effects with magnitudes of several centimetres. A tilt of about 0.4° of the reference plane with respect to the horizontal plane was detected. Moreover, our results demonstrate that the tracking algorithm faces problems when several lighthouses are used. [ABSTRACT FROM AUTHOR]