Data fusion and machine learning for industrial prognosis: Trends and perspectives towards Industry 4.0

https://users.iit.demokritos.gr/~bgat/cr1115.pdf

Text line and word segmentation of handwritten documents

Sufficient conditions are given for existence and uniqueness in Smoluchowski's coagulation equation, for a wide class of coagulation kernels and initial mass distributions. An example of nonuniqueness is constructed. The stochastic coalescent is shown to converge weakly to the solution of Smoluchowski's equation.

/pdf/smoluchowski-s-coagulation-equation-uniqueness-nonuniqueness-45o9owk4tp.pdf

Smoluchowski's coagulation equation: uniqueness, nonuniqueness and a hydrodynamic limit for the stochastic coalescent

Text extraction in video documents, as an important research field of content-based information indexing and retrieval, has been developing rapidly since 1990s. This has led to much progress in text extraction, performance evaluation, and related applications. By reviewing the approaches proposed during the past five years, this paper introduces the progress made in this area and discusses promising directions for future research.

Extraction of Text Objects in Video Documents: Recent Progress

Handwritten document image segmentation into text lines and words

Enabling the human in the loop: Linked data and knowledge in industrial cyber-physical systems

Energy production from Municipal Solid Waste (MSW) has become one of the most prominent strategies in MSW management. In this study a multi-objective mathematical programming model is developed in order to provide the candidate (Pareto optimal) solutions for a MSW management system performing structural, design and operational optimization. Besides the economic criterion the Green House Gas (GHG) emissions are taken into account as a second optimization criterion. Therefore, we do not obtain just an optimal solution (i.e. least cost), but a set of Pareto optimal solutions that spread from minimum cost to minimum GHG emissions. Each Pareto optimal solution provides the corresponding technologies and the capacities that are associated with it. An innovative issue is that we incorporate the external costs/benefits associated with (a) atmospheric pollution impacts (b) impacts on soil and groundwater (c) impacts on quality of life (d) electricity use/displacement (e) fertilizer use reduction from compost. Using the external costs/benefits as an additional term in the cost objective significantly affects the results especially regarding the Waste-to-Energy options. This is clearly illustrated in the case study for the MSW management of the Athens region in Greece.

Municipal solid waste management and energy production: Consideration of external cost through multi-objective optimization and its effect on waste-to-energy solutions

In this paper, we present tempo estimation and beat tracking algorithms by utilizing percussive/harmonic separation of the audio signal, in order to extract filterbank energies and chroma features from the respective components. Periodicity analysis is carried out by the convolution of feature sequences with a bank of resonators. Target tempo is estimated from the resulting periodicity vector by incorporating metrical relations knowledge. Tempo estimation is followed by a local tempo refinement method to enhance the beat-tracking algorithm. Beat tracking involves the computation of the beat saliencies derived from the resonators responses and proposes a distance measure between candidate beats locations. A dynamic programming algorithm is adopted to find the optimal “path” of beats. Both tempo estimation and beat tracking methods were submitted on MIREX 2011, while the tempo estimation algorithm was also evaluated on ISMIR 2004 Tempo Induction Evaluation Exchange Dataset.

Vassilis Katsouros

Papers

Handwritten document image segmentation into text lines and words

Enabling the human in the loop: Linked data and knowledge in industrial cyber-physical systems

Municipal solid waste management and energy production: Consideration of external cost through multi-objective optimization and its effect on waste-to-energy solutions

Music tempo estimation and beat tracking by applying source separation and metrical relations

Recognition of online handwritten mathematical formulas using probabilistic SVMs and stochastic context free grammars