The semi-global matching stereo algorithm is a top performing algorithm in stereo vision. The recursive nature of the computations involved in this algorithm introduces an inherent data dependency problem, hindering the progressive computations of disparities at pixel clock. In this work, a novel hardware implementation of the semi-global matching algorithm is presented. A hardware structure of parallel comparators is proposed for the fast computation of the minima among large cost arrays in one clock cycle. Also, a hardware-friendly algorithm is proposed for the computation of the minima among far-indexed disparity costs, shortening the length of computations in the datapath. As a result, the recursive path cost computation is accelerated considerably. The system is implemented in a Stratix V device and in a Zynq UltraScale+ device. A throughput of 55,1 million disparities per second is achieved with maximum disparity 128 pixels and frame resolution 1280 × 720. The proposed architecture is less elaborate and more resource efficient than other systems in the literature and its performance compares favorably to them. An implementation on an actual FPGA board is also presented and serves as a real-world verification of the proposed system.

Modern industries are constantly aiming to maximize utilization and performance of their machine equipment and minimize costly and unscheduled downtime. In the recent years, this was made possible with the advancement of technology and the coming of the fourth industrial revolution, also known as Industry 4.0, which introduced the Internet of Things and Artificial Intelligence systems in industrial applications. This allowed the employment of predictive maintenance methods able to assess the health of the equipment and diagnose possible future failures. In this work, an experimental assembly was constructed comprised by an electrical motor, a reduction gear, an axle, a coupler, a bearing and a vibration sensor attached to the latter. Three types of experiments were conducted for the purpose of producing a labeled dataset based on vibration measurements. Specifically, measurements were made during the bearing's working in normal operating state, one with lack and one with excess amount of grease. A preliminary statistical analysis was performed while a Multilayer Perceptron model was employed to automatically predict the status of the bearing. The dataset is freely available at the Zenodo data repository.

In this paper we propose a generic approach to reduce a 2-L square polynomial matrix of arbitrary degree(s), to first-order matrix pencils of the form sE1+zE2+A, utilizing the framework of zero coprime equivalence (ZC-E). This generic approach is in turn employed to derive a series of ZC-E matrix pencils, which can be obtained “by inspection” of the coefficients of the original bivariate polynomial matrix. Improving similar constructions of first order pencils in the literature, our approach results in matrix pencils whose size increases linearly with the degrees of the indeterminates of the original polynomial matrix.

This paper proposes a machine learning approach to part-of-speech tagging and named entity recognition for Greek, focusing on the extraction of morphological features and classification of tokens into a small set of classes for named entities. The architecture model that was used is introduced. The greek version of the spaCy platform was added into the source code, a feature that did not exist before our contribution, and was used for building the models. Additionally, a part of speech tagger was trained that can detect the morphology of the tokens and performs higher than the state-of-the-art results when classifying only the part of speech. For named entity recognition using spaCy, a model that extends the standard ENAMEX type (organization, location, person) was built. Certain experiments that were conducted indicate the need for flexibility in out-of-vocabulary words and there is an effort for resolving this issue. Finally, the evaluation results are discussed.