Efficient document image binarization using heterogeneous computing and parameter tuning

In the context of historical document analysis, image binarization is a first important step, which separates foreground from background, despite common image degradations, such as faded ink, stains, or bleed-through. Fast binarization has great significance when analyzing vast archives of document images, since even small inefficiencies can quickly accumulate to years of wasted execution time. Therefore, efficient binarization is especially relevant to companies and government institutions, who want to analyze their large collections of document images. The main challenge with this is to speed up the execution performance without affecting the binarization performance. We modify a state-of-the-art binarization algorithm and achieve on average a 3.5 times faster execution performance by correctly mapping this algorithm to a heterogeneous platform, consisting of a CPU and a GPU. Our proposed parameter tuning algorithm additionally improves the execution time for parameter tuning by a factor of 1.7, compared to previous parameter tuning algorithms. We see that for the chosen algorithm, machine learning-based parameter tuning improves the execution performance more than heterogeneous computing, when comparing absolute execution times.

     

Expanding the Toolbox of R-Selective Amine Transaminases by Identification and Characterization of New Members

Amine transaminases (ATAs) are used to synthesize enantiomerically pure amines, which are building blocks for pharmaceuticals and agrochemicals. R-selective ATAs belong to the fold type IV PLP-dependent enzymes, and different sequence-, structure- and substrate scope-based features have been identified in the past decade. However, our knowledge is still restricted due to the limited number of characterized (R)-ATAs, with additional bias towards fungal origin. We aimed to expand the toolbox of (R)-ATAs and contribute to the understanding of this enzyme subfamily. We identified and characterized four new (R)-ATAs. The ATA from Exophiala sideris contains a motif characteristic for d -ATAs, which was previously believed to be a disqualifying factor for (R)-ATA activity. The crystal structure of the ATA from Shinella is the first from a Gram-negative bacterium. The ATAs from Pseudonocardia acaciae and Tetrasphaera japonica are the first characterized (R)-ATAs with a shortened/missing N-terminal helix. The active-site charges vary significantly between the new and known ATAs, correlating with their diverging substrate scope.     

Further results on the disturbance response of a double integrator controlled by a saturating linear static state feedback

In this paper, we study the response to external disturbances of a double integrator with a saturating feedback. For a class of disturbances that have bounded integrals over all intervals, we show that a linear static feedback law can always be designed to ensure boundedness of the states. Moreover, boundedness can be preserved if the disturbance is biased by a small DC signal. In the special case that the disturbance is made up of a finite number of sinusoids and a small bias, any linear static feedback ensures boundedness of the states. These results are an extension of previous results by Wen, Roy, and Saberi (2008).     

Yield estimation and forecasting for winter wheat in Hungary using time series of MODIS data

Wheat is one of the most important crops in Hungary, which represents approximately 20% of the entire agricultural area of the country, and about 40% of cereals. A robust yield method has been improved for estimating and forecasting wheat yield in Hungary in the period of 2003–2015 using normalized difference vegetation index (NDVI) derived from the data of the Moderate Resolution Imaging Spectroradiometer. Estimation was made at the end of June – it is generally the beginning of harvest of winter wheat in Hungary – while the forecasts were performed 1–7 weeks earlier. General yield unified robust reference index (GYURRI) vegetation index was calculated each year using different curve-fitting methods to the NDVI time series. The correlation between GYURRI and country level yield data gave correlation coefficient (r) of 0.985 for the examined 13 years in the case of estimation. Simulating a quasi-operative yield estimation process, 10 years’ (2006–2015) yield data was estimated. The differences between the estimated and actual yield data provided by the Hungarian Central Statistical Office were less than 5%, the average difference was 2.5%. In the case of forecasting, these average differences calculated approximately 2 and 4 weeks before the beginning of harvest season were 4.5% and 6.8%, respectively. We also tested the yield estimation procedure for smaller areas, for the 19 counties (Nomenclature of Territorial Units for Statistics-3 level) of Hungary. We found that, the relationship between GYURRI and the county level yield data had r of 0.894 for the years 2003–2014, and by simulating the quasi-operative forecast for 2015, the resulting 19 county average yield values differed from the actual yield as much as 8.7% in average.