Augmenting machine learning for Amharic speech recognition: a paradigm of patient’s lips motion detection

Multimedia Tools and Applications - The method of automatic lip motion recognition is an essential input for visual speech detection. It is a technological approach to demystify people who are hard...     

Sponge-based materials for oil spill cleanups: A review

Elimination of leaked oil from aquatic environs has recently gained importance owing to the disasters associated with leakages into marine environments. The need for an environmentally friendly and viable line of action concerning the environs has brought forward numerous affordable, non-toxic, and decomposable materials; further, diverse biomasses for fabricating nano- to micro-scale materials, membranes, and sponges/aerogels have also been incorporated for the elimination and retrieval of oils from water. Moreover, selectivity, sorption capacity, and reusability of these materials after the retrieval of oils are also desired from the viewpoint of sustainability. This review encompasses the recent progress in the field of elimination and retrieval of oil spills using various sponge-based materials.     

Monotony analysis and sparse-grid integration for nonlinear chance constrained process optimization

The numerical solution of a nonlinear chance constrained optimization problem poses a major challenge. The idea of back-mapping as introduced by M. Wendt, P. Li and G. Wozny in 2002 is a viable approach for transforming chance constraints on output variables (of unknown distribution) into chance constraints on uncertain input variables (of known distribution) based on a monotony relation. Once transformation of chance constraints has been accomplished, the resulting optimization problem can be solved by using a gradient-based algorithm. However, the computation of values and gradients of chance constraints and the objective function involves the evaluation of multi-dimensional integrals, which is computationally very expensive. This study proposes an easy-to-use method for analysing monotonic relations between constrained outputs and uncertain inputs. In addition, sparse-grid integration techniques are used to reduce the computational time decisively. Two examples from process optimization under uncertainty demonstrate the performance of the proposed approach.     

Autotransformer fed traction power supply system: analysis,modeling and simulation

For many decades, Ethiopia had been using a meter gauge railway from Addis Ababa to the red sea port of Djibouti. Currently, the century old railway is completely replaced by a brand new standard gauge electrified railway line aiming to connect the country to the global market by guaranteeing a unified access to different regions of the country. In order to meet modern railway standards, a 1 x 25 kV catenary system is adopted in Ethio-Djibouti railway line corridor. In this paper, an alternative and a more superior 2 x 25 kV traction power supply system is presented. The modeling and analysis of the 2 x 25 kV traction supply system including the traction load, the substation power transformer, the autotransformer(AT), the catenary line impedance, etc., are performed. In addition, in order to validate the benefits of the proposed system, a comparative analysis of the two types of traction power supply arrangement has been conducted using MATLAB simulation. The analysis focuses on evaluating the voltage profiles of both power supply configurations on the basis of BS EN 50163:2004 international standard.     

Effect of ginning on tenacity,elongation and other fibre quality properties

Abstract

Based on single and bundle fibre properties measurements before and after ginning treatment of three commercial varieties, statistical parameters with ANOVA showed that, Acala SJ-2 genotype with greater mean fibre tenacity and elongation as well as less coefficient of variation of tenacity and elongation values before ginning treatment, maintains its higher rank position after the ginning treatment against its competitors Arba and DP-90. In this study, the variety Acala SJ-2 with greater single and bundle tenacity and elongation properties before ginning treatment was also favoured by having less amount of fibre breakage as well as relatively fewer levels of neps when compared against its competitor commercial varieties Arba and DP-90. This study shows that fibre data from single and bundle testing, before and after the application of ginning treatment, could be invaluable for the cotton breeders for cultivar selection and for the spinners to control cotton processability and improve quality of products.