Today, world is looking for alternate energy sources as the gross effect of GHG is disturbing the nature balance. Ethiopia is a
country with an aggressive plan to solely depend on clean Energy. This paper is about feasibility study of a 100MW PV power plant at
Bati, Ethiopia. For the study RETScreen software is used, Using the RETScreen the benchmark analysis, emission analysis and financial
analysis were made. From the bench mark analysis the energy cost of production is reduced to 1.6 ETB/KWh. The emission analysis
shows that 2365.3 tCO2 will be reduced from the potential emission to the environment and finally from financial analysis the NPV and
the cumulative cash flow shows positive results. Hence, this means the project is feasible financially, technically and environmentally
and it will help the country to achieve its goal in building clean energy
Traditionally, data mining algorithms and machine learning algorithms are engineered to approach the problems in isolation. These algorithms are employed to train the model in separation on a specific feature space and same distribution. Depending on the business case, a model is trained by applying a machine learning algorithm for a specific task. A widespread assumption in the field of machine learning is that training data and test data must have identical feature spaces with the underlying distribution. On the contrary, in real world this assumption may not hold and thus models need to be rebuilt from the scratch if features and distribution changes. It is an arduous process to collect related training data and rebuild the models. In such cases, Transferring of Knowledge or transfer learning from disparate domains would be desirable. Transfer learning is a method of reusing a pre-trained model knowledge for another task. Transfer learning can be used for classification, regression and clustering problems. This paper uses one of the pre-trained models – VGG - 16 with Deep Convolutional Neural Network to classify images.
The study was conducted in order to find the protein requirement of bighead catfish (Clarias macrocephalus) fingerling. The initial weight of fish was 6.29 g/ind and raised them in 8 weeks. The experiment was set up with six dietary treatments including six protein levels such as 25%, 30%, 35%, 40%, 45% and 50% with an isoenergy of approximately 4.5 Kcal/g and an isolipidic diets of 8%. Results show that the protein level effected on the survival rate. The 25% protein diet had the lowest survival rate of 67.78% while those in the remaining treatments varied from 91.1% to 100%. The specific growth rates (SGR) of fish were maximal at 3.26% per day in the 45% protein diet and minimal at 1.92% per day in the 25% protein diet. The protein efficiency ratios (PER) decreased as the protein levels in diets increased. The protein content affected significantly by the dietary protein levels. Using the Broken-line method and based on the SGR, the dietary protein requirement for bighead catfish was 46.1%.