No abstract

For the retrieval of information from documents of different natural languages, pre-processing of the document is the main task. During pre-processing, words which occur too frequently and have little semantic in the document should be identified. Such words are called Stopwords. Stopwords list for different world languages like English, Chinese, Hindi, Arabic Sanskrit etc. are identified. But as I long as I know there is no standard method to identify these words for the Amharic language. In this paper, we proposed the automatic identification of Stopwords for the Amharic text by an aggregate based methodology of words frequency, inverse document frequency, and entropy value measure. Available works on Stopwords identification techniques are based on static or dictionary based Stopwords lists. This method inefficient and very expensive and it is a time-consuming task as the searching process takes a long time. The proposed work will overcome these problems using aggregated methods of both frequency measures and entropy measures of words in the Amharic text for the automatic Stopwords identification.

No abstract

The use of smart meter in electric power consumption plays great roll benefiting customer to control and manage their electric power usage. It creates smooth communication to build fair electric power distribution for customers and better management of whole electric system for suppliers. Machine learning predictive frameworks have been worked in order to utilize the electric energy assets effectively, productively and acknowledgment of advanced energy generation, circulation and utilization. This paper presents outline of research works identified with machine learning based forecasting of customers electric power utilization from smart meter data. The paper concentrates on exhaustive study of strategies and relative examination of classifier models utilized as a part of determining customer electric power consumption. Moreover, limitations, difficulties, points of interest and disadvantage of the past works identified with machine learning based methods determining of customers electric power consumption are over viewed.

No abstract