Automatic Speech Recognition can be considered as a transcription of spoken utterances into text which can be used to monitor/command a specific system. In this paper, we propose a general end-to-end approach to sequence learning that uses Long Short-Term Memory (LSTM) to deal with the non-uniform sequence length of the speech utterances. The neural architecture can recognize the Arabic spoken digit spelling of an isolated Arabic word using a classification methodology, with the aim to enable natural human-machine interaction. The proposed system consists to, first, extract the relevant features from the input speech signal using Mel Frequency Cepstral Coefficients (MFCC) and then these features are processed by a deep neural network able to deal with the non uniformity of the sequences length. A recurrent LSTM or GRU architecture is used to encode sequences of MFCC features as a fixed size vector that will feed a multilayer perceptron network to perform the classification. The whole neural network classifier is trained in an end-to-end manner. The proposed system outperforms by a large gap the previous published results on the same database.

The purpose of this work is a bibliometric analysis of the evolution of knowledge management (KM) and intellectual capital (IC) as scientific fields in time. The used data was all articles having “intellectual capital” or “knowledge management” in their title from SCOPUS database exported in Excel and R language is used to compute the indexes. The analysis is using the indexes (H index, N index, G index, I index, lotka’s law), which are most related to references and citations of the articles. We find that KM and IC fields are heterogeneous in cases and homogeneous in other cases vis à vis the applied indexes. This analysis is usefull to researchers in the two areas to find the pionners and the most productive authors to potentially collaborate with them and, the most read articles to use them in literature review. In databases of researches, only H index is offered but to all articles of area defined by the database and not for a set of requested articles. This paper is filling this gap, as the first study of KM and IC using relative bibliometric indexes

The analysis is comparing the scientific journals of the field of IC and knowledge management. The results are presented under tables and graphs and, are commented to make a comparison between these journals. The overall objective of the final work would be the implementation of scientometric indexes using the programming language R and the interpretation of the obtained results. The originality of the paper is the proposal of relative indexes to a query, i.e., relatively to a set of papers and not applied to the overall research database.

Because we usually deal with real - world systems with real - world constraints (cost, computer resources, size, weight, power, heat dissipation, etc.), it is understood that the simplest method to accomplish a task is the one that should be used. Experts usually rely on common sense when they solve problems. They also use vague and ambiguous terms. Other experts have no difficulties with understanding and interpreting this statement because they have the background to hearing problems described like this. However, a knowledge engineer would have difficulties providing a computer with the same level of understanding. In a complex industrial process, how can we represent expert knowledge that uses vague and fuzzy terms in a computer to control it? In this work, the application is developed to control the pretreatment and pasteurization station of milk localized in Batna (Algeria) by adopting a control approach based on expert knowledge and fuzzy logic.

As we move into the 21st century, with very rapid mobile communication and access to vast stores of information, we seem to be surrounded by more and more information, with less and less time or ability to digest it. The creation of the automatic summarization was really a genius human solution to solve this complicated problem. However, the application of this solution was too complex. In reality, there are many problems that need to be addressed before the promises of automatic text summarization can be fully realized. Basically, it is necessary to understand how humans summarize the text and then build the system based on that. Yet, individuals are so different in their thinking and interpretation that it is hard to create "gold-standard" summary against which output summaries will be evaluated. In this paper, we will discuss the basic concepts of this topic by giving the most relevant definitions, characterizations, types and the two different approaches of automatic text summarization: extraction and abstraction. Special attention is devoted to the extractive approach. It consists of selecting important sentences and paragraphs from the original text and concatenating them into shorter form. Broadly, the importance of sentences is decided based on statistical features of sentences. This approach avoids any efforts on deep text understanding. It is conceptually simple and easy to implement. KeywordsText summarization; Automatic text summarization; Abstractive approach; Extractive approach; Natural language processing.