Mohammed Ghaouth BELKASMI

Dr. Mohammed Ghaouth BELKASMI

Laboratory LSE2I, National School of Applied Sciences, Mohammed First University, Oujda 60000, Morocco
orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 July 2020
Verified
Book Chapter
Closed access
PDF file
ZKZakaria Kaddari
Zakaria Kaddari
YMYoussef Mellah
Youssef Mellah
Jamal BerrichJamal Berrich
Jamal Berrich
MBMohammed Ghaouth BELKASMI
Mohammed Ghaouth BELKASMI
TBToumi Bouchentouf
Toumi Bouchentouf

1 August 2013
Verified
Conference Paper
Closed access
AZAdil Zeaaraoui
Adil Zeaaraoui
ZBZineb Bougroun
Zineb Bougroun
MBMohammed Ghaouth BELKASMI
Mohammed Ghaouth BELKASMI
TBToumi Bouchentouf
Toumi Bouchentouf
User stories present the mean of communication between customer and development team in agile methods; this paper provides a new user stories voice aimed to ease and automate analysis of objects and their action from the user story using OOADARE (Object-oriented Analysis and Design Approach for the Requirements Engineering) approach [1]. OOADARE approach was also missing a communication mean with the customer; user stories with the new template will do the job.

21 October 2020
Verified
Conference Paper
Closed access
ZKZakaria Kaddari
Zakaria Kaddari
YMYoussef Mellah
Youssef Mellah
JBJamal Berrich
Jamal Berrich
TBToumi Bouchentouf
Toumi Bouchentouf
MBMohammed Ghaouth BELKASMI
Mohammed Ghaouth BELKASMI
Thousands of biomedical research papers are published each day. Now, it takes more time than ever for researchers and healthcare information professionals to find relevant information from this huge literature. Classical information retrieval (IR) systems such as PubMed, while helpful, still provide a large number of search results that needs to be examined manually. Biomedical Question answering (QA) systems on the other hand can extract and provide one direct and exact answer to a question. While huge progress has been made recently in general-domain QA. Biomedical QA still has a long way to go. The number one reason for the slow progress of biomedical QA compared to general-domain QA, is the limited number of biomedical QA datasets and the even smaller number of annotated training instances. The goal of this survey is to list and compare the available biomedical QA datasets, and to provide an overview of traditional and end-to-end neural-based biomedical QA systems.

1 May 2021 in Journal of Computer Science
Verified
Journal Article
Open access
PDF file
YMYoussef Mellah
Youssef Mellah
ARAbdelkader Rhouati
Abdelkader Rhouati
EEEl Hassane Ettifouri
El Hassane Ettifouri
TBToumi Bouchentouf
Toumi Bouchentouf
MBMohammed Ghaouth BELKASMI
Mohammed Ghaouth BELKASMI
Using Natural Language (NL) to interacting with relational databases allows users from any background to easily query and analyze large amounts of data. This requires a system that understands user questions and automatically converts them into structured query language such as SQL. The best performing Text-to-SQL systems use supervised learning (usually formulated as a classification problem) by approaching this task as a sketch-based slot-filling problem, or by first converting questions into an Intermediate Logical Form (ILF) then convert it to the corresponding SQL query. However, non-supervised modeling that directly converts questions to SQL queries has proven more difficult. In this sense, we propose an approach to directly translate NL questions into SQL statements. In this study, we present a Sequence-to-Sequence (Seq2Seq) parsing model for the NL to SQL task, powered by the Transformers Architecture exploring the two Language Models (LM): Text-To-Text Transfer Transformer (T5) and the Multilingual pre-trained Text-To-Text Transformer (mT5). Besides, we adopt the transformation-based learning algorithm to update the aggregation predictions based on association rules. The resulting model achieves a new state-of-the-art on the WikiSQL DataSet, for the weakly supervised SQL generation.

1 October 2016
Verified
Conference Paper
Closed access
IFIlhame El Farissi
Ilhame El Farissi
MSMohammed Saber
Mohammed Saber
SCSara Chadli
Sara Chadli
MEMohamed Emharraf
Mohamed Emharraf
MBMohammed Ghaouth BELKASMI
Mohammed Ghaouth BELKASMI
The Artificial Neural Network (ANN) enables systems to think and act intelligently. In recent years, neural networks are applied in security for such tasks as attack classification, prevention, attack detection... Therefore, there are several researches in this area, particularly in Intrusion Detection System (IDS) which are based on neural network. Most of these IDSs are developed by using Neural Network for Pattern Recognition and are alimented by KDD data. However, some KDD-features have eighter no role, or a minimum impact in attack detection. Consequently, the large number of parameters that must be selected to produce a neural network detecting attacks must be optimized in order to decrease error and increase the IDSs performance. First of all, we have taken some and all of the basic attributes to aliment the network's input and to verify the dependence between these parameters and attacks. Then, we have added the parameters relating to content and time-based ones in order to demonstrate their utility and performance and also to present in which case they are crucial. It must be noted that we have employed MATLAB tool to put into practice these case studies. The analysis is realized in terms of two metrics which are the True Positive Rate (TPR) and the False Positive Rate (FPR).

23 September 2016
Verified
Book Chapter
Closed access
PDF file
MSMohammed Saber
Mohammed Saber
IFIlhame El Farissi
Ilhame El Farissi
SCSara Chadli
Sara Chadli
MEMohamed Emharraf
Mohamed Emharraf
MBMohammed Ghaouth BELKASMI
Mohammed Ghaouth BELKASMI