Pr. Hakim EL MASSARI

.01

ABOUT

PERSONAL DETAILS

Rabat, MA

h.elmassari@uca.ac.ma

00 123 456 789

Hello. I am a Professor Researcher Professor Researcher
I am passionate about technology
Welcome to my Personal and Academic profile Available as freelance

BIO

ABOUT ME

is a Professor-Researcher of Computer Science at Higher School of Technology, Cadi Ayyad University, Marrakech, Morocco. He received his Ph.D. in Computer Science from the - Faculty of Sciences and Techniques, Sultan Moulay Slimane University, Beni Mellal, Morocco -, in 2023. He has several contributions in information systems namely: machine learning, big data, semantic web, and internet of behaviors. He has served on executive and technical program committees and as a reviewer of numerous international conferences and journals. His research areas include artificial intelligence, machine learning, deep learning, intelligent systems, big data, semantic web, and ontology.

FACTS

NUMBERS ABOUT ME

1

PhD

22

PUBLICATIONS

2

LABS

+100k

FOLLOWERS

HOBBIES

INTERESTS

Duis eu finibus urna. Pellentesque facilisis tellus vel leo accumsan, a tristique est luctus. Morbi quis euismod nulla. Sed eu nibh eros.

.02

RESUME

ACADEMIC AND PROFESSIONAL POSITIONS
2023
till now

Marrakech
PROFESSOR OF COMPUTER SCIENCE

CADI AYYAD UNIVERSITY
Teaching several courses related to data engineering such as data analysis & visualisation, AI, Maching learning...
2023
till now

Marrakech
LABORATORY MEMBER

FACULTY OF SCIENCES AND TECHNIQUES, CADI AYYAD UNIVERSITY
Laboratory of Applied Mathematics and Computer Science (LaMAI Laboratory).
2023
till now

Khouribga
LABORATORY MEMBER

NATIONAL SCHOOL OF APPLIED SCIENCES, SULTAN MOULAY SLIMANE UNIVERSITY
Science and Technology for the Engineer Laboratory (LaSTI Laboratory).
2017
2023

Khouribga
SYSTEMS AND NETWORKS ADMINISTRATOR

NATIONAL SCHOOL OF APPLIED SCIENCES, SULTAN MOULAY SLIMANE UNIVERSITY
EDUCATION
2019
2023

Beni Mellal
COMPUTER SCIENCE - PHD

FACULTY OF SCIENCES AND TECHNIQUES, SULTAN MOULAY SLIMANE UNIVERSITY
2012
2014

Tetouan
COMPUTER SCIENCE - MASTER

HIGHER NORMAL SCHOOL, ABDELMALEK ESSAADI UNIVERSITY
2011
2012

Casablanca
COMPUTER SCIENCE - BACHELOR

FACULTY OF SCIENCES AIN CHOCK, HASSAN II UNIVERSITY
2009
2011

Fes
COMPUTER SCIENCE - UNIVERSITY DIPLOMA OF TECHNOLOGY

HIGHER SCHOOL OF TECHNOLOGY, SIDI MOHAMED BEN ABDELLAH UNIVERSITY
2008
2009

Er-Rich
LIFE AND EARTH SCIENCE - BACCALAUREATE

MY ALI CHERIF HIGH SCHOOL
HONORS AND AWARDS
2000
2000

Morocco
AWARD AWARD

COMPETITIVE AWARD FOR ACADEMIC EXCELLENCE
Lorem ipsum dolor sit amet, consectetur adipiscingVivam sit amet ligula non lectus cursus egestas. Cras erat lorem.
2000
2000

Morocco
AWARD AWARD

COMPETITIVE AWARD FOR ACADEMIC EXCELLENCE
Lorem ipsum dolor sit amet, consectetur adipiscingVivam sit amet ligula non lectus cursus egestas. Cras erat lorem.

.03

PUBLICATIONS

you can find all my publications here.

PUBLICATIONS LIST

ALL

ALL
JOURNAL PAPERS
CONFERENCES
DEMONSTRATIONS
THESES
BOOK CHAPTERS
BOOK

SORTING BY DATE

1 AUG 2024

Diabetes Prediction Using Machine Learning with Feature Engineering and Hyperparameter Tuning

International Journal of Advanced Computer Science and Applications

Diabetes, a chronic illness, has seen an increase in prevalence over the years, posing several health challenges. This study aims to predict diabetes onset using the Pima Indians Diabetes dataset. We implemented

Journal Paper H. El Massari, N. Gherabi, F. Qanouni, S. Mhammedi.

Diabetes Prediction Using Machine Learning with Feature Engineering and Hyperparameter Tuning

H. El Massari, N. Gherabi, F. Qanouni, S. Mhammedi. Journal Paper

Diabetes, a chronic illness, has seen an increase in prevalence over the years, posing several health challenges. This study aims to predict diabetes onset using the Pima Indians Diabetes dataset. We implemented several machine learning algorithms, namely Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost. To enhance model performance, we applied a variety of feature engineering techniques, including SelectKBest, Recursive Feature Elimination (RFE), Recursive Feature Elimination with Cross-Validation (RFECV), Forward Feature Selection, and Backward Feature Elimination. RFECV proved to be the most effective method, leading to the selection of the best feature set. In addition, hyperparameter tuning techniques are used to determine the optimal parameters for the models created. Upon training these models with the optimized parameters, XGBoost outperformed the others with an accuracy of 94%, while Random Forest and CatBoost both achieved 92.5%. These results highlight XGBoost’s superior predictive power and the significance of thorough feature engineering and model tuning in diabetes prediction.

20 MAR 2024

Enhancing Book Recommendations on GoodReads: A Data Mining Approach Based Random Forest Classification

Lecture Notes in Networks and Systems

With the rise of technology, new ways of finding books have emerged beyond traditional bookstores. Websites like www.goodreads.com allow readers to share their book reviews and ratings. This study uses the data from GoodReads

Conferences S. Mhammedi, H. El Massari, N. Gherabi, M. Amnai.

Enhancing Book Recommendations on GoodReads: A Data Mining Approach Based Random Forest Classification

S. Mhammedi, H. El Massari, N. Gherabi, M. Amnai. Conferences

With the rise of technology, new ways of finding books have emerged beyond traditional bookstores. Websites like www.goodreads.com allow readers to share their book reviews and ratings. This study uses the data from GoodReads to find the best way to suggest books to readers. Employing data mining classification, four methods - Random Forest, Naive Bayes, K-Nearest Neighbor, and Support Vector Classifier - were examined. Performance evaluation was conducted using accuracy, F-measure, recall, and precision metrics derived from the confusion matrix. Interestingly, the Random Forest algorithm stood out with remarkable results. It achieved 99.91% accuracy, 100% precision, 92% recall, a 95% F1-score, and a slight 0.09 average error. These impressive outcomes highlight the algorithm’s effectiveness in predicting user preferences and offering personalized book recommendations. Additionally, the study compared the Random Forest approach with the baseline methods, showing its clear superiority. This research showcases the promising potential of Random Forest in improving the GoodReads book recommendation system. Using the random forest classifier proved effective in predicting user preferences and generating relevant book recommendations, offering a promising approach to enhance personalized reading experiences, fitting well with changing reading habits in the digital era.

1 DEC 2023

A highly scalable CF recommendation system using ontology and SVD-based incremental approach

Bulletin of Electrical Engineering and Informatics

In recent years, the need of recommender systems has increased to enhance user engagement, provide personalized services, and increase revenue, especially in the online shopping industry

Journal Paper S. Mhammedi, N. Gherabi, H. El Massari, Z. Sabouri, M. Amnai.

A highly scalable CF recommendation system using ontology and SVD-based incremental approach

S. Mhammedi, N. Gherabi, H. El Massari, Z. Sabouri, M. Amnai. Journal Paper

In recent years, the need of recommender systems has increased to enhance user engagement, provide personalized services, and increase revenue, especially in the online shopping industry where vast amounts of customer data are generated. Collaborative filtering (CF) is the most widely used and effective approach for generating appropriate recommendations. However, the current CF approach has limitations in addressing common recommendation problems such as data inaccuracy recommendations, sparsity, scalability, and significant errors in prediction. To overcome these challenges, this study proposes a novel hybrid CF method for movie recommendations that combines the incremental singular value decomposition approach with an item-based ontological semantic filtering approach in two phases, online and offline. The ontology-based technique is leveraged to enhance the accuracy of predictions and recommendations. Evaluating our method on a real-world movie recommendation dataset using precision, F1 scores, and mean absolute error (MAE) demonstrates that our system generates accurate predictions while addressing sparsity and scalability issues in recommendation system. Additionally, our method has the advantage of reduced running time.

29 JAN 2022

Virtual OBDA Mechanism Ontop for Answering SPARQL Queries Over Couchbase

Lecture Notes on Data Engineering and Communications Technologies

In the last decade, the database field has become substantially diversified, as a consequence, a number of non-relational databases (known also as NoSQL) have been developed, e.g., key-value stores and

Book Chapters H. El Massari, S. Mhammedi, N. Gherabi, M. Nasri.

Virtual OBDA Mechanism Ontop for Answering SPARQL Queries Over Couchbase

H. El Massari, S. Mhammedi, N. Gherabi, M. Nasri. Book Chapters

In the last decade, the database field has become substantially diversified, as a consequence, a number of non-relational databases (known also as NoSQL) have been developed, e.g., key-value stores and JSON-document databases, XML, and graph databases. Several issues associated with big data were addressed as a result of the rise of this new generation of data services. However, in the rush to address the problems of big data and vast numbers of active users, NoSQL dropped certain of the core features of databases that make them highly performant and usable such as the global view, that permits users to access data without needing to know how they are logically organized or physically stored in their sources. We address, in this article, the challenge of how to fill the gap between NoSQL and the Semantic web, in order to enable access to such databases and integration of non-relational data sources. However, we extend the well-known framework for ontology-based data access (OBDA), intending to allow a mediating ontology to query arbitrary databases. We instantiate this framework to a popular JSON-document database called Couchbase, and implement a prototype extension of the virtual OBDA mechanism Ontop to answer SPARQL queries over Couchbase.

.04

RESEARCH

Coming soon inchallah...

LABORATORY TEAM

JOHN DOE

RESEARCH ASSISTANT

Lorem ipsum dolor sit amet, consectetur adipiscingVivam sit amet ligula non lectus cursus egestas. Cras erat lorem, fringilla quis sagittis in, sagittis inNam leo tortor Nam leo tortor Vivam.

JENNIFER DOE

ASSOCIATE PROFESSOR

Lorem ipsum dolor sit amet, consectetur adipiscingVivam sit amet ligula non lectus cursus egestas. Cras erat lorem, fringilla quis sagittis in, sagittis inNam leo tortor Nam leo tortor Vivam.

JOHNATAN DOE

SENIOR RESEARCH TECHNICIAN

Lorem ipsum dolor sit amet, consectetur adipiscingVivam sit amet ligula non lectus cursus egestas. Cras erat lorem, fringilla quis sagittis in, sagittis inNam leo tortor Nam leo tortor Vivam.

CATHERINE DOE

RESEARCH FELLOW

Lorem ipsum dolor sit amet, consectetur adipiscingVivam sit amet ligula non lectus cursus egestas. Cras erat lorem, fringilla quis sagittis in, sagittis inNam leo tortor Nam leo tortor Vivam.

RESEARCH PROJECTS

PROJECT TITLE

DESCRIPTION OF THE PROJECT

Lorem ipsum dolor sit amet, consectetur adipiscingVivam sit amet ligula non lectus cursus egestas. Cras erat lorem, fringilla quis sagittis in, sagittis inNam leo tortor Nam leo.Lorem ipsum dolor sit amet, consectetur adipiscingVivam sit amet ligula non lectus cursus egestas. Cras erat lorem, fringilla quis sagittis in, sagittis inNam leo tortor Nam leo.Lorem ipsum dolor sit amet, consectetur adipiscingVivam sit amet ligula non lectus cursus egestas. Cras erat lorem, fringilla quis sagittis in, sagittis inNam leo tortor Nam leo.