kamal baraka

Prof. kamal baraka


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
25 February 2025 in Frontiers in Sustainable Food Systems
Verified
Journal Article
Open access
PDF file
KBkamal baraka
kamal baraka
JEJamal Ezzahar
Jamal Ezzahar
MMMohammed Madiafi
Mohammed Madiafi
HEHassan Erraji
Hassan Erraji
GVGaetano Alessandro Vivaldi
Gaetano Alessandro Vivaldi
ATAnas Tallou
Anas Tallou
Sustainable and digital agriculture, grounded in robust scientific research, is crucial to addressing the challenges related to the water-food-energy Nexus (WFE). Ensuring global food security, particularly for small-scale farms, presents a major challenge for the scientific community in the coming decades. Despite occupying only 12% of agricultural land, small-scale farms are responsible for around 35% of the world’s food production. In this context, digital and smart farming solutions, including low-cost, energy-efficient technologies, offer a promising way forward. Low-power wide-area networks (LPWAN), such as LoRa, Sigfox, and NB-IoT, are particularly well-suited for Internet of Things (IoT)-enabled agriculture due to their affordable deployment, energy efficiency, and optimal transmission range for agricultural applications. In contrast, existing systems—often based on expensive technologies such as artificial intelligence (AI) or satellite imagery—are not suitable for smallholder farmers for several reasons (high costs, technical complexity, and insufficient resolution for small-scale plots). Therefore, this paper introduces a new IoT-based agricultural platform utilizing LoRaWAN technology, designed to provide an affordable and effective solution within the Moroccan agriculture context, suffering from severe water scarcity in the last decades. The platform, called AgriLink, uses sensors to collect data and transmit it to a gateway via LoRaWAN. The data is then processed and transferred to a server using Python, SQLite, and InfluxDB. Once the server confirms the receipt of the data, it is promptly deleted from the gateway. This approach allows farmers to monitor and manage their irrigation and fertilization systems in real-time, enhancing both efficiency and ease of use, while overcoming the limitations of existing systems. The objective of using this platform is primarily to save more water and fertilizers in fruit tree crop orchards, which consequently serve to promote sustainable agriculture.

28 June 2021 in Analog Integrated Circuits and Signal Processing
Verified
Journal Article
Closed access
PDF file
SLSara Laafar
Sara Laafar
AMAsmaa Maali
Asmaa Maali
KBkamal baraka
kamal baraka
NBNajib Boumaaz
Najib Boumaaz
ASAbdallah Soulmani
Abdallah Soulmani

7 May 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Mohammed MadiafiMohammed Madiafi
Mohammed Madiafi
JEJamal Ezzahar
Jamal Ezzahar
KBkamal baraka
kamal baraka
ABAbdelaziz Bouroumi
Abdelaziz Bouroumi
In this paper, we propose a new neural architecture for object classification, made up from a set of competitive layers whose number and size are dynamically learned from training data using a two-step process that combines unsupervised and supervised learning modes. The first step consists in finding a set of one or more optimal prototypes for each of the c classes that form the training data. For this, it uses the unsupervised learning and prototype generator algorithm called fuzzy learning vector quantization (FLVQ). The second step aims to assess the quality of the learned prototypes in terms of classification results. For this, the c classes are reconstructed by assigning each object to the class represented by its nearest prototype, and the obtained results are compared to the original classes. If one or more constructed classes differ from the original ones, the corresponding prototypes are not validated and the whole process is repeated for all misclassified objects, using additional competitive layers, until no difference persists between the constructed and the original classes or a maximum number of layers is reached. Experimental results show the effectiveness of the proposed method on a variety of well-known benchmark data sets.