In this article, the Moroccan climate is currently undergoing several changes that have negatively affected agricultural activities, especially in the field of irrigation. That's why we relied on internet of things (IoT) technology to overcome these problems. In this article, we present the design and realization of an intelligent irrigation system via a solar submersible pump. We used the ESP32 microcontroller which reads the temperature and humidity values measured by the soil moisture sensor. The communication between the blocks is ensured by the radiofrequency module. We have implemented a Web server to monitor the measured quantities. The graphical representation of the data will be ensured using the ThingSpeak platform which makes it possible to store and collect the data coming from the sensors via the hypertext transfer protocol (HTTP). Our achievement was executed and tested without any problems detected, which shows that our smart irrigation study was very successful.

The rapid growth of the automotive industry has raised significant concerns about the security of connected vehicles and their integrated supply chains, which are increasingly vulnerable to advanced cyber threats. Traditional authentication methods have proven insufficient, exposing systems to risks such as Sybil, Denial of Service (DoS), and Eclipse attacks. This study critically examines the limitations of current security protocols, focusing on authentication and data exchange vulnerabilities, and explores blockchain technology as a potential solution. Blockchain’s decentralized and cryptographically secure framework can significantly enhance Vehicle-to-Vehicle (V2V) communication, ensure data integrity, and enable transparent, immutable transactions within the supply chain. Additionally, blockchain strengthens authentication, secures digital identities, and improves data sharing, reducing the risk of unauthorized access and data breaches. Our contribution lies in the proposal to integrate Artificial Intelligence (AI) with blockchain technology to further improve security by refining cryptographic methods, automating key management, and bolstering anomaly detection. Despite challenges related to computational complexity, latency, scalability, and regulatory concerns, the combination of blockchain, AI offers the transformative potential to enhance the security, transparency, and efficiency of connected vehicle systems and their supply chains.

Automatic facial expression recognition (FER) plays a valuable role in various fields, including health, road safety, and marketing, where providing feedback on the user’s condition is crucial. While significant progress has been made in controlled environments (such as frontal, unconcluded, and well-lit conditions), recognizing facial expressions in unconstrained environments (natural settings) remains challenging. The presence of occlusions poses a particular difficulty as they obscure parts of the facial information captured in the image. To address this issue, researchers have proposed different solutions, broadly categorized into two approaches: those focusing on visible regions of the face and those attempting to reconstruct hidden parts. Currently, most solutions rely on texture or geometry-based methods, with only a few utilizing motion-based approaches. However, incorporating motion appears to be particularly promising in adapting to occlusions due to its unique characteristics, such as close-range propagation and local coherence. In this paper, our focus lies on leveraging motion to overcome the challenges posed by occlusions in FER tasks.

This paper describes our new deep learning system based on a comparison between GRU and CNN. Initially we start with the first system which uses Convolutional Neural Network (CNN) which we will compare with the second system which uses Gated Recurrent Unit (GRU). And through this comparison we propose a new system based on the positive points of the two previous systems. Therefore, this new system will take the right choice of hyperparameters recommended by the authors of both systems. At the final stage we propose a method to apply this new system to the dataset of different languages (used especially in socials networks) around a single subject, in our case the sport domain and more specifically the world cup.