A5001992393- Smart Agriculture and AI
- Advanced Wireless Communication Techniques
- Error Correcting Code Techniques
- Non-Invasive Vital Sign Monitoring
- Image Processing and 3D Reconstruction
- Wireless Power Transfer Systems
- Soil Moisture and Remote Sensing
- Radiation Effects in Electronics
- 3D Shape Modeling and Analysis
- VLSI and Analog Circuit Testing
- Coding theory and cryptography
- Irrigation Practices and Water Management
- Energy Harvesting in Wireless Networks
- Speech and Audio Processing
- ECG Monitoring and Analysis
- Voice and Speech Disorders
- Technology and Human Factors in Education and Health
- Grit, Self-Efficacy, and Motivation
- Space Satellite Systems and Control
- Composite Structure Analysis and Optimization
- Hand Gesture Recognition Systems
- Innovative Energy Harvesting Technologies
- 3D Surveying and Cultural Heritage
- Advanced Image Processing Techniques
- Wireless Body Area Networks
Mohammed V University
2015-2024
École Normale Supérieure - PSL
2008
Non-invasive crop analysis through image-based methods holds great promise for applications in plant research, yet accurate and robust trait inference from images remains a critical challenge. Our study investigates the potential of AI model ensembling hybridization approaches to infer sorghum traits RGB generated via unmanned aerial vehicle (UAV). In our study, we cultivated 21 cultivars two independent seasons (2021 2022) with gradient fertilizer water inputs. We collected 470 ground-truth...
In this paper, we deal with decoding of convolutional codes using artificial intelligence techniques. A comparison our decoder versus the Viterbi in terms performance and computing complexity is given. The simulation results show that genetic algorithms based (GAD) outperforms decoders. Furthermore GAD better for large lengths. good obtained by systematic make it more attractive.
In this paper, we propose a new architecture of deep neural network called 3D Racah Moments Convolutional Neural Network (3D RMCNN) to improve the classification accuracy and reduce computational complexity pattern recognition system. The proposed consists fusioning concepts image moments convolutional (CNN), largely utilized in applications. Indeed, advantages concerning their global information coding mechanism even lower orders, along with high effectiveness CNN, are combined make up...
Recently, Deep Learning models, such as Convolutional Neural Networks (CNNs), have shown remarkable performance on various Computer Vision tasks. Unfortunately, many application domains, agriculture image analysis, do not access to large datasets. In this study, we are interested in the prediction of soil moisture dissipation rates from aerial images using a CNN model. This entails regression task where CNN, given an input image, has predict vector values associated with at different...
A Wireless Sensor Network (WSN) is one that in continual interaction with its environment, and executes at a pace determined by environment. The use of rigorous formal method specification validation can help designers to limit the introduction potentially faulty components during construction system. Due their complex nature, WSN are extremely difficult specify validate. In this paper, we propose new model for such systems. This approach considers as Reactive Multi-Agent System consisting...
In this paper, a new modified S-shaped antenna for RFID -UHF tag application is presented. To provide good conjugate matching between the and ship, technique of adding asymmetrical triangular stubs on both side chip was applied. The proposed operating in 915MHz band here has dimensions only 51×43 mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> bandwidth from 909 to 920 MHz (to cover US Band) under -10dB reflection coefficient...
Fetal heart rate and uterine contractions diagnosis are procedures used to evaluate the well-being of fetus during pregnancy labor. In this paper, we give a description fetal rate, also most viable diagnostic technologies recording vital signals those maternal contractions. We comparative study these methods which Doppler ultrasound, electrocardiogram use piezoelectric materials. Then choose best solution technology, be in our future project.
The fetal heart rate and uterine contractions monitoring, using the non-invasive technologies, are widely used. These techniques most appropriate because an invasive test can not be used daily to evaluate well-being of fetus during pregnancy labor. This paper presents a description comparative study diagnostic technologies recording vital signals those maternal contractions.
This paper introduces a new decoder based on genetic algorithms and neural networks for binary linear codes. The search space, in contrast to our previous which was limited the codeword now covers whole vector space.The network is used favor feasible solution namely codewords. Previous algorithm decoders [2] require lot of computing resources when with large eludes great number coding operations by using network. reduces greatly complexity while maintaining comparable performances.
Attitude control has been one of the most interesting, challenging and active issues in aerospace domain. The attitude follows from need to position satellite around its center mass point antennas, sensors payloads toward a specific area Earth. Hence, it can achieve mission. Regarding this matter, many approaches have developed adopted literature. Our objective is optimize reliability Determination Control System (ADCS). Therefore, paper we briefly introduce what are satellites...
This study was primarily triggered by the requirements of crop breeding programs to rapidly, accurately and cost-effectively select genotypes with enhanced biomass Nitrogen (N) content (an essential indicator stover quality as feed) and, at same time, possibly speed up agriculture transition more sustainable precise application fertilizers (crop health status). proof concept explores whether how precisely it is possible predict N in sorghum using a minimum unmanned aerial vehicle...
The prediction of soil moisture for automated irrigation applications is a major challenge, as it affected by various environmental parameters. Application Convolutional Neural Networks (CNN), to this end, has shown remarkable results prediction. These models, however, typically need large datasets, which are scarce in the agriculture field. To paper presents Deep Generative Adversarial Network (DCGAN) that can learn good data representations and generate highly realistic samples....
This paper presents the comparative study of output voltage's numerical response new structures a curved sensor based on PVDF film. These will be used to detect incident pressure received through mechanical vibrations and convert them into usable electrical signals. kind is destined for monitoring fetal heart rate during pregnancy labor. In this study, we focused influences three parameters namely thickness sensing film, radius curvature, sensor. models were validated using FEM, with same...