Our technology is built on rigorous scientific validation. Explore the core research and academic publications driving our autonomous systems.
S. Arman, et al.
Abstract: A generalized AI framework for cross-crop disease diagnosis using the novel PlantCareNet architecture.
S. Arman, et al.
Abstract: A very fast, lightweight convolutional neural network (CNN) designed for diagnosing three prominent banana leaf diseases via mobile imagery.
S. Arman, et al.
Abstract: Research focusing on automated diagnosis of mango leaf conditions using mobile imagery and deep classification.
S. Arman, et al.
Abstract: Monitoring and classifying the growth stages of cotton seedlings using deep learning to optimize farming timelines.
S. Arman (Co-PI)
Abstract: Funded research utilizing AI to perform rapid assessment of climate-induced stress responses across multiple plant species.
S. Arman (Co-PI)
Abstract: Research grant focusing on applying deep learning architecture for epidemiological forecasting of plant diseases.
S. Arman, et al.
Abstract: An extensive collection of real-world images showcasing three prevalent diseases affecting banana leaves to aid in developing robust classification models.
S.N. Sakib, N. Haque, M.Z. Hossain, S. Arman
Abstract: A large-scale VQA dataset derived from PlantVillage comprising 193,609 high-quality question-answer pairs grounded over 55,448 images covering 14 crop species and 38 conditions.
S. Arman, et al.
Abstract: An optimized lightweight CNN for rapid on-device diagnosis of sugarcane leaf diseases achieving 98.02% accuracy tailored for low-resource regions.
Technical reports, system cards, and peer-reviewed research defining the next generation of precision agriculture.