SEARCH RESULT

Agriculture being the foundation for the existence and progress of the developing countries contributes to strengthen the health of the public. It is highly necessary and essential to enhance agricultural productivity towards sustainable and eco-friendly practices. A traditional mechanism will not enable to check the multiple factors required for determining the holistic approach towards complete development of sustainable agriculture. Examining the performances of key factors of agriculture is possible using machine learning techniques which are potentially capable for finding hidden patterns and perform predictive analytics. The key factors which build sustainable agricultural practices are soil health, crop health, water stress management, pesticide usage and yield prediction. The soil with consistent ability to produce healthy crops is the main support for agriculture. Health of the crop is defined by health of the soil. A common important factor for the health of soil and crop both is water stress management in crops and soil which is responsible for crops to absorb nutrition from the soil and for soil to retain its alkalinity and nutrition profile. This article gives review about various machine learning techniques applied on the mentioned key factors of agriculture, effectiveness of these techniques on agriculture, scope for the betterment of the results to infer precise conclusions and finally concludes that Machine learning can lead towards complete development of the sustainable agriculture.

International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES

Mr Sachin Desai Swetha Goudar Pranati.R.Karajagi Manjunath Managuli

Among the most complicated and limiting disorders affecting the human nervous system are neurological disorders, that involve multiple sclerosis, Parkinson's disease, Alzheimer's disease, and Huntington's disease. Therapeutic development is particularly difficult because of their complex nature, increasing disease, and variety of clinical presentation. Traditional methods of drug discovery are frequently excessively costly, timeconsuming, and likely to failure, particularly in late-stage clinical trials. Artificial Intelligence, particularly computer vision, has emerged as a powerful solution for tackling these challenges and advancing drug discovery by facilitating the large-scale autonomous analysis of biological images. Computer vision facilitates the accurate and methodical examination of cellular structures, tissue organization, and disease development. This article presents a comprehensive analysis of the role of computer vision in driving progress within research focused on treatments for neurological disorders. It highlights key techniques, including multimodal fusion approaches that integrate imaging with genomic and clinical data, supervised learning methods for tasks like classification and segmentation, as well as unsupervised and selfsupervised approaches for identifying patterns and insights.

International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES

Pranati.R.Karajagi Swetha Goudar Mr Sachin Desai Manjunath Managuli