Connect with:
Friday / October 18. 2024

logo
mobile-logo
HomePosts Tagged "IIT Madras"
India

Developed by Shankar Krishnapillai, Department of Mechanical Engineering, IIT Madras, jointly with farmers NGO ‘Pothu Vivasayeegal Sangam’

Researchers at IIT Madras, jointly with a farmers NGO ‘Pothu Vivasayeegal Sangam, have developed a unique, efficient and cost-effective agricultural transportation system that addresses labour shortage, a major issue faced by Indian farmers. This transportation system, which is a lightweight monorail type, can economically carry agricultural produce from the fields to collection points near the farmlands. 

An IIT Madras team, jointly with the non-governmental organisation for farmers, has successfully tested this prototype cableway system at a farm in Nanjai Thottakurichi village of Karur district in Tamil Nadu. This transportation system developed by Shankar Krishnapillai, Department of Mechanical Engineering, IIT Madras, jointly with the farmers NGO provides an economical and simple solution to this problem.

Highlighting the unique features of this transportation system, Shankar Krishnapillai, Department of Mechanical Engineering, said, “Indian farmers will face severe shortage of labour in the coming years, especially in post-harvest operations. The simple agricultural transportation system is made in local workshops, from locally available components, based on the lightweight overhead rail concept. It can be easily installed on Indian farms and reduce labour requirements in transporting the produce. The system has also minimal environmental disturbance as it passes over the ground”.

Developed by Shankar Krishnapillai, Department of Mechanical

Agro Universities

The study was conducted by Prof Sathyanarayana N Gummadi, faculty of the Department of Biotechnology, IIT Madras and Rekha Rajesh, Research Scholar, IIT Madras

Indian Institute of Technology Madras researchers have identified a bacterium that can turn agricultural waste into industrial enzymes through a cost-effective and environment-friendly process.

Industrial enzymes such as alpha-amylase and cellulase are in high demand in various industries that deal with textiles, paper, detergents, and pharmaceuticals. The IIT Madras researchers studied how a bacteria called ‘Bacillus sp PM06’ can aid in producing industrial enzymes and value-added products from agricultural waste.

The study was conducted by Prof Sathyanarayana N Gummadi, faculty of the Department of Biotechnology, IIT Madras and Rekha Rajesh, Research Scholar, IIT Madras. The findings of the research have been published in the reputed peer-reviewed journal Biomass Conversion and Biorefinery.

Highlighting the key applications of the research, Prof Sathyanarayana N Gummadi, said, “The organism which we have isolated has a fermentation capacity to hydrolyse very low-cost lignocellulosic wastes without pre-treatment, thus reducing the cost of bioprocess for production of enzymes and industrial metabolites.”

Further, speaking on how this research compares with existing technology, Prof. Sathyanarayana N Gummadi, said, “The most challenging aspect of bioconversion is the development of a one-step process which includes pre-treatment, enzyme hydrolysis and microbial fermentation thus minimising environmental impact. Many researchers are focused on isolating single microorganism producing multiple enzymes to solve the issues. But, IIT Madras researchers are successful in isolating a novel strain from sugarcane pressmud.”

Thus, the researchers studied the bacteria, Bacillus sp PM06, which was isolated from sugarcane waste press mud. This bacterium helped in the production of industrial enzymes and value-added products from agricultural waste. The wheat barn was found to be the most effective substrate followed by sago waste and rice barn. 

The study was conducted by Prof Sathyanarayana

Agro Universities, Live Stock

The researchers found that combined and coordinated use of Forest Rangers and drones were a good way to protect wildlife from poaching

Indian Institute of Technology Madras and Harvard University researchers have developed a novel Machine Learning algorithm named ‘CombSGPO’ (Combined Security Game Policy Optimisation) that can help in saving wildlife from poaching.

The researchers found that combined and coordinated use of Forest Rangers and drones were a good way to protect wildlife from poaching. As the resources (Rangers and drones) are limited, the researchers developed this algorithm which provides a good strategy to protect wildlife with the resources available. This new algorithm provides highly efficient strategies that are more scalable than the earlier ones created for the same purpose.

The algorithm works by handling resource allocation and strategising patrolling after the extent of resources available had been identified. For this task, it utilises data on the animal population in the conserved area and assumes that poachers are aware about the patrolling being done at various sites.

Prof Balaraman Ravindran, Mindtree Faculty Fellow and Professor, Department of Computer Science and Engineering, IIT Madras, and the Head of Robert Bosch Centre for Data Science and Artificial Intelligence (RBCDSAI), IIT Madras, collaborated with Prof Milind Tambe’s Research Group – Teamcore – at Harvard University, US, to carry out this study.

The work has been peer-reviewed and was well received at the 20th International Conference on Autonomous Agents and Multi-Agent Systems. 

Prof Balaraman Ravindran, Head, Robert Bosch Centre for Data Science and Artificial Intelligence (RBCDSAI), IIT Madras, said, “The work was motivated by the need to perform strategic resource allocation and patrolling in green security domains to prevent illegal activities such as wildlife poaching, illegal logging and illegal fishing. The resources we consider are human patrollers (forest rangers) and surveillance drones, which have object detectors mounted on them for animals and poachers and can perform strategic signalling and communicate with each other as well as the human patrollers.”

To extend this research for application in domains such as security, search and rescue and aerial mapping for agriculture among others, the team is trying to perform sample-efficient multi-agent reinforcement learning to learn with the least amount of data since data collection is costly in a real-world scenario.

The researchers found that combined and coordinated