Weather and volatile market demand for crops are the two biggest concerns for farmers in developing countries like Nepal. Risk of crop production has worsened by changing weather patterns due to climate change. Conventional crop insurance systems are complex and often not feasible economically. Farmers are reluctant to get covered for their crops due to lack of trust in insurance firms and the fear of delayed or non-payment of claims. Farmers want rapid assistance when a natural disaster strikes so that plantation can be redone within the growing period. Crop insurance that is simple, reliable, and affordable is consequently critical, not only for farmer’s well-being, but also for the nation's food security. In this paper, a blockchain based platform for crowd farming with weather index-based crop insurance is presented. The solution presented is a platform that allows general customers to invest in agricultural projects in return for harvest from the field. To minimize risk from climatic disasters an affordable, efficient, low-cost crop insurance solution is also integrated which will ensure that farmers are insured and benefited from timely crop insurance. Currently, the expense of administering insurance is a considerable barrier to entry into this market. With the correct technology, this cost can be drastically lowered. Decentralized architecture and smart contract is the core foundation for achieving this platform since smart contract maintains trust among two involved parties and triggers unbiased payouts based on certain parameters. The success of this model can lead to developments in crowdfunding platforms, supply chain management system as well as other form of insurance
In public auction the participation of the general public is very limited. The aim of the project is to socialize the auction so that people from far & wide and even across the continent can participate in it. The system is designed to allow users to set up their products for auctions and bidders to register and bid for various products available for bidding. The “Online Auction” site is developed with a vision to wipe out the inherent problems of “Conventional Auction House”. Online Auction is designed in such a way that it is as user friendly as possible. So, any aspiring bidder or seller can visit the site and engage in bidding with least effort.
There is an undeniable communication problem between the Deaf community and the hearing majority. Innovations in automatic sign language recognition try to tear down this communication barrier. My contribution to this domain, Nepali Sign Language Recognition, is an automated system for recognizing the gestures of Nepali Sign Language using 2D Convolutional Neural Networks (CNN). In order to recognize the provided gesture, image processing techniques namely, grayscale conversion, thresholding, edge and contour detection were used in order to create shape files of individual hand gesture images. These segmented characters were then fed into the trained CNN which contains a further 4 layers: convolution layers, pooling/subsampling layers, nonlinear layers, and fully connected layers. The ReLU activation function was applied to the output to introduce nonlinearities into the model. The Neural Network training was conducted using 1200 images each for 37 alphabets and 10 numbers of Nepali Language i.e. a total of 56,400 images. Furthermore the images of every single character were flipped along the vertical axis and were added to the training model. Finally, a set of 1200 blank images were also trained to the model which increased my final accuracy from 82.4450% to 92.4568%.