AN012 – Food PoolingTo better that experience for users by allowing them to pool orders and thus save money on delivery charges. It also aims to help them get access to coupons and use them, which they would not have been able to do previously.
A lot of times, there are incredible offers on takeouts and online shopping sites like Dominos, McDonald’s, Myntra etc. However, most of these offers require a high cart value, which one person alone cannot avail. These offers could have been availed had there been more parties on the receiving end. This is what we aim to achieve through our application.
The primary motivation is to link people who are interested in ordering a similar item, while allowing all those people to get additional discounts on their orders, which they would not have normally. Thus, also allowing people to save money.
Similarly, to get to various entertainment events across the city, people prefer public transport to avoid the hassle of finding a parking space.
Hence, to offer a smart solution to this, Pool ‘Em Up also offers an additional service wherein people from the same neighbourhood going to the same event can pool their ride, thus saving not only time in finding and picking up another passenger like in the conventional cab pooling services
AN011 – Clothing Color RecommendationIn the age of looking good, we come across that one question everyday; What should I wear to look good today ? Our choices being limited to the apparels that we already have bought, we turn to online shopping in our free time and keep on scrolling through numerous attires until we find the best that suits ourselves. Finding the best clothing that is personalised to our looks online, where there are thousands of choices takes at times, a few minutes or even hours. And after a long task of finding that perfect suit or dress that best fits us, we're left with a few doubts in our minds later; Will it suit my skin tone? Will it really look that good? These concerns can be alleviated by having an outfit recommendation system which can provide suggestions on outfits based on ones skin-tone color, occasion, current trends, sizes, etc. The proposed system aims to help the user in deciding what coloured clothing will best suit him or her on appropriate occasions by making choices based on different data-points
AN010 – Pharmaceutical ApplicationMost of times people don’t know the purpose and side effects of the medicines So it is necessary to know their use. In this project we introduce an Android based application for the people. This application will tell their user to the use and side effects of medicine. This android application will also allow users to purchase medicines.
Expanding extent of services are presently electronic services conveyed over the Internet. Internet and online websites has changed our way of shopping completely. As we know that almost everything is going to be online. The web has long been a source of medical data; it has just as of late been utilized for online shopping medical products. Now, medicines are also available online it can be order by mobile application.
IP001 – Image HomogeneityThis project concerns the problem of fully automated panoramic image stitching. The 2D or multi-row stitching is more difficult. Previous approaches have used human input or restrictions on the image sequence in order to establish matching images. In this work, we formulate stitching as a multi-image matching problem, and use invariant local features to find matches between all of the images. Because of this our method is insensitive to the ordering, orientation, scale and illumination of the input images. It is also insensitive to noise images that are not part of a panorama, and can recognise multiple panoramas in an unordered image dataset.
AN009 – Calorie Management
In recent year, healthy is a topic that people concern. It is obviously that eating the food with high amount of calories cause several problems to our health. Recording the amount of calories of the food intake in each meal is one of the stretchy to solve such problem. Although the people can record their meal and discuss with doctors or experts, it is not so convenient and they cannot know the amount of calories before the meal.
AN008 – Human Activity Recognition
Common use of smartphones is a compelling reason for performing activity recognition with on-board sensors as it is more practical than other approaches, such as wearable sensors and augmented environments. Many solutions have been proposed by academia, but practical use is limited to experimental settings. Ad hoc solutions exist with different degrees in recognition accuracy and efficiency. To ease the development of activity recognition for the mobile application eco-system, Google released an activity recognition service on their Android platform. In this paper, we present a systematic evaluation of this activity recognition service and share the lesson learnt. Through our experiments, we identified scenarios in which the recognition accuracy was barely acceptable. We analyze the cause of the inaccuracy and propose four practical and light-weight solutions to significantly improve the recognition accuracy and efficiency. Our evaluation confirmed the improvement. As a contribution, we released the proposed solutions as open-source projects for developers who want to incorporate activity recognition into their applications