OSS Trophy in Seoul
Prize Certificate for OSS Project
OSS Certificate of Achievement
Creating the project using UIPath Automation Suite
OCR feature in UIPath Automation tools for extracting data
OCR tool in UI Path Automation Suite in action
One Laptop Per Child (OLPC) is an organization dedicated to create educational opportunities for the world's poorest children by providing each child with a rugged, low-cost, low-power, connected laptop (XO) with content and software designed for collaborative, joyful, self-empowered learning. As community engineers associated with this unique proposition, we have constantly evolved our skills to align ourselves with the mission statement and develop tools for educational and healthcare purposes.
What it does
Our solution offers an Artificial Intelligence-based object detection system that utilizes blockchain solutions for sorting information obtained from a variety of cameras. With just a cell phone, users are offered a serverless solution that can detect objects in real time and more object types for better accuracy.
A greater and more seamless flow of information within a transportation infrastructure, created by electronic incident record management (E.I.R.M), encompasses and leverages digital progress and can transform the way road safety can be delivered and compensated.
- E.I.R.M helps in improved coordination.
- E.I.R.M helps in making road safety ecosystem proactive and authentic.
- E.I.R.M with the help of computer aided detection will help in early prediction and prevention of incidents.
We can utilize SocialCalc, Machine Learning Models coupled with UIPath Automation tools for analysis and prediction of incidents to provide early stage detection and prevention of accidents.
Our solution will be useful to -
- OEM and Dealerships: Vehicle diagnostics, in-car service consumption
- Federal/State Department of Transport: Breakdown data, accident data
- Smart Cities: Real-time traffic flow, incident alert, parking
- Insurance Companies: Aggregated, anonymized driving data, incident data
- Police Officers, dispatchers, drivers, pedestrians, passengers, civic bodies
- Advertisers: Customer demographics
How we built it
Humans at the mere sight of an image are capable of identifying what objects are there in an image and develop all possible relations between objects in that image. The human detection system when mimicked is capable of generating new solutions in different domains. The current image recognition softwares use classifiers and run feature sets across the image to detect objects in the image, this does lead to a great deal of accuracy. Some of the best ways to get involved with object detection is using cognitive services from Microsoft Vision, TensorFlow  and Yolo . The proposed working solution uses a python based wrapper and openCV  to feed real time data into the neural network and take intelligent actions from there on.
By running a set of same images on cognitive systems Microsoft Vision, TensorFlow and Yolo, a comparative analysis is discussed and based on which certain conclusions are drawn. Factors contributing to selection primarily include speed and accuracy under various stress factors which include distance, light, network connectivity and cost.
With the solution aimed to serve vehicles belonging to citizens of different income groups, it is important to keep the solution cost effective. Cognitive support is the backbone of this system. It is a must to choose cognitive support which comes at minimal cost and satisfies the trade off between cost and accuracy. Despite the fact, providing extremely high accuracies consistently, cognitive support offered by Microsoft comes at a price which makes it not suitable to use in the module, while TensorFlow and Yolo are free to use. Apart from that, we find Microsoft cognitive support requires the continuous presence of an active internet connection which again comes at a cost and thus, further adding to t he amount required for buying and maintaining the product. With this, the module let go of Microsoft Cognitive support despite of its amazing accuracy and consistent predictions. To perform comparative analysis between TensorFlow and Yolo, we run these free cognitive services on a same video.
Using cognitive service of Yolo, which plots the prediction number vs accuracy for the first 100 predictions, we see that the number of sharp drops are less as compared to TensorFlow and the detection is consistent over a long period of time despite consistency slightly being on the lower side. It is also evident that in the trade off between consistency and accuracy Yolo performs better by providing the required consistency over a longer duration. The application of a Convolutional Neural Network over a predicted set of boxes instead of the whole image where the confidence of finding an object in the image is greater than a set threshold makes Yolo superior and the system believes it would be the most apt cognitive service to fit in the module.
- Mart´ın Abadi et. al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. Software available from tensorflow.org.
- Joseph Redmon et. al. You only look once: Unified, real-time object detection. CoRR, abs/1506.02640, 2015.
- Culjak Ivan et. al. A brief introduction to opencv. In MIPRO, 2012 proceedings of the 35th international convention, pages 1725–1730. IEEE, 2012.
- Zhu Liya and Yong Shaohong. The effect of corporate social responsibility on employees. In 6th International Conference on Information Management and Industrial Engineering, volume 1, pages 268–271. IEEE, 2013.
Challenges we ran into
Our solution supports the notions that users should “share by default” and be able to “explore, express, debug, and critique.” Thus our solution puts an emphasis on “activities” rather than “applications.” The foundation will focus on solving the challenges that are relevant to these aspects of the interface, namely:
To make it “simple” to share user activities. This will require an architecture that allows discovery of activities.
To create versions of software that run on multiple operating systems and on multiple hardware platforms. It should be “simple” to install application everywhere. Specifically, it means packaging for every distribution and every virtual machine—removing hardware-related dependencies wherever possible.
To make it “simple” to write software activities. This necessitates stable APIs and example code that uses these APIs.
To make software activities even more secure. Our principal user community is comprised of commoners; they must be protected from malware, phishing, botnets, etc.
Accomplishments that we're proud of
Special Award Presented to SEETA, 24th Global Contest, South Korea The award was presented to SEETA on behalf of its remarkable results at 24th Global Software Contest hosted by IPAK and NIPA, South Korea.
Publications on open source spreadsheet platform:
"SocialCalc: A Spreadsheet Activity for Computer Supported Collaborative Learning", Manu Sheel Gupta, K.S. Preeti, Vijit Singh, Proceedings of the 2010 Conference on Frontiers in Education: Computer Science and Computer Engineering, FECS 2010, Las Vegas, Nevada, U.S.A., CSREA Press 2010, ISBN 1-60132-143-0, pp. 304-309 URL - http://www.informatik.uni-trier.de/~ley/db/conf/fecs/fecs2010.html
"Spreadsheet on Cloud - Framework for Learning and Health Management System", K.S. Preeti, Vijit Singh, Sushant Bhatia, Ekansh Preet Singh, Manu Sheel Gupta, Proceedings of the EuSpRIG Conference "Spreadsheet Governance - Policy and Practice" ISBN : 978-0-9566256-9-4
Deployment in Uruguay - Plan Ceibal OLPC Deployment Project, Uruguay - http://www.youtube.com/watch?v=-7cPHg4XJKY
Community work with FCC (Federal Communication Commission) - http://purplemotes.net/2009/09/13/universal-social-access-to-data-and-calculation/
Training Video by Dan Bricklin - http://www.peapodcast.com/sgi/socialtext/sctraining1/
Download - SocialCalc on Sugar page at Sugar Activities Catalogue - http://activities.sugarlabs.org/en-US/sugar/addon/4084 https://vimeo.com/5291250
What we learned:
Our solution is useful only to the extent it is used by the user community. Thus, we are working with users around the world to focus on these key challenges:
To make our solution freely and readily available to users everywhere
To explore and share best practices
To provide a forum for discussion and support for technology for learning
To provide mechanism for evaluation and dissemination of results.
What's next for Security11X
Our solution is here to support community innovation, security, and enterprise. We would like to help community members start projects that help sustain and grow the technology and communities:
To provide local and regional technical and pedagogical support.
To create new AI activities.
To provide localization and internationalization of software, content, and documentation.
To provide integration and customization services.
We extended and adapted the learning learned from a use-case such that it could used for not only incident management response system at the roads but also local air traffic control for drones and UAVs. We further explored its implication on developing an air traffic network for air taxis in Special Economic Zones under Smart Cities program. We did this exercise during the hackathon as the ability to extend and adapt towards reusable computing is the need of the hour. This would prevent orphaning of existing neat efforts in computer engineering, sciences and machine learning.