Luxembourg-India Hackathon

About Us

Luxembourg-India Hackathon

The 'India - Luxembourg Hackathon' is a social coding event of 36 hours duration that brings together students, educators, teachers, and the research community of India and Luxembourg to tackle the common challenges faced by these countries in the field of Finance Technology and Space Technology. The India Luxembourg Hackathon.

Serves as a facilitator for cultural amalgamation, strengthening economic ties and development in education, science and technology. It will help to develop a strong cross-country bond, collaboration and understanding between the youths at the level of individuals and institutions.The Hackathon will also promote learning and cooperation among students from participating countries and they will learn from each other's strengths and get acquainted with each other's culture, values, best practices and work ethics. It allows the participating students to unleash their creativity and explore new technologies to solve real-world problems under the guidance of experts/mentors.

The 'India - Luxembourg Hackathon' also serves as a symbol of the close relationship cherished by India and Luxembourg and embodies the spirit of collaboration - bringing them together to solve problems for the betterment of humanity.

Nodal Agencies

India

Name of Nodal Agency

Ministry of Education's Innovation Cell & All India Council for Technical Education

Luxembourg

Name of Nodal Agency

University of Luxembourg

Hackathon Process

Nodal Agency need to nominate students who have knowledge/specialization in coding/software development in UI/UX, AI/ML, AR/VR, IoT, DATA ANALYSIS etc.

Mentors needs to be assign with each team by the nodal agency, that will guide the team to get the optimum solution.

Nodal agency will brainstorm each team as per the requirement and provide best ideas that they will work in the hackathon.

The participants shortlisted for the grand finale, will provided by the nodal agencies after pre-screening and filtration at their end. The team size entering in the grand finale will be of 5 to 6 members.

Participants must have knowledge/specialization in coding/software development in UI/UX, AI/ML, AR/VR, IoT, DATA ANALYSIS etc.

One mentors per participating team will be provided by the nodal agencies for mentoring the team in order to achieve the best feasble solution.

Theme expert evaluators will be onboarded by the organizers and on the basis of nodal agencies recommendation.

For Team mentors

Team mentor is responsible to handhold the team in their respective domain to achieve the optimum soultion of the problem that they are working upon.

For Team Evaluator

Evaluators will be responsible to guide the team in grand finale morning session and will monitor their working through out the day. In evening session, they will evaluate them based on the pre-finalised parameters and give them scores.

Themes

Luxembourg-India Hackathon Themes

Space Technology

Leveraging the cutting-edge technology and technical expertise helps to cope with new challenges and explore opportunities for Space Technologies.

Fintech

Fintech, a portmanteau of "financial technology," is the application of new technological advancements to products and services in the financial industry.

Timeline

Tentative Timeline for the Hackathon

Identification of Nodal Agency from India and Luxembourg
Identification / Finalisation of themes
Identification and Finalization of PS
Shortlisting of Students & Team formation
Orientation Workshop ONLINE
Idea Submission & Initiate Development of Prototype
Online Grand Finale

Patrons and Organizing Committee

Patron

Shri Dharmendra Pradhan

Hon’ble Minister of Education Government of India

Co-Patrons

Smt. Annpurna Devi

Minister of State for Education Government of India

Dr. Subhas Sarkar

Minister of State for Education Government of India

Dr. Rajkumar Ranjan Singh

Minister of State for Education Government of India

Prof. T. G. Sitharam

Chairman, AICTE

Sh. Rakesh Ranjan

Additional Secretary (TE)

Dr. Abhay Jere

Chief Innovation Officer, MIC

Dr Ramesh Unnikrishnan

Adviser-II, AICTE

Dr Amit Kumar Srivastava

Director, AICTE

Dr. Nikhil Kant

Deputy Director, AICTE

Dr Elangovan Kariappan

Assistant Innovation Director, MIC

Fintech

Mr. Guruprasad Datar

Director - Financial Services at Deloitte

Mr. Abhilash Rathore

Co-Founder and CTO at 4Fin

Deakin Daney

CEO, Bootstart

Space Technology

Shri Victor Joseph

Associate Scientific Secretary, ISRO, Chairman

Dr. Jayaprakash V Thomas

Associate Director, EDPO, ISRO, Member

Shri Manish A Saxena

Director, SATNAV-PO, ISRO, Member

Contact

Address

Ministry of Education Innovation Cell

All India Council for Technical Education (AICTE),
Nelson Mandela Marg,
Vasant Kunj, New Delhi-110070.

Call Us

011-29581316

Email Us

mic-mhrd@gov.in

Spcae Technology

ID	Problem Statement ID	Problem Statement	Problem Description
1	STECH01	Processing, visualisation, and application development of raw GNSS data on Android smartphones.	These days almost every android smartphone includes a GNSS sensor. Increasingly this GNSS sensor supports hosts of GNSS constellation like GPS, Galileo, Beidou, Glonass, QZSS and NavIC. Until now, the smartphone GNSS chipsets were operating on single frequency at L1 only. However, some of the advanced smartphone chipsets now supports L5 band also. Along with this a major development has happened wherein the android has enabled access to raw GNSS data also. This opens up enormous opportunity to develop newer smartphone based GNSS applications enabling accuracy and integrity, which was not possible earlier. This problem statement deals with the processing and visualization of such raw GNSS observable from the android devices.
2	STECH02	Prediction of TEC variations with AI using space weather data as input.	The ionospheric electron density is sensitive to the space weather parameters like Sunspot numbers, F10.7, Interplanetary magnetic field etc. and shows variation with respect to them. These parameters are detected and measured at L1 point (currently by ESA / NASA satellites) and are transmitted to earth. So, the information about these parameters are available before they actually influence the terrestrial ionosphere. Importantly, all these data are freely available over internet. The abovementioned parameters affect the ionospheric TEC, which in turn shows abrupt variations and deviations from the nominal characteristics. Therefore, these unconventionalities, which are typically observed during solar and geomagnetic storms, are necessary to be identified. This is also important, because the performance of the GNSS system, which is currently driving millions of applications, are also affected by the ionospheric variabilities. So, prediction of the TEC provides a handle to take necessary actions to avoid or mitigate the resultant impairments arising out of the above facts. For the purpose, the time sequence of space-weather parameters, along with the local time, location, season, date etc. can be related to the same for the vertical TEC and a definitive relationship can be established using Artificial Intelligence (AI) methods, like neural networks or other deep learning algorithms. Once trained with known dataset, the AI based algorithm may be able to predict the expected TEC variations which can be used by the concerned users. The schematic for the approach may be as the following. The problem requires the development of the proper AI algorithm to use the available space weather and other data to predict the TEC variations at one particular location on the earth, preferably over the geomagnetic equator. For datasets and additional information, please visit https://vedas.sac.gov.in/en/sih2022.html
3	STECH03	Multispectral satellite image dehazing.	Given a multispectral image, dehazing tries to improve interpret-ability in the image regions affected by the presence of haze during acquisition. For datasets and additional information, please visit https://vedas.sac.gov.in/en/sih2022.html
4	STECH04	Producing Super Resolution Digital Elevation models from Low resolution DEMs.	DEMs could be produced from different sources. Satellite stereoscopy has its own advantages over other techniques. However, there are certain theoretical limitations in producing DEMs from a certain resolution stereo data. Here the idea is to train a machine with some super resolution DEM samples and use the model for generating super resolution elsewhere. For datasets and additional information, please visit https://vedas.sac.gov.in/en/sih2022.html

Fintech

ID	Problem Statement ID	Problem Statement	Problem Description
1	FTECH01	Fraudulent Behavior Detection	Financial institutions need to optimize the monitoring of individual transactions and identify deliberate misconduct during the onboarding and servicing of customers. Develop a machine learning application that would identify behavioral patterns. For instance, time to complete processes, missing fields, amendments, and multiple transactions are already understood to be highly correlated to suspicious activity. There are certainly many more tell-tale signs that could be used to detect potentially fraudulent behavior.
2	FTECH02	Drone Pilot Insurance	A new market is developing to insure against damage caused by commercial or private drones. Build a platform that would assess the proficiency (experience, algorithms that assess previous flights) of drone pilots , the environment (previous flights), their equipment (flight time, drone used, wear and tear) and develop pricing models for drone related insurance products.
3	FTECH03	Data Driven Credit Underwriting	"Existing credit underwriting models do not leverage new sources of qualitative and quantitative information, both for individuals and SMEs. Provide a solution that would leverage non-traditional data sources to selectively refine existing underwriting models (rather than rewrite them). This would enable financial institutions to lend to new customers that they would have rejected before. How to have earnings/revenue data points related to the following customer segments? Having these data points will help these customer segments secure loans. 1. Roadside hawkers- selling vegetables, T stalls, any other items etc 2. Maids & Servants These income sources should be verifiable by the banks/funding institutions. Students can take up any one example of a customer segment. Study these segments and prescribe methods to measure earnings and ensure these methods are verifiable."
4	FTECH04	Smart Portfolio Management	Asset Managers need to take into consideration a number of factors when building a portfolio for their customers such as: Portfolio performance The risk appetite of the customer Investment theme Risk factors and regulatory considerations Risk exposure metrics Typically these are either dealt with heuristically or through weighted averages, which leads to sub-optimal portfolio performance and diminished investor returns. Develop a portfolio management tool that would deliver a decision making framework and a calculation engine that builds a portfolio consistent with the objective of all stakeholders (investors, risk managers, salespeople, and regulators).

About Us