SEED Hackathon

As cities grow, managing urban sustainability becomes increasingly complex. Challenges such as optimising energy consumption, reducing traffic congestion, improving waste management, and enhancing air quality require smart solutions. Participants are tasked with leveraging big data analytics to develop a data-driven solution that addresses one or more of these challenges in a city of 5 million people.

Key Objectives :
• Analyse and integrate large, diverse datasets from multiple sources (e.g., IoT sensors, public transport data, energy consumption records, environmental monitoring).
• Identify patterns and insights that can lead to more efficient resource management, reduced environmental impact, and improved quality of life for residents.
• Propose predictive models or real-time monitoring tools to support decision-making by city planners and citizens.

Expected Outcomes :
• Visualisation of insights from the analysed data.
• Predictive models for future urban needs (energy, traffic, air quality, etc.).
• Scalable solutions that could be implemented in real-world smart city scenarios.

Early detection of diseases significantly improves patient outcomes, reduces healthcare costs, and enables timely interventions. With the growing availability of healthcare data, there is an opportunity to leverage AI/ML to predict the onset of diseases before they become critical. However, the challenge lies in developing models that can effectively analyse complex medical data while ensuring accuracy and reliability.

Participants are tasked with developing an AI/ML-based software solution that predicts the likelihood of specific diseases (e.g., diabetes, cardiovascular diseases, cancer) based on patient data such as electronic health records (EHR), genetic information, and lifestyle factors.

Key Objectives :
• Analyse historical patient data and identify patterns that correlate with the early stages of diseases.
• Provide personalised risk scores or predictive insights for individual patients.
• Ensure that the model is explainable and interpretable, allowing healthcare providers to understand and act on the predictions.
• Incorporate mechanisms to improve the model's generalizability across diverse patient populations.

In an increasingly digital world, the demand for secure and efficient data transmission is paramount. Traditional encryption methods, while robust, face challenges such as susceptibility to data breaches, and centralised points of failure. Simultaneously, blockchain technology offers decentralised security, immutability, and transparency, yet existing encryption algorithms used within blockchain may not fully leverage its distributed nature or protect against evolving cyber threats.

The objective is to design a novel encryption algorithm that integrates with blockchain technology, enhancing data security by decentralising key management, improving resistance to cyberattacks, and ensuring scalability

Key Objectives :
• Decentralised Key Management : Utilise blockchain’s decentralised nature to create a key management system that reduces the risk of single points of failure and unauthorised access.
• Performance and Scalability : Ensure the encryption algorithm can efficiently handle large-scale data transmission and storage across distributed networks, supporting a wide range of industries from finance to healthcare.
• Immutability and Transparency : Leverage blockchain’s immutable ledger to maintain tamper-proof records of encrypted data without compromising confidentiality.

The solution should enhance cybersecurity by integrating the cryptographic strength of blockchain technology with novel encryption methods to protect against both current and future cyber threats.