Latest news with #IndraprasthaInstituteofInformationTechnology-Delhi
Time of India
3 days ago
- Science
- Time of India
IIIT-Delhi plans AI-driven system to know space better
New Delhi: In a world where space is getting busier by the minute—with satellites darting across orbits, fragments of debris spinning unpredictably and new missions launching frequently—keeping track of what's out there is essential. This is where space situational awareness (SSA) becomes crucial, quietly monitoring the cosmic traffic jam. SSA systems are tools and technologies that help us track and understand what's happening in space, especially around Earth. Think of them like traffic control systems, but for satellites, space debris, and other objects orbiting our planet. However, most current SSA systems face significant challenges. They're expensive, complex, and heavily reliant on human input, making them slow and prone to error in a domain where precision is critical. Indraprastha Institute of Information Technology-Delhi (IIIT-Delhi) has now stepped in—with a vision and a team of professors, engineers and AI specialists looking to change the game. The institute has joined hands with Indian Space Research Organisation (ISRO), industry and academia under the 'AI for Space Initiative' to build an AI-driven, self-reliant SSA system—a smart platform that would not just track objects in orbit but also learn from patterns and predict outcomes faster than humans. "Human-in-the-loop SSA systems face several significant limitations. They must process vast amounts of data collected from thousands of active satellites, space debris and defunct rocket bodies. This overwhelming volume of information creates challenges for human analysts, who struggle to identify the most critical and relevant data needed to prevent collisions. Additionally, reliance on manual analysis leads to delayed responses, while inconsistencies in risk assessments arise from the use of varied data sources and algorithms by different operators," said Sanat K Biswas, assistant professor (ECE) at IIIT-Delhi. Coordination between satellite operators is another major bottleneck. "The lack of standardised protocols among satellite operators complicates coordination for collision avoidance. Language barriers and difficulties in locating relevant contacts for operational coordination further limit necessary actions," added Biswas. The AI-driven SSA solution from IIIT-Delhi aims to address these issues on multiple fronts. AI, when used under human supervision, can help overcome some of the limitations previously mentioned. "Currently, AI algorithms are used mainly for specific support tasks like detecting objects. In the near future, AI is expected to take on more complex roles such as managing sensors, automating data processing and detecting threats. This will speed up decision-making and improve reliability by quickly verifying data from multiple sources. To bring all these functions together, we can develop agentic AI—where multiple AI agents handle different tasks while a human oversees their work," he said. The project is one of many being explored under Infosys Centre for Artificial Intelligence (CAI). In 2016, IIIT-Delhi joined forces with Infosys Limited to establish the centre focusing on research and development in autonomous vehicles, AI in healthcare, AI in robotics, AI in mobility and satellite navigation. The SSA initiative is a natural extension of CAI's mission to apply AI for humanity's most complex challenges. Yet, even as technology advances, building a robust national SSA system demands more than just clever algorithms. It requires collaboration—something that has historically been lacking in India's space sector. "Unfortunately, there are very few examples of these collaboration pathways in India, and the capabilities of academic institutions are often underutilised in the space sector," said Biswas. He suggests multiple pathways for collaboration: "One approach is for an academic institution to develop a technology to a certain stage, after which the industry can take over to create a product that ISRO can use. Another option is for ISRO to provide a research statement, which academic institutes can refine and further develop into technology suitable for industry-led product development." But funding and patience are key. "If we aspire to become a technological leader in AI applications for space or in space technology more broadly, we must recognise that space research is resource-intensive and that immediate results are not always guaranteed. To foster productive collaboration, ISRO and Indian space industries should support academic institutions and universities with proven expertise in the space domain. This support should come in the form of focused, sustained long-term funding for both fundamental and applied research," he says. Currently, the IIIT-Delhi team—comprising professors, researchers and budding engineers—is focused on orbit computation of resident space objects, an essential step towards predicting close approaches and possible collisions. As satellites become the arteries of global communication, navigation, and defence, knowing what's out there—and what's coming—is a necessity. By reducing reliance on foreign data, increasing automation, and ensuring transparency, IIIT-Delhi's SSA platform could make space not just smarter, but safer for India and beyond.
Time of India
22-05-2025
- Health
- Time of India
IIIT-Delhi, French researchers develop AI tool to outsmart drug-resistant superbugs
New Delhi: In a boost to scientific advancement aimed at curbing the global threat of drug-resistant infections, researchers from the Indraprastha Institute of Information Technology-Delhi ( IIIT-Delhi ) and France's Inria Saclay have developed an artificial intelligence (AI)-based system that can recommend effective combinations of existing antibiotics to fight superbugs . Superbugs are germs like bacteria and fungi that cause hard-to-treat infections. Most superbugs are bacteria that have developed antibiotic resistance - the ability to survive antibiotic medications. The project, jointly led by Professor Angshul Majumdar and Dr Emilie Chouzenoux, is part of a broader India-France research collaboration between Deep Light (Delhi) and CentraleSupelec, a French engineering school, said an official statement of IIIT-D. The team includes engineer Stuti Jain and graduate researchers Kriti Kumar and Sayantika Chatterjee, it added. "This is an excellent example of how AI and international collaboration can come together to solve real-world medical challenges and our method makes it possible to use existing knowledge more effectively and opens the door to smarter, faster responses to antimicrobial resistance (AMR)," Prof. Majumdar told PTI. AMR occurs when bacteria adapt to antibiotics, rendering them ineffective. Prof. Majumdar said the misuse of antibiotics, particularly in countries like India, is a major contributor to the crisis. "We often take antibiotics even for viral infections, which don't require them. Over time, bacteria evolve and adapt. As a result, even simple infections like urinary tract infections or wounds can become resistant to treatment," he added. The AI system that the team developed goes far beyond traditional rule-based models. It analyzes real-world clinical decisions from leading Indian hospitals and combines this with bacterial genome data and the chemical structure of antibiotics to recommend optimal treatment options. The system was successfully tested on multi-drug resistant strains like Klebsiella pneumoniae, Neisseria gonorrhoeae and Mycobacterium tuberculosis. Prof. Majumdar shared a harrowing case from AIIMS, Kalyani, where a young patient's artificial hip joint became infected and was unresponsive to even last-resort antibiotics. "It was a simple muscle infection, but it became untreatable. The patient from a poor family was left bedridden and without options," he said. "This is the reality of AMR - it can devastate lives even when the infection seems ordinary." The professor said the AI model offers combination therapy suggestions, mirroring how doctors treat advanced cases today. "Instead of recommending one antibiotic, our system can propose a cocktail of drugs based on the genome sequence of the bacteria," said Majumdar. "Doctors can ask for five or ten possible options for a specific strain and the AI suggests viable treatments," he added. While the model is currently focused on bacterial infections, it can be retrained to tackle viral infections or even lifestyle diseases like hypertension, where drug resistance is emerging. "Our core motivation was to address infectious diseases - a problem that plagues countries in Southeast Asia, Africa and Latin America far more than it does the West," said Majumdar. "There's less funding for this kind of work, but the impact is massive," he added. The team hopes that their model would eventually be embedded in hospital systems and public health frameworks, particularly in regions with limited access to advanced diagnostics. With AMR recognized as one of the most pressing global health threats of the 21st century, this AI-powered solution may offer doctors a timely, data-driven ally in the battle to preserve the effectiveness of antibiotics.
