Hello everyone. I'm Abhishek Vajpayee, and I'm thrilled to discuss how AI driven IoT is transforming healthcare. Together with Ratesh Mohan, we explored how these innovations improve accessibility, personalization, and data integrity in the healthcare space. Today, we'll walk you through the evolution of chatbot architectures, the role of scalable infrastructure, real world use cases, and future impacts of these technologies. Now I will hand over to Ratesh to get started. Thanks, Abhishek. Just to get started, let's first get a general understanding of how chatbots work. Traditional chatbots can be built on static architectures with predefined responses or the more modern ones using generative AI and other machine learning driven methods. The aim here is to take input from a user and provide an output. These inputs can be text, voice, image, or user actions such as click of a button sent through some kind of user interface or any versions of those. This input passes through a processing module that can be as simple as a rule based engine. Or could be a complex module using all sorts of machine learning driven submodules to produce and process those outputs. Backend services have connected to other peripherals such as knowledge bases, integrations to other machine learning services, and other such modules that can then process these intermediate inputs and get the final output ready to be served. In contrast, IoT based chatbots integrate real time data from devices. IoT allowing adaptive and context aware responses. They connect directly with IoT sensors to offer precise, actionable insight. So just like the text or image or other signals in the traditional chatbots, IoT devices has an input layer that can get signals from sensors, smart devices, and IoT gateways. This data then is connected to a cloud and can be readily available to be processed by the next stage. This next stage could be an NLP engine, a voice engine, or a full dialogue manager. So this should give you an idea about how IoT chatbots are different but still follow a similar architecture as traditional chatbots. This shift has redefined patient care, enabling 24 7 assistance and timely intervention. One of the biggest advantages is in the accessibility benefits that IoT chatbots provide. IoT based systems are available around the clock, breaking barriers like office hours and geographical constraints. For elderly or disabled patients, voice enabled IoT devices provide effortless access to health care. For example, a voice assistant can remind a patient to take their medication or guide them through managing a chronic condition. This empowers patients to take charge of their health, fostering independence and trust in healthcare systems. This entire process can be easily automated to detect events and deliver the appropriate care. Add to this a flavor of personalization and you get a system that is calibrated to a patient's profile. AI systems use recommendation algorithms such as collaborative filtering and content filtering to deliver tailored suggestions. For instance, wearable devices can analyze your activity levels and recommend adjustment to your exercise routine, diet, or medication. Let's look at some of these personalization methods. Recommendation algorithms often fall into these categories as listed on the screen. The collaborative filtering ones, which learns from a user's behavior. The content based filtering ones, which tailors suggestions based on the item attributes. Or you can have hybrid models, which are combining both for richer insights. These are also called ensemble methods. For instance, a wearable device tracking your sleep patterns could recommend lifestyle adjustments or signal a physician if irregularities are detected. This real time personalization ensures care evolves alongside the patient's needs. I will now hand it over to Abhishek to talk about how Scalable Recommendation Systems appear. Thank you, Ratesh. Personalization at scale introduces challenges. As user bases grow, systems must maintain low latency responses and handle vast datasets. This is where Scalable Recommendation Systems shine. For example, Netflix processes billions of recommendations daily. Similar frameworks can be applied in healthcare to analyze patient data, delivering timely interventions. even with increasing demands. Scalability is critical for AI and IoT systems. Scalable infrastructure allows system to handle increased data and user demands without compromising performance. This is achieved through use of cloud platforms like AWS and Google Cloud for flexible resources. Real time Apache Kafka and distributed computing tools like Apache. part for processing massive data sets efficiently. These components ensure healthcare systems can scale seamlessly as demands grow. Now we can talk about some best practices for building scalable infrastructures. To build scalable AI ML infrastructures, organizations must follow these best practices. Use data lakes to store both structured and unstructured data. Leverage hyper parameter optimization to fine tune models for better accuracy. Automate deployment with CI CD pipelines for quicker iterations and robust systems. This ensures systems remain reliable, efficient, and future ready. AI ML infrastructure doesn't just improve technology, it also empowers teams. Pre built scalable infrastructures accelerate time to value for clients. Cloud native tools enable seamless collaboration between teams working on data analytics. As the client needs grow, scalable systems adapt without requiring complete overhauls. Now let's look at real world examples. During the pandemic, AI driven chatbots managed millions of COVID 19 related queries, reducing strain on healthcare systems. IoT based glucose monitors now send real time alerts to doctors and patients, preventing diabetic emergencies. These examples demonstrate how IoT and AI enhance healthcare outcomes while improving operational efficiency. Now, I'll hand it over to Ratesh to talk about some key takeaways. Thank you, Abhishek. To summarize, we can say that scalable infrastructure is essential for handling growing demands as The best practices like distributed data storage and automated training pipelines ensure system reliability and make your system future proof. AI and ML infrastructure empowers healthcare, just as it is providing to other domains of e commerce. And these providers help the patients, driving them with better engagement and outcomes. As a conclusion, we can, we'll say AI driven IoT is revolutionizing healthcare by making it more accessible, personalized, and efficient. Voice interfaces and proactive monitoring empowers patients while scalable system ensures healthcare providers can meet increasing demands. However, challenges like greater privacy, seamless integration, and service reliability need attention. By addressing these responsibilities, we can harness the full potential of these technologies to create a healthier, more connected future. Thank you for your time.