Saira Akram@Sakram

Microscopy is central to biology and neuroscience research; however, manually analyzing thousands of cell images is time-consuming, inconsistent, and prone to human error. Our project, Bio AI: Smart Microscopy Assistant, addresses this challenge by leveraging state-of-the-art deep learning models such as Cellpose and StarDist to automatically segment, count, and analyze cells, nuclei, or organelles from uploaded images. The platform provides robust features, including morphology metrics (size, shape, intensity, eccentricity), batch processing for large datasets, and export options to CSV or Excel for downstream analysis. Deployed via Hugging Face Spaces with a simple Gradio/Streamlit interface, Bio AI ensures accessibility for researchers without programming expertise. By reducing hours of manual work to minutes, the assistant improves reproducibility, scalability, and accessibility of microscopy analysis. Future extensions include disease detection, cancer diagnostics, and drug testing automation, making this tool a high-impact solution for labs, hospitals, and universities.

Problem Statement: People with motor disabilities struggle to use digital devices. Voice commands are slow, and existing hardware solutions are expensive. 💡 Solution: An AI-powered eye-tracking cursor using IBM Granite Vision Transformer to enable hands-free control of PCs and smartphones with just eye movements and blinks. 🚀 Key Features: ✅ Gaze-Based Cursor Movement – Move the cursor by looking around. ✅ Blink to Click – Short blink for left-click, long blink for right-click. ✅ Gaze Scrolling – Look up/down to scroll pages and reels. ✅ Real-Time AI Adaptation – Model learns user-specific gaze patterns. ✅ No Extra Hardware Needed – Works with a standard webcam.

DietDeep is an AI-powered meal planner that personalizes dietary recommendations based on user goals and meal images. It utilizes DeepSeek-R1 for meal plan generation, a pretrained YOLOv10 model for food classification, and the USDA API for nutrition data. Users enter dietary goals, upload meal images, and receive customized meal plans with portion sizes and nutritional values. The system intelligently combines detected food items with nutritional data to create well-balanced meals. Built with Streamlit for an interactive UI, DietDeep aims to simplify healthy eating using AI, making personalized nutrition accessible and efficient for individuals with diverse dietary needs.

Vision Care AI simplifies appointment scheduling for both patients and eye care practitioners. The platform streamlines the booking process, allowing patients to easily find and schedule appointments based on their availability and location. For practitioners, it optimizes their schedules, reduces no-shows with automated reminders, and efficiently allocates time slots. By bridging the gap between patients and providers, Vision Care AI ensures a smoother, more efficient workflow, enhancing the overall eye care experience. AI-powered scheduling for efficient, personalized eye care appointments for everyone.

Vision Guard is an innovative wearable device designed to protect and enhance eye health in the digital era. With the increase in screen time, many people experience digital eye strain, leading to discomfort and potential long-term issues. Vision Guard proactively addresses this by continuously monitoring eye health, detecting early signs of strain, and offering personalized insights through a companion app. Key features include real-time monitoring for eye strain, blue light filtration, environmental adaptation (adjusting based on light levels and air quality), and guided eye exercises to reduce tension and improve resilience. Vision Guard’s AI-driven algorithms provide users with tailored health insights and lifestyle adjustments to optimize eye health. Through its companion app, Vision Guard provides a daily dashboard showing key metrics such as screen time, blue light exposure, and breaks taken. It also offers personalized recommendations for eye-friendly screen settings and long-term health reports, empowering users to adopt sustainable eye care habits.

Artificial Intelligence and Generative AI have increasingly become the must-have technologies for businesses to increase revenue, reduce costs, and stay ahead of the competition. This is even truer for companies that rely on modern contract management technologies to manage their business agreements. Traditionally, contract management relied heavily on manual processes, with legal teams spending countless hours drafting, reviewing, and negotiating contracts. These methods, while effective, were often laborious, inefficient, and susceptible to human error. However, today, we bring you our AI Contract Assistant, a Generative AI Tool that can be used to negotiate contracts more efficiently, reducing time and money for enterprise sales teams, small business owners, startup entrepreneurs, or anyone who reads and signs a contract. We use the Upstage Document Parser API to extract text from PDFs and Word Documents, and we are using Llama 3.1 through TogetherAI to extract specific clause information from the extracted text. Clauses such as pricing information, term length, rights and exceptions, etc., can be extracted from lengthy contracts within seconds. We then send each clause into a specific AI Agent driven by CrewAI and to the RAG tool by Composio. Each AI Agent is trained on the specific contract language of that clause and gives a simplified analysis and recommendation for furthering the negotiation. The recommendation is based on an existing repository of standard contracts. On the front end served by Streamlit, the user can decide to Negotiate, Accept, or Reject each clause. If they choose to negotiate, they are asked to input their negotiation points. Using Llama 3.1, the system will draft a response email to the counterparty who provided the contract, indicating which clauses were accepted and rejected with recommendations and indicating which clauses have negotiation points to be negotiated further. Our current prototype is compatible with NDAs only.

Transform your meetings into actionable insights with MinuteMind! Leveraging the power of watsonx.ai, MinuteMind transcribes meetings, analyzes the discussions, and generates precise summaries with action items tailored to each participant. This AI-driven tool ensures that no key point is missed, and follow-up tasks are clearly defined and delivered straight to your inbox. Whether you're a busy professional, a project manager, or a student, MinuteMind helps you stay on track and turn every meeting into a productivity booster. MinuteMind is more than just a meeting transcript tool; it's your key to unlocking the full potential of every meeting. Boost your productivity, ensure accountability, and achieve remarkable results with this innovative AI-powered solution.

DefendX is an AI-powered cybersecurity solution focused on safeguarding edge devices by detecting and mitigating security threats like unusual login activities, background-running malware, and abnormal traffic at routers. Leveraging cutting-edge technologies such as Llama, Phi3, and Streamlit, DefendX offers real-time anomaly detection and threat analysis tailored for edge environments. Llama's robust natural language processing and Phi3's advanced machine learning algorithms enable the model to efficiently recognize and respond to potential security breaches. Integrated with a user-friendly Streamlit interface, DefendX provides seamless interaction, allowing users to easily monitor and address threats while ensuring optimal device performance and data privacy.

Join the Internet of Agents Hackathon to build real-world, rentable agents using Coral Protocol and Solana-powered payments. 📅 September 14–21, 2025 Sept 14–21: Build online with global innovators. Submit projects by the deadline. Sept 20 (NYC): On-site build day at Solana Skyline (invitation only). Sept 21 (NYC): Live pitches, networking, and winner announcements. 🧠 Mentorship from experts and Coral specialists throughout. 🤝 Participate solo or in teams. 📍 Travel and accommodation not covered. 🚀 Sign up now to secure your spot before the Kick-Off Stream!

This is your chance to push boundaries, solve real-world challenges, and create impact at the official hackathon of the RAISE Summit 2025 at one of Paris's most iconic venues: Le Carrousel du Louvre. 📅 July 4–8, 2025 — Collaborate online with a global community of innovators. 🏛️ July 8–9, 2025 — Limited on-site access to the RAISE Summit in Paris (300 participants), exclusively for selected teams. 🏆 July 9, 2025 — Winners will be announced live on stage during the RAISE Summit. 🌟 Expert mentors will guide you throughout your hackathon journey. 🤝 Work solo or build your dream team to create something extraordinary. 💰 Compete for a share of up to $150,000 in prizes. 🔒 Sign up before the Kick-Off Stream to secure your spot!

Drive efficiency, automation, and innovation by streamlining workflows and integrating seamless processes. ⏳ You have 48 hours to complete the challenge and compete for prizes. 🚀 Learn and build AI solutions with IBM Granite. 💡 Create impactful solutions that drive smarter business operations. ⭐ Gain expert guidance throughout the hackathon. 🤝 Collaborate or work solo to bring your ideas to life. 💰 $10,000 prize pool for the winners! 🧑🏻‍💻 Sign up before the Kick-Off Stream and start shaping the future with IBM Granite!