Errors, Errors, Errors. We all hate them, don't we? Well, this week presented some of the most complex technical challenges I have faced so far, requiring a deep dive into data optimization, memory management, and ensuring seamless transmission of shot data to Firebase. Despite setbacks, it was a week filled with learning and problem-solving, pushing the iCue project forward. Class Session: Progress Review & Feedback The session this week focused on reviewing our progress so far. Sir Roshan conducted a feedback session, checking everyone's blogs to ensure they were up to date and providing constructive feedback. He was particularly impressed with my detailed documentation of iCue’s development, which reassured me that I was on the right track. He then asked me to visit Dr. Judhi to update him on my progress for the week. Project Progress: Capturing & Storing Shot Data Efficiently The main challenge this week was to optimise how iCue captures and transmits shot data. The objective was to collect sensor values one second before and after the shot to ensure that the cue stick action was accurately represented. This was done by trial and error. By setting certain thresholds and identifying the rapid acceleration and deceleration measured by the sensor while taking a shot, I was able to identify if a shot was taken or not. While the logic for detecting a shot with acceleration and deceleration thresholds was successfully implemented, sending the collected data to Firebase proved to be a significant challenge. Key Challenges & Solutions: Handling Large Data Sets:  Each shot generated 240 data points (40 values per axis for X, Y, and Z before and after the shot). Initially, storing these values in a list led to memory overflow, causing system crashes. Buffer Overflow Issues:  The continuous data collection resulted in the list consuming too much memory, leading to a bottleneck when transmitting to Firebase. The system could not efficiently manage the growing buffer, which disrupted the entire process. Memory Mapping & Optimization:  After extensive debugging, I restructured the memory allocation process to ensure proper data segmentation. Adjusting the way values were stored and limiting unnecessary operations significantly improved performance. Wi-Fi Transmission Optimization:  Another challenge was transmitting the large dataset over Wi-Fi in real-time. After several tests, I refined the data transmission method to ensure all values were sent without delays or loss. Despite these issues, I successfully optimized the data handling process, ensuring that shot values were accurately stored in Firebase. With this key milestone achieved, my next focus will be on app development and integrating it with the hardware in the coming weeks. Wireframes To make the mobile application development process smoother, I worked on creating wireframes of the app towards the end of this week, which I will use while developing the app next week. Reflection & Looking Ahead This week was a reality check on the complexities of handling real-time sensor data. I had initially expected the implementation to be straightforward, but the errors and debugging took much longer than anticipated. The biggest lesson was understanding how data storage and memory management play a critical role in embedded systems, especially when handling large datasets. While these challenges pushed the project slightly behind schedule, I chose to see this as an opportunity for deep learning rather than a setback. Debugging the system and seeing it finally work was an incredibly rewarding experience. Moving forward, I’ll be shifting my focus towards developing the mobile app, ensuring seamless integration between the hardware and software. With the hardware finally done,  I am now ready to integrate AI-driven analytics and real-time personalized training recommendations shown through the mobile application. This is just the start of something truly transformative in AI-powered billiards analytics . Onwards and upwards! 🚀

This week's session focused on research ethics, which is an important element of our final-year projects. During the session, Dr. Fehmida and Mr. Roshan emphasised the necessity of upholding strong ethical standards, particularly in projects involving human participants or external data collection. The seminar highlighted the numerous ethics forms we must complete to guarantee that our projects can move forward responsibly and without causing harm to anyone involved. For my project, iCue, I worked on completing the ethics screening and application forms, as I will require participants to test the device. The project is ethical as it does not require the personal information of the participants and does not harm anyone in any way. In addition, I modified key documents such as the Participant Information Sheet, Consent Form, and Debriefing Form according to my project requirements. These documents will be distributed to all participants to ensure that they are fully informed and that their participation is purely voluntary. These resources helped me grasp the responsibility that comes with conducting research with real users, and I now feel more confident in ensuring my project is ethical. Breaking Down iCue’s Technical Implementation While iCue may seem simple on the surface, the technical implementation requires a well-structured approach that integrates hardware, software, and AI models. Hardware Setup: Sensors & Data Collection The ESP32 microcontroller is the core of iCue, processing movement data captured by the MPU-6050 sensor attached to the cue stick. The MPU-6050 will collect the following data: Acceleration (to detect force and speed of the shot), Gyroscope values (to track angle and stability of the stroke), Motion Spikes (to determine when a shot is taken). Once collected, the ESP32 will transmit this data via Bluetooth to the mobile app for further analysis. Software & Data Flow: Processing & Storing the Information The software application will handle: Shot Detection & Data Filtering – Only capturing data when a shot is played, Cloud Storage (Firebase) – Storing all shot data for later ML model training, User Dashboard – Displaying shot history, accuracy trends, and training insights. AI-Powered Analysis: Machine Learning Model Once the shot data is collected, the Machine Learning Model will: Compare a player’s shot to a professional’s, Provide feedback on shot straightness and stability, Classify the player’s skill level (Beginner, Intermediate, Advanced), Recommend practice drills to improve accuracy. Work Breakdown Structure (WBS) To effectively manage my project, I worked on my Work Breakdown Structure (WBS) this week. This will help me divide the project into manageable phases, ensuring I stay on track. Below is the WBS: Work Breakdown Structure I also made a Gantt Chart to ensure that I deliver the project on time. Gantt Chart Reflection This week was not an easy week for me. While I was able to do the lab activities properly and complete my Work Breakdown Structure, I was not able to research much on the project and start with the formal project proposal. With my master's application entrance exam and the unfortunate passing away of my late grandfather (may his soul rest in peace), the project's progress came to a halt. Hopefully, I am able to bounce back and get back on track as soon as possible. Ethics Documents (Also in Document Uploads Section)

This week’s lectures focused on the fundamentals of software testing, covering essential concepts such as testing, verification, validation, and debugging. We explored different types of software tests, including: Unit Testing  – Testing individual components for functionality. Integration Testing  – Checking how different modules interact. Functional Testing  – Verifying if the software meets specified requirements. Regression Testing  – Ensuring new code changes do not disrupt existing features. System Testing  – Evaluating the complete system’s behavior. Acceptance & Installation Testing  – Assessing software usability before deployment. Top-Down vs. Bottom-Up Integration Testing  – Different approaches to integrating and verifying software modules. For my iCue project, I plan to implement unit tests for individual app components, integration tests for Firebase communication, and functional testing to ensure smooth user interaction with the app's dashboard and chatbot. Testing Hardware and Firebase Integration Beyond software testing, this week I conducted tests to verify the hardware's ability to send data to Firebase. This was crucial for ensuring that the MPU-6050 sensor and ESP32 module accurately capture cue stick movement and transmit shot data to the cloud. This involved: Sensor Calibration:  Checking the accuracy of the ESP32 and MPU-6050 sensor readings. Data Transmission:  Verifying that the shot data is correctly logged in the Firebase database. Dashboard Integration:  Testing if the collected data could be retrieved and visualized within the app’s dashboard. The tests were successful, confirming that the system is capable of logging and storing shot data for future analysis. Moreover, I performed Regression testing while fixing the buffer error to ensure that the other code was not affected by this change and the test was successful! Advancing iCue: Data Collection and App Development As part of refining iCue, I conducted real-world data collection by visiting the billiards room to capture shot data. By recording my own shots and those of my peers, I built a diverse dataset for analysis. Plotting the data revealed structured patterns, reinforcing the reliability of my approach. On the development side, I made significant strides: Dashboard Implementation  – Designed to display plotted shot data retrieved from the Firebase real-time database. Chatbot Integration  – Introduced a chatbot to provide personalized training recommendations based on recorded shots. Firestore Database  – Introduced a Firestore database that stores the most recent shot in the real-time database to the user's document for further analysis. Firebase Authentication  – Enabled Firebase Authentication that allows only the authenticated users to access the features of the app and memory storage. Profile Page and Information Section  – Still placeholders due to competition commitments, but planned for next week’s development. Additionally, Dr. Judhi, during our meeting, provided feedback on integrating shot feedback directly into the dashboard, which I plan to refine in the coming weeks. Moreover, the chatbot was not responding as expected, which I plan on fixing as well along with the UI. From Machine Learning Misfires to API Magic Earlier in the project, I started working on my own machine learning model to analyze shot data using Python and Random Forest algorithms. I extracted data from Firebase, cleaned it, and created structured arrays based on the sensor readings from the ESP32 and MPU-6050. However, despite all the effort, the model only achieved around 50% accuracy . The biggest challenge? A very small dataset . I had only eight real-world shots to work with, which made it impossible for the model to generalize well. The analysis revealed that a much larger dataset (ideally 100+ participants with at least 15 to 20 shots each) would be needed to make the model viable. Realizing the limitations, I pivoted toward a smarter approach: using a hybrid GPT-based model . This system now analyzes shot stability in real-time by computing a “fluctuation score” from the sensor data and combining it with quiz inputs to form a detailed prompt. GPT then generates personalized, coach-style feedback for the player. The result? Much more accurate and intuitive recommendations , with an estimated accuracy of 90% based on user feedback. This switch from a traditional ML model to an LLM-based method was a turning point in the project—and one that made the iCue experience far more intelligent and human-like. Competition Achievements and Insights This week also marked an exciting phase in my competition journey, where I participated in multiple prestigious competitions: MADA Marketing Competition Finals  – My team reached the finals, offering valuable insights into branding, market positioning, and strategic outreach. This experience of market research will be instrumental in shaping iCue’s future launch strategy. TAFU-BCS Award Submission  – Alongside my team (Afrin, Anushka, and I), we submitted our research project, RoboBees, which focuses on using robotics for bee conservation and enhanced pollination techniques. The submission process helped refine our research methodology. Abu Dhabi Research Competition Submission  – I officially submitted iCue under the Innovation Category, aiming to establish it as a market-ready product. My preparation involved refining the pitch deck, validating research components, and structuring the business feasibility aspects of iCue. My team also submitted RoboBees under the Research Category for the competition. Emirates Robotics Competition:  Our team had made it to the finals and this week marked our trials before the competition. Applying months of robotics development and problem-solving experience. The competition pushed us to refine our approach to designing and optimizing autonomous systems. Looking Ahead This week’s progress has been a significant step forward, bringing iCue closer to being a polished and market-ready training tool for billiards players. With successful testing and competition experiences shaping the development of iCue, my next steps involve: Implementing real-time shot feedback within the dashboard. Completing the profile and information pages to enhance user experience. Further refining the chatbot for more advanced training recommendations. The blend of rigorous testing, hands-on data collection, and competition participation this week has provided invaluable experience, further motivating me to refine iCue into a fully functional and marketable product. Below are the submissions for the competitions if you want to have a look :)

This week marked the final week of university classes — an emotional yet fulfilling milestone in our academic journey. In our last session with Sir Roshan, we had a detailed feedback discussion on our reports. He was genuinely impressed with mine and commended the depth and clarity of the content. He also provided us with valuable viva presentation tips, outlining what should be included in our slides, how to structure our presentation, and how to manage time effectively during the session. We also received our official viva schedules, which made everything feel all the more real! Project Progress On the iCue front, I dedicated the entire week to finalizing my report, presentation, and blog for submission. Everything is now polished and ready, Alhamdulillah, the project has gone exactly as planned and was successfully completed on time. It’s been a journey of growth, learning, and resilience, and I couldn’t be more proud of how far it has come. Here are the final product snapshots and pictures. 🏆 Competition Victory: A Perfect Ending This week was also incredibly special and celebratory for another reason. My team and I were thrilled to win First Place and Best Poster Award in the Recycling Manipulator Robot category of the Third Edition of Emirates Robotics Competition! Out of 100+ teams, we advanced to the finals among 26 teams, and then emerged as champions. I had the honour of leading this wonderful team while balancing my final-year project deadlines. A heartfelt thank you to my teammates — Shamshul, Habeeba, Nimrah, and Maheen — for their tireless efforts and unstoppable spirit. Of course, none of this would have been possible without Dr. Judhi’s incredible support and mentorship throughout the journey. This win truly feels like the perfect finale to our Bachelor’s degree — a moment of pride and gratitude that I will always carry with me. Reflection This week was emotional, celebratory, and deeply fulfilling. From completing my final project to winning a major competition, every late night and tough challenge felt worth it. Seeing iCue come to life and end on such a high note gives me confidence as I take the next step in my journey. Alhamdulillah for the success. I’m immensely grateful for everyone who supported me along the way. Special gratitude to Dr. Judhi Prasetyo for everything over the years. Thank you, Sir!! 🎥 Here’s a short demo video of the iCue project! If you read this entire blog, you're a real one 💪🏽Thank you so much, and I hope this project has inspired you in one way or another. See you at the top!! 🚀 Final Project Report (Also in Document Uploads Section)

This week, I had my final meeting with Dr. Judhi, where I presented my nearly completed project report for review. He was overall happy with the structure and content, and his positive feedback was very encouraging. We also discussed the user testing results from last week, including the feedback from over 25 testers. Dr. Judhi was impressed by the system’s performance and the overwhelmingly positive response from users. To help me prepare for the final viva presentation, he provided some excellent tips on how to structure my explanation, focus on key talking points, and anticipate questions. I’ll be spending the upcoming weekend polishing the report for submission and starting my viva practice sessions based on his advice. He also advised me to continue working on this project later and take it forward by participating in pitching competitions first, which I intend to do after the viva and submissions are over.

This week’s meeting with Dr. Judhi was a little different — instead of our usual sit-down, we took it to the billiards room for a more hands-on session. Dr. Judhi himself became one of the testers for iCue, taking five shots to evaluate the system’s performance in a real environment. After reviewing the analytics and recommendations generated by the system, he expressed that he was very satisfied with the results, especially with how the feedback aligned with his shot patterns. It was great to see the system perform smoothly and meet expectations in a live testing scenario. Following the demo, I also updated him on my report progress, showing the current draft of my literature review and engineering analysis. Dr. Judhi advised me to wrap everything up by early next week, so I have enough time left to proofread the report and prepare for the viva properly. This timeline will help ensure the deliverables are polished and ready to go. Overall, it was a productive and validating meeting. The project is shaping up well!

This week, we didn’t have any scheduled lectures as it was the Eid holidays — so first, Eid Mubarak  to everyone who celebrated! 🎉 The break gave me a much-needed breather and some dedicated time to focus on polishing my project deliverables. First Half: Literature Review & Engineering Analysis Locked In During the first half of the week, I focused heavily on my final report, particularly solidifying the Literature Review and Engineering Analysis chapters. I revised my citations, cross-checked sources, and ensured both chapters aligned with the system architecture and development work I’ve done so far. Having this portion of the report finalized has been a big relief and gives me a solid foundation to move forward. Second Half: Real-World User Trials Begin! Once I was back on campus, I immediately moved into one of the most exciting (and slightly nerve-wracking) phases of the project: User Trials and System Testing. Since I had already completed unit, integration, and functionality testing through the development stages of the project, it was time to test iCue in a real-world environment — the billiards room. Day 1: Kick-off & Setback On the first day of testing, I had around 10 users, including Dr. Judhi himself, try out the iCue system. The feedback was fantastic, and everything was going smoothly… until the 3D-printed mount accidentally fell and broke mid-session 😅. But no panic — I rushed to the RoboTechX lab, re-printed a new mount, and had it ready by the next morning. Day 2: Mount V2 & More Testers With the newly printed mount securely attached, I returned to the billiards room and continued the user trials. This time, I had 15 additional testers, all of whom provided insightful feedback and helped stress-test the system under various shot styles and player skill levels. 📊 User Trial Highlights Here are some of the key findings from the user testing: Ease of Use:  92% of testers said the system was “very easy to use” and praised the simplicity of the UI. Shot Analysis Accuracy:  90% of users felt that the real-time feedback was smooth and aligned with their actual shots, although a few noted slight inconsistencies during very fast strokes. Training Value:  The personalized coaching recommendations   were a big hit! Most testers mentioned they would definitely use the system regularly for practice. 💡 Suggestions for Improvement Some excellent ideas came out of these sessions too, which I’ll be noting for future development: Reduce the device size  for better portability. Add automatic foul detection  and ball tracking. Integrate start/stop detection  with ball potting. Introduce an online leaderboard  or ranking system. Include tutorial-style guidance  based on shot history. Reflection This week has been one of the most productive so far. From academic writing to real-life feedback, everything felt like it came together. Seeing people genuinely enjoying iCue and giving constructive suggestions has made the months of development totally worth it. Now that the system and acceptance testing is complete, the next step is to incorporate what I can from the feedback, and power through to the final stages! 💪 Our team was also gearing up for the Emirates Robotics Competition Finals next week. The progress and preparation look pretty decent, and we are confident that we will perform great next week. Hoping for the best! 🤞

As part of my final year project, I researched how wearable sensors and AI feedback can enhance training in cue sports like billiards and snooker - areas that have traditionally lacked the technological advancements seen in other sports. The goal was to develop a low-cost system, iCue, that can track player motion, provide real-time feedback, and support long-term improvement through analytics. From Mirrors to Motion Sensors Historically, players have used basic tools like mirrors or laser pointers to check stroke alignment. These tools, while helpful for beginners, do not capture nuanced motion data or offer performance tracking (Nguyen et al. , 2021). The development of compact inertial sensors - like the MPU-6050, which combines a gyroscope and accelerometer - has enabled accurate real-time tracking of six-axis movement. These sensors are now common in sports wearables, VR applications, and robotics (Random Nerd Tutorials, 2022). Existing Cue Sport Tools Some cue training devices have emerged over the years: DigiCue  is a cue-mounted IMU sensor that vibrates to warn users about flawed stroke mechanics. It's simple and unobtrusive but doesn't provide session logs or improvement metrics (Billiard Warehouse, 2021). DigiCue BLUE  adds Bluetooth connectivity and a mobile app to view shot data such as acceleration, stroke smoothness, and follow-through (OB Cues, 2023). DrillRoom  uses smartphone cameras and AI to visualize shot angles and table layout. While technically impressive, it requires stable lighting and careful calibration, limiting casual use (DrillRoom, 2023). AI in Sports Coaching AI and machine learning (ML) have revolutionized training in sports like tennis, golf, and basketball. For instance: Zepp Tennis and Golf  use sensors and AI to assess swing type, power, and follow-through, showing measurable improvements in form over time (The Guardian, 2014). ShotTracker  uses sensors on basketballs and players to track accuracy and performance in real time (Designboom, 2014). Academic studies have confirmed that AI-based coaching improves consistency and reduces training duration in sports such as rowing, table tennis, and athletics (Wang et al. , 2021; Saponara & Giannetti, 2020). 💡 How iCue Fits In The iCue system brings these benefits into cue sports by combining: A low-cost MPU-6050 IMU  to capture cue stick motion An ESP-WROOM-32  module for wireless communication A React Native app  that delivers real-time insights Firebase  to store session data and enable cloud syncing Unlike camera-based systems, iCue works in any environment, requires no external setup, and supports real-time, personalized feedback through threshold-based analysis (ElectronicsHub, 2021). 📊 Table: Cue Sports Training Tools Comparison Tool Motion Tracking Analytics AI Feedback Mobile App Price DigiCue Yes (IMU) No No No ~$99 USD DigiCue BLUE Yes (IMU + BT) Yes No Yes ~$129 USD DrillRoom No (Camera only) Yes Limited Yes $200+ iCue Yes (MPU-6050) Yes Rule-based Yes <$50 USD Conclusion Cue sports still lag behind other sports in training innovation. While systems like DigiCue and DrillRoom have paved the way, they either lack feedback depth or are too environment-sensitive. iCue fills this gap by offering a low-cost, portable system that combines motion tracking, real-time alerts, and a cloud-connected mobile interface, making smart coaching accessible to all. 📚 References Billiard Warehouse (2021) DigiCue Training Aid . Available at: https://www.billiardwarehouse.com/accessories/digicue.html  (Accessed: 9 March 2025). Designboom (2014) ShotTracker wearable basketball analytics . Available at: https://www.designboom.com/technology/shottracker-wearable-technology-basketball-11-23-2014/  (Accessed: 9 March 2025). DrillRoom (2023) AI-powered snooker training . Available at: https://drillroom.ai/  (Accessed: 9 March 2025). ElectronicsHub (2021) Introduction to ESP32-WROOM-32 Module . Available at: https://www.electronicshub.org/introduction-to-esp32-wroom-32/  (Accessed: 9 March 2025). Nguyen, T. M. et al. (2021) ‘A review of inertial sensor-based motion capture systems’, Sensors , 21(15), pp. 1–22. Available at: https://www.mdpi.com/1424-8220/21/15/5281  (Accessed: 9 March 2025). OB Cues (2023) DigiCue BLUE Mobile App Overview . Available at: https://sites.google.com/view/digicueblue/home  (Accessed: 9 March 2025). Random Nerd Tutorials (2022) MPU-6050 with ESP32 and Arduino . Available at: https://randomnerdtutorials.com/esp32-mpu6050-accelerometer-gyroscope-arduino/  (Accessed: 9 March 2025). Saponara, S. and Giannetti, F. (2020) ‘Wearable sensors for AI-based sports coaching: A review’, IEEE Access , 8, pp. 137586–137601. Available at: https://ieeexplore.ieee.org/document/9144915  (Accessed: 9 March 2025). The Guardian (2014) Zepp Tennis sensor review . Available at: https://www.theguardian.com/technology/2014/jul/14/zepp-sensor-tennis-raquet-mounted-app-review  (Accessed: 9 March 2025). Wang, J. et al. (2021) ‘AI-based technique analysis in rowing using inertial sensors’, Sensors , 22(4), pp. 1–15. Available at: https://www.mdpi.com/1424-8220/22/4/1307  (Accessed: 9 March 2025).

Guest Speaker Session: Learning from Experience This week, we had the opportunity to hear from Keenan, a Middlesex University alumnus and former Computer Systems Engineering student. His guest lecture provided valuable insights into tackling final-year projects, from overcoming challenges to refining problem-solving approaches. With our own projects nearing submission, his journey served as a strong reminder of the importance of persistence and adaptability. Beyond academics, Keenan shared his career progression, illustrating how navigating different roles and industries helped him grow professionally. His passion for continuous learning was inspiring, reinforcing the idea that success is built on curiosity and the willingness to embrace new challenges. Intellectual Property and iCue’s Future Following the guest session, we explored key topics in intellectual property, including copyrights, trade secrets, patents, and trademarks. Given my long-term goal of launching iCue as a commercial product, understanding these legal protections is crucial. Ensuring that iCue's innovations—such as its training feedback system and AI-driven shot analysis—are safeguarded will be an essential step when transitioning from a research project to a marketable application. Project Progress: Refining iCue and Finalizing Features I am excited to announce that the app is almost ready!! 1. Enhancing Chatbot Accuracy This week, I presented the latest updates on iCue's mobile application. A key focus was refining the chatbot, which provides personalized training recommendations based on shot data. Dr. Judhi pointed out that its responses needed improvement due to suboptimal prompt structuring. As a result, I optimized the chatbot’s prompts to generate more precise and relevant recommendations. 2. Animation and UI Improvements I also introduced a tutorial page with animations to guide users through iCue’s features. While the animations were effective, there was feedback regarding unclear rotation directions. To address this, I will add an arrow indicator, ensuring better visual guidance. 3. Shot Data Storage and Analysis The profile page was enhanced to display stored shot data, allowing users to track their progress over time. Initially, this section lacked an in-depth analysis, so I incorporated textual feedback similar to what is available on the dashboard. Furthermore, I proposed a comparison feature that enables users to evaluate their performance over multiple sessions—an addition that was well received and marked as a priority before moving on to user testing next week. 4. Completing Development With these refinements, iCue’s development phase is now complete. The next step involves rigorous testing and evaluation to ensure functionality, user experience, and accuracy align with my initial vision. Below is the video of the app functioning. A Week of Reflection: CEI Next Steps Event This week was an emotional one as we attended the CEI Next Steps Event, a farewell gathering for final-year CEI students as we prepare to join the alumni community. It was a day filled with reflection, gratitude, and a sense of accomplishment. I had the immense privilege of receiving the Ambassador Award for the engineering batch—an honor given to individuals who have made significant contributions across academics, extracurricular activities, and university-wide initiatives. Winning the most prestigious award of the batch was truly humbling, and it reinforced my commitment to continuous learning and leadership beyond university life. After the event, we gathered for Iftar with my classmates, a moment of unity and celebration. Looking back at our journey, the day was a profound reminder of how far we have come, the friendships we have built, and the impact we have made. It is a memory I will cherish forever. Looking Ahead: Testing and Optimization With iCue’s core functionality completed, the next phase will focus on user testing, refining the user experience, and ensuring seamless performance. These final refinements will be critical in making iCue a robust, market-ready solution for billiards training. Stay tuned for further updates as I move into the final testing and evaluation stages!

In the world of sports training, technology is redefining how players improve their skills. iCue is at the forefront of this transformation, integrating AI-driven analytics to help billiards enthusiasts refine their techniques and enhance their gameplay. Designed for both amateurs and professionals, iCue provides real-time feedback and performance insights, making practice sessions more effective and engaging. Let’s explore how iCue aligns with key training methodologies, leveraging AI, biomechanics analysis, and real-time data tracking to revolutionize billiards training. 1. AI-Powered Motion Analysis Precision and consistency are crucial in billiards. iCue’s advanced AI algorithms analyze cue stick movement to detect subtle errors in alignment, stroke consistency, and shot execution. How iCue Enhances Training: Tracks gyroscopic and accelerometer data using an ESP32 and MPU-6050 sensor. Detects deviations in shot execution and provides actionable insights. Uses AI-driven recommendations to help players correct their stance and stroke. With iCue, players receive instant feedback, allowing them to refine their technique in real-time. 2. Data-Driven Performance Tracking Traditional billiards training often relies on subjective assessment. iCue introduces an objective, data-driven approach by recording shot metrics and performance history. How iCue Optimizes Training: Stores historical shot data for detailed performance analysis. Identifies patterns in errors and strengths over multiple practice sessions. Allows users to set personalized goals and track improvements over time. By utilizing a structured approach to skill development, iCue ensures consistent progress for every player. 3. Personalized Coaching Through AI Chatbot Beyond data analytics, iCue features a built-in chatbot designed to answer user queries related to billiards techniques, rules, and shot performance. How iCue’s Chatbot Adds Value: Provides instant responses to common billiards-related questions. Offers shot-specific recommendations based on performance data. Assists players in understanding advanced techniques through interactive learning. This AI-powered assistant transforms the learning process, making knowledge easily accessible for all players. 4. A Dedicated Profile Page for Player Insights To enhance user engagement, iCue includes a profile page where players can view their complete shot history, performance analytics, and personalized training insights. What the Profile Page Includes: A log of previous shot data and accuracy trends. Customizable training goals and improvement tracking. Access to personalized AI-driven feedback for skill refinement. With iCue’s holistic approach to training, users can track their journey from amateur to professional with a comprehensive performance dashboard. iCue Competes in the Innovation Category of the Abu Dhabi University Research Competition 2025! Exciting news! On March 22, 2025, I officially submitted iCue to the prestigious Abu Dhabi University Research Competition under the Innovation category. This marks a significant milestone in my journey to revolutionize billiards training through AI and data analytics. iCue is more than just a training tool—it’s a step toward making billiards training smarter, more accessible, and backed by science. The competition submission involved refining the core methodologies, integrating user feedback, and showcasing how iCue’s AI-driven approach can redefine sports training and market analysis on how to make iCue a successful business venture in the future. Participating in this competition is a fantastic opportunity to present iCue to a broader audience and demonstrate its potential impact in the sports technology space. Regardless of the results, this experience has been invaluable, offering insights, networking opportunities, and motivation to push iCue even further. A big thank you to my mentor, Dr. Judhi Prasetyo, and Middlesex University Dubai for their continuous support! Looking forward to what’s next for iCue! 🚀🎱 My submission paper can be found below and also on the 'Documents' page. Stay tuned for more updates and fingers crossed for the competition results 🤞🏼 !

This week’s session by Sir Roshan focused on coding and debugging, which could not have been more relevant given the issues I was tackling in iCue. Debugging follows a structured process: reproducing the bug, locating the issue, identifying the root cause, implementing a fix, and testing the solution. I followed this exact approach when I encountered a recurring memory error in my system. Through careful debugging and analysis, I pinpointed the issue to inefficient memory handling and implemented a circular buffering technique to resolve it. This ensured that shot data could be transmitted and stored in Firebase without overwhelming the buffer, making the system more stable and efficient. We also explored different debugging techniques, including brute force, backtracking, forward analysis, cause elimination, static analysis, dynamic analysis, collaborative debugging, and logging and tracing. In my case, I primarily relied on logging and tracing to monitor the execution flow and identify where memory issues were occurring. This approach helped in narrowing down the problem and testing solutions systematically. Events: Empowering Innovation & Leadership This week was packed with exciting events, starting with Digital Alchemy: Transforming Ideas into Scalable Ventures, which I had the pleasure of hosting and organizing. This event was particularly special because it marked the official launch of the Youth Startup Program Club, where I am a founding member and advisor. It was inspiring to see entrepreneurs coming together to talk about how they turned their ideas into successful businesses. The event fueled my motivation to take iCue beyond a project and shape it into a successful business venture. The program itself is a testament to empowering youth like me to become founders and entrepreneurs. Additionally, we celebrated International Women's Day, where I had the privilege of being a speaker as a Student Council Member. I highlighted how MDX LENS and all student-led societies play a role in promoting gender equality and creating an inclusive university environment. It was an honor to contribute to such an important discussion. Project Progress: Mobile App Development & UI Foundation While debugging took a significant portion of my time this week, I was also able to make progress on the mobile application for iCue. Initially, I had planned to develop the app using Unity, but after further research, I decided to switch to React Native with TypeScript. This decision was based on several advantages: ✅ Cross-Platform Development:  React Native allows for seamless development on both iOS and Android without requiring a MacBook for iOS compatibility, which was a limitation I faced with Unity. ✅ Optimized for Mobile UI:  Unlike Unity, which is more suited for game development and desktop applications, React Native provides a more fluid and native mobile experience, making it a better fit for iCue’s application. ✅ Faster Development Cycle:  React Native’s component-based structure allows for quicker iterations and better scalability as new features are added. With the new tech stack finalized, I started working on setting up the core screens and navigation of the app. Core Screens & Navigation Building a strong foundation is key to any great application, and that’s exactly what I am focusing on with iCue. The initial layout ensures a clean, intuitive UI, setting the stage for further development and integration with the hardware system. Sign-In & Sign-Up Screens The first step into iCue begins with an accessible login experience. Users can sign in using their email and password, with authentication powered by Firebase Authentication. The Sign-Up screen follows a smooth onboarding process, allowing new users to register with essential details such as their name, email, and password. This authentication system is already functional and seamlessly connects to Firebase. Landing Page & Dashboard Once signed in, users arrive at the iCue Dashboard, which will serve as the central hub for their training progress. Currently, I have completed the landing page UI, which provides an overview of the app’s features. The dashboard will eventually incorporate real-time shot analysis and personalized feedback based on the data collected from the ESP32 and MPU-6050 sensors. There will also be a chatbot page where users can ask general queries about billiards or their shots. There will also be a profile page that will have all the previous shot data of the user along with their details. Quiz Page To enhance user engagement, I started working on a quiz page that will prompt users with billiards-related questions after each training session. This feature aims to reinforce theoretical knowledge alongside practical training. While the UI has been implemented, the quiz responses are not yet connected to Firebase. Integrating this functionality is a priority for the coming weeks. A Clean Approach Each screen is built as an independent component, following best practices in React Native development. This modular approach ensures: ✅ Scalability: Future features can be added without breaking existing functionality. ✅ Efficiency: Optimized performance through reusable components. ✅ Maintainability: Clear structure for debugging and future enhancements. Responsive Layouts for a Seamless Experience While iCue is focused solely on mobile development, the UI is designed for a smooth and adaptive experience: 📱 Optimized for mobile screens: Ensures consistent performance across different smartphone sizes. 📱 Smooth interactions: Implemented using SafeAreaView, KeyboardAvoidingView, and ScrollView for an intuitive user experience. Reflection & Looking Ahead This week was a turning point in both debugging the hardware system and making key decisions for the mobile application. Resolving the memory issue with circular buffering was a significant milestone, ensuring stable shot data collection and transmission. The switch to React Native was another critical step, aligning iCue’s development with a framework that is more suited for mobile applications. Now that the foundational UI is in place, my next focus will be on integrating the quiz responses with Firebase, refining the dashboard, and ensuring seamless data exchange between the hardware and app. The journey ahead is exciting, and with each challenge overcome, iCue moves closer to becoming a polished, innovative billiards training tool! 🚀

This week, Dr. Judhi advised me to visit the billiards room to collect real shot data by playing a game of billiards and storing all recorded values for analysis. I was able to gather data from my own shots as well as those taken by my friends, providing a varied dataset. After visually plotting the results, Dr. Judhi was pleased to see that the data was structured well enough for further analysis. On the development front, I worked on creating the app’s dashboard, designed to display plotted shot data retrieved from the Firebase storage database. I also implemented a chatbot to offer personalized training recommendations based on recorded shots. While the profile page and the information section explaining the data visualizations and tutorial remained placeholders due to my competition submissions this week, I showcased the remaining progress to Dr. Judhi. He suggested integrating shot feedback directly into the dashboard for a better user experience, which I plan to implement next week along with the remaining application pages. Aside from the project, some of my meetings this week with Dr. Judhi focused on competition submission guidance. One notable submission was for the TAFU-BCS Award, where my team, consisting of Afrin, Anushka, and I, submitted our research project, RoboBees , which aims to revolutionize bee conservation and improve pollination lands. Dr. Judhi and Dr. Engie mentored us, providing valuable feedback that we incorporated into our final submission, which we are truly thankful for. Additionally, we adapted the project into a research paper for the Abu Dhabi Research Competition, where Dr. Judhi helped refine and strengthen our research further. I also submitted iCue under the Innovation category for the same Research Competition, as I aim to develop it into a marketable product in the future. Dr. Judhi encouraged me to apply and provided insightful suggestions to refine my pitch deck and documents for the submission. Towards the end of the week, we also went to our trials for the Emirates Robotics Competition, where Dr. Judhi was our group's mentor. He guided us throughout our project over the past few months and continues to guide us as we approach our competetion date in the next few weeks.