🎓🏫I have enlisted a few academic projects undertaken by me as a student at USC
💻📊📈Projects
🎓🧑🎓👩🎓 During my Master of Science in Computer Science (Data Science) at USC, I had the opportunity to work on a variety of academic projects that challenged me and expanded my knowledge in the field. 🤓💻📈 These projects allowed me to apply the concepts I learned in the classroom to real-world situations, and collaborate with classmates from diverse backgrounds. 💪🤝 The program's focus on both theoretical and practical aspects of data science equipped me with a well-rounded skill set. 🎯📊 I am grateful for the hands-on experience and the chance to work on cutting-edge technologies, and I am confident that the education I received at USC has set me up for success in my future endeavors. 🚀💼
Kernel Programming on Weenix OS🧑💻🐧
The CSCI 402 Operating Systems course at USC included a series of challenging kernel assignments which involved the implementation of various parts of a Weenix-based operating system. 🧑💻💡
These assignments provided hands-on experience in operating system design and implementation. 🤝💻 The assignments covered topics such as processes and threads, VFS layer and virtual memory and were implemented using C programming language and various debugging tools.
🛠️👨💻 These assignments helped students to gain valuable knowledge in system calls, process management, memory management, and file systems, as well as develop problem-solving skills and an understanding of the inner workings of an operating system. 🚀💡 This experience was a great addition to students portfolio and would be beneficial for their future endeavors. 👍📈
Emulation Based Distributed File System💾🌐
The EDFS (Emulation Based Distributed File System) project was 🔨 developed and tested using a large crime database 🕵️♀️ from Los Angeles, containing over 5 million records 📊 and 50 GB of data 💾. The goal of the project was to improve the efficiency of data retrieval ⚡.
Python libraries 🐍 such as pymysql, base64, streamlit, and numpy were utilized to implement the EDFS system. Streamlit was chosen as the front-end framework for its simplicity and ease of use compared to other frameworks like Django 🌐. As a result, the project achieved a 50% increase in data retrieval speed 🚀. The use of Streamlit allowed for an intuitive and user-friendly interface 🤖, making it easier for non-technical users 👥 to access the data stored in the EDFS.
This project showcases my skills in working with large datasets 📈, implementing complex algorithms 🤓, and developing user-friendly interfaces 🧑💻. It also demonstrates my ability to utilize the latest tools and technologies to achieve efficient and effective results 📈.
Kaggle Project for CSCI 567: Machine Learning🤖📈👨💻
🤖📈 As part of the CSCI 567 Machine Learning course at USC, a Kaggle competition was conducted with the objective of forecasting store sales using time series data. 🏪💰 The dataset, which was obtained from this link "https://www.kaggle.com/competitions/store-sales-time-series-forecasting", involved challenging time series data pertaining to store sales.
The competition involved competing with other class teams to achieve the best public score on Kaggle. 🥇🔝 Various machine learning algorithms were applied such as decision trees, and regression techniques like Ridge, Random Forest, Linear and XGBRegressor to develop the model.
🧐📊 In the final model, the best outputs were stacked together from different algorithms, which resulted in high accuracy and a final public score of 0.38212.
💯🎯 This score placed the team among the top 10 in the class, and first for the mid-term submission of the same when the public score was 0.39101. 🏆👏