Space Enthusiast, Computer Science student

github

Meet Bhatt  • Peerlist

Developed an Operating Systems project consisting of four interactive modules, each implemented with Python and Streamlit for real-time visualization and simulation. Optimal Page Replacement: Built a visualization tool for simulating optimal page replacement algorithms, demonstrating page faults and memory management. Producer-Consumer Problem: Implemented a monitor-based synchronization model using threading and queue operations to simulate real-time data production and consumption. SRTF Scheduling: Designed a Shortest Remaining Time First CPU scheduling simulator with CSV/manual input options, Gantt chart generation, and performance metrics like average waiting and turnaround time. SSTF Disk Scheduling: Created a Seek Time First disk scheduling algorithm simulator with graphical representation of head movements and total seek operations. This project deepened my understanding of OS concepts like memory management, process synchronization, CPU scheduling, and disk management through practical implementation.

OS Simulations

Using K-means clustering, this project analyzes a dataset provided by Dr. Kristen Gorman and the Palmer Station, Antarctica LTER, aiming to classify penguin species based on morphological features such as culmen length, culmen depth, flipper length, body mass, and sex. Despite lacking species labels, the project successfully identifies distinct clusters corresponding to Adelie, Chinstrap, and Gentoo penguins, contributing to our understanding of Antarctic wildlife populations and aiding conservation efforts.

Arctic Penguin Exploration: Unraveling Cluste

🌱 Delighted to share an intriguing project at the crossroads of agriculture and technology! In collaboration with a team of machine learning experts, multi-class classification models were developed to aid farmers in optimizing crop selection based on soil metrics. By scrutinizing factors such as nitrogen, phosphorous, potassium levels, and pH values, accurate predictions regarding the best crops for each field were made. Notably, the analysis highlighted the single most crucial feature for predictive performance, furnishing farmers with valuable insights to enhance yield and sustainability. This project underscores the potential of data-driven methodologies in transforming traditional farming practices. #MachineLearning #AgriculturalTech #PrecisionAgri 🌾🚜