In the CASS project, I am automating the real-time visualization of the status of devices belonging to customers in different countries through Grafana, instead of manual checks. I collect device data using Docker, Prometheus, and Python technologies, presenting it in Grafana with graphs to quickly identify and address issues. Additionally, I write optimization scripts in Python for error management and establish test automation using Selenium Testing to enhance device performance. This infrastructure increases efficiency and operational performance in Nokia's device management.

We are developing an AI-powered platform to accelerate patent drafting processes by automating the generation of claims and description texts through the upload of invention disclosure forms, technical content, and visuals. Additionally, we use chatbot-based AI to determine engineering alternatives and protection strategies, while developing AI models that extract technical information from visuals for text generation. We are also designing a flexible and user-friendly "Add-in" module for integration into Word.

Within the scope of the Predictive Maintenance Application Project, it is planned to develop AI-based models for anomaly detection and fault prediction by analyzing sensor data from industrial systems. The project aims to optimize deep learning algorithms such as RNN, LSTM, and GRU using time series data and design a user-friendly interface. Once completed, the project is expected to predict critical faults in advance, minimizing unplanned downtimes and maintenance costs.

During my data analyst internship, I gained essential skills in data analysis, processing, visualization, and exploratory analysis. I performed data mining and statistical modeling using Python. Additionally, I enhanced my teamwork and effective communication skills, increasing my ability to collaborate on data projects. This experience strengthened my analytical thinking abilities and provided a solid foundation for my career as a data analyst.