The web application developed as part of the project can be accessed and used by anyone at the following URL: http://supercapacitor-battery-artificialintelligence.vistec.ac.th/.
I had the opportunity to work as a Research Assistant at Vidyasirimedhi Institute of Science and Technology (VISTEC) from 2021 to 2022. My role was to use artificial intelligence and machine learning techniques to build a model for classifying Cyclic Voltammetry and Galvanostatic Charge-Discharge behaviors of faradaic electrode materials used in energy storage research. We developed a web application using the Flask framework to provide an interactive channel for users to classify these behaviors as either battery or pseudocapacitor types. The goal of the project was to create a useful tool for researchers in the field, and the web application was made available as open source for anyone to access and use. It was a challenging but rewarding experience, and I was proud to have contributed to something that had the potential to make a significant impact in the field of energy storage research.
Convolutional Neural Networks (CNNs) are a type of neural network specifically designed for image recognition and processing. They are made up of layers of interconnected "neurons," which process and analyze the input data. In a CNN, the input data is typically an image, which is passed through several layers of processing. The first layer, known as the convolutional layer, applies a series of filters to the image to detect patterns and features. These filters are trained to recognize specific features in the input data, such as lines, edges, and shapes.
The output of the convolutional layer is then passed through a series of additional layers, which further process and analyze the data. These may include pooling layers, which downsample the data to reduce its complexity, and fully connected layers, which apply weights to the data to make predictions.
CNNs are particularly effective at image recognition tasks because they are able to automatically learn and extract the most important features from the input data. They have been used to achieve state-of-the-art results in a wide range of image classification
