Signals, Volume 4, Issue 3
September 2023 - 10 articles
- Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Cover Story: In the field of biology, the classification of planktic foraminifera is an important task used to determine the quality of the environment that they are extracted from. For a long time, biologists have classified these organisms via direct observation under the microscope, but lately, AI has started to show promising results in automating this process. Deep learning has quickly become a booming research field with applications in a wide variety of computational tasks, and with our latest development, we took steps to improve the first convolutional neural network-based approach for foraminifera classification. We built an ensemble of CNNs trained on different versions of the same dataset by colorizing the black and white microscope pictures in distinctive and different ways, and the results have shown large improvements over the previously set baseline. View this paper