My research has always centered on the field of health using two independent directions:
Prevention through developing new technologies to protect the environment,
Treatment by developing new technologies for new drugs or diagnostic/therapeutic medical devices.
As a summer research assistant at the Electrical and Computer Engineering department, I am currently engaged in an exciting project involving the analysis of two datasets: “Solar wind” and “SuperMAG.” My primary role as a machine learning researcher is to develop a robust predictive model that can effectively handle the challenges posed by noisy time series data. To accomplish this, I am employing a combination of deep learning and traditional machine learning algorithms.
The objective of my research is to enhance the accuracy and reliability of predictions by leveraging the power of advanced techniques in machine learning. By working with these datasets, I aim to uncover meaningful patterns and insights that can contribute to our understanding of solar wind behavior and its impact on various aspects of our environment.
Through my work, I strive to improve upon existing models by implementing innovative approaches and methodologies. This involves carefully preprocessing the data to handle noise and developing novel feature engineering techniques to extract valuable information from the time series. Additionally, I am exploring cutting-edge deep learning architectures, such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs), to effectively capture temporal dependencies and spatial patterns within the data.
By combining the strengths of deep learning and traditional machine learning algorithms, I hope to create a predictive model that not only performs well in terms of accuracy but also provides insights into the underlying dynamics of the solar wind phenomena. This research has the potential to contribute to advancements in renewable energy, space weather prediction, and other related fields.
In nonlinear optics, our focus was on the thermal effects of lasers on nonlinear crystals. Laser production using nonlinear crystals is much more efficient and cheaper than previous laser production methods. But the problem is that due to the absorption of laser light in the nonlinear crystal, the temperature of the crystal rises too high, and the crystal burns. By discovering the mechanism of heat generation and propagation in nonlinear crystals, we help the manufacturers of these lasers to prevent premature burning of these crystals, thus significantly reducing the maintenance cost of these lasers. These lasers have a variety of applications in industry, such as medicine, diagnosis, and evaluation of air pollutants.
- Treatment Impact: (in medical lasers)
With proper use, lasers allow the surgeon to accomplish more complex tasks, reduce blood loss, decrease postoperative discomfort, reduce the risk of wound infection, and improve wound healing.
- Prevention Impact Through Environmental conservation: (in air pollution monitoring lasers)
Rayleigh scattering laser radiation is elastically scattered from atoms or molecules with no frequency change. Several remote sensing instruments are used to measure pollutants.
