ilyaskarimov’s Site

Hello. I will talk about the progress that has taken place in 2 weeks. While drowning in the search for medical topics, a lecture on Monday COVID-19 came to our aid. Although the subject is analyzed statistically, Dr. Sagdeev's presentation gave us the idea of predicting the virus through Machine Learning. Since the issue was new and we had not arranged a meeting with the Professor's team, we had to think about a new topic as we would not be able to present that topic for initial briefing.  After thinking for a while with my teammate, we focused on a topic that I also suffer a lot from. This was to study the impact of people's emotions on their success by reading their emotions in the classroom through cameras. Thus, the goal was to help professors treat students individually, and in addition to students working hard, to determine their moods and to what extent they influenced their success.  Emotion detection projects are pre-executed, and in those projects the dataset is a single, pre-captured human image(s). The first part is finding facial landmarks in human images. It was used to detect the nose, eyes, mouth, and face. Once these landmarks are detected, it becomes possible to detect people's emotions by finding the Euclidian distance. Using these images, the url, distances, and labels of that image are written to the .csv file. Examples of these data are AffectNet, Ascertain, FER-2013, Google Facial Expression Comparison Dataset, EMOTIC, K-EmoCon. Our project differs from others in that the goal here is not to capture individual people, but to detect emotions as a group. Here it will be a video sequence, not a static image. We wanted to take into account not only the video, but also the sound of the students from the classroom. One of the problems is that it can be a little difficult to separate those voices because the classroom might be chaotic sometimes. In addition, based on the feedback we received from professors, I can say that it may be difficult to reach the desired point of this project in that dedicated period.

First of all, we talked about qualitative and quantitative research, which I remembered from our first lesson. Then we talked about Natural Langauge Processing and Sentiment Analysis in the analytics section. Our last lecture focused on Machine Learning. Additional lectures were given by the Recurrent Neural Network and the Long-Short Term Memory. The lecture was informative, but I think we could understand better if the practical part was also explained.

As for the data part, first of all I would like to talk about the areas of my interest. Although much of Computer Science is interesting, I think choosing a topic related to Computer Vision will force me to acquire new knowledge. Because I love medicine, I am interested in the topics that will unite these parts. To do this, I looked at the Kaggle website, taking the professor's advice. There are Datasets and Competitions in that section. The first one I found was a Brain MRI segmentation contest, the pictures were store in .tif format and I think the images looked poor quality. According to Professor Kaisler, if a tumor is to be detected on images, it will be important to improve the quality of the pictures first. Then I was looking for cancer detection.  This can be extra work for me, because there are so many pictures. The first thing I found were breath cancer datasets. The data here were limited, there were 58 histopathological images but I would say their quality was better than the first. For now, I am researching topics, and when choosing a topic, I need to make sure that it is in demand in any field of application in my country.

For now, I am researching topics, and when choosing a topic, I need to make sure that it is in demand in any field of application in my country as well. Surely, when choosing a topic, as Professor Pless said, I will try to make sure that the data is ready in advance so that it does not take time to collect data again.

P.S. I started reading Research Methodologies, and although I haven't made much progress yet, I think I'll do it in the coming weeks.

I'm going to summarize everything I learned over the first week. I'll write this section based on what I comprehended during lectures, rather than what I read outside of lecture. 

First and foremost, it was apparent from the start that we needed to pick a topic. Although selecting a topic appears to be a simple task, I discovered that there are other factors to consider. Before you begin, make sure you have the following information. Before we go through these stages, we need to answer certain basic, yet innovative, and essential questions developed by DARPA, and these questions are a method of achieving our objectives. 

In addition, I knew that we would conduct study, which is more than just theory. At the end of the day, we must have a working system to give over, along with the documentation document.

When it came to picking a topic, I discovered that the most important factor to consider was data accessibility. If we want to develop a system that identifies lung cancer, for example, we should use pictures of healthy and malignant lungs that are freely available on the Internet. Because obtaining that data necessitates the utilization of time, authoritative individuals, and resources.

As a result, it is important to examine trustworthy sources, such as Kaggle contests themselves, before deciding on a topic.

I recall the professor saying that documentation is highly essential and that using diagrams within is recommended. Finally, while selecting a topic, as I learnt here, it is critical to go through each step carefully and ensure that our responses match the criteria we set for ourselves.

I’m Ilyas Karimov, a master's student in Computer Science and Data Analytics. Here’s brief information about me. 

Since I can remember, I've been a tech nerd. I've been interested in technology since I was four years old, and I began playing the piano at that age.

In computer science, I have been and still am interested in related projects that link medicine to this field. Data Science is the second area of focus. So far, I've completed some data science-related research that has been published in the IEEE. Game development is another fascinating field. I created a game for a small business that is available on the App Store and Google Play Store.

Aside from computer science, I'm a big fan of psychology. I enjoy looking for old studies and reading all of the conditions and outcomes of its application. I even conducted some mock-up psychological study on my own. In addition, I am passionate about leadership and project management, and at work, I oversee two teams of five and thirty employees.

I, like many others, am fascinated by art. In addition to playing the piano, I dabble in painting and occasionally sing. Margaret Keane's Big Eyes is one of my favorites.

Welcome to your brand new blog at GW Blogs.

To get started, simply log in, edit or delete this post and check out all the other options available to you.

For assistance, visit our comprehensive support site, check out our Edublogs User Guide guide or stop by The Edublogs Forums to chat with other edubloggers.

You can also subscribe to our brilliant free publication, The Edublogger, which is jammed with helpful tips, ideas and more.