I am a PhD Student in the Biomedical and Health Informatics
program at Case Western Reserve University School of Medicine. My
research focuses on Biomedical Data Science, Medical Imaging
(X-ray, CT, MRI, and Histopathology), Explainable AI, Clinical
Informatics, Deep Learning and Machine Learning in Healthcare,
Signal Processing (EEG, ECG, and EMG). I'd really describe myself
as a person with a versatile skill set, a lot of integrity, and a
willingness to go the extra mile to conduct top-quality research.
I am not special or different, but I am very enthusiastic and
intensive to learn. you can say I am a hunger to acquire the
newish or renewed things. I am not only a dependable person who is
great at time management but also a creative person who always
thinking out of the box. I am very much decisive and persistent to
succeed in this competitive field.
kxm828@case.edu
Krishna Mridha, Masrur Ahsan Priyok, MD Rayhan Hussain Razu, Madhu Shukla, Manas Ranjan Pradhan, Biwaranjan Acharya,” Implementing a Heart Disease Prediction Model with Explainable Machine Learning Techniques” SN Computer Science [ACCEPTED]
Krishna Mridha, Ajoy Chandra Kuri, Trinoy Saha, Madhu Shukla, Ankush Ghosh, Rabindra Nath Shawb”, Interpretable Machine Learning for Cardiovascular Disease Diagnosis with Wearable Devices Multimedia Tools and Application [SUBMITTED]
Krishna Mridha, Masrur Ahsan Priyok, Madhu Shukla” Unraveling the Intricacies of EEG Seizure Detection: A Comprehensive Exploration of Machine Learning Model Performance Interpretability, and Clinical Insights” Multimedia Tools and Application [SUBMITTED]
Krishna Mridha, Suborno Deb Bappon, Dipayan Barua, Shahriar Mahmud Sabuj” ResCNet: An Explainable and Classification Model for Alzheimer’s Disease Using Residual Convolutional Neural Network” Diagnostics [SUBMITTED]
Case Western Reserve University School of Medicine, OH, USA
Marwadi University, Rajkot, Gujrat, India
Basically, this is an interesting application to detect the "Phishing URLs". Sometimes, stranger want to access the credentials of any users. For this reason, they have send so many URL link. This link may be contain abnormalities. So, this application is gonna help to identify those URL. This is the very first stage of this research . It's performance is not good at all. We are trying to increase the performance.
Breast Cancer currently affects and destroys most women. This is because breast cancer is the world's second-most deadly cancer. 12% of all current forms of cancer and 25% of all women's cancers are breast cancer. Tumors that can be cancerous are called the being out influence implementation of cells in an organ. Benign and malignant are two types of tumors that are available in the world.
This project predicts the admission of a student based on different features including university rating, student’s undergraduate GPA, GRE score, research experience and etc. This predicts that how many chances are there that the student will get admission to his selected university or not. Normally, students suffering from habitation what they should do.
Education is a very important issue regarding the development of a country. The main objective of educational institutions is to provide high-quality education to their students. One way to accomplish this is by predicting a student's academic performance and thereby taking early steps to improve student's performance and teaching quality.
We can make our Attendance Management System (AMS) intelligent by using a face-to-face recognition strategy. For that, we have to fix a CCTV camera at the classroom at any best point, which makes a person's picture at the fixed time and tests a face-to-face image. Traditionally, student attendance at the institutes is manually reported on the attendance sheets.
This is a really interesting automated forecasting
framework for every bank that offers a loan to
customers. The Company wants to automate the credit
eligibility process (real-time) based on the customer
information given when filling out the online
application form. This information includes gender,
marital status, education, number of dependents, wages,
loan size, credit history, and others.
The purpose of this project is to make accurate salary
predictions that are based on existing known salaries so
the company is able to recruit and retain top talent.
This model will help the company offer
Using a Data analysis technique, one can study a huge dataset and find deeper information, deeper patterns, deeper symptoms from the data, and predict outcome accordingly. The intension of this recitation is to scheme a unique model that can predict diabetes with maximum accuracy. In the existing method, the classification and prediction accuracy is not that high.
Machine Learning is a part of Artificial Intelligence.
In Machine Learning, there are many algorithms exist. In
this project usually I used Linear Regression to predict
the Air Flight Price. Even though we have many apps in
line through them we also can check the price but the
difference between this app and my model is this price
is select or modified by the author of the particular
airlines but my model can predict the price without any
modifications.
Using a Data analysis technique, one can study a huge dataset and find deeper information, deeper patterns, deeper symptoms from the data, and predict outcome accordingly. The intension of this recitation is to scheme a unique model that can predict diabetes with maximum accuracy. In the existing method, the classification and prediction accuracy is not that high.
descriptionMachine Learning is a part of Artificial
Intelligence. In Machine Learning, there are many
algorithms exist. In this project usually I used Linear
Regression to predict the Air Flight Price. Even though
we have many apps in line through them we also can check
the price but the difference between this app and my
model is this price is select or modified by the author
of the particular airlines but my model can predict the
price without any modifications.
Cardiovascular diseases (CVDs) are one of the leading
causes of mortality globally. Early and accurate
diagnosis is crucial for the effective treatment and
management of CVDs. In this study, we propose a machine
learning-based approach for CVD diagnosis using the
“cardiovascular disease dataset” obtained from Kaggle.
The dataset comprises 70,000 records of patient data,
including 11 features and a target variable. The
features are classified into three types: objective,
examination, and subjective. We implemented six machine
learning algorithms, and our results showed that
logistic regression performed better with an accuracy of
74%.
Driver drowsiness is a very common issue that can lead
to severe accidents on the road. According to studies,
drowsy driving is a factor in about 20% of road
accidents, with some estimates suggesting that the
number could be even higher. The consequences of drowsy
driving accidents can be devastating, including loss of
life, serious injuries, and significant property damage.
Drowsy driving is especially dangerous because it
impairs a driver's reaction time, decision-making
ability, and overall awareness of their surroundings.
People of all ages can contract pneumonia, a deadly
respiratory illness that is more common in
underdeveloped countries. For successful treatment and
higher survival rates, pneumonia must be accurately and
quickly diagnosed. While chest X-ray imaging is a
frequently used diagnostic technique for detecting
pneumonia, its interpretation can be arbitrary and
error-prone. In this study, we used a convolutional
neural network (CNN) architecture to construct a
computer-aided diagnostic system for pneumonia
identification in chest X-ray images.
In recent years, the application of deep learning
techniques for plant disease classification has become
increasingly important for smart agriculture. Early
classification and treatment of plant diseases are
crucial for maintaining the quality and quantity of
crops, and deep learning algorithms have the potential
to provide accurate and efficient solutions to this
problem. In this study, we used two datasets collected
from Mendeley for coffee leaf disease classification.
The first dataset contained two classes of images, while
the second dataset contained the remaining three types
of images. The two datasets were combined to create a
more robust dataset for training the two-transfer
learning and CNN model.
The past few decades have seen revolutionary
advancements in the field of Healthcare and Medicine.
During this period, the underlying reasons for many
fatal diseases have been unveiled, novel diagnosis
techniques were invented, and medical solutions were
developed. Instead of these breakthroughs, we are still
vulnerable and haunted by certain diseases like cancer.
Globally, cancer is the second most common cause of
mortality which accounts for the death of one in every
six affected individuals. Among many other types, the
colon and lung are the most prevailing and
life-threatening ones. Only these two variants are
responsible for 25% of all cancer cases around the
world. However, early lung and colon cancer detection
can significantly enhance the possibility of survival.
Electroencephalogram (EEG) and Electrocardiogram (ECG)
are electrical signals that reflect activities of the
brain and cardiac, respectively, based on which some
neurological disorders and mental status are determined.
In this paper, a novel set of temporal features like
energy, Shannon energy, entropy, and temporal energy,
all together along with machine learning-based
classifiers to identify the relaxing state of humans and
while performing mental tasks like arithmetic operations
using these signals are proposed.
The most fundamental input of the construction sector is
concrete, which would be a massively complicated
element. Concrete is among the most common structural
construction materials due to its strength. Since some
manufacturers manufacture out of reach and low quality,
there is a growing demand for earthquake-resistant
design in the fully prepared concrete industry.
Concrete's strength-gaining properties are influenced by
a variety of factors. This research aims to use the
results of early compressive strength tests to predict
strength properties at various ages. The ability to
estimate the determination and strength of normal
concrete using the early day strength properties result
has been examined.
Diabetes mellitus, commonly known as diabetes, is a
metabolic disease that causes high blood sugar. We all
know that the hormone normally passing through the blood
to our cells for gathered energy. Any Diabetes contains
unprocessed high blood that can damage our nerves, eyes,
kidneys, hearts, and other organs. In certain times,
there are a lot of people suffer or affected by diabetes
for the reason the people have to go to the diagnostic
center, hospital, or clinic for tests. So naturally, the
management has to store the required tests report and
provide a proper diagnosis based on them report. But the
rise in machine learning approaches solves this critical
problem.
Acoustic For a limited number of disorders, early
diagnosis of any illness may be curable to mankind's
commitment. Before it becomes chronic, most persons fail
to detect their illness. This adds to a global rise in
mortality rates. Breast cancer is one of the cancers
that can be treated until it progresses to all areas of
the body as the condition is diagnosed at early stages.
Breast cancer primarily affects women and it is also an
important factor in raising the rate of female
mortality. We are both mindful that the diagnosis of
breast cancer is very time-consuming.
We can make our Attendance Management System (AMS)
intelligent by using a face-to-face recognition
strategy. For that, we have to fix a CCTV camera in the
classroom at any best point, which makes a person's
picture at a fixed time and tests a face-to-face image.
Traditionally, student attendance at the institutes is
manually reported on the attendance sheets. It's not a
productive operation, because it takes 5 or more minutes
for attendance. Normally, the length of our class is 50
minutes, and every day we have more than 5
lessons.
Aug 2018 – Jun 2019
Employment Duration: 11
months
Location: Mirpur, Dahaka, Bangladesh.
Jul 2019 – Aug 2020
Employment Duration: 1 year 2
months
Location: Mirpur,Dhaka,Bangladesh
Take part in the IEEEXtreme Micro Volunteering Challenges i.e Micro Activities that excites you to be part of the IEEEXtreme team as an Ambassador
International MUN brings youth together from around the world to learn and share ideas from a diverse set of experiences and backgrounds in its offline & online Model United Nations conferences.
I have completed one internship where I worked as a campus ambassador. As a campus ambassador, I did many different works to increase the awareness of the program in my university, at a time that suits my schedule.
National Service Scheme, Popularly known as NSS is an
extension of activities to the higher education system
to orient the student youth to community service while
they are studying in education institutions, under the
aegis of Ministry of Youth Affairs & Sports, Govt.
of India.
Aenean tortor est, vulputate quis leo in, vehicula rhoncus lacus. Praesent aliquam in tellus eu gravida.
Very first day I have gotten on challenge. The challenge was a simple yet tricky classification problem. The problem was a basic image classification, which expected us to train a machine learning model to classify between various cloth patterns. The data was provided and consisted of a set of clean e-commerce images distributed in a balanced format under various classes.
I feel very proud to be a Machine Learning Intern of this famous organization. In this internship period, I completed my selected project name is "Stock Market Prediction" and completed my task successfully. My task was selected as an Outstanding Project.
I am very grateful to this institution for providing me a professional internship environment. Even though I am a 2nd-year student, I start my research career from here. I completed my project that name is Salary prediction based on jobs description with the help of machine learning approaches.
'Time and Tide wait for none" this sentence is not only sentence but also its carried huge meaning. our team mate at this internship are very kind and helpful. They help me a lot at any time and any kind of problem.
This internship is helping me a lot. This is my first internship in Machine Learning. From this internship, I learned more knowledge about Artificial Intelligence, Computer Vision, Deep Learning. Python Framework likes Flask, Django, Stramlit, and the Heroku server.
- Krishna Mridha
In an era defined by rapid technological advancements and an overwhelming influx of data, the archetype of a successful scientist has evolved significantly. "How to Be a Modern Scientist" by Jeff Leek offers a roadmap for navigating this new terrain. Through his book, Leek advocates for a blend of traditional scientific rigor and modern data science skills. This blog post delves into key takeaways from the book, emphasizing how they can revolutionize scientific practices.
Data literacy stands as the cornerstone of modern scientific research. Leek articulates that understanding data isn't merely about statistical calculations; it encompasses data management, interpretation, and clear communication. He insists that a modern scientist must be proficient in software tools that manage and analyze large datasets, apply complex statistical models, and visualize data effectively. This skill set enables scientists to extract meaningful insights from vast amounts of information, a capability that is now indispensable in most scientific inquiries.
Leek's book stresses the significance of open science—an approach that promotes accessibility, transparency, and collaboration in research. Open access to publications, sharing data freely, and using preprints to disseminate findings promptly are practices that enhance the reproducibility of scientific results and accelerate the advancement of knowledge. This shift towards openness is not only about accessibility but also about building a global community of researchers who can contribute to, and benefit from, shared resources.
With the power of data comes great responsibility. Leek dedicates a substantial portion of his book to the ethical dimensions of handling data. Modern scientists must navigate the complexities of data privacy, security, and ethical use. This involves understanding the legal implications of data use, ensuring the confidentiality of sensitive information, and conducting research that adheres to high ethical standards. These practices are crucial for maintaining public trust and integrity in scientific research.
Leek also emphasizes the importance of effective communication in the life of a modern scientist. This includes not only writing clear, accessible research papers but also engaging with non-scientific audiences through popular media, blogs, and public talks. Communication skills extend to the ability to craft grant proposals that persuade and to present findings in ways that resonate with stakeholders, funding bodies, and the general public.
The field of science is continually changing, and staying updated with the latest research methods, tools, and technologies is vital. Leek encourages a mindset of ongoing learning and adaptation. This could mean engaging with new statistical software, learning programming languages relevant to one’s field, or staying abreast of methodological advancements. The modern scientist must be a lifelong learner, always ready to incorporate new knowledge and techniques into their repertoire.
Jeff Leek's "How to Be a Modern Scientist" is more than a manual; it is a manifesto for rethinking the approach to scientific research in the 21st century. By fostering data literacy, embracing open science, adhering to ethical standards, honing communication skills, and committing to continuous learning, scientists can remain at the forefront of discovery and innovation. These practices not only enhance individual research but also propel the scientific community towards more collaborative, transparent, and impactful contributions to society