Shams Nafisa AliBangladesh University of Engineering and Technology | BUET · Department of Biomedical Engineering
Shams Nafisa Ali
Bachelor of Engineering
About
33
Publications
26,998
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
411
Citations
Introduction
I am a biomedical engineer with a wide range of research interests. As an active member of the mHealth Research Group, I am currently working to introduce AI-assisted data-centric problem-solving methods on different domains of healthcare informatics. Experimenting with optimized neural network architecture primarily in the domain of physiological sound (heart sound, respiratory sound) analysis, fascinates me. In future, I would like to explore the intersection of Biomaterials, Robotics and ML.
Education
February 2017 - May 2022
Publications
Publications (33)
Listening to lung sounds through auscultation is vital in examining the respiratory system for abnormalities. Automated analysis of lung auscultation sounds can be beneficial to the health systems in low-resource settings where there is a lack of skilled physicians. In this work, we propose a lightweight convolutional neural network (CNN) architect...
The alarmingly high mortality rate and increasing global prevalence of cardiovascular diseases signify the crucial need for early detection schemes. Phonocardiogram (PCG) signals have been historically applied in this domain owing to its simplicity and cost-effectiveness. In this paper, we propose CardioXNet, a novel lightweight end-to-end CRNN arc...
Rapid and precise diagnosis of COVID-19 is one of the major challenges faced by the global community to control the spread of this overgrowing pandemic. In this paper, a hybrid neural network is proposed, named CovTANet, to provide an end-to-end clinical diagnostic tool for early diagnosis, lesion segmentation, and severity prediction of COVID-19 u...
Cellulose is a versatile material with multiple derivatives and numerous composites. Owing to great biocompatibility, biodegradability, light weight, ample chemically modifying capacity, actuation capability, and eco-friendly nature of cellulose, nowadays natural resource-based renewable cellulosic biopolymers are being major contributors in the fa...
The recent monkeypox outbreak has become a public health concern due to its rapid spread in more than 40 countries outside Africa. Clinical diagnosis of monkeypox in an early stage is challenging due to its similarity with chickenpox and measles. In cases where the confirmatory Polymerase Chain Reaction (PCR) tests are not readily available, comput...
Cardiac auscultation, an integral tool in diagnosing cardiovascular diseases (CVDs), often relies on the subjective interpretation of clinicians, presenting a limitation in consistency and accuracy. Addressing this, we introduce the BUET Multi-disease Heart Sound (BMD-HS) dataset - a comprehensive and meticulously curated collection of heart sound...
The recent ‘Mpox’ outbreak, formerly known as ‘Monkeypox’, has been a significant public health concern and
spread to over 110 countries globally. The challenge of clinically diagnosing mpox early on is due, in part,
to its similarity to other types of rashes. Computer-aided screening tools have been proven valuable in cases
where Polymerase Chain...
Diagnosis of Ocular toxoplasmosis (OT) usually involves clinical examination and imaging, which can be expensive and require specialized personnel. The use of artificial intelligence (AI) to analyze fundus images for diagnosing ocular diseases is gaining traction. Despite that, there has not been much work done focusing on the detection of OT. To a...
Object orientation programming is a standard practice for ease of working in large-scale projects, The definition of the core concepts of OOP with examples are provided in the presentation.
The recent 'Mpox' outbreak, formerly known as 'Monkeypox', has become a significant public health concern and has spread to over 110 countries globally. The challenge of clinically diagnosing mpox early on is due, in part, to its similarity to other types of rashes. Computer-aided screening tools have been proven valuable in cases where Polymerase...
Ocular Toxoplasmosis (OT), is a common eye infection caused by T. gondii that can cause vision problems. Diagnosis is typically done through a clinical examination and imaging, but these methods can be complicated and costly, requiring trained personnel. To address this issue, we have created a benchmark study that evaluates the effectiveness of ex...
p>Objective: The heart sound signals captured via a digital stethoscope are often distorted by environmental and physiological noise, altering their salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels which degrades the diagnostic performance. In this study, we present a novel...
Objective: The heart sound signals captured via a digital stethoscope are often distorted by environmental and physiological noise, altering their salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels which degrades the diagnostic performance. In this study, we present a novel d...
Rapid blood infusion is a life-saving technology during an emergency or a surgical intervention. Since blood banks preserve whole blood by refrigerating at (1-6)°C, to avoid hypothermic shock, it is suggested to infuse the blood into the body at a temperature of 37°C, the homeostatic core temperature of the human body. However, existing solutions a...
p>The heart sound signal captured via a digital stethoscope is often corrupted with environmental and physiological noise, altering its salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels. In this study, inspired by the heart sound’s quasi-periodic nature, we present a novel d...
p>The heart sound signal captured via a digital stethoscope is often corrupted with environmental and physiological noise, altering its salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels. In this study, inspired by the heart sound’s quasi-periodic nature, we present a novel d...
p>The heart sound signal captured via a digital stethoscope is often corrupted with environmental and physiological noise, altering its salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels. In this study, inspired by the heart sound’s quasi-periodic nature, we present a novel d...
This study aims to analyze the impact of the structure of a cryoprobe tip on the transient thermal phenomenon that takes place during cryoablation of breast cancer. A 2D axisymmetric breast model with an embedded tumor has been constructed using COMSOL Multiphysics ® interface. Three different tip structures (conical, spherical, cylindrical) have b...
Covid 19 is a global pandemic. Different companies are trying to develop vaccines to cope with this. Covid Vaccine production involves different vaccine technologies. Messenger RNA (mRNA) based technology vaccine is one of them. The COVID vaccines from Pfizer-BioNTech and Moderna utilize this technology to create their vaccines. This presentation i...
The alarmingly high mortality rate and increasing global prevalence of cardiovascular diseases (CVDs) signify the crucial need for early detection schemes. Phonocardiogram (PCG) signals have been historically applied in this domain owing to its simplicity and cost-effectiveness. In this paper, we propose CardioXNet, a novel lightweight end-to-end C...
Rapid and precise diagnosis of COVID-19 is one of the major challenges faced by the global community to control the spread of this overgrowing pandemic. In this paper, a hybrid neural network is proposed, named CovTANet, to provide an end-to-end clinical diagnostic tool for early diagnosis, lesion segmentation, and severity prediction of COVID-19 u...
Listening to lung sounds through auscultation is vital in examining the respiratory system for abnormalities. Automated analysis of lung auscultation sounds can be beneficial to the health systems in low-resource settings where there is a lack of skilled physicians. In this work, we propose a lightweight convolutional neural network (CNN) architect...
Pneumonia is one of the most acute respiratory diseases having remarkably high prevalence and mortality rate. Chest X-ray (CXR) has been widely utilized for the diagnosis of this disease owing to its availability, diagnostic speed and accuracy. However, even for an expert radiologist, it is quite challenging to readily determine pneumonia opacity b...
Social media platforms have become one of the primary mediums of communication nowadays. Along with communication, they are currently being utilized in a wide range of activities like digital marketing, customer care, e-learning etc. The unceasing use of social media is generating gigantic amount of textual data everyday. It is essential to properl...
In this study, a real transient therapeutic heating situation has been simulated for analyzing and comparing the effect of gender-divergent tissue distribution on the thermal
distribution profile in the interior of male and female knee joint. 3D geometric models of the knee joint have been constructed using SolidWorks® on the basis of the cross-sec...
In this work, a fully-functional prototype of a
wristworn device has been developed for detecting convulsive
epileptic seizure. A 3-risk factor based detection scheme employing accelerometer derived muscle spasm, PPG acquired heart rate
variability and body temperature variation has been proposed
by utilizing the distinctive change in the patterns...
In this work, a fully-functional working prototype of a low-cost smart E-pants has been designed and developed for preventing pressure ulcers. Smart E-pants are able to redistribute the excess pressure formed under the bony prominences of immobile patients by stimulating the gluteal muscles upon detecting exposure to prolonged pressure exceeding th...
The slide contains an overview of an Epileptic Seizure Detection System developed by us, which:
1) Is wearable, light weighted, low-cost and easy to use
2) Effectively detects seizure events with the consideration of 3-risk factors, i.e., convulsion, heart rate variability and body temperature
3) Notifies the nearby people regarding the health ris...
Pneumonia is one of the most acute respiratory diseases having remarkably high prevalence and mortality rate. Chest X-ray (CXR) has been widely utilized for the diagnosis of this disease owing to its availability, diagnostic speed and accuracy. However, even for an expert radiologist, it is quite challenging to readily determine pneumonia opacity b...
In this paper, the goal is to develop Smart E-pants which are
- Light weighted, wearable, washable, low cost, easy to use
- Effectively redistribute prolonged pressure
- Ensure better tissue oxygenation
- Eliminate the need of constant caregiver and frequent repositioning
- Mimic natural human fidgeting mechanism
The hidden skillset within an individual determines how elegantly and efficiently an activity can be done by him or her. That skillset regarding academic results and technical performance paves the way to future opportunities in career building. Furthermore, one's opinions and productive mindset are also influenced by that expertise and competence...
Questions
Questions (3)
Hello everyone!
I am working with a comparatively small audio dataset for classification task. I was searching for a means to ensure robust performance and thus, came across the following paper [1] that performed test-time augmentation on the test set. The test-time augmentation includes four procedures: augmentation, prediction, dis-augmentation and merging as follows:
First, the test images are augmented (rotation, flip) as done on the training set. Prediction is performed on both the original and the augmented images, then they revert the transformation on the obtained predictions (dis-augmentation). Merging can be done by employing the majority voting criterion with several additional steps.
I am confused regarding the dis-augmentation and the merging steps in case of time-frequency representation of audio signals (spectrograms, scalograms). Is this method applicable for time-frequency representation of audio signals? If any of you can enlighten me in this regard, that will be really helpful. Thanks in advance!
[1] Moshkov, N., Mathe, B., Kertesz-Farkas, A. et al. Test-time augmentation for deep learning-based cell segmentation on microscopy images. Sci Rep 10, 5068 (2020).
Hi,
I am planning to work on a in-house mixed audio dataset, consisting of several speakers. Can anybody suggest me what deep learning strategy should I consider for separating the speakers?
Thanks in advance!
Hello everyone!
I am looking for a PCG dataset of congenital heart disease afflicted patients for one of my undergraduate course projects. I have already explored the PASCAL, PhysioNet/CinC 2016, Michigan databases, but none of them seem to contain the congenital heart disease based annotation. I will be very thankful if anyone recommends where I can get such dataset.
