- Liver Disease and Transplantation
- Speech and Audio Processing
- Liver Disease Diagnosis and Treatment
- Network Security and Intrusion Detection
- Hepatitis Viruses Studies and Epidemiology
- Hepatitis B Virus Studies
- Emotion and Mood Recognition
- Speech Recognition and Synthesis
- Internet Traffic Analysis and Secure E-voting
- Amoebic Infections and Treatments
- Moringa oleifera research and applications
- Music and Audio Processing
- Software Engineering Techniques and Practices
- Digital Media Forensic Detection
- Stock Market Forecasting Methods
- IoT-based Smart Home Systems
- Context-Aware Activity Recognition Systems
- Face recognition and analysis
- Non-Invasive Vital Sign Monitoring
- Metabolism and Genetic Disorders
- Face and Expression Recognition
- Blind Source Separation Techniques
- IoT and Edge/Fog Computing
- AI in Service Interactions
- Video Surveillance and Tracking Methods
United International University
2023-2025
Independent University
2024
East Delta University
2023
United Hospital
2017
Bangabandhu Sheikh Mujib Medical University
2000-2009
A noninvasive diagnostic test for amebic liver abscess is needed, because and bacterial abscesses appear identical on ultrasound or computer tomography it rarely possible to identify Entamoeba histolytica in stool specimens from patients with abscess. Here we report a method of detection serum circulating E. Gal/GalNAc lectin diagnose abscess, which was used Dhaka, Bangladesh. The TechLab II (which differentiates the true pathogen dispar ) detected sera 22 23 (96%) tested prior treatment...
Fulminant hepatic failure (FHF) is a devastating complication of acute viral hepatitis, leading to death in most cases. The etiology and predictors outcome differ according the geographical region. This study was conducted with aim evaluating etiology, complications, FHF Bangladesh.In this prospective study, we included 67 consecutive cases presenting Department Hepatology, Bangabandhu Sheikh Mujib Medical University, Dhaka, between November 2003 May 2008. Thirty-nine patients were male 28...
Predicting the closing price of stock market with accuracy is highly uncertain and volatile. Deep learning (DL) can analyze vast amounts historical data to identify patterns correlations, aiding in predictive modeling. By from past behavior, deep algorithms potentially forecast future movements some degree accuracy. This research presents a hybrid Long Short-Term Memory (LSTM) Neural Network (DNN) model designed tackle complexities prediction, including volatility intricate patterns....
<b>Background/Aim:</b> Bangladesh is a densely populated country with intermediate endemicity for chronic hepatitis B (CHB). The aim of the present study was to evaluate biochemical, virological and histological character CHB patients examine relationship between these indices. <b> Materials Methods:</b> One thousand twenty-two fulfilled our inclusion criteria. Inclusion criteria were (1) HBsAg positive at least 6 months, (2) HBeAg-positive or negative (3) virus (HBV) DNA positive. Patients...
Ascitic fluid Complement 3 (C3) concentration is the most important factor to offer local defense against infection of ascitic fluid. Hepatic synthesis and its in significantly reduced patients with advanced cirrhosis. The aim study was assess level cirrhotic without spontaneous bacterial peritonitis (SBP) identify group ascites at risk developingA prospective case control carried out compare SBP (case-group) (control-group). estimated 15 (case) another (control).In study, 7.3+/-4.3 mg/dL...
Infant cry classification involves utilizing machine learning techniques to automatically recognize and categorize various types of infant cries. The goal using deep is develop a robust accurate system capable recognizing categorizing the different This technology can potentially assist healthcare professionals or caregivers in identifying underlying reasons for crying, such as hunger, discomfort, pain, etc., aiding prompt appropriate responses infant's needs. paper presents an innovative...
Amidst the global health crisis, importance of face masks persists as a crucial measure in mitigating contagious diseases. Wearing is advised comprehensive strategy to lessen transmission infectious and airborne Face are required for entry into many hospitals, offices, other establishments. The proposed Smart Surveillance System will assist identifying individuals who not wearing enforce this. To address this issue, we propose mask detection system that uses convolutional neural networks...
Background: Hyperbilirubinemia is a common problem in newborn. Most of the cases are benign but severe hyperbilirubinemia can lead to kernicterus and brain damage which preventable. The gold standard asses neonatal hyperbilirubinaemia serum bilirubin measurement. Unfortunately, this procedure invasive, painful time consuming. As consequence missing serious, there constant search find out safe method detect jaundice. Transcutaneous bilirubinometry offers objective assessing degree jaundice...
Speech Emotion Recognition (SER) is an act of recognizing human emotion and affective states from speech. This because voice often reflects underlying through tone pitch. recognition a component speech which gaining more popularity need for it increasing exceptionally. Our paper aims to use the Feedforward Neural Network recognize emotions unseen data (i.e., audio files) label them according range different using appropriate variables (such as modality, emotion, intensity, repetition etc.)...
Accent Variation Classification is the technique of detecting an accent or dialect a human speech based on patterns and features from speech. This useful in developing recognition systems, language learning preservation sociolinguistic studies, voice assistance, improving synthesis voiceover systems. It can be used conducting forensic analysis audio data to determine regional origin specific traits. Furthermore, it tool criminal investigations judicial actions. Deep Neural Networks (DNNs)...
Background : Magnesium (Mg++) deficiency is associated with poor glycemic control and Mg++ supplementation lowers blood sugar, improves insulin sensitivity delays diabetic complications such as nephropathy, neuropathy, retinopathy. Objective This study was designed to know the status of serum in type 2 subjects microalbuminuria normoalbuminuria.Methodology conducted at Department Laboratory Medicine (Clinical Pathology) collaboration BIRDEM General Hospital, Dhaka. In this study, magnesium...
Obesity is a global epidemic affecting people of all ages and genders. An imbalance between the calories consumed burned in energy primary cause this disease. To combat issue, researchers have developed an intelligent system based on supervised unsupervised techniques to detect obesity levels assist consumers healthcare professionals leading healthier lifestyles. Our proposed method uses public domain dataset, WISDM human activity recognition, 3-layered LSTM recognize physical activities...
Aims: In cirrhotic ascitic patients the rate of diuretic induced complications is high. Moreover, 5–10% do not respond to diuretics. Paracentesis safer. The current recommendation administer albumin at 6–8 gm/L fluid removed. But some studies show no survival benefit. Our aim confirm safety and effectiveness large volume paracentesis without on renal function make it a cost-saving alternative strategy. Methods: prospective randomized study was done 30 with ascites in Hepatology Department...