A5066799557- Sparse and Compressive Sensing Techniques
- Network Security and Intrusion Detection
- Image and Signal Denoising Methods
- Advanced Malware Detection Techniques
- Advanced MRI Techniques and Applications
- Brain Tumor Detection and Classification
- Advanced Image Processing Techniques
- AI in cancer detection
- COVID-19 diagnosis using AI
- Quantum-Dot Cellular Automata
- Quantum Computing Algorithms and Architecture
- Photoacoustic and Ultrasonic Imaging
- Medical Imaging Techniques and Applications
- Low-power high-performance VLSI design
- Text and Document Classification Technologies
- Adversarial Robustness in Machine Learning
- Remote-Sensing Image Classification
- Spam and Phishing Detection
- Fuel Cells and Related Materials
- Electrocatalysts for Energy Conversion
- Cutaneous Melanoma Detection and Management
- Advanced Image Fusion Techniques
- Artificial Intelligence in Healthcare
- Radiation Dose and Imaging
- Security in Wireless Sensor Networks
Dhaka University of Engineering & Technology
2019-2024
University of Canberra
2016-2024
UNSW Sydney
2012-2024
UNSW Canberra
2012-2024
Charles Sturt University
2015-2024
National Institute of Neurosciences & Hospital
2019-2023
Princess Alexandra Hospital
2023
Rajshahi University of Engineering and Technology
2022
University of Dhaka
2015-2020
Bangabandhu Sheikh Mujib Medical University
2019-2020
CuO/ZnO composites are synthesized using a simple mechanochemical combustion method. X-ray diffraction (XRD), scanning electron microscopy (SEM), energy-dispersive spectroscopy (EDX), and Fourier transform infrared (FTIR) used to characterize the prepared oxides. reveals that exhibit wurtzite ZnO crystal structure composed of CuO ZnO. The strong peaks Cu, Zn, O elements exhibited in EDX spectrum. FTIR spectra appear at around 3385 cm−1 1637 cm−1, caused by O–H stretching, 400 590 ascribable...
Tannery wastewater contains large amount of chemical compounds including toxic substances. So an attempt was made to characterize physiochemical parameters tannery and investigate the efficacy, applicability biological treatment utilizing aquatic plants macrophytes algae. Total suspended solids TSS total Dissolved solid in original were found 1250 mg/l 21300 respectively. The pH temperature 8.3 29°C. Oxygen (DO), Biological Demand (BOD) Chemical (COD) 2.72 mg/l, 4464 12840 Electrical...
TiO2 nanofluids with water-ethylene glycol (EG) as base fluid can be used coolants in proton exchange membrane (PEM) fuel cells. The high electrical conductivity of these potentially suppress the performance PEM Hence, it is important to accurately predict their before considering them for use 0.05-0.5 vol% concentrations (as suggested by earlier studies) were selected study experimentally range 20-70 ˚C (i.e. operating condition a cell). Increasing nanoparticles concentration causes...
Magnetic Resonance Imaging (MRI) is an important diagnostic technique for early detection of brain Tumor and the classification from MRI image a challenging research work because its different shapes, location intensities. For successful classification, segmentation method required to separate Tumor. Then features are extracted segmented that used classify In this work, efficient multilevel developed combining optimal thresholding watershed followed by morphological operation Convolutional...
'Khoyer' is prepared by boiling the wood of Acacia catechu in water and then evaporating resultant brew. The hard material powdered chewed with betel leaves lime or without tobacco a large number people Bangladesh as an addictive psycho-stimulating euphoria-inducing formulation. There are folk medicinal claims that khoyer helps relief pain also useful to diabetic patients maintain normal sugar levels. Thus far no scientific studies have evaluated antihyperglycemic antinociceptive effects...
Brain tumors are critical neurological ailments caused by uncontrolled cell growth in the brain or skull, often leading to death. An increasing patient longevity rate requires prompt detection; however, complexities of tissue make early diagnosis challenging. Hence, automated tools necessary aid healthcare professionals. This study is particularly aimed at improving efficacy computerized tumor detection a clinical setting through deep learning model. novel thresholding-based MRI image...
Federated Learning (FL) allows users to collaboratively train a global machine learning model by sharing local only, without exposing their private data central server. This distributed is particularly appealing in scenarios where privacy crucial, and it has garnered substantial attention from both industry academia. However, studies have revealed vulnerabilities FL, adversaries can potentially infer sensitive information the shared parameters. In this paper, we present an efficient...
Brain tumors are devastating and shorten the patient’s life. It has an impact on physical, psychological, financial well‐being of both patients family members. Early diagnosis treatment can reduce patients’ chances survival. Detecting diagnosing brain cancers using MRI scans is time‐consuming requires expertise in that domain. Nowadays, instead traditional approaches to tumor analysis, several deep learning models used assist professionals mitigate time. This paper introduces a stack...
In this paper, the effect of operating temperature on optimal purge interval for maximum energy efficiency in a proton exchange membrane fuel cell (PEMFC) with dead-ended anode (DEA) was experimentally investigated. The study conducted focus challenges associated operation at temperatures lower than recommended designed temperature. With DEA, gradual voltage drop happens due to accumulation water and impurities such as nitrogen. Hence, periodic purging side is required remove excess that are...
Undoped and B/Sn-doped ZnO nanoparticles are successfully produced by a simple mechanochemical method, characterized XRD, FTIR, EDX, SEM, XPS BET techniques. The XRD studies reveal that the prepared possess hexagonal wurtzite structure of ZnO. presence various functional groups (–OH, –CH, Zn–O) observed FTIR. It is clear from EDX analysis B, Sn, Zn O elements present in nanoparticles. SEM images confirm relatively smooth surface results indicate B Sn doped into matrix. photocatalytic...
Chronic kidney disease (CKD) is a progressive condition characterized by the gradual deterioration of functions, potentially leading to failure if not promptly diagnosed and treated. Machine learning (ML) algorithms have shown significant promise in diagnosis, but healthcare, clinical data pose challenges: missing values, noisy inputs, redundant features, affecting early-stage CKD prediction. Thus, this study presents novel, fully automated machine approach tackle these complexities...
Classifying user emails correctly from penetration of spam is an important research issue for anti-spam researchers. This paper has presented effective and efficient email classification technique based on data filtering method. In our testing we have introduced innovative
Melanoma skin cancer is one of the most dangerous and life-threatening cancer. Exposure to ultraviolet rays may damage cell's DNA, which causes melanoma However, it difficult detect classify nevus mole at immature stages. In this work, an automatic deep learning system developed based on intensity value estimation with a convolutional neural network model (CNN) more accurately. Since levels are distinctive features for object or region interest identification, high-intensity pixel values...
Bangla handwriting recognition is becoming a very important issue nowadays. It potentially task specially for speaking population of Bangladesh and West Bengal. By keeping that in our mind we are introducing comprehensive handwritten character dataset named BanglaLekha-Isolated. This contains numerals, basic characters compound characters. was collected from multiple geographical location within includes sample variety aged groups. can also be used other classification problems i.e: gender,...
A doctor needs to know the patients’ medical history investigate root cause of symptoms. Traditionally it is done by a questionnaire at clinic’s reception desk, or asks series questions obtain relevant history. An incomplete wrong affects doctor’s decision. The challenge for busy all in short period time accurately and without missing any important Affordable clinics employ an assistant junior sort out paper-based mark points. It increases doctors’ work performance saving doctors making room...
In multi-slice magnetic resonance imaging (MRI) the resolution in slice direction is usually reduced to allow faster acquisition times and reduce amount of noise each 2-D slice. this paper, a novel image super (SR) algorithm presented that used improve 3D MRI volumes direction. The proposed SR uses complex wavelet-based de-blurring approach with Gaussian scale mixture model sparseness constraint. takes several same anatomical region captured at different angles combines these low-resolution...