Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Rafsanjani MuhammodSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works27 from public data
- Identification and recognition of rice diseases and pests using convolutional neural networks550
A two-stage small CNN architecture has been proposed, and compared with the state-of-the-art memory efficient CNN architectures such as MobileNet, NasNet Mobile and SqueezeNet, and shows that the proposed architecture can achieve the desired accuracy with a significantly reduced model size.
- 62
- Rice grain disease identification using dual phase convolutional neural network based system aimed at small dataset.36
A CNN based dual phase method has been proposed which can work effectively on small rice grain disease dataset with heterogeneity and provides a 5 fold cross validation accuracy of 88.07%.
- A deep-learning model for quantifying circulating tumour DNA from the density distribution of DNA-fragment lengths26
The method’s versatility, speed and accuracy for ctDNA quantification suggest that it may have broad clinical utility, and it is validated by using low-pass whole-genome-sequencing data from multiple cancer types and healthy control cohorts.
- A convolution based computational approach towards DNA N6-methyladenine site identification and motif extraction in rice genome18
This study develops a convolutional neural network (CNN) based tool i6mA-CNN capable of identifying 6mA sites in the rice genome and evaluates the model on three other plant genome 6mA site identification test datasets to suggest that the proposed tool is able to generalize its ability of 6AMA site identification on plant genomes irrespective of plant species.
- Synthetic Error Dataset Generation Mimicking Bengali Writing Pattern11
This research presents an algorithm for automatic misspelled Bengali word generation from correct word through analyzing Bengali writing pattern using QWERTY layout English keyboard.
- Benchmarking Recent Computational Tools for DNA-binding Protein Identification6
It is shown that combining the predictions of the two best computational tools with BLAST based prediction significantly enhances DBP identification capability, and the two best-performing ML-based tools, BLAST and the ensemble method as user-friendly software are provided.
- Automatic signboard detection and localization in densely populated developing cities6
The proposed method can detect signboards accurately (even if the images contain multiple signboards with diverse shapes and colours in a noisy background) achieving 0.90 mAP (mean average precision) score on SVSO independent test set.
- Automatic Signboard Detection from Natural Scene Image in Context of Bangladesh Google Street View6
This research introduces a novel approach to detect signboard accurately by applying smart image processing techniques and statistically determined hyperparameter based deep learning method, Faster R-CNN.
- A Comprehensive Comparison of Machine Learning Based Methods Used in Bengali Question Classification5
This work demonstrates phases of assembling a QA type classification model and presents a comprehensive comparison among some machine learning based approaches used in QC for Bengali language.
- GCfix: a fast and accurate fragment length-specific method for correcting GC bias in cell-free DNA4
GCfix, a method for robust GC bias correction in cfDNA data across diverse coverages, is presented, developed following an in-depth analysis of cfDNA GC bias at the region and fragment length levels, and is both fast and accurate.
- ReviewRanker: A Semi-Supervised Learning Based Approach for Code Review Quality Estimation4
A semi-supervised learning based system ReviewRanker which is aimed at assigning each code review a confidence score which is expected to resonate with the quality of the review, trained based on simple and well defined labels provided by developers.
- Fragle: Universal ctDNA quantification using deep learning of fragmentomic profiles4
Prediction of minimal residual disease in resected lung cancer patients demonstrated significant risk stratification beyond a tumor-naïve gene panel, and Fragle is a versatile, fast, and accurate method for ctDNA quantification with potential for broad clinical utility.
- 3
- Judge a Sentence by Its Content to Generate Grammatical Errors2
This work proposes a learning based two stage method for synthetic data generation for GEC that relaxes this constraint on sentences containing only one error and shows that a GEC model trained on the authors' synthetically generated corpus outperforms models trained on synthetic data from prior work.
- 1
- 1
- Constraints in Developing a Complete Bengali Optical Character Recognition System1
The aim of this research is to analyze the challenges prevalent in developing a Bengali OCR system through robust literature review and implementation, and suggest some possible solutions related to it.
- Abstract P23: A deep-learning model for quantifying circulating tumour DNA from the density distribution of DNA-fragment lengths–
FRAGLE converts lpWGS or panel off-target data into 1-minute-fast, NGS <US$50, tumour-agnostic ctDNA estimates with a LoD of ∼1%.
- –
- –
- –
- –
- –
- –
- A Hybrid Approach Towards Two Stage Bengali Question Classification Utilizing Smart Data Balancing Technique–
This work presents a two stage QC system for Bengali that categorizes the factoid type questions asked in natural language after extracting features of the questions into coarse classes in the first stage and a smart data balancing technique for giving data hungry convolutional neural network the advantage of a greater number of effective samples to learn from.
- Comparison of Machine Learning Based Methods Used in Bengali Question Classification–
The work to question classification in Bengali on machine learning approach using different types of algorithms such as Multi-Layer Perceptron (MLP), Naive Bayes Classifier (NBC), Support Vector Machine (SVM), Gradient Boosting Classifier (GBC), Stochastic Gradient Descent (SGD) by eliminating and without eliminating stop words.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.