Deep Learning-Based Brain Tumor Segmentation in MRI Images: A MobileNetV2-DeepLabv3+ Approach
Applies a MobileNetV2–DeepLabv3+ architecture to brain tumour segmentation in MRI.
Read paperResearch output
Publications.
Journal articles and conference papers, grouped by research area.
Google Scholar · Last checked 4 October 2026
Research area
Publication type
Medical imaging
Enhancing Multi-class Diabetic Retinopathy Detection Using Tuned Hyper-parameters and Modified Deep Transfer Learning
Investigates image enhancement, transfer learning and hyperparameter tuning for retinal fundus classification.
Paper / DOIEfficientNetB0’s Hybrid Approach for Brain Tumor Classification from MRI Images Using Deep Learning and Bagging Trees
Combines EfficientNetB0 image features with bagging trees for brain tumour classification.
Paper / DOIAn Efficient Approach for Breast Abnormality Detection through High-Level features of Thermography Images
Explores high-level thermography image features for breast abnormality detection.
Paper / DOIComputational neuroscience
Brain connectivity, EEG signal processing and AI for neurodevelopmental disorders, including ADHD and autism.
Hybrid Deep Transfer Learning Based Early Diagnosis of Autism Spectrum Disorder Using Scalogram Representation of Electroencephalography Signals
Combines EEG scalograms with convolutional and recurrent models for autism classification.
Paper / DOIImproved ADHD Diagnosis Using EEG Connectivity and Deep Learning through Combining Pearson Correlation Coefficient and Phase-Locking Value
Combines linear and phase-based EEG connectivity with an attention-based convolutional network.
Paper / DOIEEG-Based Effective Connectivity Analysis for Attention Deficit Hyperactivity Disorder Detection Using Color-Coded Granger-Causality Images and Custom Convolutional Neural Network
Models EEG effective connectivity with Granger-causality images and a convolutional network.
Paper / DOIPotential Biomarker for Early Detection of ADHD Using Phase-Based Brain Connectivity and Graph Theory
Investigates phase-based functional connectivity and graph features in childhood ADHD.
Paper / DOINeurodegenerative disorders
Signal and image processing with AI for Parkinson’s disease, dementia and other neurodegenerative disorders, using gait, voice and MRI data.
Voice-driven Parkinson’s Detection Using Bidirectional Long Short-term Memory and Attention on Mobile-recorded Speech
Studies acoustic features and attention-based bidirectional recurrent networks for Parkinson’s detection from mobile-recorded speech.
Paper / DOIA Deep Time-frequency Approach in Automated Diagnosis of Neurodegenerative Diseases Using Gait Signals
Studies deep learning and time-frequency representations of gait signals for neurodegenerative disease classification.
Read paperAn Efficient Tool for Parkinson’s Disease Detection and Severity Grading Based on Time-Frequency and Fuzzy Features of Cumulative Gait Signals through Improved LSTM Networks
Studies time-frequency and fuzzy gait features with recurrent networks for Parkinson’s detection and grading.
Read paperSimultaneous Time-Frequency Analysis of Gait Signals of Both Legs in Classifying Neurodegenerative Diseases
Uses interlimb wavelet coherence and transfer learning to study neurodegenerative gait patterns.
Paper / DOIEffectiveness of Learning Rate in Dementia Severity Prediction Using VGG16
Examines the effect of learning rate on VGG16 models for dementia severity prediction.
Paper / DOIEnhancing Parkinson’s Disease Severity Assessment through Voice-Based Wavelet Scattering, Optimized Model Selection, and Weighted Majority Voting
Studies voice features, wavelet scattering and ensemble learning for Parkinson’s severity assessment.
Paper / DOIBiomedical signals
A Pre-Processing-Free Mental State Detection Model Using Noisy ECG Plots and Deep Transfer Learning
Studies mental-state classification from noisy ECG plots using deep transfer learning.
Paper / DOIMachine learning & tools
Crude Oil Price Forecasting Using K-means Clustering and LSTM Model Enhanced by Dense-Sparse-Dense Strategy
Combines clustering and recurrent modelling for crude oil price forecasting.
Paper / DOIAuto-UFSTool: An Automatic Unsupervised Feature Selection Toolbox for MATLAB
An open MATLAB toolbox for automatic unsupervised feature selection.
Paper / DOI Code ↗No publications match these filters.
For the latest citation information and new work, visit Google Scholar.