On-device Applications of Small Language Models
Ongoing
A systematic study on small language models designed for on-device deployment, covering optimization techniques, performance benchmarks, and practical applications.
Research & Publications
NLP · Image Processing · On-Device AI · LLMs
2026
2024
An intelligent telediagnosis of Acute Lymphoblastic Leukemia Using histopathological deep learning
Journal of Computing Theories & Applications
Leukemia, a global health challenge characterized by malignant blood cell proliferation, demands innovative diagnostic techniques due to its increasing incidence. Among leukemia types, Acute Lymphoblastic Leukemia (ALL) emerges as a particularly aggressive form affecting diverse age groups. This study proposes an advanced mechanized system utilizing Deep Neural Networks for detecting ALL blast cells in microscopic blood smear images. Achieving a remarkable accuracy of 97% using MobileNetV2, our system demonstrates high sensitivity and specificity in identifying multiple ALL sub-types.
2023
An experimental study for early diagnosing Parkinson's disease using machine learning
arXiv Preprint
One of the most catastrophic neurological disorders worldwide is Parkinson's Disease. This experimental work used Machine Learning techniques to automate the early detection of Parkinson's Disease from clinical characteristics, voice features and motor examination. We obtained 100% accuracy in classifying PD and RBD patients, as well as 92% accuracy in classifying PD and HC individuals.
Streamlining brain tumor classification with custom transfer learning in MRI images
IEEE International Conference on Smart Information Systems and Technologies (SIST)
Brain tumors are increasingly prevalent, characterized by the uncontrolled spread of aberrant tissues in the brain. We propose an efficient solution for classifying brain tumors from MRI images using custom transfer learning networks. We employ the VGG-19 architecture with additional hidden layers, achieving a classification accuracy of 96.42%.
2022
Automated detection of acute lymphoblastic leukemia subtypes from microscopic blood smear images using Deep Neural Networks
BS Thesis - City University
The most dangerous and deadly type of leukemia is acute lymphoblastic leukemia (ALL), which affects people of all age groups. We propose an automated system to detect various-shaped ALL blast cells from microscopic blood smears images using Deep Neural Networks with 98% accuracy.
Detecting chronic kidney disease (CKD) at the initial stage: A novel hybrid feature-selection method and robust data preparation pipeline for different ML techniques
5th International Conference on Computing and Informatics (ICCI)
Chronic Kidney Disease (CKD) has infected almost 800 million people around the world. We present a structured method for dealing with medical data complexities, applying various ML techniques. The Random Forest can detect CKD with 100% accuracy without any data leakage.
2021
A comparative study of sentiment analysis using NLP and different machine learning techniques on US airline Twitter data
International Conference on Electronics, Communications and Information Technology (ICECIT)
We introduce NLP techniques and various ML classification algorithms to find an effective approach for Sentiment Analysis on airline Twitter data. Our best approaches provide 77% accuracy using Support Vector Machine and Logistic Regression with Bag-of-Words technique.