← Back to portfolio

Anowarul Faruk Shishir

Ph.D. Student & Graduate Research Assistant · Computer Science · Kennesaw State University

Experience

Graduate Research Assistant

Department of Computer Science

Kennesaw State University (KSU), Georgia, USA

August 2026 - Present

Lecturer

Department of Computer Science and Engineering

BGMEA University of Fashion & Technology (BUFT)

October 2025 - June 2026

Former Lecturer

Department of Computer Science and Engineering

Bangladesh University

August 2025 - September 2025

Education

Kennesaw State University (KSU), Georgia, USA

Doctor of Philosophy (Ph.D.) in Computer Science

August 2026 - Present

Khulna University of Engineering & Technology (KUET), Khulna, Bangladesh

Bachelor of Science in Electronics and Communication Engineering

2019 - 2024 | CGPA: 3.78 out of 4.00 (3.84 after IEE Evaluation) | Position: 6th |

Coursework: Machine Learning, Digital Image Processing, Wireless Network, Database System and Management, Computer Networks, Biomedical Engineering, Digital Signal Processing

Publications

Online Sequential Extreme Learning Machine with Forgetting Factor and PCA-based Initial Weight Initialization for Time Series Forecasting

COMPAS 2026 | IEEE 3rd International Conference on Computing, Applications and Systems

• Proposed an online sequential extreme learning machine that combines a forgetting factor with PCA-based initial weight initialization for time series forecasting.

Game-Based versus Training-Based Virtual Reality for Cognitive Rehabilitation in Mild Cognitive Impairment and Dementia: A Systematization of Design Paradigms, Outcomes, and Evaluation Rigor

VRST 2026 | 32nd ACM Symposium on Virtual Reality Software and Technology (Accepted)

• Systematized research on game-based and training-based virtual reality for cognitive rehabilitation in mild cognitive impairment and dementia, comparing their design paradigms, reported outcomes, and evaluation rigor.

PriBan: A Benchmark Dataset and Modeling Framework for Privacy Preservation in Bengali Texts

ICCIT 2025 | 28th International Conference on Computer and Information Technology

• Developed a benchmark dataset and framework to preserve user privacy during interactions with large language models, addressing the tendency of LLMs to inadvertently leak sensitive information, with a specific focus on the Bangla language.

Thesis

Sentiment Analysis from a Bengali Dataset Using Hybrid Deep Learning and Contextualized Word Embedding Techniques

• Utilized contextualized Bangla BERT word embedding techniques to replace traditional methods (Word2Vec, GloVe, FastText) combined with a CNN-BiLSTM model, achieving 96.84% accuracy.

• Compared performance with 8 machine learning and 2 deep learning models, and introduced a feature for expressing sentiment with relative sentiment scores.

Undergraduate Projects

Intelligent Information Retrieval via Question Answering

Knowledge Graphs, Graph Neural Networks, Semantic Reasoning

• Explored intelligent information retrieval through question answering by leveraging knowledge graphs and graph neural networks. Incorporated structured semantic relationships and graph-based reasoning to challenge conventional models for improved accuracy and interpretability.

Accident Detection and Developing an Alert System Using Deep Learning

Deep Learning, Computer Vision, GPS Integration, Real-time Detection

• Developed a system to detect accidents from CCTV camera video footage with an integrated alert system. Incorporated GPS functionality to inform authorities about accident locations. Capable of detecting accidents from both live camera feeds and stored footage.

Pneumonia Detection from X-ray Images with Deep Learning

CNN, VGG-16, Transfer Learning, Medical Image Classification

• Built a conventional CNN model to accurately detect pneumonia from chest X-rays. Implemented and compared performance with pre-trained VGG-16 model to classify chest X-rays as normal or pneumonia-positive.

Language Translator using Seq2Seq Model

Encoder-Decoder, Seq2Seq, NLP, Machine Translation

• Designed a French-to-English language translator using an Encoder-Decoder seq2seq architecture. Performed extensive text preprocessing and cleaning to optimize translation accuracy.

Test Score

TOEFL (97)

• Reading- 25, Listening- 23, Speaking- 23, Writing- 26

Technical Skills and Interests

• Research Areas: Natural Language Processing, Cloud Computing, Data Science, Extended Reality

• Frameworks: ASP.NET

• Editor/IDE: Google Colab, Jupyter Notebook, Code Block, Visual Studio, Pycharm

• Database: SQL Server, MySQL

• Tools: NumPy, Pandas, Scikit-Learn,Keras, Matplotlib, Seaborn

• Hands-on: Cisco Packet Tracer

• Professional Skills: Problem Solving, Leadership, Management, Microsoft Office

Awards and Scholarships

Dean's Award

• 2 times for outstanding academic performance.

HSC Board Scholarship

• From Education Board, Cumilla, Bangladesh.

SSC Board Scholarship

• From Education Board, Cumilla, Bangladesh.

Contacts

Email: anowarulfaruks@gmail.com

LinkedIn: Anowarul Faruk Shishir

Location: Marietta, Georgia, USA