Amrita Das Tipu
I'm a Researcher
Amrita Das Tipu
Lecturer, Department of Computer Science and Engineering, Dhaka International University.
Google Scholar |
ORCID |
GitHub |
|
|
|
|
About Me
I am a dedicated lecturer at Dhaka International University, committed to enhancing the quality of education through continuous self-improvement. I earned my Bachelor of Science in Computer Science and Engineering from Hajee Mohammad Danesh Science and Technology University (HSTU) in 2023. Shortly after graduation, I joined DIU as a lecturer, where I continue to teach and inspire students.
Beyond teaching, I have a strong passion for research, particularly in machine learning and natural language processing. I am always eager to explore emerging technologies and expand my knowledge. In my free time, I enjoy reading books and engaging in intellectual discussions that fuel my curiosity and drive for innovation.
Research Interest
- Artificial Intelligence (AI) and Machine Learning (ML)
- Natural Language Processing (NLP)
- Interpretable AI
- Foundation Models
- Human-AI Interaction
News
- 2024-12-28: I became advisor of the Cyber Security Club at Dhaka International University (Link).
- 2024-05-02: I joined as a lecturer in CSE at Dhaka International University (Link).
- 2024-03-30: My first conference paper was published (Link).
- 2022-03-05: My team became the Champion in the Mujib 100 Years' Programming Contest 2022, organized by Programmers Arena (PA), HSTU.
- 2021-02-09: I was awarded the Dean's Merit List Award for my exceptional performance in the second academic year. See more...
Publications Conference and Book Chapters
Projects Web, Android and Desktop Applications
Professional Experience University Lecturer
Activities Contributing to Society
Skills
Languages
Programming Languages
Web Technologies
Database Systems
Version Control
Frameworks
Code Editor and IDEs
Soft Skills
Work Experience
May 2024 - Present
Lecturer
Department of Computer Science and Engineering
Dhaka International University (DIU), Satarkul, Badda, Dhaka-1212, Bangladesh
Responsibilities
- Develope teaching and student guiding skills.
- Implemented outcome-based education (OBE), enhancing learning for students.
Teaching Area:
- Artificial Intelligence and Neural Networks
- Digital Logic Design
- Object-Oriented Programming Languages
- System Analysis and Design
- Software Engineering
- Database Management Systems
- Algorithm Design and Analysis
- E-commerce and Web Engineering
- Data and Telecommunication
Education
Bachelor of Science (Engineering)
2018 - 2021
Hajee Mohammad Danesh Science and Technology University, Dinajpur-5200, Bangladesh
- Major: Computer Science and Engineering
- Total Credit: 154.75
- Results were delayed due to COVID-19 and published on November 29, 2023.
Selected Publications
Some of my selected publications are given here. To view all publications please visit my Google Scholar profile.
- All
- Conference Proceedings
- Book Chapters
A Romanization Method for the Bengali Language with Efficient Encoding Scheme
Tipu, A.D., Fahad, M. and Mandal, A.K.
September 2023
International Conference on Big Data, IoT and Machine Learning (pp. 605-619). Singapore: Springer Nature Singapore.
Transliteration is crucial in natural language processing as it enables the conversion between two languages while retaining their phonetic representation. The ability to transliterate the Bengali language is essential for cross-lingual communication. Most Bengali machine transliteration techniques rely on one-hot coding to numerically represent features, which is computationally intensive, requires significant memory, and results in lower accuracy in some cases. Addressing these limitations, we present an efficient feature representation method utilizing binary coding and compare it against the one-hot coding approach using two machine learning models: SVM and random forest. The proposed method is evaluated on the Dakshina dataset and the NEWS 2018 dataset for Bengali to English transliteration. The experimental results indicate that our approach outperforms the traditional methods while requiring significantly less memory and training time. Overall, the proposed method enables a better romanization of frequently used words.
Influence of Contextual Information on Bengali-English Forward and Backward Transliteration Using Binary Coding
Fahad, M.*, Tipu, A.D.* and Mandal, A.K.
December 2023
2023 1st International Conference on Optimization Techniques for Learning (ICOTL) (pp. 1-6). IEEE.
Transliteration of words across different scripts carries importance for both social media platforms and messaging apps. It preserves the phonetic meaning of words across various writing systems. This study evaluates the influence of contextual information within words on the transliteration of Bengali and English language pair. It utilizes the Dakshina and NEWS 2018 datasets and binary encoding for feature representation. With the random forest classifier, the results demonstrate that using neighboring transliteration units as context yields the best performance on both datasets, obtaining the highest accuracy of 81.04%. These findings highlight the vital role of contextual information within words in enhancing the performance of transliteration.
An Interpretable Machine Learning Approach for Identification of the Risk Factors of Early-Stage Overweight and Obesity
Roy, P. and Tipu, A.D.
April 2024
2024 3rd International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE) (pp. 1-6). IEEE.
The increasing overweight and obesity rates pose a significant risk to public health globally, as it is closely associated with various diseases and higher rates of morbidity and mortality. Prompt and effective intervention in the early stages is therefore crucial. Furthermore, identifying obesity risk factors is essential to combat the growing rates of several secondary health problems such as cardiovascular disease, type II diabetes, and other comorbidities. This study aims to unveil the key factors playing a remarkable role in shaping this situation, utilizing the immense potential of machine learning methods. The proposed pipeline implements feature selection using Recursive Feature Elimination to effectively reduce the dimensionality of the dataset. The extracted subset of the original secondary dataset is then employed to train different state-of-the-art machine learning classifiers, including Logistic Regression, Random Forest, Decision Trees, along with the proposed novel stacking ensemble model. The proposed model outperforms other models, achieving a noteworthy accuracy of 99.58% with an AUC score of 1.0, when combined with the SMOTE-ENN balancing technique. Additionally, model explainable tool SHAP is used to rank the features according to their individual contribution, providing a more in-depth explanation of how each feature impacts the model outcome. By leveraging advanced machine learning algorithms and extensive datasets, this approach can significantly improve early-stage obesity prediction by uncovering its underlying causes.
Improving the Analysis of CO2 Emissions with a Filter and Imputation-Based Processing Method
Tipu, A.D., Roy, P., Uddin, M. P. and Hasan, M.
In Press
Machine Learning Technologies on Energy Economics and Finance - Energy and Sustainable Analytics (MLTEEF2024), Springer.
We analyzed carbon emissions, proposed a new data preprocessing model and explored the impact of greenhouse gases emissions on various factors.
An Evidence-based Explainable AI Approach for Analyzing the Influence of CO2 Emissions on Sustainable Economic Growth
Roy, P., Tipu, A.D., Hasan, M. and Uddin, M. P.
In Press
Machine Learning Technologies on Energy Economics and Finance - Energy and Sustainable Analytics (MLTEEF2024), Springer.
We investigated the impact of greenhouse gases emissions on various economic factors and provided detailed analysis.
Projects
The projects and applications I completed as part of my undergrad degree and self-interest.
- All
- Android
- Desktop
- Terminal
- Web
Activities
The co-curriculur, extra-curricular and volunteering activities during undergrad and after graduation.
Batch Councilor
Coordinating between students and faculty for prompt and effective communications and encouraging students to do better.
Advisor
Conducting workshops and one-to-one discussion on career opportunities in Bangladesh and abroad.
Mentor
Conducting workshops, developing learning materials and mentoring students in applying machine learning techniques to real-world problems.
Research Assistant
Gaining experience on working with Raspberry Pi computers and fingerprint sensors for biometric data collection and system development.
Executive Member
Solving programming problems, participating in various contests and organizing programming contest and workshops.