publications

2019

1. A heuristic aided Stochastic Beam Search algorithm for solving the transit network design problem

   Kazi Ashik Islam, Ibraheem Muhammad Moosa, Jaiaid Mobin, and 2 more authors

   Swarm and Evolutionary Computation, 2019

   Abs

   Designing efficient routes for a transit network is one of the main problems faced by city planners of the world. Due to the largeness and complexity of modern day road networks it is impossible to make a good route design manually. So, at present computer algorithms are used to design the routes. Designing routes for transit network is a multi-criteria decision making problem which has to search a large solution space to find an optimal solution. This paper presents a novel heuristic that can quickly generate good solutions. Also we propose a Stochastic Beam Search algorithm with a heuristic inspired successor operator. We conduct extensive experiments on some benchmark datasets and perform statistical tests on the results. We show that our algorithm can successfully explore the search space. Also we compare our results with previous studies and show that our algorithms produce superior results. In particular, for large datasets, the solutions generated by our heuristic in less than a second turn out to be better than solutions generated in two hours by the state of the art algorithm.

2020

1. Dielectric or plasmonic Mie object at air–liquid interface: The transferred and the traveling momenta of photon*

   M R C Mahdy, Hamim Mahmud Rivy, Ziaur Rahman Jony, and 6 more authors

   Chinese Physics B, Jan 2020

   Abs

   Considering the inhomogeneous or heterogeneous background, we have demonstrated that if the background and the half-immersed object are both non-absorbing, the transferred photon momentum to the pulled object can be considered as the one of Minkowski exactly at the interface. In contrast, the presence of loss inside matter, either in the half-immersed object or in the background, causes optical pushing of the object. Our analysis suggests that for half-immersed plasmonic or lossy dielectric, the transferred momentum of photon can mathematically be modeled as the type of Minkowski and also of Abraham. However, according to a final critical analysis, the idea of Abraham momentum transfer has been rejected. Hence, an obvious question arises: whence the Abraham momentum? It is demonstrated that though the transferred momentum to a half-immersed Mie object (lossy or lossless) can better be considered as the Minkowski momentum, Lorentz force analysis suggests that the momentum of a photon traveling through the continuous background, however, can be modeled as the type of Abraham. Finally, as an interesting sidewalk, a machine learning based system has been developed to predict the time-averaged force within a very short time avoiding time-consuming full wave simulation.

2022

2023

1. Does Transliteration Help Multilingual Language Modeling?

   Ibraheem Muhammad Moosa, Mahmud Elahi Akhter, and Ashfia Binte Habib

   In Findings of the Association for Computational Linguistics: EACL 2023, May 2023

   Abs

   Script diversity presents a challenge to Multilingual Language Models (MLLM) by reducing lexical overlap among closely related languages. Therefore, transliterating closely related languages that use different writing scripts to a common script may improve the downstream task performance of MLLMs. We empirically measure the effect of transliteration on MLLMs in this context. We specifically focus on the Indic languages, which have the highest script diversity in the world, and we evaluate our models on the IndicGLUE benchmark. We perform the Mann-Whitney U test to rigorously verify whether the effect of transliteration is significant or not. We find that transliteration benefits the low-resource languages without negatively affecting the comparatively high-resource languages. We also measure the cross-lingual representation similarity of the models using centered kernel alignment on parallel sentences from the FLORES-101 dataset. We find that for parallel sentences across different languages, the transliteration-based model learns sentence representations that are more similar.

2. COVID-19 Diagnosis and Classification from CXR Images Using Vision Transformer

   Md Mahbubur Rahman, Shihabur Rahman Samrat, Abdullah Al Ahad, and 4 more authors

   In Medical Imaging and Computer-Aided Diagnosis, May 2023

   Abs

   The COVID-19 pandemic is yet to come to a halt, and the current primary method of diagnosis is Reverse Transcription Polymerase Chain Reaction (RT-PCR). Although RT-PCR is reliable, it is known to have a long turnaround time and high false-negative rates that can severely hinder the accuracy of diagnosis. Alongside RT-PCR, Rapid Antigen Tests (RAT) are also used, but they have much lower accuracy than RT-PCR. Motivated by the flaws of the current diagnosis methods, we present a Vision Transformer-based classifier for the successful diagnosis and classification of COVID-19 using chest X-Ray (CXR) images. In order to address dataset imbalance and bias issues, a 15,000 sample CXR dataset was compiled, which consisted of 5000 CXR per class. Afterwards, a Vision Transfer (ViT) was fine-tuned on the dataset. Resnet-50 and DenseNet121 were used as baseline models. It is observed that for multiclass classification, the Vision Transformer-based model has the highest classification accuracy of 96.2% with a F1 score of 0.965 and the average precision and recall of 0.9617 and 0.962, respectively. This study demonstrates the adequacy of the ViT for the identification and classification of COVID-19 and Pneumonia.

2024

1. MT-Ranker: Reference-free machine translation evaluation by inter-system ranking

   Ibraheem Muhammad Moosa, Rui Zhang, and Wenpeng Yin

   In The Twelfth International Conference on Learning Representations, May 2024
2. Automated Assessment of Creativity in Multilingual Narratives

   Simone A Luchini, Moosa I Muhammad, John D Patterson, and 8 more authors

   Aug 2024