Annajiat Alim Rasel

A. N. M. Sajedul Alam, Rimi Reza, Asir Abrar et al.

This research presents an examination of categorizing the severity states of patients based on their electronic health records during a certain time range using multiple machine learning and deep learning approaches. The suggested method uses an EHR dataset collected from an open-source platform to categorize severity. Some tools were used in this research, such as openRefine was used to pre-process, RapidMiner was used for implementing three algorithms (Fast Large Margin, Generalized Linear Model, Multi-layer Feed-forward Neural Network) and Tableau was used to visualize the data, for implementation of algorithms we used Google Colab. Here we implemented several supervised and unsupervised algorithms along with semi-supervised and deep learning algorithms. The experimental results reveal that hyperparameter-tuned Random Forest outperformed all the other supervised machine learning algorithms with 76% accuracy as well as Generalized Linear algorithm achieved the highest precision score 78%, whereas the hyperparameter-tuned Hierarchical Clustering with 86% precision score and Gaussian Mixture Model with 61% accuracy outperformed other unsupervised approaches. Dimensionality Reduction improved results a lot for most unsupervised techniques. For implementing Deep Learning we employed a feed-forward neural network (multi-layer) and the Fast Large Margin approach for semi-supervised learning. The Fast Large Margin performed really well with a recall score of 84% and an F1 score of 78%. Finally, the Multi-layer Feed-forward Neural Network performed admirably with 75% accuracy, 75% precision, 87% recall, 81% F1 score.

Md Abu Obaida Zishan, Annajiat Alim Rasel

Locating objects for the visually impaired is a significant challenge and is something no one can get used to over time. However, this hinders their independence and could push them towards risky and dangerous scenarios. Hence, in the spirit of making the visually challenged more self-sufficient, we present SonoVision, a smart-phone application that helps them find everyday objects using sound cues through earphones/headphones. This simply means, if an object is on the right or left side of a user, the app makes a sinusoidal sound in a user's respective ear through ear/headphones. However, to indicate objects located directly in front, both the left and right earphones are rung simultaneously. These sound cues could easily help a visually impaired individual locate objects with the help of their smartphones and reduce the reliance on people in their surroundings, consequently making them more independent. This application is made with the flutter development platform and uses the Efficientdet-D2 model for object detection in the backend. We believe the app will significantly assist the visually impaired in a safe and user-friendly manner with its capacity to work completely offline. Our application can be accessed here https://github.com/MohammedZ666/SonoVision.git.

Md Sabbir Hossain, Nishat Nayla, Annajiat Alim Rasel

Product market demand analysis plays a significant role for originating business strategies due to its noticeable impact on the competitive business field. Furthermore, there are roughly 228 million native Bengali speakers, the majority of whom use Banglish text to interact with one another on social media. Consumers are buying and evaluating items on social media with Banglish text as social media emerges as an online marketplace for entrepreneurs. People use social media to find preferred smartphone brands and models by sharing their positive and bad experiences with them. For this reason, our goal is to gather Banglish text data and use sentiment analysis and named entity identification to assess Bangladeshi market demand for smartphones in order to determine the most popular smartphones by gender. We scraped product related data from social media with instant data scrapers and crawled data from Wikipedia and other sites for product information with python web scrapers. Using Python's Pandas and Seaborn libraries, the raw data is filtered using NLP methods. To train our datasets for named entity recognition, we utilized Spacey's custom NER model, Amazon Comprehend Custom NER. A tensorflow sequential model was deployed with parameter tweaking for sentiment analysis. Meanwhile, we used the Google Cloud Translation API to estimate the gender of the reviewers using the BanglaLinga library. In this article, we use natural language processing (NLP) approaches and several machine learning models to identify the most in-demand items and services in the Bangladeshi market. Our model has an accuracy of 87.99% in Spacy Custom Named Entity recognition, 95.51% in Amazon Comprehend Custom NER, and 87.02% in the Sequential model for demand analysis. After Spacy's study, we were able to manage 80% of mistakes related to misspelled words using a mix of Levenshtein distance and ratio algorithms.

A. N. M. Sajedul Alam, Junaid Bin Kibria, Arnob Kumar Dey et al.

Manual approvals are still used by banks and other NGOs to approve loans. It takes time and is prone to mistakes because it is controlled by a bank employee. Several fields of machine learning mining technologies have been utilized to enhance various areas of credit rating forecast. A major goal of this research is to look at current sentiment analysis techniques that are being used to generate creditworthiness.

Neelavro Saha, Rafi Shahriyar, Nafis Ashraf Roudra et al.

Bangla Sign Language (BdSL) translation represents a low-resource NLP task due to the lack of large-scale datasets that address sentence-level translation. Correspondingly, existing research in this field has been limited to word and alphabet level detection. In this work, we introduce Bangla-SGP, a novel parallel dataset consisting of 1,000 human-annotated sentence-gloss pairs which was augmented with around 3,000 synthetically generated pairs using syntactic and morphological rules through a rule-based Retrieval-Augmented Generation (RAG) pipeline. The gloss sequences of the spoken Bangla sentences are made up of individual glosses which are Bangla sign supported words and serve as an intermediate representation for a continuous sign. Our dataset consists of 1000 high quality Bangla sentences that are manually annotated into a gloss sequence by a professional signer. The augmentation process incorporates rule-based linguistic strategies and prompt engineering techniques that we have adopted by critically analyzing our human annotated sentence-gloss pairs and by working closely with our professional signer. Furthermore, we fine-tune several transformer-based models such as mBart50, Google mT5, GPT4.1-nano and evaluate their sentence-to-gloss translation performance using BLEU scores, based on these evaluation metrics we compare the model's gloss-translation consistency across our dataset and the RWTH-PHOENIX-2014T benchmark.

Md Abu Obaida Zishan, Jannatun Noor, Annajiat Alim Rasel

Stable Diffusion (SD) has evolved DDPM (Denoising Diffusion Probabilistic Model) based image generation significantly by denoising in latent space instead of feature space. This popularized DDPM-based image generation as the cost and compute barrier was significantly lowered. However, these models could only generate fixed-resolution images according to their training configuration. When we attempt to generate higher resolutions, the resulting images show object duplication artifacts consistently. To solve this problem without finetuning SD models, recent works have tried dilating the convolution kernels of the models and have achieved a great level of success. But dilated kernels are harder to fine-tune due to being zero-gapped. Apart from this, other methods, such as patched diffusion, could not solve the object-duplication problem efficiently. Hence, to overcome the limitations of dilated convolutions, we propose kernel interpolation of SD models for higher-resolution image generation. In this work, we show mathematically that interpolation can correctly scale convolution kernels if multiplied by a constant coefficient and achieve competitive empirical results in generating beyond-training-resolution images with Stable Diffusion using zero training. Furthermore, we demonstrate that our method enables interpolation of deep neural networks to adapt to higher-dimensional training data, with a worst-case performance drop of $2.6\%$ in accuracy and F1-Score relative to the baseline. This shows the applicability of our method to be general, where we interpolate fully-connected layers, going beyond convolution layers. We also discuss how we can reduce the memory footprints of training neural networks, using our method up to at least $4\times$.

S M Rakib Hasan, Aakar Dhakal, Md Humaion Kabir Mehedi et al.

Efforts on the research and development of OCR systems for Low-Resource Languages are relatively new. Low-resource languages have little training data available for training Machine Translation systems or other systems. Even though a vast amount of text has been digitized and made available on the internet the text is still in PDF and Image format, which are not instantly accessible. This paper discusses text recognition for two scripts: Bengali and Nepali; there are about 300 and 40 million Bengali and Nepali speakers respectively. In this study, using encoder-decoder transformers, a model was developed, and its efficacy was assessed using a collection of optical text images, both handwritten and printed. The results signify that the suggested technique corresponds with current approaches and achieves high precision in recognizing text in Bengali and Nepali. This study can pave the way for the advanced and accessible study of linguistics in South East Asia.

Azher Ahmed Efat, Farzana Islam, Annajiat Alim Rasel et al.

Recorded history shows the long coexistence of humans and animals, suggesting it began much earlier. Despite some beneficial interdependence, many animals carry viral diseases that can spread to humans. These diseases are known as zoonotic diseases. Recent outbreaks of SARS-CoV-2, Monkeypox and swine flu viruses have shown how these viruses can disrupt human life and cause death. Fast and accurate predictions of the host from which the virus spreads can help prevent these diseases from spreading. This work presents BiLSTM-VHP, a lightweight bidirectional long short-term memory (LSTM)-based architecture that can predict the host from the nucleotide sequence of orthohantavirus, rabies lyssavirus, and rotavirus A with high accuracy. The proposed model works with nucleotide sequences of 400 bases in length and achieved a prediction accuracy of 89.62% for orthohantavirus, 96.58% for rotavirus A, and 77.22% for rabies lyssavirus outperforming previous studies. Moreover, performance of the model is assessed using the confusion matrix, F-1 score, precision, recall, microaverage AUC. In addition, we introduce three curated datasets of orthohantavirus, rotavirus A, and rabies lyssavirus containing 8,575, 95,197, and 22,052 nucleotide sequences divided into 9, 12, and 29 host classes, respectively. The codes and dataset are available at https://doi.org/10.17605/OSF.IO/ANFKR

Tanzir Hossain, Ar-Rafi Islam, Md. Sabbir Hossain et al.

This study presents a cascaded architecture for extractive summarization of multimedia content via audio-to-text alignment. The proposed framework addresses the challenge of extracting key insights from multimedia sources like YouTube videos. It integrates audio-to-text conversion using Microsoft Azure Speech with advanced extractive summarization models, including Whisper, Pegasus, and Facebook BART XSum. The system employs tools such as Pytube, Pydub, and SpeechRecognition for content retrieval, audio extraction, and transcription. Linguistic analysis is enhanced through named entity recognition and semantic role labeling. Evaluation using ROUGE and F1 scores demonstrates that the cascaded architecture outperforms conventional summarization methods, despite challenges like transcription errors. Future improvements may include model fine-tuning and real-time processing. This study contributes to multimedia summarization by improving information retrieval, accessibility, and user experience.