Ashim Dey

The skin, as the largest organ of the human body, is vulnerable to a diverse array of conditions collectively known as skin lesions, which encompass various dermatoses. Diagnosing these lesions presents significant challenges for medical practitioners due to the subtle visual differences that are often imperceptible to the naked eye. While not all skin lesions are life-threatening, certain types can act as early indicators of severe diseases, including skin cancers, underscoring the critical need for timely and accurate diagnostic methods. Deep learning algorithms have demonstrated remarkable potential in facilitating the early detection and prognosis of skin lesions. This study advances the field by curating a comprehensive and diverse dataset comprising 39 categories of skin lesions, synthesized from five publicly available datasets. Using this dataset, the performance of five state-of-the-art deep learning models -- MobileNetV2, Xception, InceptionV3, EfficientNetB1, and Vision Transformer - is rigorously evaluated. To enhance the accuracy and robustness of these models, attention mechanisms such as the Efficient Channel Attention (ECA) and the Convolutional Block Attention Module (CBAM) are incorporated into their architectures. Comprehensive evaluation across multiple performance metrics reveals that the Vision Transformer model integrated with CBAM outperforms others, achieving an accuracy of 93.46%, precision of 94%, recall of 93%, F1-score of 93%, and specificity of 93.67%. These results underscore the significant potential of the proposed system in supporting medical professionals with accurate and efficient prognostic tools for diagnosing a broad spectrum of skin lesions. The dataset and code used in this study can be found at https://github.com/akabircs/Skin-Lesions-Classification.

Automatic text summarization, particularly headline generation, remains a critical yet underexplored area for Bengali religious news. Existing approaches to headline generation typically rely solely on the article content, overlooking crucial contextual features such as sentiment, category, and aspect. This limitation significantly hinders their effectiveness and overall performance. This study addresses this limitation by introducing a novel corpus, BeliN (Bengali Religious News) - comprising religious news articles from prominent Bangladeshi online newspapers, and MultiGen - a contextual multi-input feature fusion headline generation approach. Leveraging transformer-based pre-trained language models such as BanglaT5, mBART, mT5, and mT0, MultiGen integrates additional contextual features - including category, aspect, and sentiment - with the news content. This fusion enables the model to capture critical contextual information often overlooked by traditional methods. Experimental results demonstrate the superiority of MultiGen over the baseline approach that uses only news content, achieving a BLEU score of 18.61 and ROUGE-L score of 24.19, compared to baseline approach scores of 16.08 and 23.08, respectively. These findings underscore the importance of incorporating contextual features in headline generation for low-resource languages. By bridging linguistic and cultural gaps, this research advances natural language processing for Bengali and other underrepresented languages. To promote reproducibility and further exploration, the dataset and implementation code are publicly accessible at https://github.com/akabircs/BeliN.

Arupa Barua, Md Osama, Ashim Dey. Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages. 2025.

Farjana Alam Tofa, Khadiza Sultana Sayma, Md Osama, Ashim Dey. Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages. 2025.

Khadiza Sultana Sayma, Farjana Alam Tofa, Md Osama, Ashim Dey. Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages. 2025.

The total amount of waste is increasing all around the world day-by-day especially in urban areas. The increasing amount of unprocessed waste is very dangerous to mankind as it creates severe pollution in the environment. Most of this wastage is recyclable. For recycling, the waste needs to be separated at first, as different types of waste require different recycling techniques. But unfortunately, categorizing waste manually is very costly and time-consuming. So, in this work, a method is proposed to automatically classify waste into four categories. For this, a dataset named OrgalidWaste is prepared by collecting images from four other waste datasets. The prepared dataset contains around 5600 images with four classes including one organic waste class and three solid waste classes (glass, metal, and plastic). On this dataset, several CNN architectures including 3-layer CNN, VGG16, VGG19, Inception-V3, and ResNet50 have been implemented for training. Among them, VGG16 outperforms other models with 88.42% accuracy. It is believed that this work will be greatly beneficial in the waste management sector.