Md Ashraful Amin

Independent University Bangladesh · Computer Science & Engineering

This research explores the performance of various language models for generating Bangla text, with an emphasis on the task of text abstractive summarization, specifically newspaper headline generation. Given the concern regarding the lack of diversity in previous newspaper article datasets, we have created a dataset from Bangla online newspapers, f...

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains challenging. This process demands acoustic, semantic, and contextual information for precise speech representations. Ex...

Social media users express their feelings, experiences, ideas, and stories with little or no regard for the conventions of traditional grammar. Online discourse, by its very nature, is rife with transliterated text along with code-mixing and code-switching. Transliteration is heavily featured due to the ease of inputting romanized text with standar...

Land Use Land Cover (LULC) analysis on satellite images using deep learning-based methods is significantly helpful in understanding the geography, socio-economic conditions, poverty levels, and urban sprawl in developing countries. Recent works involve segmentation with LULC classes such as farmland, built-up areas, forests, meadows, water bodies,...

Deep learning models for traffic forecasting gained a lot of success in recent years. Important application in traffic domain is to predict traffic congestion after certain time window based on historical data. While most of the deep learning models are evaluated using well-known traffic dataset containing vehicle speed collected using loop detecto...

Background Hilsa shad (Tenualosa ilisha) is a popular anadromous fish in Bangladesh known to cause allergies. Despite recognized allergenicity, there is a paucity of research at the molecular level on hilsa allergen. Method Muscle transcriptomes of hilsa from freshwater, brackish, and deep sea habitats were sequenced using Illumina NovaSeq 6000 an...

The emergence of gestational diabetes mellitus (GDM) in pregnant women is a serious health concern and an alarming issue. According to the most recent data from the International Diabetes Federation (IDF), in 2021, 16.7% of pregnant women had GDM, affecting 21.1 million live births [1]. Predictive models using an Explainable AI (XAI) technique to d...

Stroke-induced physical disabilities necessitate consistent and effective rehabilitation exercises. While a typical regime encompasses 20–60 min daily, ensuring adherence and effectiveness remains a challenge due to lengthy recovery periods, potential demotivation, and the need for professional supervision. This paper presents an innovative home-ba...

In recent years, healthcare and safety have been a major focus of deep learning research. This paper focuses on the detection of Medical Personal Protective Equipment (MPPE) in the healthcare sector using YOLOv7. Improper use of personal protective equipment (PPE) can result in the contamination and cross-contamination of infectious diseases, so it...

The silver pride of Bangladesh, migratory shad, Tenualosa ilisha (Hilsa), makes the highest contribution to the total fish production of Bangladesh. Despite its noteworthy contribution, a well-annotated transcriptome data is not available. Here we report a transcriptomic catalog of Hilsa, constructed by assembling RNA-Seq reads from different tissu...

The number of heart disease cases as well as the death associated with it are rising in numbers every year. It is now more important than ever to diagnose heart abnormalities quickly and correctly to ensure proper treatment is provided in time. A common tool for diagnosing heart abnormalities is the Electrocardiogram (ECG). The ECG is a procedure t...

Kidney tumor is a health concern that affects kidney cells and may leads to mortality depending on their type. Benign tumors can be unproblematic whereas malignant tumors pose the threat of kidney cancer. Early detection and diagnosis are possible through kidney tumor recognition based on deep learning techniques. In this paper, a method based...

The silver pride of Bangladesh, migratory shad, Tenualosa ilisha (Hilsa), makes the highest contribution to the total fish production of Bangladesh. Despite its noteworthy contribution, a well-annotated transcriptome data is not available. Here we report a transcriptomic catalog of Hilsa, constructed by assembling RNA-Seq reads from different tissu...

This paper aims to detect rice field damage from natural disasters in Bangladesh using high-resolution satellite imagery. The authors developed ground truth data for rice field damage from the field level. At first, NDVI differences before and after the disaster are calculated to identify possible crop loss. The areas equal to and above the 0.33 th...

Neuromarketing is a modern marketing research technique whereby consumers' behavior is analyzed using neuroscientifc approaches. In this work, an EEG database of consumers' responses to image advertisements was created, processed, and studied with the goal of building predictive models that can classify the consumers' preference based on their EEG...

Out of the estimated few trillion galaxies, only around a million have been detected through radio frequencies, and only a tiny fraction, approximately a thousand, have been manually classified. We have addressed this disparity between labeled and unlabeled images of radio galaxies by employing a semi-supervised learning approach to classify them i...

The study of brain-to-brain synchrony has a burgeoning application in the brain-computer interface (BCI) research, offering valuable insights into the neural underpinnings of interacting human brains using numerous neural recording technologies. The area allows exploring the commonality of brain dynamics by evaluating the neural synchronization amo...

While describing Spatio-temporal events in natural language, video captioning models mostly rely on the encoder's latent visual representation. Recent progress on the encoder-decoder model attends encoder features mainly in linear interaction with the decoder. However, growing model complexity for visual data encourages more explicit feature intera...

Depression is the most common mental illness, which has become the major cause of fear and suicidal mortality or tendencies. Currently, about 10% of the world population has been suffering from depression. The classical approach for detecting depression relies on the clinical questionnaire, which depends on the patients’ responses as well as observ...

Decomposition of the evidence lower bound (ELBO) objective of VAE used for density estimation revealed the deficiency of VAE for representation learning and suggested ways to improve the model. In this paper, we investigate whether we can get similar insights by decomposing the ELBO for semi-supervised classification using VAE model. Specifically,...

Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. For these tasks, different pooling strategies have been proposed to generate a graph-level representation by downsampling and summarizing nodes’ features in a graph. However, most existing pooling methods are unable to capture dist...

Research in deep learning models to forecast traffic intensities has gained great attention in recent years due to their capability to capture the complex spatio-temporal relationships within the traffic data. However, most state-of-the-art approaches have designed spatial-only (e.g. Graph Neural Networks) and temporal-only (e.g. Recurrent Neural N...

Graph Neural Networks (GNNs) learn low dimensional representations of nodes by aggregating information from their neighborhood in graphs. However, traditional GNNs suffer from two fundamental shortcomings due to their local (l-hop neighborhood) aggregation scheme. First, not all nodes in the neighborhood carry relevant information for the target no...

The advancement of deep learning technology has enabled us to develop systems that outperform any other classification technique. However, success of any empirical system depends on the quality and diversity of the data available to train the proposed system. In this research, we have carefully accumulated a relatively challenging dataset that cont...

High-resolution image segmentation remains challenging and error-prone due to the enormous size of intermediate feature maps. Conventional methods avoid this problem by using patch based approaches where each patch is segmented independently. However, independent patch segmentation induces errors, particularly at the patch boundary due to the lack...

The novel coronavirus pandemic has brought our concern towards the necessity of digital infrastructure for remote monitoring of infected people as well as the people who are with close contact with them. Though, many nations have finished the clinical trials period of vaccination and started vaccination to people, still there are many uncertainties...

To capture spatial relationships and temporal dynamics in traffic data, spatio-temporal models for traffic forecasting have drawn significant attention in recent years. Most of the recent works employed graph neural networks(GNN) with multiple layers to capture the spatial dependency. However, road junctions with different hop-distance can carry di...

Wearable sensor based human activity recognition is a challenging problem due to difficulty in modeling spatial and temporal dependencies of sensor signals. Recognition models in closed-set assumption are forced to yield members of known activity classes as prediction. However, activity recognition models can encounter an unseen activity due to bod...

Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. For these tasks, different pooling strategies have been proposed to generate a graph-level representation by downsampling and summarizing nodes' features in a graph. However, most existing pooling methods are unable to capture dist...

Graph Neural Networks (GNNs) learn low dimensional representations of nodes by aggregating information from their neighborhood in graphs. However, traditional GNNs suffer from two fundamental shortcomings due to their local ($l$-hop neighborhood) aggregation scheme. First, not all nodes in the neighborhood carry relevant information for the target...

Research in deep learning models to forecast traffic intensities has gained great attention in recent years due to their capability to capture the complex spatio-temporal relationships within the traffic data. However, most state-of-the-art approaches have designed spatial-only (e.g. Graph Neural Networks) and temporal-only (e.g. Recurrent Neural N...

Traffic congestion research is on the rise, thanks to urbanization, economic growth, and industrialization. Developed countries invest a lot of research money in collecting traffic data using Radio Frequency Identification (RFID), loop detectors, speed sensors, high-end traffic light, and GPS. However, these processes are expensive, infeasible, and...

Motor disability due to stroke, accident, or other illnesses in many cases can be partially or fully recovered with guided and/or prescribed physiotherapy. Moreover, due to the nature of the problem, in most of the case, the treatment is needed to be continued for years. Thus, one of the main challenges in this is the availability of an expert phys...

To capture spatial relationships and temporal dynamics in traffic data, spatio-temporal models for traffic forecasting have drawn significant attention in recent years. Most of the recent works employed graph neural networks(GNN) with multiple layers to capture the spatial dependency. However, road junctions with different hop-distance can carry di...

Wearable sensor based human activity recognition is a challenging problem due to difficulty in modeling spatial and temporal dependencies of sensor signals. Recognition models in closed-set assumption are forced to yield members of known activity classes as prediction. However, activity recognition models can encounter an unseen activity due to bod...

Rapid globalization and the interdependence of the countries have engendered tremendous in-flow of human migration towards the urban spaces. With the advent of high definition satellite images, high-resolution data, computational methods such as deep neural network analysis, and hardware capable of high-speed analysis; urban planning is seeing a pa...

The availability of images of events almost in real-time on social media has a prospect in many application developments. A humanitarian technology for disaster type and level assessment can be developed using the images and video available on social media. In this paper, we investigate the potential use of various available deep learning technique...

The energy crisis has two sides to it; first, the demand is increasing exponentially as per day progress, and the other one is: fossil fuel is perishing at a faster rate than ever before. In order to mitigate this ever-growing demand usual conventional sources are on the play such as coal, oil, and natural gas. Solar energy, which utilizes sun lig...

Rapid globalization and the interdependence of humanity that engender tremendous in-flow of human migration towards the urban spaces. With advent of high definition satellite images, high resolution data, computational methods such as deep neural network, capable hardware; urban planning is seeing a paradigm shift. Legacy data on urban environments...

Traffic congestion research is on the rise, thanks to urbanization, economic growth, and industrialization. Developed countries invest a lot of research money in collecting traffic data using Radio Frequency Identification (RFID), loop detectors, speed sensors, high-end traffic light, and GPS. However, these processes are expensive, infeasible, and...

This paper demonstrates an application which provides vehicle monitoring and tracking system to prevent sexual/physical harassment in public transport via IoT-based smart technology. In the current scenario of public transport in Bangladesh and all over the world, especially females who usually travel in public transport for various purposes are mo...

This work presents use of Fully Convolutional Network (FCN-8) for semantic segmentation of high-resolution RGB earth surface satel-lite images into land use land cover (LULC) categories. Specically, we propose a non-overlapping grid-based approach to train a Fully Convo-lutional Network (FCN-8) with vgg-16 weights to segment satellite im-ages into...

Contamination of electroencephalogram (EEG) signals due to natural blinking electrooculogram (EOG) signals is often removed to enhance the quality of EEG signals. This paper discusses the possibility of using solely involuntary blinking signals for human authentication. The EEG data of 46 subjects were recorded while the subject was looking at a se...

Human Activity Recognition from body-worn sensor data poses an inherent challenge in capturing spatial and temporal dependencies of time-series signals. In this regard, the existing recurrent or convolutional or their hybrid models for activity recognition struggle to capture spatio-temporal context from the feature space of sensor reading sequence...

Human Activity Recognition from body-worn sensor data poses an inherent challenge in capturing spatial and temporal dependencies of time-series signals. In this regard, the existing recurrent or convolutional or their hybrid models for activity recognition struggle to capture spatio-temporal context from the feature space of sensor reading sequence...

Monitoring the environment of a certain area provides information that is useful in knowing climate change, level of pollution, the effect on human health and their way of life. In this paper, design, and implementation of a low-cost and portable environment monitoring system is proposed. The proposed system is designed and built exploiting Interne...

Word embeddings are vector representations of word that allow machines to learn semantic and syntactic meanings by performing computations on them. Two well- known embedding models are CBOW and Skipgram. Different methods proposed to evaluate the quality of embeddings are categorized into extrinsic and intrinsic evaluation methods. This paper focus...