Md. Kamrul Hasan

Syed Rifat Raiyan, Md. Nafis Faiyaz, Shah Md. Jawad Kabir et al.

The art of mathematical reasoning stands as a fundamental pillar of intellectual progress and is a central catalyst in cultivating human ingenuity. Researchers have recently published a plethora of works centered around the task of solving Math Word Problems (MWP) $-$ a crucial stride towards general AI. These existing models are susceptible to dependency on shallow heuristics and spurious correlations to derive the solution expressions. In order to ameliorate this issue, in this paper, we propose a framework for MWP solvers based on the generation of linguistic variants of the problem text. The approach involves solving each of the variant problems and electing the predicted expression with the majority of the votes. We use DeBERTa (Decoding-enhanced BERT with disentangled attention) as the encoder to leverage its rich textual representations and enhanced mask decoder to construct the solution expressions. Furthermore, we introduce a challenging dataset, $\mathrm{P\small{ARA}\normalsize{MAWPS}}$, consisting of paraphrased, adversarial, and inverse variants of selectively sampled MWPs from the benchmark $\mathrm{M\small{AWPS}}$ dataset. We extensively experiment on this dataset along with other benchmark datasets using some baseline MWP solver models. We show that training on linguistic variants of problem statements and voting on candidate predictions improve the mathematical reasoning and robustness of the model. We make our code and data publicly available.

Md Kamrul Hasan, Md Saiful Islam, Sangwu Lee et al.

Pre-trained large language models have recently achieved ground-breaking performance in a wide variety of language understanding tasks. However, the same model can not be applied to multimodal behavior understanding tasks (e.g., video sentiment/humor detection) unless non-verbal features (e.g., acoustic and visual) can be integrated with language. Jointly modeling multiple modalities significantly increases the model complexity, and makes the training process data-hungry. While an enormous amount of text data is available via the web, collecting large-scale multimodal behavioral video datasets is extremely expensive, both in terms of time and money. In this paper, we investigate whether large language models alone can successfully incorporate non-verbal information when they are presented in textual form. We present a way to convert the acoustic and visual information into corresponding textual descriptions and concatenate them with the spoken text. We feed this augmented input to a pre-trained BERT model and fine-tune it on three downstream multimodal tasks: sentiment, humor, and sarcasm detection. Our approach, TextMI, significantly reduces model complexity, adds interpretability to the model's decision, and can be applied for a diverse set of tasks while achieving superior (multimodal sarcasm detection) or near SOTA (multimodal sentiment analysis and multimodal humor detection) performance. We propose TextMI as a general, competitive baseline for multimodal behavioral analysis tasks, particularly in a low-resource setting.

Md. Farhadul Islam, Sarah Zabeen, Meem Arafat Manab et al.

The majority of medical images, especially those that resemble cells, have similar characteristics. These images, which occur in a variety of shapes, often show abnormalities in the organ or cell region. The convolution operation possesses a restricted capability to extract visual patterns across several spatial regions of an image. The involution process, which is the inverse operation of convolution, complements this inherent lack of spatial information extraction present in convolutions. In this study, we investigate how applying a single layer of involution prior to a convolutional neural network (CNN) architecture can significantly improve classification and segmentation performance, with a comparatively negligible amount of weight parameters. The study additionally shows how excessive use of involution layers might result in inaccurate predictions in a particular type of medical image. According to our findings from experiments, the strategy of adding only a single involution layer before a CNN-based model outperforms most of the previous works.

Oshayer Siddique, J. M Areeb Uzair Alam, Md Jobayer Rahman Rafy et al.

The discipline of physics stands as a cornerstone of human intellect, driving the evolution of technology and deepening our understanding of the fundamental principles of the cosmos. Contemporary literature includes some works centered on the task of solving physics problems - a crucial domain of natural language reasoning. In this paper, we evaluate the performance of frontier LLMs in solving physics problems, both mathematical and descriptive. We also employ a plethora of inference-time techniques and agentic frameworks to improve the performance of the models. This includes the verification of proposed solutions in a cumulative fashion by other, smaller LLM agents, and we perform a comparative analysis of the performance that the techniques entail. There are significant improvements when the multi-agent framework is applied to problems that the models initially perform poorly on. Furthermore, we introduce a new evaluation benchmark for physics problems, ${\rm P{\small HYSICS}E{\small VAL}}$, consisting of 19,609 problems sourced from various physics textbooks and their corresponding correct solutions scraped from physics forums and educational websites. Our code and data are publicly available at https://github.com/areebuzair/PhysicsEval.

Md. Kamrul Hasan, Guang Yang, Choon Hwai Yap

Cardiac anatomy segmentation is useful for clinical assessment of cardiac morphology to inform diagnosis and intervention. Deep learning (DL), especially with motion information, has improved segmentation accuracy. However, existing techniques for motion enhancement are not yet optimal, and they have high computational costs due to increased dimensionality or reduced robustness due to suboptimal approaches that use non-DL motion registration, non-attention models, or single-headed attention. They further have limited adaptability and are inconvenient for incorporation into existing networks where motion awareness is desired. Here, we propose a novel, computationally efficient Temporal Attention Module (TAM) that offers robust motion enhancement, modeled as a small, multi-headed, cross-temporal attention module. TAM's uniqueness is that it is a lightweight, plug-and-play module that can be inserted into a broad range of segmentation networks (CNN-based, Transformer-based, or hybrid) for motion enhancement without requiring substantial changes in the network's backbone. This feature enables high adaptability and ease of integration for enhancing both existing and future networks. Extensive experiments on multiple 2D and 3D cardiac ultrasound and MRI datasets confirm that TAM consistently improves segmentation across a range of networks while maintaining computational efficiency and improving on currently reported performance. The evidence demonstrates that it is a robust, generalizable solution for motion-awareness enhancement that is scalable (such as from 2D to 3D).

Md. Tariquzzaman, Audwit Nafi Anam, Naimul Haque et al.

Data augmentation involves generating synthetic samples that resemble those in a given dataset. In resource-limited fields where high-quality data is scarce, augmentation plays a crucial role in increasing the volume of training data. This paper introduces a Bangla Text Data Augmentation (BDA) Framework that uses both pre-trained models and rule-based methods to create new variants of the text. A filtering process is included to ensure that the new text keeps the same meaning as the original while also adding variety in the words used. We conduct a comprehensive evaluation of the framework's effectiveness in Bangla text classification tasks. Our framework achieved significant improvement in F1 scores across five distinct datasets, delivering performance equivalent to models trained on 100% of the data while utilizing only 50% of the training dataset. Additionally, we explore the impact of data scarcity by progressively reducing the training data and augmenting it through BDA, resulting in notable F1 score enhancements. The study offers a thorough examination of BDA's performance, identifying key factors for optimal results and addressing its limitations through detailed analysis.

Md. Kamrul Hasan, Haobo Zhu, Guang Yang et al.

Temporal echocardiography image registration is a basis for clinical quantifications such as cardiac motion estimation, myocardial strain assessments, and stroke volume quantifications. In past studies, deep learning image registration (DLIR) has shown promising results and is consistently accurate and precise, requiring less computational time. We propose that a greater focus on the warped moving image's anatomic plausibility and image quality can support robust DLIR performance. Further, past implementations have focused on adult echocardiography, and there is an absence of DLIR implementations for fetal echocardiography. We propose a framework that combines three strategies for DLIR in both fetal and adult echo: (1) an anatomic shape-encoded loss to preserve physiological myocardial and left ventricular anatomical topologies in warped images; (2) a data-driven loss that is trained adversarially to preserve good image texture features in warped images; and (3) a multi-scale training scheme of a data-driven and anatomically constrained algorithm to improve accuracy. Our tests show that good anatomical topology and image textures are strongly linked to shape-encoded and data-driven adversarial losses. They improve different aspects of registration performance in a non-overlapping way, justifying their combination. Despite fundamental distinctions between adult and fetal echo images, we show that these strategies can provide excellent registration results in both adult and fetal echocardiography using the publicly available CAMUS adult echo dataset and our private multi-demographic fetal echo dataset. Our approach outperforms traditional non-DL gold standard registration approaches, including Optical Flow and Elastix. Registration improvements could be translated to more accurate and precise clinical quantification of cardiac ejection fraction, demonstrating a potential for translation.

Md. Kamrul Hasan, Sifat Redwan Wahid, Faria Rahman et al.

People undergoing neuromuscular dysfunctions and amputated limbs require automatic prosthetic appliances. In developing such prostheses, the precise detection of brain motor actions is imperative for the Grasp-and-Lift (GAL) tasks. Because of the low-cost and non-invasive essence of Electroencephalography (EEG), it is widely preferred for detecting motor actions during the controls of prosthetic tools. This article has automated the hand movement activity viz GAL detection method from the 32-channel EEG signals. The proposed pipeline essentially combines preprocessing and end-to-end detection steps, eliminating the requirement of hand-crafted feature engineering. Preprocessing action consists of raw signal denoising, using either Discrete Wavelet Transform (DWT) or highpass or bandpass filtering and data standardization. The detection step consists of Convolutional Neural Network (CNN)- or Long Short Term Memory (LSTM)-based model. All the investigations utilize the publicly available WAY-EEG-GAL dataset, having six different GAL events. The best experiment reveals that the proposed framework achieves an average area under the ROC curve of 0.944, employing the DWT-based denoising filter, data standardization, and CNN-based detection model. The obtained outcome designates an excellent achievement of the introduced method in detecting GAL events from the EEG signals, turning it applicable to prosthetic appliances, brain-computer interfaces, robotic arms, etc.

Hasan Mahmud, Mashrur M. Morshed, Md. Kamrul Hasan

The dynamic hand gesture recognition task has seen studies on various unimodal and multimodal methods. Previously, researchers have explored depth and 2D-skeleton-based multimodal fusion CRNNs (Convolutional Recurrent Neural Networks) but have had limitations in getting expected recognition results. In this paper, we revisit this approach to hand gesture recognition and suggest several improvements. We observe that raw depth images possess low contrast in the hand regions of interest (ROI). They do not highlight important fine details, such as finger orientation, overlap between the finger and palm, or overlap between multiple fingers. We thus propose quantizing the depth values into several discrete regions, to create a higher contrast between several key parts of the hand. In addition, we suggest several ways to tackle the high variance problem in existing multimodal fusion CRNN architectures. We evaluate our method on two benchmarks: the DHG-14/28 dataset and the SHREC'17 track dataset. Our approach shows a significant improvement in accuracy and parameter efficiency over previous similar multimodal methods, with a comparable result to the state-of-the-art.

Ovishake Sen, Mohtasim Fuad, MD. Nazrul Islam et al.

The Bangla language is the seventh most spoken language, with 265 million native and non-native speakers worldwide. However, English is the predominant language for online resources and technical knowledge, journals, and documentation. Consequently, many Bangla-speaking people, who have limited command of English, face hurdles to utilize English resources. To bridge the gap between limited support and increasing demand, researchers conducted many experiments and developed valuable tools and techniques to create and process Bangla language materials. Many efforts are also ongoing to make it easy to use the Bangla language in the online and technical domains. There are some review papers to understand the past, previous, and future Bangla Natural Language Processing (BNLP) trends. The studies are mainly concentrated on the specific domains of BNLP, such as sentiment analysis, speech recognition, optical character recognition, and text summarization. There is an apparent scarcity of resources that contain a comprehensive review of the recent BNLP tools and methods. Therefore, in this paper, we present a thorough analysis of 75 BNLP research papers and categorize them into 11 categories, namely Information Extraction, Machine Translation, Named Entity Recognition, Parsing, Parts of Speech Tagging, Question Answering System, Sentiment Analysis, Spam and Fake Detection, Text Summarization, Word Sense Disambiguation, and Speech Processing and Recognition. We study articles published between 1999 to 2021, and 50% of the papers were published after 2015. Furthermore, we discuss Classical, Machine Learning and Deep Learning approaches with different datasets while addressing the limitations and current and future trends of the BNLP.

Taylan K. Sen, Gazi Naven, Luke Gerstner et al.

In this work, we present a database of multimodal communication features extracted from debate speeches in the 2019 North American Universities Debate Championships (NAUDC). Feature sets were extracted from the visual (facial expression, gaze, and head pose), audio (PRAAT), and textual (word sentiment and linguistic category) modalities of raw video recordings of competitive collegiate debaters (N=717 6-minute recordings from 140 unique debaters). Each speech has an associated competition debate score (range: 67-96) from expert judges as well as competitor demographic and per-round reflection surveys. We observe the fully multimodal model performs best in comparison to models trained on various compositions of modalities. We also find that the weights of some features (such as the expression of joy and the use of the word we) change in direction between the aforementioned models. We use these results to highlight the value of a multimodal dataset for studying competitive, collegiate debate.

Md. Kamrul Hasan, Md. Tasnim Jawad, Kazi Nasim Imtiaz Hasan et al.

The novel COVID-19 is a global pandemic disease overgrowing worldwide. Computer-aided screening tools with greater sensitivity is imperative for disease diagnosis and prognosis as early as possible. It also can be a helpful tool in triage for testing and clinical supervision of COVID-19 patients. However, designing such an automated tool from non-invasive radiographic images is challenging as many manually annotated datasets are not publicly available yet, which is the essential core requirement of supervised learning schemes. This article proposes a 3D Convolutional Neural Network (CNN)-based classification approach considering both the inter- and intra-slice spatial voxel information. The proposed system is trained in an end-to-end manner on the 3D patches from the whole volumetric CT images to enlarge the number of training samples, performing the ablation studies on patch size determination. We integrate progressive resizing, segmentation, augmentations, and class-rebalancing to our 3D network. The segmentation is a critical prerequisite step for COVID-19 diagnosis enabling the classifier to learn prominent lung features while excluding the outer lung regions of the CT scans. We evaluate all the extensive experiments on a publicly available dataset, named MosMed, having binary- and multi-class chest CT image partitions. Our experimental results are very encouraging, yielding areas under the ROC curve of 0.914 and 0.893 for the binary- and multi-class tasks, respectively, applying 5-fold cross-validations. Our method's promising results delegate it as a favorable aiding tool for clinical practitioners and radiologists to assess COVID-19.

Wasifur Rahman, Md. Kamrul Hasan, Sangwu Lee et al.

Recent Transformer-based contextual word representations, including BERT and XLNet, have shown state-of-the-art performance in multiple disciplines within NLP. Fine-tuning the trained contextual models on task-specific datasets has been the key to achieving superior performance downstream. While fine-tuning these pre-trained models is straightforward for lexical applications (applications with only language modality), it is not trivial for multimodal language (a growing area in NLP focused on modeling face-to-face communication). Pre-trained models don't have the necessary components to accept two extra modalities of vision and acoustic. In this paper, we proposed an attachment to BERT and XLNet called Multimodal Adaptation Gate (MAG). MAG allows BERT and XLNet to accept multimodal nonverbal data during fine-tuning. It does so by generating a shift to internal representation of BERT and XLNet; a shift that is conditioned on the visual and acoustic modalities. In our experiments, we study the commonly used CMU-MOSI and CMU-MOSEI datasets for multimodal sentiment analysis. Fine-tuning MAG-BERT and MAG-XLNet significantly boosts the sentiment analysis performance over previous baselines as well as language-only fine-tuning of BERT and XLNet. On the CMU-MOSI dataset, MAG-XLNet achieves human-level multimodal sentiment analysis performance for the first time in the NLP community.

Md. Kamrul Hasan, Tajwar Abrar Aleef

Mammography is the most widely used gold standard for screening breast cancer, where, mass detection is considered as the prominent step. Detecting mass in the breast is, however, an arduous problem as they usually have large variations between them in terms of shape, size, boundary, and texture. In this literature, the process of mass detection is automated with the use of transfer learning techniques of Deep Convolutional Neural Networks (DCNN). Pre-trained VGG19 network is used to extract features which are then followed by bagged decision tree for features selection and then a Support Vector Machine (SVM) classifier is trained and used for classifying between the mass and non-mass. Area Under ROC Curve (AUC) is chosen as the performance metric, which is then maximized during classifier selection and hyper-parameter tuning. The robustness of the two selected type of classifiers, C-SVM, and \u{psion}-SVM, are investigated with extensive experiments before selecting the best performing classifier. All experiments in this paper were conducted using the INbreast dataset. The best AUC obtained from the experimental results is 0.994 +/- 0.003 i.e. [0.991, 0.997]. Our results conclude that by using pre-trained VGG19 network, high-level distinctive features can be extracted from Mammograms which when used with the proposed SVM classifier is able to robustly distinguish between the mass and non-mass present in breast.

Md Kamrul Hasan, Christopher J. Pal

We examine a new form of smooth approximation to the zero one loss in which learning is performed using a reformulation of the widely used logistic function. Our approach is based on using the posterior mean of a novel generalized Beta-Bernoulli formulation. This leads to a generalized logistic function that approximates the zero one loss, but retains a probabilistic formulation conferring a number of useful properties. The approach is easily generalized to kernel logistic regression and easily integrated into methods for structured prediction. We present experiments in which we learn such models using an optimization method consisting of a combination of gradient descent and coordinate descent using localized grid search so as to escape from local minima. Our experiments indicate that optimization quality is improved when learning meta-parameters are themselves optimized using a validation set. Our experiments show improved performance relative to widely used logistic and hinge loss methods on a wide variety of problems ranging from standard UC Irvine and libSVM evaluation datasets to product review predictions and a visual information extraction task. We observe that the approach: 1) is more robust to outliers compared to the logistic and hinge losses; 2) outperforms comparable logistic and max margin models on larger scale benchmark problems; 3) when combined with Gaussian- Laplacian mixture prior on parameters the kernelized version of our formulation yields sparser solutions than Support Vector Machine classifiers; and 4) when integrated into a probabilistic structured prediction technique our approach provides more accurate probabilities yielding improved inference and increasing information extraction performance.

Md. Rakib Hassan, Md. Kamrul Hasan, M. M. A. Hashem

Solving large traveling salesman problem (TSP) in an efficient way is a challenging area for the researchers of computer science. This paper presents a modified version of the ant colony system (ACS) algorithm called Red-Black Ant Colony System (RB-ACS) for the solutions of TSP which is the most prominent member of the combinatorial optimization problem. RB-ACS uses the concept of ant colony system together with the parallel search of genetic algorithm for obtaining the optimal solutions quickly. In this paper, it is shown that the proposed RB-ACS algorithm yields significantly better performance than the existing best-known algorithms.