Abu Kaisar Mohammad Masum

Sabrina Hassan Moon, Abu Kaisar Mohammad Masum, Sercan Aygun et al.

Hyperdimensional computing (HDC) is a promising approach for energy-efficient edge machine learning (ML), where low latency, low power, and tight memory budgets are essential. However, traditional HDC relies on symbolic binding and pseudo-random high-dimensional vectors, which require large dimensionality and heuristic updates to reach competitive accuracy, limiting deployment on edge hardware. We introduce XL-HD, a deterministic, projection-based, fully learnable HDC framework tailored for in-memory acceleration within edge computing systems. The method uses a fixed Sobol sequence to project binary inputs, extending learning beyond conventional HDC. During training, class prototypes are optimized in real-valued space and later binarized, enabling an entirely binary dot-product inference pipeline ideal for IMC hardware such as ReRAM crossbars. XL-HD achieves competitive accuracy on MNIST, UCIHAR, and ISOLET while maintaining a compact IMC-based inference engine with $0.395 \ \text{mm}^2$ area and only $0.40 \ μ\text{J}$ per single-cycle inference.

Jabir Al Nahian, Abu Kaisar Mohammad Masum

Plagiarism is the practice of claiming to be someone else content, thoughts or ideas as one own without any proper credit and citations. This paper is a survey paper that, represent the some of the great research paper and its comparison that is work done on plagiarism. Now a days, plagiarism became one of the most interesting and crucial research points in Natural Language Processing area. We review some old research paper based on different types of plagiarism detection and their models and algorithm, and comparison of the accuracy of those papers. There are many several ways which are available for plagiarism detection in different language. There are a few algorithms to detecting plagiarism. Like, corpus, CL-CNG, LSI, Levenshtein Distance etc. We analysis those papers, and learn that they used different types of algorithms for detecting plagiarism. After experiment those papers, we got that some of the algorithms give a better output and accuracy for detecting plagiarism. We are going to give a review on some papers about Plagiarism and will discuss about the pros and cons of their models. And we also show a propose method for plagiarism detection method which based on sentience separation, word separation and make sentence based on synonym and compare with any sources.

Abu Kaisar Mohammad Masum, Nusrat Badhon, S. M. Saiful Islam Badhon et al.

Abnormal growth of cells in the brain and its surrounding tissues is known as a brain tumor. There are two types, one is benign (non-cancerous) and another is malignant (cancerous) which may cause death. The radiologists' ability to diagnose malignancies is greatly aided by magnetic resonance imaging (MRI). Brain cancer diagnosis has been considerably expedited by the field of computer-assisted diagnostics, especially in machine learning and deep learning. In our study, we categorize three different kinds of brain tumors using four transfer learning techniques. Our models were tested on a benchmark dataset of $3064$ MRI pictures representing three different forms of brain cancer. Notably, ResNet-50 outperformed other models with a remarkable accuracy of $99.06\%$. We stress the significance of a balanced dataset for improving accuracy without the use of augmentation methods. Additionally, we experimentally demonstrate our method and compare with other classification algorithms on the CE-MRI dataset using evaluations like F1-score, AUC, precision and recall.

Abu Kaisar Mohammad Masum, Anshul Maurya, Dhruthi Sridhar Murthy et al.

The collaboration between quantum computing and classical machine learning offers potential advantages in natural language processing, particularly in the sentiment analysis of human emotions and opinions expressed in large-scale datasets. In this work, we propose a methodology for sentiment analysis using hybrid quantum-classical machine learning algorithms. We investigate quantum kernel approaches and variational quantum circuit-based classifiers and integrate them with classical dimension reduction techniques such as PCA and Haar wavelet transform. The proposed methodology is evaluated using two distinct datasets, based on English and Bengali languages. Experimental results show that after dimensionality reduction of the data, performance of the quantum-based hybrid algorithms were consistent and better than classical methods.

Md. Zahin Hossain George, Naimul Hossain, Md. Rafiuzzaman Bhuiyan et al.

There have recently been many cases of unverified or misleading information circulating quickly over bogus web networks and news portals. This false news creates big damage to society and misleads people. For Example, in 2019, there was a rumor that the Padma Bridge of Bangladesh needed 100,000 human heads for sacrifice. This rumor turns into a deadly position and this misleading information takes the lives of innocent people. There is a lot of work in English but a few works in Bangla. In this study, we are going to identify the fake news from the unconsidered news source to provide the newsreader with natural news or real news. The paper is based on the combination of convolutional neural network (CNN) and long short-term memory (LSTM), where CNN is used for deep feature extraction and LSTM is used for detection using the extracted feature. The first thing we did to deploy this piece of work was data collection. We compiled a data set from websites and attempted to deploy it using the methodology of deep learning which contains about 50k of news. With the proposed model of Multichannel combined CNN-LSTM architecture, our model gained an accuracy of 75.05%, which is a good sign for detecting fake news in Bangla.

Abu Kaisar Mohammad Masum, Naveed Mahmud, M. Hassan Najafi et al.

Fine-tuning BERT for text classification can be computationally challenging and requires careful hyper-parameter tuning. Recent studies have highlighted the potential of quantum algorithms to outperform conventional methods in machine learning and text classification tasks. In this work, we propose a hybrid approach that integrates an n-qubit quantum circuit with a classical BERT model for text classification. We evaluate the performance of the fine-tuned classical-quantum BERT and demonstrate its feasibility as well as its potential in advancing this research area. Our experimental results show that the proposed hybrid model achieves performance that is competitive with, and in some cases better than, the classical baselines on standard benchmark datasets. Furthermore, our approach demonstrates the adaptability of classical-quantum models for fine-tuning pre-trained models across diverse datasets. Overall, the hybrid model highlights the promise of quantum computing in achieving improved performance for text classification tasks.

Jabir Al Nahian, Abu Kaisar Mohammad Masum, Sheikh Abujar et al.

In this era, the moment has arrived to move away from disease as the primary emphasis of medical treatment. Although impressive, the multiple techniques that have been developed to detect the diseases. In this time, there are some types of diseases COVID-19, normal flue, migraine, lung disease, heart disease, kidney disease, diabetics, stomach disease, gastric, bone disease, autism are the very common diseases. In this analysis, we analyze disease symptoms and have done disease predictions based on their symptoms. We studied a range of symptoms and took a survey from people in order to complete the task. Several classification algorithms have been employed to train the model. Furthermore, performance evaluation matrices are used to measure the model's performance. Finally, we discovered that the part classifier surpasses the others.

Md. Mahadi Hasan Sany, Mumenunnesa Keya, Sharun Akter Khushbu et al.

The global world is crossing a pandemic situation where this is a catastrophic outbreak of Respiratory Syndrome recognized as COVID-19. This is a global threat all over the 212 countries that people every day meet with mighty situations. On the contrary, thousands of infected people live rich in mountains. Mental health is also affected by this worldwide coronavirus situation. Due to this situation online sources made a communicative place that common people shares their opinion in any agenda. Such as affected news related positive and negative, financial issues, country and family crisis, lack of import and export earning system etc. different kinds of circumstances are recent trendy news in anywhere. Thus, vast amounts of text are produced within moments therefore, in subcontinent areas the same as situation in other countries and peoples opinion of text and situation also same but the language is different. This article has proposed some specific inputs along with Bangla text comments from individual sources which can assure the goal of illustration that machine learning outcome capable of building an assistive system. Opinion mining assistive system can be impactful in all language preferences possible. To the best of our knowledge, the article predicted the Bangla input text on COVID-19 issues proposed ML algorithms and deep learning models analysis also check the future reachability with a comparative analysis. Comparative analysis states a report on text prediction accuracy is 91% along with ML algorithms and 79% along with Deep Learning Models.

Mirajul Islam, Nushrat Jahan Ria, Jannatul Ferdous Ani et al.

A deep learning model gives an incredible result for image processing by studying from the trained dataset. Spinach is a leaf vegetable that contains vitamins and nutrients. In our research, a Deep learning method has been used that can automatically identify spinach and this method has a dataset of a total of five species of spinach that contains 3785 images. Four Convolutional Neural Network (CNN) models were used to classify our spinach. These models give more accurate results for image classification. Before applying these models there is some preprocessing of the image data. For the preprocessing of data, some methods need to happen. Those are RGB conversion, filtering, resize & rescaling, and categorization. After applying these methods image data are pre-processed and ready to be used in the classifier algorithms. The accuracy of these classifiers is in between 98.68% - 99.79%. Among those models, VGG16 achieved the highest accuracy of 99.79%.

Abu Kaisar Mohammad Masum, Sheikh Abujar, Sharmin Akter et al.

An AI chatbot provides an impressive response after learning from the trained dataset. In this decade, most of the research work demonstrates that deep neural models superior to any other model. RNN model regularly used for determining the sequence-related problem like a question and it answers. This approach acquainted with everyone as seq2seq learning. In a seq2seq model mechanism, it has encoder and decoder. The encoder embedded any input sequence, and the decoder embedded output sequence. For reinforcing the seq2seq model performance, attention mechanism added into the encoder and decoder. After that, the transformer model has introduced itself as a high-performance model with multiple attention mechanism for solving the sequence-related dilemma. This model reduces training time compared with RNN based model and also achieved state-of-the-art performance for sequence transduction. In this research, we applied the transformer model for Bengali general knowledge chatbot based on the Bengali general knowledge Question Answer (QA) dataset. It scores 85.0 BLEU on the applied QA data. To check the comparison of the transformer model performance, we trained the seq2seq model with attention on our dataset that scores 23.5 BLEU.