Browsing by Author "Khushbu, Sharun Akter"

Now showing 1 - 15 of 15

A Comprehensive Study of DCNN Algorithms-based Transfer Learning for Human Eye Cataract Detection
(IJACSA, 2023-06-01) Jidan, Omar Jilani; Paul, Susmoy; Roy, Anirban; Khushbu, Sharun Akter; Islam, Mirajul; Badhon, S.M. Saiful Islam
This study presents a comparative analysis of different deep convolutional neural network (DCNN) architectures, including VGG19, NASNet, ResNet50, and MobileNetV2, with and without data augmentation, for the automatic detection of cataracts in fundus images. Utilizing hybrid architecture models, namely ResNet50-NASNet and ResNet50+MobileNetV2, which combine two state-of-the-art DCNNs, this research demonstrates their superior performance. Specifically, MobileNetV2 and the combined ResNet50+MobileNetV2 outperform other models, achieving an impressive accuracy of 99.00%. By emphasizing the efficacy of diverse datasets and pre-processing techniques, as well as the potential of pretrained DCNN models, this study contributes to accurate cataract diagnosis. Furthermore, the proposed system has the potential to reduce reliance on ophthalmologists, decrease the cost of eye check-ups, and improve accessibility to eye care for a wider population. These findings showcase the successful application of deep learning and image processing techniques in the early detection and treatment of various medical conditions, including cataracts, addressing the needs of individuals with diminished vision through ocular images and innovative hybrid architectures.
A Deep Learning Based Assistive System to Classify COVID-19 Face Mask for Human Safety with YOLOv3
(IEEE, 2020-07) Bhuiyan, Md. Rafiuzzaman; Khushbu, Sharun Akter; Islam, Md. Sanzidul
Computer vision learning pay a high attention due to global pandemic COVID-19 to enhance public health service. During the fatality, tiny object detection is a more challenging task of computer vision, as it recruits the pair of classification and detection beneath of video illustration. Compared to other object detection deep neural networks demonstrated a helpful object detection with a superior achievement that is Face mask detection. However, accession with YOLOv3 covered by an exclusive topic which through certainly happening natural disease people get advantage. Added with face mask detection performed well by the YOLOv3 where it measures real time performance regarding a powerful GPU. whereas computation power with low memory YOLO darknet command sufficient for real time manner. Regarding the paper section below we have attained that people who wear face masks or not, its trained by the face mask image and non face mask image. Under the experimental conditions, real time video data that finalized over detection, localization and recognition. Experimental results that show average loss is 0.0730 after training 4000 epochs. After training 4000 epochs mAP score is 0.96. This unique approach of face mask visualization system attained noticeable output which has 96% classification and detection accuracy.
A Study on Dengue Fever in Bangladesh:
(5th International Conference on Intelligent Computing and Control Systems (ICICCS), IEEE, 2021-05-26) Islam, Md. Sanzidul; Khushbu, Sharun Akter; Rabby, Akm Shahariar Azad; Bhuiyan, Touhid
The “2019 Dengue Outbreak” was a nationwide pandemic situation in Bangladesh, particularly in Dhaka city. About 179 people died and 101,354 confirmed dengue cases were found all over the country. The developing countries like Bangladesh have some limitations in the medical sector and many people don't get proper treatment in time. Henceforth, this research work has attempted to predict the chances to get infected with dengue fever from some external behaviors, like-fever, pain, sitophobia, headache etc. This article has demonstrated a model to predict the probability of dengue fever before taking the pathological test. So, the suspective patient may get some initial diagnosis by giving their anatomical symptoms as input and further this will decrease the dependency on the pathological test for acquiring the primary treatment. Different machine learning models are used to predict the probability and an accuracy near to 100% has been achieved finally.
A Study Review of Neural Audio Speech Transposition over Language Processing
(IEEE, 2023-04-17) Khushbu, Sharun Akter; Ajmain, Moshfiqur Rahman; Rahman, Mahafozur; Noori, Sheak Rashed Haider
Natural Language processing is the advancement of Artificial Intelligence in the modern technological era. Machine Translation this is the vast majority of languages transformation among human languages and computer interaction. NLP domain creates a sequential analysis of the path where the neural network basement is mathematically and theoretically strong enough. In unwritten language aim to multimodal language transformation. According to the spoken language there are several aspects of prosperity. Thereby coming up with the development of linguistic CNN models for all manpower who spoke in their mother tongue. Therefore, concern with english speech language processing advancement has a great impact on language transformation. In a sense other languages can be placed by the speech to language transformation computational period emerged on severally made corpus languages. Due to this implementation of model refer probabilistic model. Consequently, this is a study of a benchmark of recent happenings in unwritten language to language modeling in which summarization or transformation will be faster. With concern current research work that has described how performing best in CNN model and attention model, described statistical deployment. Finally, this paper is capable of inflicting the solution. Furthermore, studies have discussed the impact of result, observation, challenges and limitation with the respect of the solution. The challenge is voice identification without noise is challenging.
BTSD: A Curated Transformation of Sentence Dataset for Text Classification in Bangla Language
(Elsevier, 2023-07-24) Das, Rajesh Kumar; Islam, Mirajul; Khushbu, Sharun Akter
The Bangla Transformation of Sentence Classification dataset addresses the resource gap in natural language processing (NLP) for the Bangla language by providing a curated resource for Bangla sentence classification. With 3,793 annotated sentences, the dataset focuses on categorizing Bangla sentences into Simple, Complex, and Compound classes. It serves as a benchmark for evaluating NLP models on Bangla sentence classification, promoting linguistic diversity and inclusive language models. Collected from publicly accessible Facebook pages, the dataset ensures balanced representation across the categories. Preprocessing steps, including anonymization and duplicate removal, were applied. Three native Bangla speakers independently assessed the Transformation of Sentence labels, enhancing the dataset's reliability. The dataset empowers researchers, practitioners, and developers to build accurate and robust NLP models tailored to the Bangla language. It offers insights into Bangla syntax and structure, benefiting linguistic research. The dataset can be used to train models, uncover patterns in Bangla language usage, and develop effective NLP applications across domains.
Covid-19 in Bangladesh
(Procedia Computer Science, Elsevier, 2020) Khushbu, Sharun Akter; Keya, Mumenun Nessa; Abujar, Sheikh; Hossain, Syed Akhter; Masum, Abu Kaisar Mohammad
A global pandemic on March 11th of 2020, which was initially renowned by the World Health Organization (WHO) revealed the coronavirus (the COVID-19 epidemic). Coronavirus was flown in -December 2019 in Wuhan, Hubei region in China. Currently, the situation is enlarged by the infection in more than 200 countries all over the world. In this situation it was rising into huge forms in Bangladesh too. Modulated with a public dataset delivered by the IEDCR health authority, we have produced a sustainable prognostic method of COVID-19 outbreak in Bangladesh using a deep learning model. Throughout the research, we forecasted up to 30 days in which per day actual prediction was confirmed, death and recoveries number of people. Furthermore, we illustrated that long short-term memory (LSTM) demands the actual output trends among time series data analysis with a controversial study that exceeds random forest (RF) regression and support vector regression (SVR), which both are machine learning (ML) models. The current COVID-19 outbreak in Bangladesh has been considered in this paper. Here, a well-known recurrent neural network (RNN) model in order to referred by the LSTM network that has forecasted COVID-19 cases on per day infected scenario of Bangladesh from May 15th of 2020 till June 15th of 2020. Added with a comparative study that drives into the LSTM, SVR, RF regression which is processed by the RMSE transmission rate. In all respects, in Bangladesh the gravity of COVID-19 has become excessive nowadays so that depending on this situation public health sectors and common people need to be aware of this situation and also be able to get knowledge of how long self-lockdown will be maintained. So far, to the best of our knowledge LSTM based time series analysis forecasting infectious diseases is a well-done formula.
Multihead Text Mining from COVID-19 Feedback Using Machine Learning, Deep Learning, and Hybrid Deep Learning Approaches
(2024-08-24) Kobra, Khadijatul; Sammi, Samrina Sarkar; Rahman, Naimur; Khushbu, Sharun Akter; Islam, Mirajul
This study examines the impact of the COVID-19 epidemic on students in Bangladesh through text classification using various machine learning (ML) algorithms and deep learning (DL) models. The pandemic led to emergency crisis protocols in the country, including self-quarantine and the closure of educational and governmental institutions, resulting in significant negative impacts on individuals’ physical and mental health, including anxiety, sadness, and terror. To better understand the psychological effects of the epidemic, the authors collected survey data from 400 students in various divisions of Bangladesh using self-administered questionnaires through Google Forms. Preprocessing techniques such as tokenization, filtering, and n-gram modeling were used in the analysis. The study deployed eight different ML algorithms and DL models, including LSTM, BiLSTM, and CNN, to classify the effects on students’ academic, mental, and social lives. The results show that the ML classifier algorithms were highly effective, achieving accuracies of 95.00%, 93.75%, and 95.00% for academic, mental, and social life impact, respectively. Furthermore, hybrid DL models, such as CNN-LSTM and CNN-BiLSTM, produced good scores in predicting the impacts on students’ lives. Overall, this study provides valuable insights into the impacts of the COVID-19 epidemic on students’ academic, mental, and social well-being in Bangladesh.
Neural Network Based Bengali News Headline Multi Classification System
(11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020 , IEEE, 2020-07-01) Khushbu, Sharun Akter; Masum, Abu Kaisar Mohammad; Hossain, Syed Akhter
The modern era is gradually developing in all sectors. Moreover, development is necessary to research. Accordingly natural language processing is the expanding area of process text. At present year, memorizing the data is very tough due to the rapidly growing volume of data. Newspapers are a great habit to the whole world of all ages. To acquire a variety of knowledge from different segments is entertaining by themselves. According to this work using bengali news headline may be more specific to others by defining its news type. Therefore the machine can smartly review the sequence of sentences within reach output to find newstype. With experiment, we connect our approach by Neural Network of adoption with 90% accuracy performance. Coming with a momentous outcome we've done Multi Classification reached at SVM, NB, Logistic Regression, Neural Network, Random forest applying Bengali dataset.
Predicting the Appropriate Category of Bangla and English Books for Online Book Store Using Deep Learning
(Scopus, 2021) Islam, Md. Majedul; Khushbu, Sharun Akter; Islam, Md. Sanzidul
At the era of this technology, we are seeking every stuff online first. Book was the best friend to us, still, it is. But this changed the way and medium by which we are being engaged with the book. Nowadays bookselling is more popular online than physically from the store. So books categorizing correctly is a very important problem. But there are many category books available like—Novel, Fiction, non-Fiction, etc. So manually categorizing books was a big deal for everyone. For that having an automatic book category system that uses a book title to categorizing books will help many people. Here, a method is proposed where Long short-term memory (LSTM) technique is used for categorizing books using books title. This model was trained on 1500 English and Bangla books title of four categories. The model reported promising results with training accuracy was 95.08% for English and 83.81% for Bangla. Different preprocessing techniques such as removing numeric data, null value removal, repeat data remove are used. In the Long short-term memory (LSTM) networks activation function ReLU is used in the hidden layer and softmax for the output layer.
Predicting the Level of Safety Feeling of Bangladeshi Internet users using Data Mining and Machine Learning
(Science and Information Ogranization, 2023-01-15) Alam, Md. Safiul; Roy, Anirban; Majumder, Partha Protim; Khushbu, Sharun Akter
An amazing combination of cutting-edge data mining and machine learning methodologies to predict the level of safety feeling among Bangladeshi internet users, which is a significant departure in this subject. By leveraging cutting-edge algorithms and innovative data sources, this work provides previously unheard-of insights into how this demographic perceives online safety, shedding light on an essential yet underappreciated aspect of their digital lives. This exceptional study's original research increases the body of knowledge of online safety and sets the road for policy recommendations and intervention tactics that will enable Bangladesh to become a global leader in internet security.
Sentiment Analysis in Multilingual Context: Comparative Analysis of Machine Learning and Hybrid Deep Learning Models
(Elsevier, 2023-09-19) Das, Rajesh Kumar; Islam, Mirajul; Hasan, Md Mahmudul; Razia, Sultana; Hassan, Mocksidul; Khushbu, Sharun Akter
This research paper investigates the efficacy of various machine learning models, including deep learning and hybrid models, for text classification in the English and Bangla languages. The study focuses on sentiment analysis of comments from a popular Bengali e-commerce site, "DARAZ," which comprises both Bangla and translated English reviews. The primary objective of this study is to conduct a comparative analysis of various models, evaluating their efficacy in the domain of sentiment analysis. The research methodology includes implementing seven machine learning models and deep learning models, such as Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Convolutional 1D (Conv1D), and a combined Conv1D-LSTM. Preprocessing techniques are applied to a modified text set to enhance model accuracy. The major conclusion of the study is that Support Vector Machine (SVM) models exhibit superior performance compared to other models, achieving an accuracy of 82.56% for English text sentiment analysis and 86.43% for Bangla text sentiment analysis using the porter stemming algorithm. Additionally, the Bi-LSTM Based Model demonstrates the best performance among the deep learning models, achieving an accuracy of 78.10% for English text and 83.72% for Bangla text using porter stemming. This study signifies significant progress in natural language processing research, particularly for Bangla, by enhancing improved text classification models and methodologies. The results of this research make a significant contribution to the field of sentiment analysis and offer valuable insights for future research and practical applications.
Simulating Using Deep Learning The World Trade Forecasting of Export-Import Exchange Rate Convergence Factor During COVID-19
(Daffodil International University, 2022-04-20) Lucky, Effat Ara Easmin; Sany, Md. Mahadi Hasan; Keya, Mumenunnesa; Rahaman, Md. Moshiur; Happy, Umme Habiba; Khushbu, Sharun Akter; Hasan, Md. Arid
By trade we usually mean the exchange of goods between states and countries. International trade acts as a barometer of the economic prosperity index and every country is overly dependent on resources, so international trade is essential. Trade is significant to the global health crisis, saving lives and livelihoods. By collecting the dataset called "Effects of COVID19 on trade" from the state website NZ Tatauranga Aotearoa, we have developed a sustainable prediction process on the effects of COVID-19 in world trade using a deep learning model. In the research, we have given a 180-day trade forecast where the ups and downs of daily imports and exports have been accurately predicted in the Covid-19 period. In order to fulfill this prediction, we have taken data from 1st January 2015 to 30th May 2021 for all countries, all commodities, and all transport systems and have recovered what the world trade situation will be in the next 180 days during the Covid-19 period. The deep learning method has received equal attention from both investors and researchers in the field of in-depth observation. This study predicts global trade using the Long-Short Term Memory. Time series analysis can be useful to see how a given asset, security, or economy changes over time. Time series analysis plays an important role in past analysis to get different predictions of the future and it can be observed that some factors affect a particular variable from period to period. Through the time series it is possible to observe how various economic changes or trade effects change over time. By reviewing these changes, one can be aware of the steps to be taken in the future and a country can be more careful in terms of imports and exports accordingly. From our time series analysis, it can be said that the LSTM model has given a very gracious thought of the future world import and export situation in terms of trade.
Survey-Based Machine Learning Approaches to Diagnosis of Hair Fall Disorder in Bangladeshi Community
(Daffodil International University, 2022-12-29) Khatun, Mst. Farhana; Ajmain, Moshfiqur Rahman; Khushbu, Sharun Akter; Ria, Nushrat Jahan; Noori, Sheak Rashed Haider
Hair symbolizes the beauty of women and men. All of us are jealous of our hair. We lose hair at a young age due to some mistakes or irregularities. Lots of men and women all over the world are suffering from hair falling and the number of females is suffering growing per year. Genetically, dandruff, allergy and stress are the major problems for falling hair. We are doing this research survey for helping people. This study is representing two things. First of all, we are findings how many reasons are involved in hair fall. Another thing is we train our dataset with machine learning algorithms to find out the accuracy. Machine learning technologies have rapidly evolved to analyze survey datasets. SVM, Logistic Regression, Naive Bayes, Decision Tree, Random Forest, K-nearest Neighbor and XGBoost algorithms for performance comparison. The experimental results indicated that XGBoost had the best performance, with an accuracy of 92.62%.
The Corporeality of Infotainment on Fans Feedback Towards Sports Comment Employing Convolutional Long-Short Term Neural Network
(Daffodil International University, 2022-05-27) Saha, Uchchhwas; Mahmud, Md. Shihab; Shimu, Sumaia; Eva, Shabikun Naher; Khushbu, Sharun Akter; Asif, Imtiaz Ahmmed
In ODIs, World Cups and T-20 matches of various sports like Football, Cricket, Hockey, Basketball and Badminton, fans express their feelings and emotions towards the players by posting their status on social media like Facebook, Twitter etc. By collecting these opinions and feelings of the fans from different mediums, this research study has become more focused on a sentimental analysis of the sport with a total of 3759 comments related to Football (both national, international), Cricket, Hockey and Badminton. Since sports related opinions have been taken up in Bengali, global vector (glove) word embedding techniques are used for pre-processing which can retrieve word meanings and synthetic information. It also specializes in creating word vectors, including the structure of word embedding infrastructure, and provides a special advantage over statistics. Three models have been proposed in our study, one of which is a hybrid model of CNN-LSTM. In the proposed CNN-LSTM model, the CNN model is used to quote various features from word embedding that reflect short-term sentiment dependence while creating long-term sentimental relationships between LSTM words. In comparison to the hybrid model, two single models CNN and LSTM are proposed in five categories (i.e. Positive, Negative, Neutral, Happy, Sad). The sport's dataset integrates the CNN-LSTM hybrid model with the glove embedding layer, providing 97.45% accuracy. Lastly, the LSTM-CNN hybrid models perform comparatively better, realizing the feeling of the fans' comments.
Toward an Enhanced Bengali Text Classification Using Saint and Common Form
(Scopus, 2020) Ria, Nushrat Jahan; Khushbu, Sharun Akter; Yousuf, Mohammad Abu; Masum, Abu Kaisar Mohammad; Abujar, Sheikh; Hossain, Syed Akhter
Language processing tool has been strengthened by the measurements of text classification. Due to this concern many approaches investigate through the text documentation problem. Behalf of this conception we have focused on our bengali text written format. A long period of time bengali people are familiar with two bengali accents about saint and common form. With concern text document processing becomes easier to translate. Most well-known supervised six classifiers we have used to classify these two bengali forms of saint and common. Classifiers prediction will determine whether it is saint or common form. Collection of text documents more than 1200 mix sentences grabbed from bengali written sources. Each text needs preprocess to classify the text into a solid form of output. Before applying algorithms there has been some prerequisite ability to split the sentences, stemming, remove stop words, construct contraction. Ending with preprocess, the processed bengali text had been taken as input on machine learning classifiers that have raised very spontaneous outcomes over the accent of bengali data. Foremost output produced by NB classifier to identify the actual form about 77% on bengali text of saint and common form. Apart from that, other ML classifiers XGB, RB, DT, SVC, KNN showed nearly prediction upto 77% -64% accuracy which we have proposed in different segments of this paper.