Browsing by Author "Dey, Krishno"

Now showing 1 - 5 of 5

A Review on Applications of Machine Learning in Healthcare
(Daffodil International University, 2022-06-16) Dey, Krishno; Tumpa, Eteka Sultana
Machine Learning has become a huge tendency in the modern and highly experienced technological purpose in the industry sector. The impact of Machine Learning [ML] techniques is witnessed in many areas like medical, industry and security sectors. ML has the potential to detect patterns from the data and also it has the ability to predict disease from medical information sources. This research study has reviewed many types of machine learning algorithms and some techniques in the methodology section is useful for developing healthcare applications. The proposed study also discusses how healthcare domain uses machine learning and its properties. This review paper is mainly considered as an overview of how machine learning is being used to further improve the healthcare sector by making it easier to diagnose and cure diseases too early and also reduce its cost. In this pandemic situation, everyone is working to improve the healthcare sector by using some of machine learning methods and techniques. Form the research literature, it observed that the the Machine Learning [ML] techniques can predict a huge change in the health sectors by making our daily lives more easier.
Bangladeshi Indigenous Fish Classification Using Convolutional Neural Networks
(2021 International Conference on Information Technology (ICIT), IEEE, 2021-07-21) Dey, Krishno; Hassan, Md. Mustahid; Rana, Md. Masud; Hena, Mst. Hasna
Fish is an important part of Bangladeshi culture and cuisine. Fish is the main and sometimes the only source of protein in the rural household of Bangladesh. Moreover, thousands of peoples of Bangladesh are directly and indirectly dependent on the fish industry. With time many traditional indigenous Bangladeshi fish has lost their existence and many of them are in danger of losing their existence. Furthermore, the young generation of Bangladesh is unable to recognize these traditional indigenous fishes besides they are also missing out on the protein and nutrition provided by these indigenous fishes. Hence an automatic fish classification system can help us not only to recognize traditional fishes but also in the production and preservation of these indigenous fishes. So, in this paper, we propose a convolutional neural network (CNN) based automatic fish classification system. In this paper, we mainly focus on the classification of traditional indigenous fishes of Bangladesh. We used a dataset of eight classes of indigenous fish which contains 8000 images after performing 8 types of augmentation methods. We fed our data to VGG16, Inception V3, Mobile Net pre-train models with slight modification in the output layer. We also applied this dataset to a 5 layers CNN model which we name Fishnet, where convolutional layers of the CNN model uses "Adam optimizer", "ReLU" and the "SoftMax" activation function. Fishnet surpasses VGG16 in all the performance measures and goes toe to toe with InceptionV3 and Mobile Net models. Finally, we see all the models provide excellent performance measures.
Bangladeshi Indigenous Fish Classification Using Convolutional Neural Networks
(2021 International Conference on Information Technology (ICIT), IEEE, 2021-07-26) Dey, Krishno; Hassan, Md. Mustahid; Rana, Md. Masud; Hena, Mst. Hasna
Fish is an important part of Bangladeshi culture and cuisine. Fish is the main and sometimes the only source of protein in the rural household of Bangladesh. Moreover, thousands of peoples of Bangladesh are directly and indirectly dependent on the fish industry. With time many traditional indigenous Bangladeshi fish has lost their existence and many of them are in danger of losing their existence. Furthermore, the young generation of Bangladesh is unable to recognize these traditional indigenous fishes besides they are also missing out on the protein and nutrition provided by these indigenous fishes. Hence an automatic fish classification system can help us not only to recognize traditional fishes but also in the production and preservation of these indigenous fishes. So, in this paper, we propose a convolutional neural network (CNN) based automatic fish classification system. In this paper, we mainly focus on the classification of traditional indigenous fishes of Bangladesh. We used a dataset of eight classes of indigenous fish which contains 8000 images after performing 8 types of augmentation methods. We fed our data to VGG16, Inception V3, MobileNet pre-train models with slight modification in the output layer. We also applied this dataset to a 5 layers CNN model which we name FishNet, where convolutional layers of the CNN model uses "Adam optimizer", "ReLU" and the "SoftMax" activation function. FishNet surpasses VGG16 in all the performance measures and goes toe to toe with InceptionV3 and MobileNet models. Finally, we see all the models provide excellent performance measures.
FakeDTML at CheckThat! 2023: Identifying Check-Worthiness of Tweets and Debate Snippets
(Conference and Labs of the Evaluation Forum, 2023-09-18) Sardar, Abdullah Al Mamun; Karim, Md. Ziaul; Dey, Krishno; Hasan, Md. Arid
"There is a wealth of knowledge available online. Some are trustworthy, while others are deceptive and phony. The need to identify such false information arises from the danger it poses to society at a mass. Nowadays, there is a significant need for information that requires fact-checking. As a result, we need a layer preceding fact-checking, where it can be determined whether a claim is check-worthy. This will streamline the automated fact-checking process by filtering out a lot of unnecessary data that is nonetheless necessary. We carried out such a study as part of CLEF 2023 CheckThat! Lab (CTL) task 1B, where we were provided with a dataset of tweets and debate snippets and were asked to conduct an experiment to verify whether a particular news tweet/debate snippet is check worthy. The dataset contains 3 languages (English, Arabic, Spanish). We used several machine learning and deep learning algorithms in our experiments. Among them, XLM-RoBERTa which outperformed other algorithms for English and Arabic but for Spanish we found that Logistic Regression can outperform other models."
NN at CheckThat! 2023: Subjectivity in News Articles Classification with Transformer Based Models
(CEUR Workshop Proceedings, 2023-08-31) Dey, Krishno; Tarannum, Prerona; Hasan, Md. Arid; Noori, Sheak Rashed Haider
The CheckThat! Lab is a challenging lab designed to address the issue of disinformation. We participated in CheckThat! Lab Task 2, which is focused on classification of subjectivity in news articles. This shared task included datasets in six different languages, as well as a multilingual dataset created by combining all six languages. We followed standard preprocessing steps for Arabic, Dutch, English, German, Italian, Turkish, and multilingual text data. We employed a transformer-based pretrained model, specifically XLM-RoBERTa large, for our official submission to the CLEF Task 2. Our results were impressive, as we achieved the 1st, 1st, 2nd, 5th, 2nd, 2nd, and 3rd positions on the leaderboard for the multilingual, Arabic, Dutch, English, German, Italian, and Turkish text data, respectively. Furthermore, we also applied BERT and BERT multilingual (BERT-m) models to assess the subjectivity of the text data. Our study revealed that XLM-RoBERTa large outperformed BERT and BERT-m in all performance measures for this particular dataset provided in the shared task.