Browsing by Author "Shamsojjaman, Muhammad"

Now showing 1 - 4 of 4

An Automated Convolutional Neural Network Based Approach for Paddy Leaf Disease Detection
(International Journal of Advanced Computer Science and Applications(IJACSA), 2021) Islam, Md. Ashiqul; Shuvo, Md. Nymur Rahman; Shamsojjaman, Muhammad; Hasan, Shazid; Hossain, Md. Shahadat; Khatun, Tania
Bangladesh and India are significant paddy-cultivation countries in the globe. Paddy is the key producing crop in Bangladesh. In the last 11 years, the part of agriculture in Bangladesh's Gross Domestic Product (GDP) was contributing about 15.08 percent. But unfortunately, the farmers who are working so hard to grow this crop, have to face huge losses because of crop damages caused by various diseases of paddy. There are approximately more than 30 diseases of paddy leaf and among them, about 7-8 diseases are quite common in Bangladesh. Paddy leaf diseases like Brown Spot Disease, Blast Disease, Bacterial Leaf Blight, etc. are very well known and most affecting one among different paddy leaf diseases. These diseases are hampering the growth and productivity of paddy plants which can lead to great ecological and economical losses. If these diseases can be detected at an early stage with great accuracy and in a short time, then the damages to the crops can be greatly reduced and the losses of the farmers can be prevented. This paper has worked on 4 types of diseases and one healthy leaf class of the paddy. The main goal of this paper is to provide the best results for paddy leaf disease detection through an automated detection approach with the deep learning CNN models that can achieve the highest accuracy instead of the traditional lengthy manual disease detection process where the accuracy is also greatly questionable. It has analyzed four models such as VGG-19, Inception-Resnet-V2, ResNet-101, Xception, and achieved better accuracy from Inception-ResNet-V2 is 92.68%.
An Automated Convolutional Neural Network Based Approach for Paddy Leaf Disease Detection
(Scopus, 2021) Islam, Md. Ashiqul; Shuvo, Md. Nymur Rahman; Shamsojjaman, Muhammad; Hasan, Shazid; Hossain, Md. Shahadat; Khatun, Tania
Abstract: Bangladesh and India are significant paddy-cultivation countries in the globe. Paddy is the key producing crop in Bangladesh. In the last 11 years, the part of agriculture in Bangladesh's Gross Domestic Product (GDP) was contributing about 15.08 percent. But unfortunately, the farmers who are working so hard to grow this crop, have to face huge losses because of crop damages caused by various diseases of paddy. There are approximately more than 30 diseases of paddy leaf and among them, about 7-8 diseases are quite common in Bangladesh. Paddy leaf diseases like Brown Spot Disease, Blast Disease, Bacterial Leaf Blight, etc. are very well known and most affecting one among different paddy leaf diseases. These diseases are hampering the growth and productivity of paddy plants which can lead to great ecological and economical losses. If these diseases can be detected at an early stage with great accuracy and in a short time, then the damages to the crops can be greatly reduced and the losses of the farmers can be prevented. This paper has worked on 4 types of diseases and one healthy leaf class of the paddy. The main goal of this paper is to provide the best results for paddy leaf disease detection through an automated detection approach with the deep learning CNN models that can achieve the highest accuracy instead of the traditional lengthy manual disease detection process where the accuracy is also greatly questionable. It has analyzed four models such as VGG-19, Inception-Resnet-V2, ResNet-101, Xception, and achieved better accuracy from Inception-ResNet-V2 is 92.68%.
Measuring the Heart Attack Possibility using Different Types of Machine Learning Algorithms
(International Conference on Artificial Intelligence and Smart Systems (ICAIS), IEEE, 2021-04-12) Keya, Maria Sultana; Shamsojjaman, Muhammad; Hossain, Faruq; Akter, Farzana; Islam, Fakrul; Emon, Minhaz Uddin
The heart seems to be a very complicated organ in human body. If some part of the heart has been seriously damaged, the remaining part of the heart will still remain functioning. But as a result of the injury, the heart can be weakened and unable to pump as much blood as normal. With timely detection of multiple possible hamstring issues, proper care, and dietary changes after a heart attack, the additional injury can be reduced or avoided. In this paper, different types of machine learning algorithms are used for measuring the possibility heart attack, they are logistic regression, random forest, bagging, MLP, and decision tree. By finding the best algorithm, this paper also shows the correlation matrices, visualizes the feature, and AUC. From this research work, it is evident that the logistic regression is the best model with an accuracy of about 80% and also gives the best AUC of about 87%.
Recognizing Human Emotions from Eyes and Surrounding Features: A Deep Learning Approach
(Scopus, 2021) Shuvo, Md Nymur Rahman; Akter, Shamima; Islam, Md. Ashiqul; Hasan, Shazid; Shamsojjaman, Muhammad; Khatun, Tania
Abstract: The need for an efficient intelligent system to detect human emotions is imperative. In this study, we proposed an automated convolutional neural network-based approach to recognize the human mental state from eyes and their surrounding features. We have applied deep convolutional neural network based Keras applications with the help of transfer learning and fine-tuning. We have worked with six universal emotions (i.e., happiness, disgust, sadness, fear, anger, and surprise) with a dataset containing 588 unique double eye images. In this study, we considered the eyes and their surrounding areas (Upper and lower eyelid, glabella, and brow) to detect the emotional state. The state and movement of the iris and pupil can vary with the various mental states. The common features found within the entire eyes during different mental states can help to capture human expression. The dataset was trained with pre-trained weights and used a confusion matrix to analyze the prediction to achieve better accuracy. The highest accuracy was achieved by DenseNet-201 is 91.78%, whereas VGG-16 and Inception-ResNet-v2 show 90.43% and 89.67%, respectively. This study will provide an insight into the current state of research to obtain better facial recognition.