Browsing by Author "Hena, Most. Hasna"

Now showing 1 - 8 of 8

Bangladeshi Local Potatoes Dataset and Classification Using Deep Learning
(IEEE, 2020-12) Deb, Shrabosty; Laboni, Marfi Akter; Hena, Most. Hasna
Potato is one of the major foods in Bangladesh during winter which shows the most environmentally amiable vegetables. Variations of potatoes in Bangladesh that are grown here are extensively categorized into two divisions, high yielding and local. Assuredly, potato is the world’s most important crop when it comes to rank according to the volume of the fresh products. Moreover, the minerals, fibers, and vitamins it delivers can serve convenience for human healthiness and guard against diseases. Recently, different kinds of potatoes of Bangladesh has been exporting to various countries worldwide. Hence, a lot of people are engaging in agriculture to cultivate potatoes. It is very essential for the farmers to acknowledge that; which kinds of potato cultivation will be beneficial according to the market price and cultivating process. This system can help agriculturists, farmers, and general people to find out the local species of potatoes. This dataset of locally recognized potatoes like Diamond Alu, Mete Alu, Lal Alu, Jam Alu, Lal Mishti Alu, Chhoto Lal Alu, Mete Chhora Alu, Shunno Alu, Shada Mishti Alu, and Keshar Alu. Using a dataset of potatoes (5190 images) that have been collected by us, this research trained a CNN (Convolutional Neural Network) and deep learning based model to identify potatoes. The model gets an accuracy of 98.87%.
CNN based Disease Detection Approach on Potato Leaves
(IEEE, 2020-12) Asif, Md. Khalid Rayhan; Rahman, Md. Asfaqur; Hena, Most. Hasna
Potatoes are a well-known vegetable to all of us. If the other countries are taken into consideration, it can be easily concluded that potatoes are the number one vegetable all over the world, which has been increasingly claimed by many Agricultural departments. Despite the hype, potato leaf disease causes significant damage to the potatoes.. Various types of diseases such as early blight, late blight, septoria blight etc. will attack potato plants and exhibit their syndrome in the leaf of these disorders. The farmer would not face incurring major economic losses if these outbreaks are detected at the primary stage and sufficient action is taken. The proposed model will strongly identify and detect diseases of potato leaf stand on image processing methods in this research paper. Machine Learning includes several algorithms, but the CNN model is used for this research to detect the disease from images of the potato leaf because in CNN is used for image classification & it gives the best result than others. There are 5 algorithms is used for this research they are AlexNet, VggNet, ResNet, LeNet & Sequential model which is our offered one. Normal & disorder-impacted leaf were used for the model provided in order to segregate normal and abnormal aspects of potato leaf. Those kind of photographs are then analyzed through the algorithm provide & the potato plant leaf is labeled as either diseased or normal. This provided model established 97% of great precision.
Leaf Diseases Detection for Commercial Cultivation of Obsolete Fruit in Bangladesh Using Image Processing System
(Proceedings of the 2019 8th International Conference on System Modeling and Advancement in Research Trends, SMART 2019, IEEE, 2020-06-16) Sheikh, Md. Helal; Mim, Tahmina Tashrif; Reza, Md. Shamim; Hena, Most. Hasna
Bangladesh is country of seasons. Naturally the people of Bangladesh are blessed with various native seasonal fruits to fulfill their needs and appetites. So, hundreds of local fruits are cultivated through the yearlong by the local farmers. But in recent times some obsolete fruits like apple, blueberry, cherry, grape, orange, peach, raspberry, strawberry etc. are getting popularity amongst local consumers of Bangladesh and that is the reason why local farmers are now contemplating towards the commercial cultivation of these obsolete fruits. But there are too many obstacles in that process of commercial cultivation including weather demand, quality of soil, cultivation technology, diseases, insects attack etc. Most of the time diseases of these fruits notice our eyes when fruits are attacked and we cannot help but let the fruits get rotten and suffer the financial loss too. Even though we might not handle every barrier, but we can use deep learning and image processing technology for the detection of diseases of these fruits and help the farmers taking necessary steps on time. To simplify the work, we have taken the images of these obsolete fruits leaves and implemented image processing algorithm and deep learning methods on them. After the completion of this research we have accomplished an accuracy of 92.56%. This research is going to help the farmers to cultivate and promote these obsolete fruits more in a broaden way by reducing the diseases. It is an eco-friendly system which detects diseases without much effort only by clicking attacked images and putting that in the system and the system will give an output of which disease the plant is attacked by.
Mango Species Detection from Raw Leaves Using Image Processing System
(Springer, 2021) Hena, Most. Hasna; Sheikh, Md. Helal; Reza, Md. Shamim; Marouf, Ahmed Al
Mango is the national tree of Bangladesh which is one of the most popular fruits here during the hot summer enriching the highest quality of nutrition. Various species of mango cover the fruit market making the summer festivities. In recent times, different species of mango are also being exported to different countries of the world. So more and more people are entering into the commercial mango cultivation nowadays as new farmers. It is necessary for them to know which mango species they are cultivating and what is the market demand of that species. It is hard for the new farmers to find out the species just by asking and trusting the sapling seller. So, we plan to establish a system that can accurately ensure the species of the mango sapling. This research used convolutional neural network (CNN) and deep learning for training the dataset. This method can showcase the species of the mango sapling only by observing the image of a leaf holding an accuracy of 78.65%.
Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI
(Scopus, 2024) Islam, Taminul; Sheakh, Md. Alif; Tahosin, Mst. Sazia; Hena, Most. Hasna; Akash, Shopnil; Jardan, Yousef A. Bin; Wondmie, Gezahign Fentahun; Nafidi, Hiba-Allah; Bourhia, Mohammed
Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model’s predictions and understand the impact of each feature on the model’s output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%.
Predictive Modeling for Breast Cancer Classification in the Context of Bangladeshi Patients by Use of Machine Learning Approach with Explainable Ai
(Springer Nature, 2024-04-11) Islam, Taminul; Sheakh, Md. Alif; Tahosin, Mst. Sazia; Hena, Most. Hasna; Akash, Shopnil; Jardan, Yousef A. Bin; Wondmie, Gezahign Fentahun; Nafidi, Hiba‑Allah; Bourhia, Mohammed
Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model’s predictions and understand the impact of each feature on the model’s output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%.
Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI
(Scopus, 2024-04-11) Islam, Taminul; Sheakh, Md. Alif; Tahosin, Mst. Sazia; Hena, Most. Hasna; Akash, Shopnil; Jardan, Yousef A. Bin; Wondmie, Gezahign Fentahun; Nafidi, Hiba-Allah; Bourhia, Mohammed
Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model’s predictions and understand the impact of each feature on the model’s output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%.
Rice Disease Detection Based on Image Processing Technique
(Springer, 2021) Rahman, Md. Asfaqur; Shoumik, Md. Shahriar Nawal; Rahman, Md. Mahbubur; Hena, Most. Hasna
Rice plant diseases are major problems in Bangladesh. Detection and monitoring of these rice plant diseases is a critical issue. Rice plants are affected in various kind of disease like hispa, brown spot, and leaf blast and show the syndrome in the leaf of these diseases. If these diseases are detected early and take appropriate action, it will restrain extensive economic loss for the farmer. In this research paper, the proposed model will successfully classify and find out the rice leaf diseases based on image processing techniques. Machine learning algorithm CNN is used to implement this model. Healthy and disease-affected leaves are taken for the proposed method and separated healthy and unhealthy characteristics of rice plant leaves. After that, these images are being processed with the proposed model and classified the leaf as either infected by disease or healthy. This proposed model provided the accuracy of 90%. This model successfully identifies the infected and healthy rice plant.