Browsing by Author "Rajbongshi, Aditya"

Now showing 1 - 16 of 16

A Comprehensive Guava Leaves and Fruits Dataset for Guava Disease Recognition
(Daffodil International University, 2022-04-12) Rajbongshi, Aditya; Sazzad, Sadia; Shakil, Rashiduzzaman; Akter, Bonna; Sara, Umme
Guava (Psidium guajava) is a delicious fruit native to Mexico, Central or South America, and the Caribbean region. It's high in vitamin C, Calcium, Pectins and is a good source of fiber. Due to concerns with natural and environmental resources, technical issues, and other impediments, the production level decreases day-to-day. However, we'll concentrate on the most critical challenges, such as infections that affect guava plants, fruits, and disease outbreak prevention through early identification. Besides, the early recognition of guava disease using the expert system will lead to higher yields that will eventually help guava farmers reduce their economic losses. In the recent era, image processing and computer vision have been broadly applied to recognize multiple diseases that are not identified with the naked eyes. This article presents a dataset of guava images containing both leaves and fruit images (diseases affected and disease-free) are classified into six classes: for guava fruits-Phytophthora, Scab, Styler end Rot, and Disease-free fruit, and for guava leaves-Red Rust, and diseases-free leave. All images are basically captured from the guava garden located at Bangladesh Agricultural University in July when the guava fruits are almost ripened, and the infections are found in guava plants. This dataset is mainly for those researchers who work with computer vision, machine learning, and deep learning to develop a system that recognizes the guava disease to assist guava farmers in their cultivation.
A Machine Learning Approach for Predicting the Sunspot of Solar Cycle
(IEEE, 2020-07) Khan, Thaharim; Arafat, Faisal; Mojumdar, Mayen Uddin; Rajbongshi, Aditya; Siddiquee, Shah Md Tanvir; Chakraborty, Narayan Ranjan
Sunspots are the fascinating things on the periphery which is the reason it would be all the more captivating if sunspots become predictable. Sunspot number (SSN) is used in this regard to predicting the Solar Cycle (SC) 25 using the data set containing data from the year of 1818. This is work mainly a representation of Artificial Neural Network (ANN) for predicting the Solar Cycle (SC). For time series related data set as well as continuous data set the main issue is gap length of the data set. Long Short Term Memory (LSTM) network can handle this type of continuous dataset also capable of learning long term dependencies as well. This work mainly detaches various sunspot numbers (SSN) for measuring the Solar Cycle (SC) 25. Like other sunspot numbers (SSN) prediction method this work is not splitting the data set into many parts for analyzing. This result is propulsion for disclosing various differences as well as influence. This model is one of the most effective time series model for measuring the Solar Cycle (SC) 25 compared with other predicted models of time series.
A Machine Learning Approach to Detect the Brain Stroke Disease
(Daffodil International University, 2022-03-15) Akter, Bonna; Rajbongshi, Aditya; Sazzad, Sadia; Shakil, Rashiduzzaman; Biswas, Jahanur; Sara, Umme
The brain, which comprises the cerebrum, cere-bellum, and brainstem and is covered by the skull, is a very complex and intriguing organ in the human body. Stroke is the world's second-leading cause of mortality; as a result, it requires prompt treatment to avoid brain damage. Early detection of a brain stroke can help to prevent or lessen the severity of the stroke, which can lower death rates. Using machine learning algorithms to identify risk variables is a promising method. This paper proposed a model that included a methodology to achieve an accurate brain stroke forecast. The efficient data collection, data pre-processing, and data transformation methods have been applied to provide reliable information for our proposed model to be successful. A “brain stroke dataset” was employed to build up the model. The standardization technique is used to standardize data. In the training and testing procedure, Random Forest (RF), Support Vector Machine (SVM), and Decision Tree (DT) classifiers are applied. The performance of each classifier has been estimated by adopting performance evaluation metrics such as accuracy, sensitivity (SEN), error rate, false-positive rate (FPR), false-negative rate (FNR), root mean square error, and log loss. Based on the outcome while using the RF classifier, we can determine that our proposed model provided the maximum accuracy, which was 95.30%.
A Transfer Learning Approach to the Development of an Automation System for Recognizing Guava Disease Using CNN Models for Feasible Fruit Production
(IEEE, 2023-05-25) Shakil, Rashiduzzaman; Akter, Bonna; Rajbongshi, Aditya; Sara, Umme; Barman, Mala Rani; Dhali, Aditi
Guava (Psidium guava) is one of the most popular fruits which plays a vital role in the world economy. To increase guava production and sustain economic development, early detection and diagnosis of guava disease is important. As traditional recognition systems are time-consuming, expensive, and sometimes their predictions are also inaccurate, farmers are facing a lot of losses because of not getting the proper diagnosis and appropriate cure in time. In this study, an automatic system based on Convolution Neural Networks (CNN) models for recognizing guava disease has been proposed. To make the dataset more efficient, image processing techniques have been employed to boost the dataset which is collected from the local Guava Garden. For training and testing the applied models named InceptionResNetV2, ResNet50, and Xception with transfer learning technique, a total of 2,580 images in five categories such as Phytophthora, Red Rust, Scab, Stylar end rot, and Fresh leaf are utilized. To estimate the performance of each applied classifier, the six-performance evaluation metrics have been calculated where the Xception model conducted the highest accuracy of 98.88% which is good enough compared to other recent relevant works.
Addressing Agricultural Challenges: An Identification of Best Feature Selection Technique for Dragon Fruit Disease Recognition
(Elsevier, 2023-11-02) Shakil, Rashiduzzaman; Islam, Shawn; Shohan, Yeasir Arafat; Mia, Anonto; Rajbongshi, Aditya; Rahman, Md Habibur; Akter, Bonna
Dragon fruit is a prominent substance in global agriculture. Despite this, it is gaining popularity and is a viable solution in resource-poor, environmentally degraded areas because of its many health benefits. Nevertheless, many dragon fruit plantations have been impacted by the disease, reducing their yield, and the detection system is still conventional. Farmers’ lack of disease identification and management expertise diminished crop quality and products. As a result, little research was carried out to assist those specific farmers requiring adequate agricultural support. This research has proposed an autonomous agro-based system to recognize dragon diseases using in-depth analysis of feature selection techniques. After the collection of real-time images of the dragon, the images are preprocessed using various image-processing techniques. The two important features are retrieved after segmentation. The analysis of variance (ANOVA) and the least absolute shrinkage and selection operator (LASSO) are used as feature selection techniques to assess the feature rank based on the mutual score. To analyze the effectiveness of the machine learning algorithms that were used, six distinct machine learning classifiers were applied to the top-ranked feature sets, and their performance was measured using seven distinct performance evaluation metrics. AdaBoost and Random Forest classifiers for the LASSO feature ranking approach got the maximum accuracy, which is 96.29%, based on a comparison of classifiers based on the ANOVA and LASSO feature set. Despite this, we have optimized the computational resources of each classifier for the LASSO feature set.
An Extensive Sunflower Dataset Representation for Successful Identification and Classification of Sunflower Diseases
(Daffodil International University, 2022-05-13) Sara, Umme; Rajbongshi, Aditya; Shakil, Rashiduzzaman; Akter, Bonna; Sazzad, Sadia; Uddin, Mohammad Shorif
Sunflowers are agricultural seed crops that can be used for essential edible oils and ornamental purposes. This cash crop is primarily cultivated in North and South America. Sunflower crops are prone to various diseases, insects, and nematodes, resulting in a wide range of production losses. Digital image processing and computer vision approaches have been widely utilized to categorize and detect plant diseases including leaves, fruits, and flowers over the last few decades. Early diagnosis of infections in sunflowers helps to prevent them from spreading throughout the farm and reducing financial losses to the farmers. This article offers a resourceful dataset of sunflower leaves and flowers that will help the researchers in developing effective algorithms for the detection of diseases. The dataset contains healthy and affected sunflower leaves and flowers with downy mildew, gray mold, and leaf scars. The images were captured manually between 25th to 29th November 2021 from the demonstration farm of Bangladesh Agricultural Research Institute (BARI) at Gazipur in cooperation with its one domain expert when the sunflower plants were about to bloom and the maximum diseases can be found. The dataset is hosted by the Department of Computer Science and Engineering, National Institute of Textile Engineering and Research (NITER), Bangladesh and freely available at https://data.mendeley.com/datasets/b83hmrzth8/1.
Automated classification of diseased cauliflower: a feature-driven machine learning approach
(Scopus, 2023-12-27) Barman, Mala Rani; Biswas, Al Amin; Sultana, Marjia; Rajbongshi, Aditya; Zulfiker, Md. Sabab; Tabassum, Tasnim
Cauliflower is a popular winter crop in Bangladesh. However, cauliflower plants are vulnerable to several diseases that can reduce the cauliflowers’ productivity and degrade their quality. The manual monitoring of these diseases takes a lot of effort and time. Therefore, automatic classification of the diseased cauliflower through computer vision techniques is essential. This study has retrieved ten different statistical and gray-level co-occurrence matrix (GLCM)-based features from the cauliflower image dataset by implementing a variety of image processing techniques. Afterwards, the SelectKBest method with the analysis of variance f-value (ANOVA F-value) has been used to identify the most important attributes for classification of the diseased cauliflower. Based on the ANOVA F-value, the top N (5≤N ≤9) most dominant attributes is used to train and test five machine learning (ML) models for classification of diseased cauliflower. Finally, different performance metrics have been used for evaluating the effectiveness of the employed ML models. The bagging classifier achieved the highest accuracy of 82.35%. Moreover, this model has outperformed other ML classifiers in terms of other performance metrics also.
Automated Classification of Diseased Cauliflower: A Feature-driven Machine Learning Approach
(UAD Universitas Ahmad Dahlan, 2024-07-15) Barman, Mala Rani; Biswas, Al Amin; Sultana, Marjia; Rajbongshi, Aditya; Zulfiker, Md. Sabab; Tabassum, Tasnim
Cauliflower is a popular winter crop in Bangladesh. However, cauliflower plants are vulnerable to several diseases that can reduce the cauliflowers’ productivity and degrade their quality. The manual monitoring of these diseases takes a lot of effort and time. Therefore, automatic classification of the diseased cauliflower through computer vision techniques is essential. This study has retrieved ten different statistical and gray-level co-occurrence matrix (GLCM)-based features from the cauliflower image dataset by implementing a variety of image processing techniques. Afterwards, the SelectKBest method with the analysis of variance f-value (ANOVA F-value) has been used to identify the most important attributes for classification of the diseased cauliflower. Based on the ANOVA F-value, the top N (5≤N ≤9) most dominant attributes is used to train and test five machine learning (ML) models for classification of diseased cauliflower. Finally, different performance metrics have been used for evaluating the effectiveness of the employed ML models. The bagging classifier achieved the highest accuracy of 82.35%. Moreover, this model has outperformed other ML classifiers in terms of other performance metrics also.
Recognition of Local Birds of Bangladesh Using Mobile Net and Inception-v3
(Scopus, 2020) Rahman, Md. Mahbubur; Biswas, Al Amin; Rajbongshi, Aditya; Majumder, Anup
Recognition of bird species can be a challenging task due to various complex factors. The purpose of this work is to distinguish various local bird species of Bangladesh from the image data. The MobileNet and Inception-v3 model which is mainly an image classification model used here to accomplish this work. Here, we have used a total of four approaches namely Inception-v3 without transfer learning, Inception-v3 with transfer learning, MobileNet without transfer learning, and MobileNet with transfer learning to accomplish the task. To evaluate our experimental results, we have calculated F1 Score besides the model’s accuracy and also presented the ROC curve to evaluate the model’s output quality. Then we have done a comparison among the applied four approaches. The experimental result has proved the working capability of the applied four approaches. Among these four approaches, MobileNet with transfer learning outperforms the others and obtained a test accuracy of 91.00%. For each of the classes, MobileNet with transfer learning obtained the highest F1 Score than other approaches.
Recognition of Local Birds Using Different CNN Architectures with Transfer Learning
(2021 International Conference on Computer Communication and Informatics (ICCCI), IEEE, 2021-04-21) Biswas, Al Amin; Rahman, Md. Mahbubur; Rajbongshi, Aditya; Majumder, Anup
The global world is dependent and integrated with all the ecosystems. To survive in the race, we must need to know about the birds and their habitats and importance to the existence of the human race on earth. However, it is difficult to recognize several species of birds, animals, and so on. In this paper, we presented a methodology to recognize local birds of Bangladesh using transfer learning techniques. The whole research work has been done using transfer learning in six different CNN architecture namely DenseNet201, InceptionResNetV2, MobileNetV2, ResNet50, ResNet152V2, and Xception. As to defeat the lack of much image data, augmentation is performed on the collected image data too. All the models are trained by 2800 data images and tested by 700 data images. Among all the discussed models, MobileNetV2 model exhibits the best performance in terms of various indicators such as F1-score, precision, recall, and accuracy. The accuracy, precision, recall, and F1 Score of MobileNetV2 are 96.71%, 96.93%, 96.71%, 96.75%. Then a comparative analysis has been performed for this work among the approaches as well. The obtained result shows that the working method is optimal and efficient for recognizing local birds of Bangladesh.
Recognition of Mango Leaf Disease Using Convolutional Neural Network Models
(Indonesian Journal of Electrical Engineering and Computer Science, 2021) Rajbongshi, Aditya; Khan, Thaharim; Rahman, Md. Mahbubur; Pramanik, Anik; Siddiquee, Shah Md Tanvir; Chakraborty, Narayan Ranjan
The acknowledgment of plant diseases assumes an indispensable part in taking infectious prevention measures to improve the quality and amount of harvest yield. Mechanization of plant diseases is a lot advantageous as it decreases the checking work in an enormous cultivated area where mango is planted to a huge extend. Leaves being the food hotspot for plants, the early and precise recognition of leaf diseases is significant. This work focused on grouping and distinguishing the diseases of mango leaves through the process of CNN. DenseNet201, InceptionResNetV2, InceptionV3, ResNet50, ResNet152V2, and Xception all these models of CNN with transfer learning techniques are used here for getting better accuracy from the targeted data set. Image acquisition, image segmentation, and features extraction are the steps involved in disease detection. Different kinds of leaf diseases which are considered as the class for this work such as anthracnose, gall machi, powdery mildew, red rust are used in the dataset consisting of 1500 images of diseased and also healthy mango leaves image data another class is also added in the dataset. We have also evaluated the overall performance matrices and found that the DenseNet201 outperforms by obtaining the highest accuracy as 98.00% than other models
Rose Diseases Recognition Using MobileNet
(Scopus, 2020) Rajbongshi, Aditya; Sarker, Toma; Ahamad, Md. Meraj; Rahman, Md. Mahbubur
Plants always prove a great assessment of human life for many years in many sectors. Nowadays plant diseases are affecting our agricultural sector very badly. As a result, farmers are facing huge losses. For developing an early treatment process, the exact and fastest detection of plant diseases can help to reduce huge economical suffering. To detect rose diseases manually we need expert knowledge about rose diseases which is very complex, time taking and tiring. In this paper, we have used transfer learning and without transfer learning technique by using a MobileNet model to detect rose diseases. Augmentation has been performed on the collected image data for the lack of many images. For experimental purpose, 1600 data images are used to train the model and 400 data images are used to test the model. For evaluating our empirical eventuality we have reckoned the F1 score beside the model's exactitude and used the ROC curve to compare the result generated using both techniques. Using MobileNet with transfer learning technique for each class we get better accuracy and F1 score than without transfer learning. Within two approaches, MobileNet with transfer learning omits the MobileNet without transfer learning technique and achieves 95.63% accuracy. The acquired result exhibits that the working method for recognizing rose diseases is appeasement and feasible.
RoseNet:
(Daffodil International University, 22-08-02) Sazzada, Sadia; Rajbongshi, Aditya; Shakil, Rashiduzzaman; Akter, Bonna; Kaiser, M. Shamim
For the welfare of self-development and the country’s economic evolution, people invest their youth and money in different cultivation and sustainable production business sectors. The crops or fruits get all the attention for this purpose, but currently, the commercial cultivation of flowers is becoming a numerous beneficial investment. As a consequence, the rose(Genus Rosa) is one of the most beautiful and commercially demanding flowers among different flowers. However, insecticide resistance is considered one of the lion’s share issues facing agricultural production of roses by decreasing plants’ growth and the quality as well as the quantity of healthy-looking flowers. Apart from this, due to different natural and environmental issues, rose’s quality and production level are losing their fame. Additionally, the cultivators of this sector are not educated enough to identify the initial affection of different diseases of leaves with beard eyes. Besides, the lack of communication skills to consult with an agriculturist timely turns the situation worst more than the estimation of the production. With this concern, early detection of diseases that affected different parts of roses, such as leaves, is crucial. Recently, image processing techniques and machine learning classifiers have been primarily applied to recognize multiple diseases. This article presents an extensive dataset of rose leaves images, both diseases affected and diseases free are classified into three classes (Blackspot, Downy Mildew, and Fresh Leaf). The dataset is composed of the collected images which were captured during the seasonal time of diseases affection with the consultation of a domain expert and the dataset is accessible at https://data.mendeley.com/datasets/7z67nyc57w/2
Sentiment Analysis on User Reaction for Online Food Delivery Services Using Bert Model
(2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), IEEE, 2021-06-03) Biswas, Jahanur; Rahman, Md. Mahbubur; Biswas, Al Amin; Khan, Md. Akib Zabed; Rajbongshi, Aditya; Niloy, Hasnaine Amin
In this era of the information age, a major number of people spend their time on social networking sites. Among different social networking sites, Facebook is one of the most popular due to its accessibility and many other reasons. Nowadays, people use Facebook not only for general purposes but also for business purposes as it provides free opportunity to promote products and services. Users of the products or services share their opinion and feedback on the Facebook page. The amount of the users’ data regarding the opinion and feedback is huge. This is very essential to analyze this vast amount of data and extract knowledge from it. For business owners, it is important to consider their clients’ sentiments as proper analysis of customers’ feedback helps them to take better future planning. In this research work, we proposed a noble strategy to predict users’ sentiments from their Facebook comments on online food delivery services. To accomplish this research work, we have mainly considered the BERT machine learning technique. To understand the performance of the BERT in this context, we have applied Char-CNN, Graph-CNN, LSTM, and Bi-LSTM machine learning techniques also. Lastly, the obtained result of the BERT is compared with other four applied techniques in terms of performance evaluation techniques. It is found that BERT outperforms the other applied techniques with achieving the accuracy of 92.86%.
Sunflower Diseases Recognition Using Computer Vision-Based Approach
(Scopus, 2021) Rajbongshi, Aditya; Biswas, Al Amin; Biswas, Jahanur; Shakil, Rashiduzzaman; Akter, Bonna; Barman, Mala Rani
Sunflower (Helianthus annuus) is a plant categorized as a low to medium drought-sensitive crop. It adds a significant value to the agricultural-based economy. But nowadays worldwide sunflower production is in crisis due to its many diseases. But if proper action is not adopted earlier, many serious diseases will have affect plants. Consequently, it will reduce the productivity, quantity, and quality of sunflower. Manual identification of disease is a very tedious task or perhaps impossible at times. Nowadays, computer vision-based technique has gained its popularity in the field of object recognition. In this paper, we proposed an approach for sunflower disease recognition. A total of 650 images were used to accomplish this work. The image data processing techniques such as resizing, contrast, and color enhancement have also been used. We have used k-means clustering for segmenting the diseases affected region and then extracted features from the segmented images. The classification has performed using five classifiers. We calculated the seven performance evaluation metrics for the performance measurement of each classifier. The highest average accuracy of 90.68% has been obtained for the Random Forest classifier that outperformed others.
VegNet
(Daffodil International University, 2022-06-26) Sara, Umme; Rajbongshi, Aditya; Shakil, Rashiduzzaman; Akter, Bonna; Uddin, Mohammad Shorif
Cauliflower, a winter seasoned vegetable that originated in the Mediterranean region and arrived in Europe at the end of the 15th century, takes the lead in production among all vegetables. It's high in fiber and can keep us hydrated, and have medicinal properties like the chemical glucosinolates, which may help prevent cancer. If proper care is not given to the plants, several significant diseases can affect the plants, reducing production, quantity, and quality. Plant disease monitoring by hand is extremely tough because it demands a great deal of effort and time. Early detection of the diseases allows the agriculture sector to grow cauliflower more efficiently. In this scenario, an insightful and scientific dataset can be a lifesaver for researchers looking to analyze and observe different diseases in cauliflower development patterns. So, in this work, we present a well-organized and technically valuable dataset “VegNet’ to effectively recognize conditions in cauliflower plants and fruits. Healthy and disease-affected cauliflower head and leaves by black rot, downy mildew, and bacterial spot rot are included in our suggested dataset. The images were taken manually from December 20th to January 15th, when the flowers were fully blown, and most of the diseases were observed clearly. It is a well-organized dataset to develop and validate machine learning-based automated cauliflower disease detection algorithms.