Browsing by Author "Rayhan, Abu"

Now showing 1 - 4 of 4

Detection of potato leaf disease using deep learning approaches
(Daffodil International University, 2024-07-24) Rayhan, Abu
Throughout the globe, potatoes are one of the most important food crops. Potato farming has grown quite common across Bangladesh in the previous few decades. Plants of potatoes cannot grow properly under several conditions. This plant has obvious illnesses in its leaf area. Potato Early Blight (EB) , Late Blight (LB), Septoria blight etc. are both prevalent and well-known leaf diseases of potato crops will target potato plants and display their symptoms in the affected leaves. Whenever these pandemics are identified in their early stages and appropriate intervention is done, the landowner will not be concerned about suffering significant financial losses. That being said, improved crop productivity would result from early detection of these illnesses. Image processing is the greatest alternative for finding and assessing these illnesses in order to fix the issue at hand. This work puts forward a technology that uses deep learning and image processing to recognize and categorize potato diseases of the leaves. In this particular work, there have been use three types of classes like: Early blight, Late blight and healthy leaf with using of deep learning models. Four models use for predicting and detecting potato leaf classification MobilenetV3 large, EfficientNetB7, MobileNetV2 and RestNet50. The MobileNetV3 Large model emulate provides a reliability of 99.67% within them. my suggested method thus opens the door to autonomous plant-leaf illness recognition. Ultimately, the CNN InceptionV3 model is used for classification with the goal to identify potato leaves to create web prototype
Smart Indoor Air Pollution Caution System
(Daffodil International University, 2019-02-24) Ahmed, Kawsar; Rayhan, Abu; Alam, Mohammad Saiful
Air pollution is not well known by people also they do not know about utile steps .As of late, peoples are suffering much from air pollution .They feel discomfort such as fatigue, headaches and more serious reactions. People breathing in air of poor quality could suffer from difficulty in breathing, wheezing and asthma. In addition to the human health, air pollution also has a major effect on the global environment and the worldwide economy. Scientific evidence has indicated that the air within homes and other buildings can be more seriously polluted than the outdoor air. Other research indicates that people spend approximately 90 percent of their time indoors. To avoid this problem, we are going to implement the project “Smart indoor air pollution caution system” for ensuring hygienic situation and making people conscious. Sensor system will detect volatile components (like Co2, benzene, alcohol, smoke etc.) of indoor air. Air quality information will be shown in live data streaming by using android application, included utile steps feature in apps for people’s consciousness. People will get their indoor air quality info from anywhere. To reduce volatile organic compounds from indoor, we used window automation in this smart system which will reduce polluted air. If indoor air quality is bad then window will open automatically until get the good air quality.
Utilizing deep learning models for accurate classification of authentic real-world images and ai-generated images
(Daffodil International University, 2024-07-24) Rayhan, Abu
In this paper, i present a study focused on effectively classifying images into two categories: real-world images and artificially generated images using deep learning techniques. To achieve this, i first gathered a public dataset named CIFAKE, which comprises both real images captured from the real world and synthetic images generated by artificial intelligence algorithms. I then developed a convolutional neural network (CNN) with a custom attention module tailored to enhance classification accuracy. Our approach involved comparing the performance of our custom CNN model with several state-of-the-art CNN models commonly used for image classification tasks. These models include VGG16, ResNet50, InceptionV3, MobileNet, and DenseNet. By evaluating these models on the CIFAKE dataset, I aimed to discern the effectiveness of our proposed architecture in distinguishing between real and AI-generated images. Furthermore, I conducted a thorough analysis of the results using various statistical measurements to assess the classification performance of each model. This analysis included metrics such as accuracy, precision, recall, and F1 score. Through these statistical analyses, I sought to provide insights into the strengths and limitations of different deep learning models for image classification tasks, particularly in distinguishing between real-world and AIgenerated images. Overall, our study contributes to the advancement of image classification techniques by addressing the increasingly relevant challenge of differentiating between authentic real-world images and synthetic images generated by artificial intelligence. The findings of this research could have significant implications for various applications, including image forensics, content moderation, and computer vision systems deployed in real-world scenarios.
Web Based Educational E-Support System for TVE department of IUT
(IUT, TVE, 2016-11-20) Hossain, Md Riad; Rayhan, Abu; Hosain, Mosaddek