Browsing by Author "Labib, Farhan"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Design And Implemantation Iot Based Smart Village Farming With Sun Detecting Solar Powered Renewable Energy.
    (DAFFODIL INTERNATIONAL UNIVERSITY, 2024-02-05) Labib, Farhan; Akter, Mahfuza
    In order to implement effective and sustainable farming methods, this project suggests developing a smart farming system that makes use of cutting-edge sensor technology and Internet of Things integration. In this project, a PIR motion sensor, an infrared sensor, a rain detection sensor, a soil moisture sensor, and a humidity sensor have been used. For the actuator, a servo motor has been used to control irrigation valves and gates. For the central control system, an ESP8266 microcontroller with Wi-Fi has been used for data collection by mobile app communication, which is powered by solar panels for sustainable operation where sun-detecting solar panels capture renewable energy. In this project, the PIR motion sensor has detected and notified animals, or trespassers. An infrared sensor has been used for automated watering and feeding based on distance and soil moisture, which is useful for monitoring crop and animal positions. A rain detection sensor has been used to measure rainfall data, alert the farmer about impending flooding, and automate the irrigation system based on rain data. A soil moisture sensor has been used to determine soil moisture content, which enables automatic irrigation or notifies the farmer based on soil conditions, and a humidity sensor has also been used to measure air humidity, which gives real-time monitoring and actuator control via a mobile app. This project has been tested several times and has successfully achieved the desired output. This Internet of Things (IoT)-based Smart Village Farming system presents a viable means of advancing sustainability, updating agricultural methods, and providing farmers with data-driven decision-making resources.
  • Thumbnail Image
    Item
    Fusion-based multimodal deep learning to improve detection of diabetic retinopathy and macular edema: integrating retinal imaging, clinical data and systemic biomarkers
    (BRAC University, 2025-10) Islam, MD. Raisul; Emon, Samir Yeasir; Sumaiya, Nowshin; Khan, Sakib; Labib, Farhan; Mukta, Jannatun Noor; Siddiqui, Md. Saiful Bari
    Diabetic Retinopathy, a silent threat to vision, is one of the major causes of vision impairment worldwide, where the retina of the eye is damaged before noticeable symptoms appear. Accompanying DR (Diabetic Retinopathy), DME (Diabetic Macular Edema) frequently develops, stating both are overlapping ocular conditions threatening visual acuity that can be effectively diagnosed by analyzing retinal images. However, relying only on a single modality has proven inadequate accuracy in distinguishing between DME and DR. Traditional diagnostic methods are employed primarily on fundus imaging, OCT (Optical Coherence Tomography), or OCTA (Optical Coherence Tomography Angiography). To date, single modality alone fails to provide a complete contextual understanding necessary for precise classification.This work proposes to offset the limitation by developing deep learning architectures that leverage several image modalities to improve classification performance and yield context-aware outputs. Specifically, the work proposes to develop personalized Convolutional Neural Networks (CNNs) driven mainly by superior fusion methods such as Multi-Head Self-Attention (MSA) Fusion, Gated Fusion, and Feature-wise Linear Modulation (FiLM) Fusion, with model interpretability at each step. The multimodal DR and DME classification strategy proposed architecture fuses two forms of image data or biomarkers so that the model may accommodate both structural and context-specific differences. Our proposed architecture has achieved an impressive accuracy of 95.52% and an F1-score of 0.975, outperforming the existing benchmark. Furthermore, this accuracy is achieved with a lower parameter count of 1.75 million and 2.57 million, with faster inference times of 19.289 ms and 19.843 ms for the two architectures, respectively, setting a state-of-the-art benchmark in the medical field.