Yazar "Kumar, V. Dhilip" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Retinal blood vessels and optic disc segmentation using U-Net
    (Hindawi Ltd, 2022) David, S. Alex; Kumar, V. Dhilip; Polat, Kemal; Alhudhaif, Adi; Nour, Majid
    A color fundus image is a photograph obtained using a fundus camera of the inner wall of the eyeball. In the image, doctors may see changes in the retinal vessels, which can be used to diagnose various dangerous disorders such as arteriosclerosis, some macular degeneration related to age, and glaucoma. To diagnose certain disorders as early as possible, automatic segmentation of retinal arteries is used to help the doctors. Also, it is a challenge for the medical community to analyze the image with the right procedure to diagnose the disorders with high accuracy. Furthermore, this will help the doctor to make the right decision on effective treatment. Hence, the authors have implemented an enhanced architecture called U-Net to segment retinal vessels in this paper. The proposed conventional U-Net permits using all the accessible spatial setting information by adding the multiscale input layer and a thick square to the conventional U-Net in terms of improving the accuracy level of image segmentation. It achieved 95.6% accuracy with a comparatively traditional U-Net model. Moreover, the segmentation results have proved that the proposed approach outperformed in detecting most complex low-contrast blood vessels even when they are very thin. The task of segmenting vessels in retinal images is known as retinal vessel segmentation. Blood vessel density can be assessed using dense pixel values. Data augmentation and analytics play a major role in building the true value of eye blood vessels for medical diagnosis. The proposed method is very promising in the automatic segmentation of retinal arteries.
  • Küçük Resim
    Öğe
    Wi-Fi signal-based human action acknowledgement using channel state information with CNN-LSTM: A device less approach
    (Springer London Ltd, 2022) Kumar, V. Dhilip; Rajesh, P.; Polat, Kemal; Alenezi, Fayadh; Althubiti, Sara A.
    Human action acknowledgment is an abundant and significant area for machine learning-based researchers due to the level of accuracy in identifying human actions. Due to the rapid growth of technologies in the machine and deep learning techniques, wireless sensors, handy Internet of Things (IoT) devices, and Wireless Fidelity (Wi-Fi), the activity recognition process is made effective with higher accuracy. By using those booming technologies and preserving the privacy of the test person we propose a novel human action recognition model that uses the channel state information (CSI) from Wi-Fi and the most prominent machine learning model, CNN with LSTM. Initially, CSI is introduced, the changes in CSI signals are assessed, and the obtained data samples are made as input to the CNN-LSTM model. To make the recognition more accurate, we also incorporated Kalman filters for noise removal and smoothed the data sample. Furthermore, we have used an image segmentation procedure to identify the initial and end times of all the activities considered and to fragment the image obtained, which is further fed as input to the CNN-LSTM model. Getting a dataset for the experiment is a herculean task. Hence a self-collected dataset is used to assess, or model proposed. Finally, the results obtained are verified and validated for their correctness with appropriate machine learning metrics and parameters like accuracy, F1 score, etc. Our proposed model affords the accuracy of 98.96% for all the considered activities. The model can adapt itself even for a minimum sampling rate and subcarriers found in the test bed.