Yazar "Alesmaeil, Abdullah" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    FACE TOUCH DETECTION BASED ON HAND GESTURE RECOGNITION USING WEARABLE MOTION SENSORS AND DEEP LEARNING
    (2022-01) Alesmaeil, Abdullah
    Wearable devices like fitness bands and smartwatches have increased in popularity in recent years. Those devices are fitted with wide range of health, fitness, and motion sensors that can be utilized to analyze and monitor body and hand activities. Being worn on the wrist or arm make them a good candidate for hand activity monitoring applications like Hand Gesture Recognition (HGR). With the worldwide spread of COVID-19 pandemic, many recommendations were issued by World Health Organization (WHO), to avoid touching the face as it was a main method for viral infections. However, most face touches are done unconsciously that is why, it is difficult for people to monitor their hand moves and try to avoid touching the face which opens the need for automatic Face-Touch Detection (FTD) solution. This thesis proposes a smartwatch application that uses small, efficient, and end-to-end Convolutional Neural Networks (CNN) models to classify hand motion and identify Face-Touch moves. The application provides a real-time feedback and alerts the user with vibration and sound whenever attempting to touch the face, which leads to lower unconscious face touches and lower infection rates. The obtained results for recall, precision, F1-Score, and accuracy were calculated as 96.75%, 95.1%, 95.85%, 99.70% respectively, with low False Positives Rate (FPR) of 0.04%. By using efficient configurations and small models, the application can run for long hours without significant impact on battery which makes it applicable on most out-of-the-shelf smartwatches.
  • Küçük Resim Yok
    Öğe
    Real-time nail-biting detection on a smartwatch using three CNN models pipeline
    (Wiley-Blackwell Publishing, 2025-02-01) Alesmaeil, Abdullah; Şehirli, Eftal
    Nail-biting (NB) or onychophagia is a compulsive disorder that affects millions of people in both children and adults. It has several health complications and negative social effects. Treatments include surgical interventions, pharmacological medications, or additionally, it can be treated using behavioral modification therapies that utilize positive reinforcement and periodical reminders. Although it is the least invasive, such therapies still depend on manual monitoring and tracking which limits their success. In this work, we propose a novel approach for automatic real-time NB detection and alert on a smartwatch that does not require surgical intervention, medications, or manual habit monitoring. It addresses two key challenges: First, NB actions generate subtle motion patterns at the wrist that lead to a high false-positives (FP) rate even when the hand is not on the face. Second, is the challenge to run power-intensive applications on a power-constrained edge device like a smartwatch. To overcome these challenges, our proposed approach implements a pipeline of three convolutional neural networks (CNN) models instead of a single model. The first two models are small and efficient, designed to detect face-touch (FT) actions and hand movement away (MA) from the face. The third model is a larger and deeper CNN model dedicated to classifying hand actions on the face and detecting NB actions. This separation of tasks addresses the key challenges: decreasing FPs by ensuring NB model is activated only when the hand on the face, and optimizing power usage by ensuring the larger NB model runs only for short periods while the efficient FT model runs most of the time. In addition, this separation of tasks gives more freedom to design, configure, and optimize the three models based on each model task. Lastly, for training the main NB model, this work presents further optimizations including developing NB dataset from start through a dedicated data collection application, applying data augmentation, and utilizing several CNN optimization techniques during training. Results show that the model pipeline approach minimizes FPs significantly compared with the single model for NB detection while improving the overall efficiency.