Faculty Of Computer Science Research Paper

Permanent URI for this collectionhttp://185.252.233.37:4000/handle/123456789/304

Browse

Browsing Faculty Of Computer Science Research Paper by Subject "Accelerometer"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    IoT System Based on parameter optimization of Deep Learning using Genetic Algorithm
    (Intelligent Network and Systems Society, 2021-03) Slim, S.O; Elfattah, M.M.A; Atia, A; Mostafa, M.-S.M
    View references (73) Nowadays, more and more human activity recognition (HAR) tasks are being solved with deep learning techniques because it’s high recognition rate. The architectural design of deep learning is a challenge because it has multiple parameters which effect on the result. In this work, we propose a novel method to enhance deep learning architecture by using genetic algorithm and adding new statistical features. Genetic algorithm is utilized as an enhancing method to get the optimal value parameters of deep learning. Also new statistical features are appended to the features that are extracted automatically from CNN technique. Because the spread of the internet and its significance in our life, we developed Internet of Things (IoT) system. Therefore, we evaluated the performance of the proposed method in its system and found satisfactory results. Moreover, the proposed method was trained on two benchmark datasets (WISDM and UCI) and tested on the dataset, which was collected from IoT system. The results showed that the proposed model improved the accuracy up to 93.8% and 86.1% for user-dependent and independent. © 2020
  • Thumbnail Image
    Item
    Multi-Sensor Fusion for Online Detection and Classification of Table Tennis Strokes
    (Intelligent Network and Systems Society, 2021-03) Hegazy, H; Abdelsalam, M; Hussien, M; Elmosalamy, S; Hassan, Y; Nabil, A; Atia, A
    Sports training generally focuses on speed of response and variety of strategies aimed at encouraging sustainable physical activity and improving learning skills for players, thus, enhance their performance and skills through matches. In this paper, we are presenting a methodology for multi-sensor fusion method of IR depth camera and smart band sensors using curve fitting to recognize and group the characteristics of strokes performed by players and adapt the training accordingly. The main aim of the methodology is to classify various techniques played in table tennis and enhance the strokes based on various body joints. Moreover, the main contribution of this paper is to experiment different sensors to get the most optimal tools in classifying players strokes. Also, to test various classification algorithms to get the optimal and best result possible. Overall, based on the experiments we have concluded that sensor fusion between internal sensors and IR depth camera has increased the classification results and robustness of the solution. The system’s results indicate an average accuracy of 95% - 100%. © 2020