Yazar "Mokhtar, Bassem" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Deep Learning-Based Context-Aware Video Content Analysis on IoT Devices
    (Mdpi, 2022) Gad, Gad; Gad, Eyad; Cengiz, Korhan; Fadlullah, Zubair; Mokhtar, Bassem
    Integrating machine learning with the Internet of Things (IoT) enables many useful applications. For IoT applications that incorporate video content analysis (VCA), deep learning models are usually used due to their capacity to encode the high-dimensional spatial and temporal representations of videos. However, limited energy and computation resources present a major challenge. Video captioning is one type of VCA that describes a video with a sentence or a set of sentences. This work proposes an IoT-based deep learning-based framework for video captioning that can (1) Mine large open-domain video-to-text datasets to extract video-caption pairs that belong to a particular domain. (2) Preprocess the selected video-caption pairs including reducing the complexity of the captions' language model to improve performance. (3) Propose two deep learning models: A transformer-based model and an LSTM-based model. Hyperparameter tuning is performed to select the best hyperparameters. Models are evaluated in terms of accuracy and inference time on different platforms. The presented framework generates captions in standard sentence templates to facilitate extracting information in later stages of the analysis. The two developed deep learning models offer a trade-off between accuracy and speed. While the transformer-based model yields a high accuracy of 97%, the LSTM-based model achieves near real-time inference.
  • Küçük Resim Yok
    Öğe
    Full Connectivity Driven K-LEACH Algorithm for Efficient Data Forwarding in Wireless Sensor Networks
    (Springer International Publishing Ag, 2023) Afify, Ahmed Ashraf; Tadros, Catherine Nayer; Cengiz, Korhan; Mokhtar, Bassem
    Due to the usage of Internet in everything in our life, our environment is transformed into digital society, in which everything can be accessed from anywhere. This is the main concept of Internet of Things (IoT), which consists of intelligent devices connected together without location limitation. These devices can be sensors and actuators, which are used in environmental monitoring, home automation, disaster management and more. This is the definition of Wireless Sensor Network (WSN), which is considered a subset from IoT environment. WSN consists of hundreds of nodes spread in different area for monitoring different physical objects, it suffers from highest energy consumption of nodes, which affect network lifetime. Different routing protocols are used to cope with this challenge, Low Energy Adaptive Clustering Hierarchy (LEACH) protocol is the most common used one. LEACH is a cluster-based micro sensor network protocol that offers energy-efficient, and scalable routing for sensor nodes. So, in this paper, we investigate and present a modified algorithm using LEACH in conjunction with K-means clustering approach in order to achieve a Full Connectivity Driven K-LEACH algorithm (FCDK-LEACH). Based on the CH selection, the k-means algorithm aids in decreasing energy usage and therefore extending network lifetime. The CH is chosen based on the remaining energy level and the CH's position with relation to the sensor node. The evaluation results show that our modified k-means-based hierarchical clustering enhances network lifetime.