HYBRID DEEP LEARNING MODEL FOR NETWORK BOTTLENECK DETECTION IN IOT SYSTEMS
ETDT · 20.03.2026 · 244
DOI: 10.65713/etdtv2i125 ↗Kurz gefasst
Fachartikel in der Zeitschrift ETDT, online erschienen am 20.03.2026. Verfasst von SATYAVEDU NAVEEN KUMAR und 2 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben.
Abstract (Originalsprache)
Hybrid deep learning technique that recognizes limits in order to improve the reliability and efficiency of the Internet of Things (IoT) network. Network congestion and delays are common results of the proliferation of Internet of Things (IoT) devices. Preserving the continual flow of communication among interconnected devices requires the identification of these bottlenecks. In order to find limitations and evaluate network traffic patterns in real-time, this research presents a hybrid deep learning model that combines Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) networks. In order to determine the precise location of objects, the model analyses a large amount of data collected from the Internet of Things (IoT) and acquires both spatial and temporal information. In order to classify typical and overloaded network conditions, machine learning algorithms are used. By detecting fewer false positives and more real positives, the suggested strategy outperforms conventional monitoring methods. On top of that, it helps find performance issues in IoT infrastructures faster. Findings from the experiments show that the hybrid model can reliably predict when a network will slow down in a changing setting. Improving resource efficiency and enabling scalable IoT systems are two of the main goals of the framework. The overall system speed is increased, latency is decreased, and network stability is improved. The development of more sophisticated methods for managing IoT networks is made possible by this research.
Zitieren
APA
KUMAR, S. N., SUBBALAKSHMAMMA, M., & REDDY, M. V. (2026). HYBRID DEEP LEARNING MODEL FOR NETWORK BOTTLENECK DETECTION IN IOT SYSTEMS. ETDT, 244. https://doi.org/10.65713/etdtv2i125
Vancouver
KUMAR SN, SUBBALAKSHMAMMA M, REDDY MV. HYBRID DEEP LEARNING MODEL FOR NETWORK BOTTLENECK DETECTION IN IOT SYSTEMS. ETDT. 2026:244. doi:10.65713/etdtv2i125
BibTeX
@article{KUMAR2026,
author = {KUMAR, SATYAVEDU NAVEEN and SUBBALAKSHMAMMA, Mrs.T. and REDDY, Mr.P. VISWANATHA},
title = {HYBRID DEEP LEARNING MODEL FOR NETWORK BOTTLENECK DETECTION IN IOT SYSTEMS},
journal = {ETDT},
year = {2026},
pages = {244},
doi = {10.65713/etdtv2i125}
}
EUVIMED