Browsing by Author "Gungor, Vehbi Cagrı"

Now showing 1 - 2 of 2

Intelligent traffic light systems using edge flow predictions
(ELSEVIER, 2024) Thahir, Adam Rizvi; Coşkun, Mustafa; Kılıç, Sultan Kübra; Gungor, Vehbi Cagrı; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Thahir, Adam Rizvi; Kılıç, Sultan Kübra; Gungor, Vehbi Cagrı
In this paper, we propose a novel graph-based semi-supervised learning approach for traffic light management in multiple intersections. Specifically, the basic premise behind our paper is that if we know some of the occupied roads and predict which roads will be congested, we can dynamically change traffic lights at the intersections that are connected to the roads anticipated to be congested. Comparative performance evaluations show that the proposed approach can produce comparable average vehicle waiting time and reduce the training/learning time of learning adequate traffic light configurations for all intersections within a few seconds, while a deep learning-based approach can be trained in a few days for learning similar light configurations.
Node-Level Error Control Strategies for Prolonging the Lifetime of Wireless Sensor Networks
(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC445 HOES LANE, PISCATAWAY, NJ 08855-4141, 2021) Tekin, Nazli; Yildiz, Huseyin Ugur; Gungor, Vehbi Cagr; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Gungor, Vehbi Cagrı
In Wireless Sensor Networks (WSNs), energy-efficiency and reliability are two critical requirements for attaining a long-term stable communication performance. Using error control (EC) methods is a promising technique to improve the reliability of WSNs. EC methods are typically utilized at the network-level, where all sensor nodes use the same EC method. However, improper selection of EC methods on some nodes in the network-level strategy can reduce the energy-efficiency, thus the lifetime of WSNs. In this study, a node-level EC strategy is proposed via mixed-integer programming (MIP) formulations. The MIP model determines the optimum EC method (i.e., automatic repeat request (ARQ), forward error correction (FEC), or hybrid ARQ (HARQ)) for each sensor node to maximize the network lifetime while guaranteeing a pre-determined reliability requirement. Five meta-heuristic approaches are developed to overcome the computational complexity of the MIP model. The performances of the MIP model and meta-heuristic approaches are evaluated for a wide range of parameters such as the number of nodes, network area, packet size, minimum desired reliability criterion, transmission power, and data rate. The results show that the node-level EC strategy provides at least 4.4% prolonged lifetimes and 4.0% better energy-efficiency than the network-level EC strategies. Furthermore, one of the developed meta-heuristic approaches (i.e., extended golden section search) provides lifetimes within a 3.9% neighborhood of the optimal solutions, reducing the solution time of the MIP model by 89.6%.