Browsing by Author "Ayyildiz, Cem"

Now showing 1 - 4 of 4

Deep learning approaches for vehicle type classification with 3-D magnetic sensor
(ELSEVIER, 2022) Kolukisa, Burak; Yildirim, Veli Can; Elmas, Bahadir; Ayyildiz, Cem; Gungor, Vehbi Cagri; 0000-0003-0423-4595; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Gungor, Vehbi Cagri; Kolukisa, Burak
In the Intelligent Transportation Systems, it is crucial to determine the type of vehicles to improve traffic management, increase human comfort, and enable future development of transport infrastructures. This paper presents a deep learning-based vehicle type classification approach for intermediate road traffic. Specifically, a low-cost, easy-to-install, battery-operated 3-D traffic sensor is designed and developed. In addition, a total of 376 vehicle samples are collected, and the vehicles are identified into three different classes according to their structures: light, medium, and heavy. Firstly, an oversampling method is applied to increase the number of samples in the training set. Then, the signals are converted into time series for LSTM and GRU and 2-D images for transfer learning models. Finally, soft voting is proposed using the LSTM, GRU, and VGG16, which is the best transfer learning method for vehicle type classification. The developed system is portable, power-limited, battery-operated, and reliable. Comparative performance results show that the soft voting ensemble method using a deep learning classifier improves the accuracy and f-measure performances by 92.92% and 93.42%, respectively. Additionally, the battery lifetime of the developed magnetic sensor node can work for up to 2 years.
A deep neural network approach with hyper-parameter optimization for vehicle type classification using 3-D magnetic sensor
(ELSEVIER, 2023) Kolukisa, Burak; Yildirim, Veli Can; Ayyildiz, Cem; Gungor, Vehbi Cagri; 0000-0003-0423-4595; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Gungor, Vehbi Cagri; Kolukısa, Burak
The identification of vehicle types plays a critical role in Intelligent Transportation Systems. In this study, battery-operated, easy-to-install, low-cost 3-D magnetic traffic sensors have been developed for vehicle type classification problems. In addition, a new machine learning approach based on deep neural networks (DNN) with hyper-parameter optimization using feature selection and extraction methods has been proposed for vehicle type classification. A dataset is collected from the field, and vehicles are classified into three different classes, i.e., light: motorcycles, medium: passenger cars, and heavy: buses, based on vehicle structures and sizes. The proposed system is portable, energy-efficient, and reliable. The performance results show that the proposed method, which is based on a DNN classifier, has an accuracy of 91.15%, an f-measure of 91.50%, and a battery life of up to 2 years.
Physical layer authentication for extending battery life
(ELSEVIERRADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS, 2021) Ayyildiz, Cem; Cetin, Ramazan; Khodzhaev, Zulfidin; Kocak, Taskin; Soyak, Ece Gelal; Gungor, V. Cagri; Kurt, Gunes Karabulut; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Gungor, V. Cagri
Increasing population density in cities, and the increasing demand for efficiency in resource usage call for architectures enabling smart cities, such as the Internet of Things (IoT). In most such scenarios, the data generated by IoT sensors is not confidential, but its integrity is critical. Data integrity can be achieved by establishing certification mechanisms that provide cryptographic message authentication protocols; however, this requires relatively expensive components for storing and processing the encryption key on the sensor and consumes more power while processing and transmitting data, which leads to the renunciation of security issues in cost sensitive deployments. In this paper, we propose a security solution that provides data integrity without draining the batteries of IoT sensors. Our solution consists of, (i) differentiating legitimate sensors by taking advantage of their impurities formed during the manufacturing process of the transceiver components, and (ii) eliminating the complex components that carry out cryptography as well as the redundant packet header fields, thereby yielding power savings. The testbed implementation of the proposed solution yields power measurement results providing an estimate of 2.52 times improvement in battery life without compromising the integrity of communications in the system, in addition to offering an increase in spectral efficiency and a decrease in the overall IoT device cost.
Structure Health Monitoring Using Wireless Sensor Networks on Structural Elements (vol 82, pg 68, 2019)
(ELSEVIER, RADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS, 2020) Ayyildiz, Cem; Erdem, H. Emre; Dirikgil, Tamer; Dugenci, Oguz; Kocak, Taskin; Altun, Fatih; Gungor, V. Cagri; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
This paper presents a system that monitors the health of structural elements in Reinforced Concrete (RC), concrete elements and/or masonry buildings and warn the authorities in case of physical damage formation. Such rapid and reliable detection of impairments enables the development of better risk management strategies to prevent casualties in case of earthquake and floods. Piezoelectric (PZT) sensors with lead zirconate titanate material are the preferred sensor type for fracture detection. The developed sensor mote hardware triggers the PZT sensors and collects the responses they gather from the structural elements. It also sends the collected data to a data center for further processing and analysis in an energy-efficient manner utilizing low-power wireless communication technologies. The access and the analysis of the collected data can be remotely performed via a web interface. Performance results show that the fractures serious enough to cause structural problems can be successfully detected with the developed system.