Metehan Guzel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Metehan Guzel has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Suat Ozdemir
Gazi UniversityDepartment of Computer Engineering,AnkaraTurkey
3 shared publications- Suat Ozdemir
Hacettepe University
3 shared publications Beyza Bagiroz
Gazi University,Computer Engineering Department,Ankara,Turkey
1 shared publication- Burak H. Corak
Avionics Integration, ASELSAN,Ankara,Turkey
1 shared publication Celalettin Uyar
Bilgisayar Mhendislii Blm, Gazi niversitesi 06500, Ankara, Trkiye
1 shared publicationChalermpol Charnsripinyo
National Science and Technology Development Agency of Thailand Bangkok Thailand
1 shared publication
Latest Publications
- 23 March 2022
- Published by Wiley in International Journal of Communication Systems
- Vol. 35 (10)
QoS‐aware IoT networks and protocols: A comprehensive survey
Summary: The vast number of smart cloud applications that communicate with the “things” over a variety of physical networks and communication protocols contribute to the rise of complexity in Internet of Things (IoT) systems. The diversity of end‐user requirements related to the volume of generated data, its variety, and the velocity of its transmission makes quality of service (QoS) provisioning even more crucial and challenging in IoT. This paper provides a comprehensive and up‐to‐date survey of QoS support in IoT networks and communication protocols. An analysis of the QoS‐aware IoT architectures, layer‐dependent QoS metrics, and network resource optimization methods utilized in IoT systems are given. The limitations of the current state‐of‐the‐art studies for efficient delivery of QoS metrics are discussed. The paper concludes with future research directions on end‐to‐end QoS provisioning in IoT.
- 23 March 2022
- Published by Wiley in International Journal of Communication Systems
- Vol. 35 (10)
QoS‐aware IoT networks and protocols: A comprehensive survey
Summary: The vast number of smart cloud applications that communicate with the “things” over a variety of physical networks and communication protocols contribute to the rise of complexity in Internet of Things (IoT) systems. The diversity of end‐user requirements related to the volume of generated data, its variety, and the velocity of its transmission makes quality of service (QoS) provisioning even more crucial and challenging in IoT. This paper provides a comprehensive and up‐to‐date survey of QoS support in IoT networks and communication protocols. An analysis of the QoS‐aware IoT architectures, layer‐dependent QoS metrics, and network resource optimization methods utilized in IoT systems are given. The limitations of the current state‐of‐the‐art studies for efficient delivery of QoS metrics are discussed. The paper concludes with future research directions on end‐to‐end QoS provisioning in IoT.
- 19 March 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (11) , 13427-13454
Fair and energy-aware IoT service composition under QoS constraints
- 19 March 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (11) , 13427-13454
Fair and energy-aware IoT service composition under QoS constraints
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2128-2133
QoS Prediction Methods in IoT A Survey
Emergence of Internet of Things (IoT) concept is expected to deeply change everyday life through a vast number of services and applications. Heterogeneity of IoT networks and unique characteristics of individual services, causes requirement of different quality factors for services and applications. Research on Quality-of-Service (QoS) aims to satisfy quality requirements of different services on heterogeneous IoT networks. To ensure a certain level of QoS, QoS prediction methodology is used to enhance service selection for IoT users. In this survey, QoS prediction approaches are briefly explained. The advantages and disadvantages of the existing approaches are presented and response times of QoS prediction methods are compared using two statistical metrics, namely Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2128-2133
QoS Prediction Methods in IoT A Survey
Emergence of Internet of Things (IoT) concept is expected to deeply change everyday life through a vast number of services and applications. Heterogeneity of IoT networks and unique characteristics of individual services, causes requirement of different quality factors for services and applications. Research on Quality-of-Service (QoS) aims to satisfy quality requirements of different services on heterogeneous IoT networks. To ensure a certain level of QoS, QoS prediction methodology is used to enhance service selection for IoT users. In this survey, QoS prediction approaches are briefly explained. The advantages and disadvantages of the existing approaches are presented and response times of QoS prediction methods are compared using two statistical metrics, namely Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).
- 1 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
SMOTE and Gaussian Noise Based Sensor Data Augmentation
Deep learning achieves successful prediction results by training multilayer neural network based machine learning models on large amounts of data. One of the best ways to improve performance of artificial neural networks is to add more data to the training set. In the literature, some data augmentation techniques have been developed for this purpose and they are widely used in processing image data. For example, data can be enriched by replicating the images in the training set with views from different angles and sufficient data can be obtained to find a generalizable model. In this study, we focused on augmenting sensor data by applying image data augmentation methods. A data set including temperature, humidity, light, and air quality sensor data was augmented using two different data augmentation techniques (SMOTE Regression and Gaussian Noise), and their effect on the performance of an LSTM model which estimates missing or incorrect values was investigated. RMSE values obtained by using real and augmented data were compared to evaluate the impact of both techniques. The most successful test estimation model from the data set was the air quality model. In addition, it was concluded that SMOTE regression gave better results when the two techniques were compared.
- 1 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
SMOTE and Gaussian Noise Based Sensor Data Augmentation
Deep learning achieves successful prediction results by training multilayer neural network based machine learning models on large amounts of data. One of the best ways to improve performance of artificial neural networks is to add more data to the training set. In the literature, some data augmentation techniques have been developed for this purpose and they are widely used in processing image data. For example, data can be enriched by replicating the images in the training set with views from different angles and sufficient data can be obtained to find a generalizable model. In this study, we focused on augmenting sensor data by applying image data augmentation methods. A data set including temperature, humidity, light, and air quality sensor data was augmented using two different data augmentation techniques (SMOTE Regression and Gaussian Noise), and their effect on the performance of an LSTM model which estimates missing or incorrect values was investigated. RMSE values obtained by using real and augmented data were compared to evaluate the impact of both techniques. The most successful test estimation model from the data set was the air quality model. In addition, it was concluded that SMOTE regression gave better results when the two techniques were compared.
- 20 June 2019
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 32 (2)
ANFIS and Deep Learning based missing sensor data prediction in IoT
Summary: Internet of Things (IoT) consists of billions of devices that generate big data which is characterized by the large volume, velocity, and heterogeneity. In the heterogeneous IoT ecosystem, it is not so surprising that these sensor‐generated data are considered to be noisy, uncertain, erroneous, and missing due to the lack of battery power, communication errors, and malfunctioning devices. This paper presents Deep Learning (DL) and Adaptive‐Network based Fuzzy Inference System (ANFIS) based prediction models for missing sensor data problem in IoT ecosystem. First, we build ANFIS based models and optimize their parameters. Then, we construct DL based models by using Long Short Term Memory (LSTM) network structure and optimize its parameters by applying the grid search method. Finally, we evaluate all the proposed models with Intel Berkeley Lab dataset. Experimental results demonstrate that the proposed models can significantly improve the prediction accuracy and may be promising for missing sensor data prediction.
- 20 June 2019
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 32 (2)
ANFIS and Deep Learning based missing sensor data prediction in IoT
Summary: Internet of Things (IoT) consists of billions of devices that generate big data which is characterized by the large volume, velocity, and heterogeneity. In the heterogeneous IoT ecosystem, it is not so surprising that these sensor‐generated data are considered to be noisy, uncertain, erroneous, and missing due to the lack of battery power, communication errors, and malfunctioning devices. This paper presents Deep Learning (DL) and Adaptive‐Network based Fuzzy Inference System (ANFIS) based prediction models for missing sensor data problem in IoT ecosystem. First, we build ANFIS based models and optimize their parameters. Then, we construct DL based models by using Long Short Term Memory (LSTM) network structure and optimize its parameters by applying the grid search method. Finally, we evaluate all the proposed models with Intel Berkeley Lab dataset. Experimental results demonstrate that the proposed models can significantly improve the prediction accuracy and may be promising for missing sensor data prediction.
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A New CEP-based Air Quality Prediction Framework for Fog based IoT
Air pollution (AP) is a major problem for public health. To reduce effect of AP, air quality monitoring stations are deployed world-wide. But in addition to monitoring, by predicting air pollution levels, peoples exposure to pollution can be further reduced. In this work, we firstly review air quality (AQ) prediction literature in an algorithmic point-of-view. Then we introduce a new AQ prediction framework. The proposed framework utilizes Complex Event Processing to process huge amount of data in near real time. Fog Computing is utilized to achieve scalability, extendibility and Software Defined Network utilized to enhance manageability of the network. In this paper, we explain the network architecture and methodology behind the framework. The proposed framework can operate in near real time and does not need any human assistance.
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A New CEP-based Air Quality Prediction Framework for Fog based IoT
Air pollution (AP) is a major problem for public health. To reduce effect of AP, air quality monitoring stations are deployed world-wide. But in addition to monitoring, by predicting air pollution levels, peoples exposure to pollution can be further reduced. In this work, we firstly review air quality (AQ) prediction literature in an algorithmic point-of-view. Then we introduce a new AQ prediction framework. The proposed framework utilizes Complex Event Processing to process huge amount of data in near real time. Fog Computing is utilized to achieve scalability, extendibility and Software Defined Network utilized to enhance manageability of the network. In this paper, we explain the network architecture and methodology behind the framework. The proposed framework can operate in near real time and does not need any human assistance.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Comparative Analysis of IoT Communication Protocols
With the proliferation of machine-to-machine communication, there are many communication protocols standardized for IoT applications. Performances of these protocols may significantly deviate from each other even under the same operating conditions. In this paper, we quantitatively compare the performances of a set of well-known IoT communication protocols, namely CoAP (Constrained Application Protocol), MQTT (Message Queuing Telemetry Transport) and XMPP (Extendible Message Persistent Protocol) in a real-world testbed. CoAP employs UDP packets for transmission while others use TCP. For this purpose, we design as small testbed that collects real-time environmental data. By designing such a system, we aim to reveal the differences among protocols in terms of packet creation time and packet transmission time. The obtained results show that XMPP is worse than other protocols in both metrics and MQTT and CoAP perform almost equally.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Comparative Analysis of IoT Communication Protocols
With the proliferation of machine-to-machine communication, there are many communication protocols standardized for IoT applications. Performances of these protocols may significantly deviate from each other even under the same operating conditions. In this paper, we quantitatively compare the performances of a set of well-known IoT communication protocols, namely CoAP (Constrained Application Protocol), MQTT (Message Queuing Telemetry Transport) and XMPP (Extendible Message Persistent Protocol) in a real-world testbed. CoAP employs UDP packets for transmission while others use TCP. For this purpose, we design as small testbed that collects real-time environmental data. By designing such a system, we aim to reveal the differences among protocols in terms of packet creation time and packet transmission time. The obtained results show that XMPP is worse than other protocols in both metrics and MQTT and CoAP perform almost equally.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 104-109
Multi sensor based indoor positioning
Decreasing the effectiveness of GPS technology in indoor environments has necessitated the use of different and cheaper technologies in these environments. Today's indoor positioning systems tend to be developed using wireless medium technologies such as RFID, BLE, WLAN, Geo-Magnetism, UWB and mobile device technology. The fact that these technologies are more likely to be affected by the environment causes problems such as instability, cost, low sensitivity and low accuracy in the systems. The method we propose for solving these problems is based on combining BLE, WLAN and Geo-Magnetism technologies and creating a control mechanism using mobile device sensor technologies. With the control mechanism created, the accuracy value will be increased by reducing the effect of instant false data. An average error of 56 cm was obtained in the system.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 104-109
Multi sensor based indoor positioning
Decreasing the effectiveness of GPS technology in indoor environments has necessitated the use of different and cheaper technologies in these environments. Today's indoor positioning systems tend to be developed using wireless medium technologies such as RFID, BLE, WLAN, Geo-Magnetism, UWB and mobile device technology. The fact that these technologies are more likely to be affected by the environment causes problems such as instability, cost, low sensitivity and low accuracy in the systems. The method we propose for solving these problems is based on combining BLE, WLAN and Geo-Magnetism technologies and creating a control mechanism using mobile device sensor technologies. With the control mechanism created, the accuracy value will be increased by reducing the effect of instant false data. An average error of 56 cm was obtained in the system.
- 1 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 139-142
A survey of insect eye inspired visual sensors
Recent progress on computer technologies is focused on mobility and size reduction rather than functionality. That provided us researchers and commercial manufacturers with low-cost, compact and high-capability electronic hardware. Visual sensors are no exception. Hereby in the light of recent technological advance it is possible to organize sensors with a two dimension array hierarchy and build very-capable systems which are not enormous. These systems can be used and is being used in variety of needs like surveillance, virtual environment applications and robotic vision. Nature is a step ahead of us in this subject.
- 1 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 139-142
A survey of insect eye inspired visual sensors
Recent progress on computer technologies is focused on mobility and size reduction rather than functionality. That provided us researchers and commercial manufacturers with low-cost, compact and high-capability electronic hardware. Visual sensors are no exception. Hereby in the light of recent technological advance it is possible to organize sensors with a two dimension array hierarchy and build very-capable systems which are not enormous. These systems can be used and is being used in variety of needs like surveillance, virtual environment applications and robotic vision. Nature is a step ahead of us in this subject.