Nihat İnanç

Nihat İnanç

Auto-generated profile, based on publicly available information

Nihat İnanç

Haliç Üniversitesi

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 April 2023 in IEEE Journal of Emerging and Selected Topics in Power Electronics
Verified
Journal Article
Closed access
ANAbdülhamit Nurettin
Abdülhamit Nurettin
NINihat İnanç
Nihat İnanç
To achieve a balance between estimation accuracy and the chattering problem for sensorless induction motor IM drive systems at very low and zero speeds, an adaptive-gain super-twisting sliding mode observer (AGSTSMO) is proposed. The value of the adaptive gains (experimental observer coefficients) in the control law is assigned utilizing Lyapunov stability theory to ensure expeditious convergence of the estimated variables to improve the accuracy and suppress chattering at very low and zero speeds operation. The AGSTSM observer eliminates the need to use a low-pass filter to obtain the equivalent control, as in the traditional first-order sliding-mode observer, which causes a delay in estimating the equivalent control law. Simulation and experimental results are shown under different operating conditions to illustrate the effectiveness of the suggested approach, which achieves excellent estimation precision and chattering elimination capability simultaneously, thus increasing robustness versus deviations of the motor parameters. Moreover, to prove the superiority and efficiency of the proposed observer is compared to that of a super-twisting sliding mode observer (STSMO) under various operating conditions.

15 May 2025 in Journal of High Speed Networks
Verified
Journal Article
Closed access
GFGeorg Thamer Francis
Georg Thamer Francis
Alireza SouriAlireza Souri
Alireza Souri
NINihat İnAnç
Nihat İnAnç
Cybersecurity has increased on software-defined networks (SDNs) since its inception in the early 2010s. That is due to the SDN's centralized nature in controlling the network, human-centered generative methods, and transferring data in the internet of behavior. The widespread usage of Internet of Things (IoT) networks, integrating SDNs with IoT, the intelligent industrial revolution, and the inclusion of the human-centric industrial revolution in the infrastructure of major industrial fields all were reasons to focus on creating effective attack detection systems intrusion detection system (IDS) for these industrial IoT (IIoT) networks. In this paper, we present an IDS we call SPAARC_DDSDN_IIoT. It is a four-layer industrial IoT architecture weaponized by security devices at each layer and uses the SDN's centralized approach. First is an application layer-based prediction approach called SPAARC. SPAARC is a split-point algorithm combined with an attribute-reduced classifier (SPAARC). It is applied to the proposed IDS-based SDN approach in the IIoT. SPAARC is a decision tree algorithm, and intrusion detection will be performed on the leaves of the resulting tree. Two datasets were used for the experiment: the DDoS_SDN and the XIIoT_ID. The firefly algorithm, as a swarm intelligence based on the behavior of fireflies, was used for feature selection. SPAARC achieved a notable accuracy of 99.9962% and 99.991%, surpassing all the other machine learning algorithms tested. SPAARC also achieved a mean absolute error of 0 and 0.008, a root mean squared error of 0.0062 and 0.0016, and a perfect score on both datasets for the remaining metrics.

31 December 2021 in International Scientific and Vocational Studies Journal
Verified
Journal Article
Closed access
MEMustafa Yasin Erten
Mustafa Yasin Erten
NINihat İnanç
Nihat İnanç
Nowadays, there are many problems with the electricity system, such as increasing consumption, short-time overload during the intra-day, environmental problems caused by fossil fuel, and foreign-source dependency. Therefore, it is necessary to meet these increasing energy needs, minimize environmental impacts, and develop cost optimization solutions. In order to meet these requirements, it is necessary for the network to have a more dynamic structure and to have real-time monitoring and control systems. Furthermore, to develop the aforementioned system, it is necessary to estimate the load of the users in the system. Therefore, the developed artificial neural network-based load estimation algorithm is capable of high accuracy load estimates, and high precision data were obtained for use in the demand side management system

31 December 2021 in International Scientific and Vocational Studies Journal
Verified
Journal Article
Open access
PDF file
Hüseyin AydilekHüseyin Aydilek
Hüseyin Aydilek
NINihat İnanç
Nihat İnanç
Due to its spectral properties, hyperspectral imaging is superior to other types of imaging tools in identifying, distinguishing and classifying objects. Hyperspectral imaging instruments can detect light reflected from certain wavelengths between infrared and ultraviolet, apart from the wavelength that the human eye can distinguish on the electromagnetic spectrum. While this feature provides detailed information about the spectral feature of the object under investigation, it causes its spatial resolution to be low due to the technical overlap between spatial resolution and spectral resolution. Today, applications of hyperspectral images are increasing in important fields such as agriculture, mining, medicine and pharmacy, especially for military purposes. In order for applications to produce more precise results, high spatial resolution is required, as well as high spectral information. Hardware solving of low spatial resolution problem is a difficult and costly method. Therefore, software solution is an interesting area in the field of image processing. In this thesis, a hybrid solution method based on deep learning and sparse representation is proposed to increase the low spatial resolution of hyperspectral images. The method obtains a super-resolution image from a single hyperspectral image with a low spatial image with a deep convolutional mesh. Later, the super-resolution image obtained and the original low-spatial-resolution hyperspectral image are fused with the dictionary learning method, resulting in a new super-resolution image with high spectral and spatial resolutions. The application results show that our method achieves successful results compared to many super resolution applications in the literature.

11 August 2026 in Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi
Verified
Journal Article
Closed access
Hüseyin AydilekHüseyin Aydilek
Hüseyin Aydilek
NINihat İnAnç
Nihat İnAnç
Background/Aim: Hyperspectral images provide rich spectral information but often suffer from low spatial resolution due to hardware limitations and long imaging distances. This study aims to enhance the spatial resolution of low-resolution hyperspectral images while preserving their spectral information by proposing a hybrid super-resolution method that combines deep learning and sparse representation.Methods: The proposed framework comprises two components. Spatial resolution is enhanced using deep learning models, while the spectral information of the original low-resolution hyperspectral cube is reintroduced into the reconstructed image through Bayesian sparse-representation-based dictionary learning. A deep convolutional network and a deep residual network were adapted to hyperspectral images. To reduce the convolutional workload, two-dimensional convolution was applied to one band selected from every three bands. The method was evaluated on the CAVE and Harvard datasets at scale factors of ×2, ×3, and ×4 using root mean square error (RMSE) and spectral angle mapper (SAM), and was compared with bicubic interpolation, GFPCA, and SCT_SDCNN.Results: At the dataset-average level, the deep residual network-based hybrid model yielded the lowest RMSE and SAM values among the evaluated methods at all three scale factors. On CAVE, the RMSE/SAM values were 2.0146/2.8507, 2.1380/4.0742, and 2.4712/5.1211 at ×2, ×3, and ×4, respectively. The corresponding values on Harvard were 1.5753/2.1328, 1.7373/2.7135, and 2.1524/3.3576. Relative to SCT_SDCNN, the SAM reductions ranged from 19.12% to 24.80% on CAVE and from 21.93% to 26.02% on Harvard.Conclusion: The findings suggest that combining deep-learning-based spatial enhancement with sparse-representation-based spectral fusion can support lower spatial and spectral reconstruction errors under the evaluated conditions. The need for training data with characteristics comparable to the target data remains a limitation.