Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- BildiriAçık Erişim2024A New Hybrid CNN Model for Abnormal Behaviour Detection in Smart Campus
Yilmazer, Merve; Karakose, Mehmet; Ay, Berhan Turku
Security and monitoring systems are provided through video cameras in public places such as universities, hospitals, cinemas and theater halls. In smart campuses created by the integration of various sensors and digital technologies, there are many video cameras indoors and outdoors in the campus areas to ensure the safety of students, academics, administrators and visitors. Examining the images recorded with these video cameras in terms of security and detecting abnormal behaviours requires a long time and effort. In this study, a new hybrid convolutional neural network (CNN) model is proposed to detect abnormal behaviors occurring in smart campus areas. In the proposed method, firstly, the features of the UTI public dataset, which includes various student behaviors, are extracted with the hybrid use of InceptionV3 and MobileNetV2 deep transfer learning models. The extracted features of the images were combined and classified by converting them into a single feature vector. 6 different behavior classes, 3 of which are normal and 3 of which are abnormal, have been classified and detected with 92.7 % accuracy. Experimental results show that the proposed method for abnormal behavior detection produces more efficient results than other methods in terms of feature extraction, accuracy and computational costs.
AtıfScopus2OpenAlex1
İncele - MakaleYalnız künye2020Scopus SJRQ1Approximate-derivative-based signalprocessing method to segment power-quality disturbances
Akmaz, Düzgün
The increasing complexity of power systems and the increase in power quality (PQ) data have made it necessary to develop different and simple signal-processing tools. In this study, an approximate-derivative (AD) signal-processing tool based on a simple mathematical processing approach was developed for the segmentation of PQ disturbances. Although the developed method was highly effective for the segmentation of noise-free signals, the method was unable to properly handle the segmentation of noisy signals. Thus, to mitigate this situation, a denoising method based on the Sqtwolog threshold was applied to the noisy signals. After denoising, the proposed AD method effectively performed the segmentation. Subsequently, AD and a single-level discrete wavelet transform (DWT) with Daubechies 4 mother wavelets were compared through simulations, which showed that successful results can be obtained using the proposed method. Furthermore, all simulations showed that the application of AD and single-level DWT to PQ signals under different conditions resulted in similar patterns with different amplitudes. Therefore, this study provides a different approach for analysing signal using single-level DWT.
AtıfScopus5WoS4OpenAlex5
İncele - MakaleYalnız künye2019Scopus SJRQ2Design and development of travelling-wave-frequency-based transmission line fault locator using TMS320 DSP
Arkan, Müslüm; Akmaz, Düzgün; Mamiş, Mehmet S.; Tağluk, Mehmet Emin
The authors use a TMS320 digital signal processor (TMS320-DSP) to determine fault instants and estimate their location in real time in a laboratory environment. The fault instant is determined via examining the instantaneous differential changes in the line currents. After the fault is detected, the fault location is determined by processing the time-domain transient current waves. First, the travelling-wave frequency is determined by application of the fast Fourier transform to the positive-sequence-component line current after the fault, and subsequently, the fault location is estimated by utilising this frequency. The alternative transients programme (ATP)–electromagnetic transient programme is used to simulate the line currents and create short-circuit fault conditions. Furthermore, LabVIEW software and a National Instruments data acquisition board are used to transform the line currents obtained through the ATP programme into analogue signals. The TMS320-DSP determines the fault in real time and estimates the fault location using the completed software and analogue input signals. Their results indicate that the prototype device designed with the use of the TMS320-DSP is suitable for real-time fault detection.
AtıfScopus16WoS16OpenAlex16İncele - DergiIET Science, Measurement and Technology
- DergiIET Generation, Transmission and Distribution
- DergiIET Conference Proceedings