Search

In this study, some measurements like the current, voltage and hydrogen flow based on the fuel cell are investigated in spectral-domain as well as their time-domain representations and then, their spectral properties are extracted. Besides this, taking the simplified transfer function approach into account, which is defined between the hydrogen flow and current of the cell as an input-output pair, more detailed results are obtained. Therefore, the spectral parts of the fuel cell are put into categories under the impacts coming from the process, measurement circuits and digitizers. The process noise to be defined at very small frequencies (

Security systems play a crucial role in protecting individuals and assets within diverse infrastructures, including seaports. The uninterrupted operation of these systems heavily relies on a continuous power supply, as any disruptions can lead to severe consequences. Therefore, security systems are classified as critical loads requiring uninterrupted power availability. This study focuses on the investigation of an optimal hybrid energy system (HES) to ensure a reliable power supply for security systems in two seaports located in Turkiye. Through the utilization of the HOMER software, optimization analyses were conducted, considering both conventional sources such as grid-generator or grid-generator-battery configurations, as well as off-grid and on-grid HES solutions integrating photovoltaic (PV) and wind turbine technologies. The findings reveal that on-grid HES solutions incorporating PV and wind technologies offer a more cost-effective and dependable energy supply for security systems in seaports, surpassing traditional alternatives. This study represents a significant contribution to the existing literature, as it presents the first comprehensive optimization study on the design of HES for security systems. The outcomes serve as a valuable reference for future research endeavors in this field. [ABSTRACT FROM AUTHOR]

This study highlights the intricate relationship between Gray-Level Co-occurrence Matrix (GLCM) metrics and machine learning model performance in the context of plant disease identification. It emphasizes the importance of rigorous dataset evaluation and selection protocols to ensure reliable and generalizable classification outcomes. Through a comprehensive examination of publicly available plant disease datasets, focusing on their performance as measured by GLCM metrics, this research identified dataset_2 (D2), a database of leaf images, as the top performer across all GLCM analyses. These datasets were then utilized to train the DarkNet19 deep learning model, with D2 exhibiting superior performance in both GLCM analysis and DarkNet19 training (achieving about 91% testing accuracy) according to performance metrics such as accuracy, precision, recall, and F1-score. The datasets other than dataset_1 and 2 exhibited significantly low classification performance, particularly in supporting GLCM analysis. The findings underscore the need for transparency and rigor in dataset selection, particularly given the abundance of similar datasets in the literature and the growing trend of utilizing deep learning methods in future scientific research. [ABSTRACT FROM AUTHOR]

Light emitting diodes (LEDs) play an essential role in lighting, and green earth activities because of their high efficiency, longevity, and reduction of carbon dioxide emissions during illumination. However, the brightness level of LED light sources must be adjusted appropriately for the backlight source or illumination; therefore, pulse amplitude modulation (PWM) is a commonly used method of LED control. This article experimentally investigated human interaction with the visual comfort effect of the light obtained using different PWM frequencies on an object in a sensor-based intelligent lighting system. Critical light frequencies are vital for the eye to distinguish light stimuli according to time. Histograms of the object were created according to the light frequency, and the results are discussed. The eye's response to light frequencies changing over time is important for visual comfort, and examining light frequencies in the range of 25–250 Hz was sufficient to conclude the study. It has been experimentally shown that light frequencies around 160 Hz, and above this value provide visual comfort. [ABSTRACT FROM AUTHOR]

Background: Facial surgeries require meticulous planning and outcome assessments, where facial analysis plays a critical role. This study introduces a new approach by utilizing three-dimensional (3D) imaging techniques, which are known for their ability to measure facial areas and volumes accurately. The purpose of this study is to introduce and evaluate a free web-based software application designed to take area and volume measurements on 3D models of patient faces. Methods: This study employed the online facial analysis software to conduct ten measurements on 3D models of subjects, including five measurements of area and five measurements of volume. These measurements were then compared with those obtained from the established 3D modeling software called Blender (version 3.2) using the Bland–Altman plot. To ensure accuracy, the intra-rater and inter-rater reliabilities of the web-based software were evaluated using the Intraclass Correlation Coefficient (ICC) method. Additionally, statistical assumptions such as normality and homoscedasticity were rigorously verified before analysis. Results: This study found that the web-based facial analysis software showed high agreement with the 3D software Blender within 95% confidence limits. Moreover, the online application demonstrated excellent intra-rater and inter-rater reliability in most analyses, as indicated by the ICC test. Conclusion: The findings suggest that the free online 3D software is reliable for facial analysis, particularly in measuring areas and volumes. This indicates its potential utility in enhancing surgical planning and evaluation in facial surgeries. This study underscores the software's capability to improve surgical outcomes by integrating precise area and volume measurements into facial surgery planning and assessment processes. [ABSTRACT FROM AUTHOR]

Electrified autonomous vehicles have become quite popular and have a wide range of applications. The traction and steering motors to be used on an electrified autonomous vehicle are designed considering the lateral and longitudinal forces in the environment where the vehicle operates, and they are selected with extra safety margins and "over-engineering" features. This causes wastage of rare earth elements, along with both cost and energy inefficiencies. For autonomous shuttle vehicles, traction and steering performances can be analyzed based on driving scenarios. The reference speed and steering signals for the selected driving scenarios were run on a dynamic vehicle model and the minimum performance requirements for the traction and steering motors were determined. Then, the determined design parameters by DoE (Design of Experiments) were trained in two different ANN (Artificial Neural Networks) models created for motor models. The trained ANN models were run according to the minimum performance criteria and predicted motor models with new design parameters for the traction and steering motors. The performance results of the predicted traction and steering motor models showed a significant improvement in terms of the minimum performance requirements. [ABSTRACT FROM AUTHOR]

Automated Machine Learning (AutoML) tools are revolutionizing the field of machine learning by significantly reducing the need for deep computer science expertise. Designed to make ML more accessible, they enable users to build high-performing models without extensive technical knowledge. This study delves into these tools in the context of time series analysis, which is essential for forecasting future trends from historical data. We evaluate three prominent AutoML tools—AutoGluon, Auto-Sklearn, and PyCaret—across various metrics, employing diverse datasets that include Bitcoin and COVID-19 data. The results reveal that the performance of each tool is highly dependent on the specific dataset and its ability to manage the complexities of time series data. This thorough investigation not only demonstrates the strengths and limitations of each AutoML tool but also highlights the criticality of dataset-specific considerations in time series analysis. Offering valuable insights for both practitioners and researchers, this study emphasizes the ongoing need for research and development in this specialized area. It aims to serve as a reference for organizations dealing with time series datasets and a guiding framework for future academic research in enhancing the application of AutoML tools for time series forecasting and analysis. [ABSTRACT FROM AUTHOR]

Globally, over 17 million people annually die from cardiovascular diseases, with heart disease being the leading cause of mortality in the United States. The ever-increasing volume of data related to heart disease opens up possibilities for employing machine learning (ML) techniques in diagnosing and predicting heart conditions. While applying ML demands a certain level of computer science expertise—often a barrier for healthcare professionals—automated machine learning (AutoML) tools significantly lower this barrier. They enable users to construct the most effective ML models without in-depth technical knowledge. Despite their potential, there has been a lack of research comparing the performance of different AutoML tools on heart disease data. Addressing this gap, our study evaluates three AutoML tools—PyCaret, AutoGluon, and AutoKeras—against three datasets (Cleveland, Hungarian, and a combined dataset). To evaluate the efficacy of AutoML against conventional machine learning methodologies, we crafted ten machine learning models using the standard practices of exploratory data analysis (EDA), data cleansing, feature engineering, and others, utilizing the sklearn library. Our toolkit included an array of models—logistic regression, support vector machines, decision trees, random forest, and various ensemble models. Employing 5-fold cross-validation, these traditionally developed models demonstrated accuracy rates spanning from 55% to 60%. This performance is markedly inferior to that of AutoML tools, indicating the latter's superior capability in generating predictive models. Among AutoML tools, AutoGluon emerged as the superior tool, consistently achieving accuracy rates between 78% and 86% across the datasets. PyCaret's performance varied, with accuracy rates from 65% to 83%, indicating a dependency on the nature of the dataset. AutoKeras showed the most fluctuation in performance, with accuracies ranging from 54% to 83%. Our findings suggest that AutoML tools can simplify the generation of robust ML models that potentially surpass those crafted through traditional ML methodologies. However, we must also consider the limitations of AutoML tools and explore strategies to overcome them. The successful deployment of high-performance ML models designed via AutoML could revolutionize the treatment and prevention of heart disease globally, significantly impacting patient care. [ABSTRACT FROM AUTHOR]

Epilepsy is a neurological disease characterized by recurrent seizures caused by abnormal electrical activity in the brain. One of the methods used to diagnose epilepsy is through electroencephalogram (EEG) analysis. EEG is a non-invasive medical test for quantifying electrical activity in the brain. Applying machine learning (ML) to EEG data for epilepsy diagnosis has the potential to be more accurate and efficient. However, expert knowledge is required to set up the ML model with correct hyperparameters. Automated machine learning (AutoML) tools aim to make ML more accessible to non-experts and automate many ML processes to create a high-performing ML model. This article explores the use of automated machine learning (AutoML) tools for diagnosing epilepsy using electroencephalogram (EEG) data. The study compares the performance of three different AutoML tools, AutoGluon, Auto-Sklearn, and Amazon Sagemaker, on three different datasets from the UC Irvine ML Repository, Bonn EEG time series dataset, and Zenodo. Performance measures used for evaluation include accuracy, F1 score, recall, and precision. The results show that all three AutoML tools were able to generate high-performing ML models for the diagnosis of epilepsy. The generated ML models perform better when the training dataset is larger in size. Amazon Sagemaker and Auto-Sklearn performed better with smaller datasets. This is the first study to compare several AutoML tools and shows that AutoML tools can be utilized to create well-performing solutions for the diagnosis of epilepsy via processing hard-to-analyze EEG timeseries data. [ABSTRACT FROM AUTHOR]

The power system is one of the most susceptible systems to failures, which are most frequently caused by transmission line faults. Transmission line failures account for 85% of all power system malfunctions. However, over the last decade, numerous fault detection methods have been developed to ensure the reliability and stability of power systems. A hybrid detection method based on the idea of redundancy property is presented in this paper. Because the continuous wavelet transform itself does not extract fault features for small defects effectively, the stationary wavelet transform approach is employed to assist in their detection. As a result of its ability to decompose the signal into high- and low-frequency components, undecimated reconstruction by using the algebraic summation operation (ASO) is used. This approach creates redundancy, which is useful for the feature extraction of small defects and makes faulty parts more evident. The numerical value of the redundancy ratio's contribution to the original signal is approximately equal to 36%. Following this method for redundant signal reconstruction, a continuous wavelet transform is used to extract the fault characteristic significantly easier in the time-scale (frequency) domain. Finally, the suggested technique has been demonstrated to be an efficient fault detection and identification tool for use in power systems. In fact, using this advanced signal processing technique will help with early fault detection, which is mainly about predictive maintenance. This application provides more reliable operation conditions. [ABSTRACT FROM AUTHOR]

In this study, for the diagnosis and classification of breast cancer, the authors used and applied five classical pretrained deep convolutional neural network models (DCNN) which have proven successful many times in different fields (ResNet-18, AlexNet, GoogleNet and SuffleNet). In order to make pre-trained DCNN models suitable for the purpose of this study, some layers were updated according to the new situation by using the transfer learning technique. The weights of all layers used in these five pre-trained DCNN models were not changed. Instead, new weights were given to the new layers so that new layers adapt faster to the emerging new DCNN models. With these five pre-trained DCNN models, a quadruple classification as “cancer”, “normal”, “actionable” and “benign”, and a binary classification as “actionable + cancer” and “normal + benign” was realized. With these two separate classification and diagnosis studies, comparative experimental examination and analysis of pre-trained DCNN models for breast cancer diagnosis were carried out. In the study, it was concluded that successful results can be achieved with pre-trained DCNN models without extra time-consuming procedures such as feature extraction, as well as DCNN can perform quite successfully in cancer diagnosis and image comment. [ABSTRACT FROM AUTHOR]

It is very important to accurately detect wind direction and speed for wind energy that is one of the essential sustainable energy sources. Studies on the wind speed forecasting are generally carried out for long-term predictions. One of the main reasons for the long-term forecasts is the correct planning of the area where the wind turbine will be built due to the high investment costs and long-term returns. Besides that, short-term forecasting is another important point for the efficient use of wind turbines. In addition to estimating only average values, making instant and dynamic short-term forecasts are necessary to control wind turbines. In this study, short-term forecasting of the changes in wind speed between 1-20 minutes using deep learning was performed. Wind speed data was obtained instantaneously from the feedback of the emulated wind turbine's generator. These dynamically changing data was used as an input of the deep learning algorithm. Each new data from the generator was used as both test and training input in the proposed approach. In this way, the model accuracy and enhancement were provided simultaneously. The proposed approach was turned into a modular independent integrated system to work in various wind turbine applications. It was observed that the system can predict wind speed dynamically with around 3% error in the applications in the test setup applications. [ABSTRACT FROM AUTHOR]

In this study, an analysis was conducted by using discrete wavelet packet transform (DWPT) and support vector machine (SVM) methods to determine undamaged and cracked plates. The pendulum was used to land equal impacts on plates in this experimental study. Sounds, which emerge from plates as a result of the impacts applied to undamaged and cracked plates, are sound signals used in the analysis and DWPT of these sound signals were obtained with 128 decompositions for feature extraction. The first four components, reflecting the characteristics of undamaged and cracked plates within these 128 components, were selected for enhancing the performance of the classifier and energy values were used as feature vectors. In the study, the SVM model was created by selecting appropriate C and γ parameters for the classifier. Undamaged and cracked plates were seen to be successfully identified by an analysis of the training and testing phases. Undamaged and cracked statuses of the plates that are undamaged and have the analysis had identified different cracks. The biggest advantage of this analysis method used is that it is high-precision, is relatively low in cost regarding experimental equipment and requires hardware. [ABSTRACT FROM AUTHOR]

Copyright of Electrotechnical Review / Elektrotehniski Vestnik is the property of Electrotechnical Society of Slovenia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to ensure that electrical energy reaches consumers uninterrupted, researchers constantly try to improve power transmission lines. To realize this improvement, probable faults should be analysed through every known method, and new methods should also be implemented. In this study, firstly, the Keban power transmission line located in the Eastern Anatolia region of Turkey was modelled. After that, probable short circuit scenarios were applied on the model, and the short circuit faults in the scenarios were analysed by using the Fourier analysis. The Fourier analysis is a mathematical method that is used as an effective way to determine the sudden changes in the frequency and time band. The study was successful in determining phase and grounding faults through the analyses of the scenarios using Fourier analysis. The fact that the mathematical method was applied on the probable scenarios on a physical model increases the importance of the study. [ABSTRACT FROM AUTHOR]

This study is related to determination of the ferroresonance phenomenon for Seyitomer-Isiklar part of the Electric Power System of 380 kV in Turkey. In this manner, Simulation data, which is produced from the Matlab-Simulink model, is considered for voltage variation of the R-Phase of the power system and then the continuous wavelet transform (CWT) is applied to this voltage variation. Results are examined on the time-scale plane and most dominant scale can be determined as a feature of the ferroresonance phenomenon. Hence, it can be shown that this extracted feature provides all pre-definitions of the ferroresonance event. Consequently, the ferroresonance phenomenon can be determined by overvoltage variations from the sub-scales of the original voltage variation. [ABSTRACT FROM AUTHOR]

In this experimental study, it was achieved to detect internal or surface cracks that can occur in the production of ceramic plates by using the method of impulse noise. This method is a test technique which was not used in the applications. In this experimental study, a pulse is applied on the ceramic material. This pulse is produced by pendulum mechanism. With the reflected sound material, the deformation of the material is analyzed. The application of the study was performed on ceramic plates. Ceramic double plates, made from same materials, with same characteristics, but in different models, were used. One of these ceramic double plates, both of which are entirely of the same kind, is un-defonned plate, and the other is cracked plate. Impulse noises, having arisen from the equal impulse power applied on these intact and cracked plates of the same model, were examined by wavelet analysis. By means of the applied method, it was seen to have shown significant results in distinguishing intact and cracked plates. Having the frequency and magnitude dimensions of the deformations on the plates also examined by means of the applied analysis, important distinguishing findings were attained therefrom. [ABSTRACT FROM AUTHOR]

This study is focused on the investigating of a power plant generator in reverse power condition. For this purpose, reverse power data were collected from a Combined Heat and Power Plant generator protection relay. The reverse power conditions were evaluated by means of the time-frequency and time-scale methods. As a result of this evaluation, it can be said that the time-frequency and time-scale properties of the signals like current, voltage, frequency, active and reactive powers were extracted with all details. [ABSTRACT FROM AUTHOR]

This research aims to detect spectral properties under thermal and current variations for power cables. Therefore, spectral diversities are exposed under current unbalances and different load conditions through the spectral analysis techniques. Also, huge load variations are easily detected from the current signals in the time-frequency plane using the short-time frequency analysis. Hence, this study presents the determination of the frequency characteristics and spectral similarities between the phase currents and thermal variations. [ABSTRACT FROM AUTHOR]

Renewable energy sources will come at the beginning of the future energy resources. In particular, wind power is among the most discussed sources in Turkey and all over the world. In this study, a model of the three-blade horizontal-axis wind turbine was designed. Analysis of fault, which may occur as a result of a possible blade deformation, was performed with the model. Comparison is provided between generator rotor speeds and torques for the states of healthy and damaged blades. Continuous wavelet transform (CWT) approach was adopted as the analysis method. The state of the healthy blade and the broken one were clearly identified by means of the CWT. [ABSTRACT FROM AUTHOR]

In this study, an auto-associative neural network (AANN) is designed as a fault detector using the cybernetic concepts. In this sense, an artificial neural network structure is connected with a finite state system or a finite automata and an AANN topology is described as a virtual detector. In terms of the practical application, vibration signals, which are taken from an induction motor of 5 HP for both the healthy and faulty motor cases, are considered in the spectral domain. The vibration signal presented in the healthy motor case is separated into 4 blocks and the spectral set of these blocks is used as input and target pattern sets during the training of the AANN. After the training process, a new vibration spectrum, which is defined in the faulty motor case is applied to this trained network and the faulty case is determined by the error variation at output nodes of the AANN. In this application, the error signal shows huge amplitudes between 2 and 4 kHz as an indicator of the bearing damage. [ABSTRACT FROM AUTHOR]