Nevzat Olgun

Identifying individuals in non-line-of-sight (NLOS) environments is a challenging problem. This difficulty stems from the absence of direct signal propagation and the dominance of multipath components in measurements. A significant portion of current studies focuses on suppressing these components as noise, which can lead to the loss of potentially discriminative individual-specific biometric information. In this study, a controlled, multichannel acoustic experimental setup representing NLOS conditions was designed. Using the data obtained from the designed experimental setup, multipath components were analyzed as a source of discriminative information, and an identification framework based on this analysis was developed. For this purpose, data were collected from 10 different subjects through an acoustic experimental setup consisting of 8 speakers and 8 microphones. In this study, secondary echo is treated as a delayed multipath component due to subject environment interaction, observed after the early time region dominated by direct speakers to microphone leakage and early wall reflections. Therefore, the raw signal from each microphone channel was divided into non-overlapping 1024 sample windows, and the last window exceeding the adaptive energy threshold was selected as the secondary echo segment. While this process temporally filters out early components, the selected segment may include the effects of room reverberation as well as delayed subject–environment interactions. Two different feature representations were extracted from the secondary echo segments. First, a time-averaged spectral representation (STFT) based on the short-time Fourier transform was obtained. Then, topological features based on the Limited Penetrable Visibility Graph (LPVG) were extracted. Spectral and topological representations were combined at the feature level to create a hybrid feature space. These obtained features were classified using Random Forest (RF), Extra Trees, and SVM. Model performance was evaluated under varying environmental conditions within the same room geometry. For this purpose, an object-configuration-based Leave-One-Scene-Out validation protocol was applied. The highest performance was obtained with the RF classifier under the configuration combining single and simultaneous multi speaker excitations. Under these conditions, STFT and LPVG representations achieved mean accuracies of 94.17% ± 6.48% and 88.83% ± 9.18%, respectively. The average accuracy of the fusion representation was found to be 96.17 ± 4.07%. The findings showed that the combined use of spectral and topological representations generally provided higher accuracy than either individual representation. A lower inter-fold standard deviation was also observed for the fusion approach. Furthermore, the results indicate that secondary acoustic echo components can carry discriminative patterns between individuals in NLOS environments. It was observed that environmental object configurations can influence discriminability by altering the multipath structure, and under certain conditions, this effect can be enhanced.

This study proposes a hybrid deep learning model based on the Stationary Wavelet Transform (SWT), a Frequency Attention mechanism, and a Temporal Convolutional Network architecture (TCN) for short-term electricity consumption forecasting at the university campus scale. The study utilizes a total of 40,896 observations collected from the central campus of Afyon Kocatepe University between 1 March 2024 and 30 April 2025, at 15 min intervals. Feature ablation analysis was conducted to determine the contribution of the candidate input variables. The results show that the inclusion of meteorological variables did not provide any additional improvement in forecasting accuracy. Therefore, the final compact model uses only historical electricity consumption together with the Hour and Day of Week calendar variables, which are known at the forecast origin. In the proposed model, the historical electricity consumption sequence is first decomposed into different frequency components using SWT, and the more informative frequency scales are adaptively weighted through the Frequency Attention mechanism. The resulting multiscale representation is then processed by the TCN architecture to model temporal dependencies and directly predict electricity consumption one hour ahead. Model performance was evaluated using the MAE, MSE, RMSE, MAPE, SMAPE, and R² metrics under rolling and anchored walk-forward validation strategies. The proposed SWT + Frequency Attention + TCN model achieved the best overall performance among the evaluated models, with an RMSE of 10.614 and an R² of 0.942 under the rolling walk-forward strategy and an RMSE of 10.286 and an R² of 0.946 under the anchored walk-forward strategy. The findings demonstrate that the integration of SWT-based multiscale representation, selective frequency weighting, and TCN-based temporal dependency modeling provides an effective and robust framework for short-term campus electricity consumption forecasting.

Speech is one of the most natural and effective forms of human communication, carrying both linguistic and non-linguistic information. It plays a crucial role in many applications such as gender classification, biometric authentication, and personalized human-computer interaction. This study aims to investigate the contribution of a hybrid deep learning model based on Neural Circuit Policies (NCP), inspired by biological neural systems, for gender classification on Turkish speech data, by evaluating its performance in terms of accuracy and computational efficiency in comparison with conventional recurrent models. Mel-Frequency Cepstral Coefficients (MFCC) and log-Mel spectrogram features are combined to simultaneously capture the spectral and temporal properties of speech signals. These features are learned as low-level acoustic patterns via Conv1D layers. Long-term temporal dependencies are modeled using Liquid Time Constant (LTC) cells defined within the NCP architecture. To evaluate the generalizability of the model, the experiments were conducted under a speaker-independent setup, and ablation studies were performed by removing different components of the architecture to clearly assess the contribution of the NCP component. Cross-validation was applied on the Mozilla Common Voice 12.0 Turkish dataset during the experiments. The Conv1D+NCP model achieved 99.29% accuracy and 99.28% F1-score, while the LSTM-based model yielded slightly lower results. The NCP-based model offers high performance and computational efficiency with fewer parameters, making it a powerful alternative for real-time applications

The healthy operation of solar energy panels used for electricity production from solar energy is important in terms of the efficiency of the energy produced. In this study, the types of damage that affect energy production from solar energy panels, the effects of these damages on energy production and the methods of detecting the damages are discussed in detail. Damages in solar energy panels occur due to environmental, mechanical, thermal and electrical factors. These damages directly affect energy production negatively and reduce efficiency.The types of damages were examined under four main headings in the study. These are mechanical damages (micro cracks, delamination), thermal damages (hot spot formation, overheating), electrical damages (short circuit, disconnections) and environmental damages (dusting, effect of UV rays). Early detection of damages is important to prevent energy losses and extend the life of the panels. When the damage detection methods were examined, they were grouped under three main headings: Traditional methods, advanced technology-based methods and other methods.The findings obtained in the study were compiled and the difficulties encountered in the damage detection processes, as well as the inadequacies of traditional methods and the advantages and disadvantages of advanced technological methods based on artificial intelligence were revealed, and solution suggestions for damage detection processes were presented. This study provides an important guide for the development and application of damage detection methods.

In this study, a model based on Hybrid CNN-NCP and Self-Attention is proposed to recognize human activities from sensor data. The proposed model aims to improve the accuracy of human activity recognition (HAR) systems by learning spatial and temporal dependencies more effectively. The CNN layer, one of the main components of the model, extracts low-level spatial patterns from sensor data. These features are then transferred to the NCP layer, where long-term dependencies in time series data are learnt using dynamic feedback mechanisms. In the final stage, the Self-Attention mechanism improves the decision-making process of the model by focusing on critical information in different time periods. In this study, accelerometer and gyroscope sensor data are used to classify 12 different movement activities that are frequently performed in daily life. The performance of the model was evaluated by Group K-Fold cross-validation method and an average accuracy rate of 90.38% was obtained. The proposed hybrid model provides an innovative solution in HAR systems by providing higher performance compared to traditional deep learning approaches.

Fish is important for human health due to its high nutritional value. However, it is prone to spoilage due to its structural characteristics. Traditional freshness assessment methods, such as visual inspection, are subjective and prone to inconsistency. This study proposes a novel, cost-effective hybrid methodology for automated three-level fish freshness classification (Day 1, Day 2, Day 3) by integrating single-wavelength laser reflectance data with deep learning-based image features. A comprehensive dataset was created by collecting visual and laser data from 130 mackerel specimens over three consecutive days under controlled conditions. Image features were extracted using four pre-trained CNN architectures and fused with laser features to form a unified representation. The combined features were classified using SVM, MLP, and RF algorithms. The experimental results demonstrated that the proposed multimodal approach significantly outperformed single-modality methods, achieving average classification accuracy of 88.44%. This work presents an original contribution by demonstrating, for the first time, the effectiveness of combining low-cost laser sensing and deep visual features for freshness prediction, with potential for real-time mobile deployment.

Bees, which have a critical role in the sustainability of our ecosystem, are of vital importance in maintaining ecological balance and biodiversity. More than one-third of the world’s food production is dependent on pollinators, and one of the most important of these is the honey bee. As the decline of bee populations threatens ecological balance and biodiversity, the importance of computer vision techniques for the automatic detection of these species is increasing. In this study, two different deep learning models based on classical convolutional neural network (CNN) and Residual Neural Network (ResNet) architectures are proposed and their effectiveness in classifying honey bee species is examined. Model1 is based on the CNN structure and Model2 uses CNN-ResNet integration. In the experiments on the BeeImage dataset containing images of six different honey bee species, it was determined that Model1 achieved 94.91%, and Model2 achieved 93.63% with the K-fold Cross-Validation technique. The results show that deep learning models can classify bee species in a fast and low-cost way. It is seen that these technologies have significant potential in biological research. The high success rates obtained in the study show that the developed deep learning models can contribute to the protection of biodiversity.Cite this article as: M. Çalışan and N. Olgun, “Evaluation of classification performance of honey bee species with deep learning models,” Electrica, 25, 0157, 2025. doi: 10.5152/electr.2025.24157.

This paper systematically explores the applications of image processing techniques in machined surface analysis, a critical area in industries like manufacturing, aerospace, automotive, and healthcare. It examines the integration of image processing in traditional Computer Numerical Control (CNC) machining and micromachining, focusing on its role in tool wear analysis, workpiece detection, automatic CNC programming, and defect inspection. With AI and machine learning advancements, these technologies enhance defect detection, surface texture analysis, predictive maintenance, and quality optimization. The paper also discusses future advancements in high resolutions, 3D imaging, augmented reality, and Industry 4.0, highlighting their impact on productivity, precision, and challenges such as data privacy. In conclusion, image processing remains vital to improving manufacturing efficiency and quality control.