Publications from 2021 to 2026
Filter Showing 10 of 362 papers
Predictive modeling of mineral prospectivity by deep self-organizing map: Implications for copper exploration targeting in saveh district, central Iran
Damage Evolution in Cu-B4C Composites: Influence of Particle Size, Compaction Method, and Temperature
Production of elicitor-induced phytochemicals in adventitious root culture of Glycyrrhiza glabra L.
Modeling the photovoltaic characteristics of Zr-doped TiO <sub>2</sub> dye-sensitized solar cells by incorporating CNT@TiO <sub>2</sub>
Development of a diffusion differential model to predict J – V characteristics for DSSCs based on CNT@TiO 2 and Zr-doped TiO 2 nanoparticles.
Read moreVirtual Reality Assisted Language Learning
1Effects of Re addition and initial microstructure on high-temperature oxidation of AlMo0.5NbTa0.5TiZr refractory high entropy alloy
1A new tensile testing approach with hourglass-shaped specimens for evaluating fracture mechanisms and fracture toughness in rock-like materials: Experimental and numerical investigation
Comparative Analysis of Time-Frequency Representations for Pediatric Respiratory Sound Classification Using Deep Learning
Respiratory sound classification has emerged as a promising non-invasive and scalable tool for the early detection of respiratory disorders. While most previous studies have relied on a single feature extraction method-such as Melfrequency cepstral coefficients (MFCC), Mel-spectrograms, or Short-Time Fourier Transform (STFT)-this study provides a comprehensive comparative analysis of these three approaches, evaluated individually, in pairwise combinations, and in a combined three-method configuration. Experiments are conducted on the SPRSound dataset, a pediatric respiratory sound database comprising 6,656 annotated events from seven unbalanced classes. Three architectures are assessed under identical preprocessing and augmentation strategies: a custom convolutional neural network (CNN), and two pre-trained models (VGG16 and InceptionV3) fine-tuned via transfer learning. Results show that STFT consistently delivers the highest performance for CNN and VGG16 models, while MFCC achieves the best accuracy with InceptionV3. Specifically, VGG16 with STFT attained 93.43% accuracy (score: 0.9545), whereas InceptionV3 with MFCC achieved the top performance within its architecture. These findings highlight the importance of aligning feature extraction techniques with model architecture and provide a systematic benchmark for SPRSound-based respiratory sound classification.
Read moreMechanical alloying of filler for René 142 superalloy wide-gap brazing via partitioned alloy component healing (PACH) method
Enhanced photocatalytic performance of mixed-phase TiO2–RGO nanocomposite for fast methylene blue decomposition under visible light
Copyright 2026 Cactus Communications. All rights reserved.
