Artificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited data type for training CNN-based speech emotion recognition (SER). The research experiments employed five popular datasets: Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Surrey Audio-Visual Expressed Emotion (SAVEE), Toronto Emotional Speech Set (TESS), and The Interactive Emotional Dyadic Motion Capture (IEMOCAP). Six different classes of emotions were used: happiness, anger, sadness, fear, disgust, and neutral. However, some experiments were prepared to recognize just four emotions due to the characteristics of the IEMOCAP dataset. A comparison of classification efficiency on different datasets and an attempt to develop a universal model trained using all datasets were also performed. This approach brought an accuracy of 55.89% when recognizing four emotions. The most accurate model for six emotion recognition was trained and achieved 57.42% accuracy on a combination of four datasets (CREMA-D, RAVDESS, SAVEE, TESS). What is more, another study was developed that demonstrated that improper data division for training and test sets significantly influences the test accuracy of CNNs. Therefore, the problem of inappropriate data division between the training and test sets, which affected the results of studies known from the literature, was addressed extensively. The performed experiments employed the popular ResNet18 architecture to demonstrate the reliability of the research results and to show that these problems are not unique to the custom CNN architecture proposed in experiments. Subsequently, the label correctness of the CREMA-D dataset was studied through the employment of a prepared questionnaire.
27 September 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
The rise of Artificial Neural Networks (ANNs) has revolutionized various fields of research, demonstrating their effectiveness in solving complex problems. However, there are still unexplored areas where the application of neural networks, particularly Convolutional Neural Network (CNN) models, has yet to be explored. One area where the application of Artificial Neural Networks is even expected is geomorphology. One of the tasks of geomorphology is the classification of landforms in a broad sense. Such classification requires a precise interpretation approach to create a homogeneous product, and this requires time and a uniform, consistent approach by the interpreter, which is not easy to achieve with manual operations. Classifications in geomorphology are mainly performed by manual or semi-automatic methods. The use of Artificial Neural Networks can complement and, in many areas, replace manual classification and reduce the time commitment of the interpreter, not least because of its repeatability and objectivity, which is a definite advantage in the case of geomorphological interpretation of vast areas. This study uses two popular CNN architectures, including VGG and Residual Neural Network (ResNet), to solve the problem of classifying glacial and fluvioglacial landforms based on a Digital Elevation Model (DEM). The results of this study show that CNNs can produce high accuracy scores (up to 87% overall accuracy) for a ground-based dataset and are a suitable method for identifying glacial and fluvioglacial landforms using DEM data as input. The presented method provides an objective, reproducible and fast tool for automatic geomorphological analysis of terrain imagery of vast areas.
Classification of glacial landforms is a task in geomorphology that has not been widely explored with deep neural network methods. This study uses Vision Transformer (ViT) architecture to classify glacial landforms using Digital Elevation Model (DEM) in three study sites: Elise Glacier in Svalbard, Norway; Gardno-Leba Plain and Lubawa Upland in Poland. In datasets each of those sites has different DEM resolutions and terrain types which includes end moraines, hummocky moraines, kettle holes, outwash/glaciolacustrine plains, till plains and valleys. The results of the classification show that ViT architecture is a suitable method for this type of task and can achieve up to 97.5% of accuracy. The classification process described in this study can be reproducible and applied to other terrain types around the world.
18 November 2024 in International Journal of Electronics and Telecommunications
Glacial landforms, created by the continuous movements of glaciers over millennia, are crucial topics in geomorphological research. Their systematic analysis affords invaluable insights into past climatic oscillations and augments understanding of long-term climate change dynamics. The classification of these types of terrain traditionally depends on labor-intensive manual or semi-automated methods. However, the emergence of automated techniques driven by deep learning and neural networks holds promise for enhancing efficiency of terrain classification workflows. This study evaluated the effectiveness of Convolutional Neural Network (CNN) architectures, particularly Residual Neural Network (ResNet) and VGG in comparison with Vision Transformer (ViT) architecture in the glacial landform classification task. By using preprocessed input data from Digital Elevation Model (DEM) which covers regions such as the Lubawa Upland and Gardno-Leba Plain in Poland, as well as the Elise Glacier in Svalbard, Norway, comprehensive assessments of those methods were conducted. The final results highlight the unique ability of deep learning methods to accurately classify glacial landforms. Classification process presented in this study can be the efficient, repeatable and fast solution for automatic terrain classification.
Automatic liver segmentation of Computed Tomography (CT) images is becoming increasingly important. Although there are many publications in this field there is little explanation why certain pre-processing methods were utilised. This paper presents a comparison of the commonly used approach of Hounsfield Units (HU) windowing, histogram equalisation, and a combination of these methods to try to ascertain what are the differences between them and how big the differences are. All experiments were conducted on the LiTS dataset. To achieve comparable and reliable results only one architecture of neural network is used which is U-Net with ResNet34 blocks.
2 January 2026 in International Journal of Digital Earth