Search Results (3)

Instabilities in energy supply caused by equipment failures, particularly in power transformers, can significantly impact efficiency and lead to shutdowns, which can affect the population. To address this, researchers have developed fault diagnosis strategies for oil-immersed power transformers using dissolved gas analysis (DGA) to enhance reliability and environmental responsibility. However, the fault diagnosis of oil-immersed power transformers has not been exhaustively investigated. There are gaps related to real scenarios with imbalanced datasets, such as the reliability and robustness of fault diagnosis modules. Strategies with more robust models increase the overall performance of the entire system. To address this issue, we propose a novel approach based on Kolmogorov–Arnold Network (KAN) for the fault diagnosis of power transformers. Our work is the first to employ a dedicated KAN in an imbalanced data real-world scenario, named KAN_Diag, while also applying the synthetic minority based on probabilistic distribution (SyMProD) technique for balancing the data in the fault diagnosis. Our findings reveal that this pioneering employment of KAN_Diag achieved the minimal value of Hamming loss—0.0323—which minimized the classification error, guaranteeing enhanced reliability for the whole system. This ground-breaking implementation of KAN_Diag achieved the highest value of weighted average F₁-Score—96.8455%—ensuring the solidity of the approach in the real imbalanced data scenario. In addition, KAN_Diag gave the highest value for accuracy—96.7728%—demonstrating the robustness of the entire system. Some key outcomes revealed gains of 68.61 percentage points for KAN_Diag in the fault diagnosis. These advancements emphasize the efficiency and robustness of the proposed system. Full article

Several sign language datasets are available in the literature. Most of them are designed for sign language recognition and translation. This paper presents a new sign language dataset for automatic motion generation. This dataset includes phonemes for each sign (specified in HamNoSys, a transcription system developed at the University of Hamburg, Hamburg, Germany) and the corresponding motion information. The motion information includes sign videos and the sequence of extracted landmarks associated with relevant points of the skeleton (including face, arms, hands, and fingers). The dataset includes signs from three different subjects in three different positions, performing 754 signs including the entire alphabet, numbers from 0 to 100, numbers for hour specification, months, and weekdays, and the most frequent signs used in Spanish Sign Language (LSE). In total, there are 6786 videos and their corresponding phonemes (HamNoSys annotations). From each video, a sequence of landmarks was extracted using MediaPipe. The dataset allows training an automatic system for motion generation from sign language phonemes. This paper also presents preliminary results in motion generation from sign phonemes obtaining a Dynamic Time Warping distance per frame of 0.37. Full article

This paper proposes, analyzes, and evaluates a deep learning architecture based on transformers for generating sign language motion from sign phonemes (represented using HamNoSys: a notation system developed at the University of Hamburg). The sign phonemes provide information about sign characteristics like hand configuration, localization, or movements. The use of sign phonemes is crucial for generating sign motion with a high level of details (including finger extensions and flexions). The transformer-based approach also includes a stop detection module for predicting the end of the generation process. Both aspects, motion generation and stop detection, are evaluated in detail. For motion generation, the dynamic time warping distance is used to compute the similarity between two landmarks sequences (ground truth and generated). The stop detection module is evaluated considering detection accuracy and ROC (receiver operating characteristic) curves. The paper proposes and evaluates several strategies to obtain the system configuration with the best performance. These strategies include different padding strategies, interpolation approaches, and data augmentation techniques. The best configuration of a fully automatic system obtains an average DTW distance per frame of 0.1057 and an area under the ROC curve (AUC) higher than 0.94. Full article