Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: Bi-GRU

Sortuj według:

Ogranicz wyniki do:

Fault diagnosis algorithm of electric vehicle gearbox based on SDEA-Bi GRU

Zhao Linlin, Wu Tao

Diagnostyka

2024

Vol. 25, No. 2

art. no. 2024215

This paper suggests a hybrid method that combines the strengths of a bidirectional gated recurrent unit with a stacked denoising autoencoder to enhance the precision and effectiveness of diagnosing transmission faults in electric vehicles. The bidirectional gated recurrent unit makes advantage of these deep features for efficient fault pattern identification and classification. The results revealed that the hybrid algorithm had the best feature extraction ability for gear fault signals, and the signal features extracted by the algorithm were more concentrated and crossed each other less. The neurons in the hidden layer of the stacked denoising autoencoder was 180, and the number of neurons in the bidirectional gated recurrent unit was 160, and the hybrid algorithm performed best when the neurons in the hidden layer was 180 and the neurons in the bidirectional gated recurrent unit was 160. The hybrid algorithm performed best when the number of neurons was 160. The hybrid algorithm had the highest diagnostic accuracy for the faults, with the highest diagnostic accuracy of 97.98% in the balanced samples and 94.86% in the unbalanced samples. The hybrid algorithm constructed in the study effectively improves the diagnostic accuracy of transmission gear faults in electric vehicles.

Multimodal Sarcasm Detection via Hybrid Classifier with Optimistic Logic

Bavkar Dnyaneshwar Madhukar, Kashyap Ramgopal, Khairnar Vaishali

Journal of Telecommunications and Information Technology

2022

nr 3

97--114

This work aims to provide a novel multimodal sarcasm detection model that includes four stages: pre-processing, feature extraction, feature level fusion, and classification. The pre-processing uses multimodal data that includes text, video, and audio. Here, text is pre-processed using tokenization and stemming, video is pre-processed during the face detection phase, and audio is pre-processed using the filtering technique. During the feature extraction stage, such text features as TF-IDF, improved bag of visual words, n-gram, and emojis as well on the video features using improved SLBT, and constraint local model (CLM) are extraction. Similarly the audio features like MFCC, chroma, spectral features, and jitter are extracted. Then, the extracted features are transferred to the feature level fusion stage, wherein an improved multilevel canonical correlation analysis (CCA) fusion technique is performed. The classification is performer using a hybrid classifier (HC), e.g. bidirectional gated recurrent unit (Bi-GRU) and LSTM. The outcomes of Bi-GRU and LSTM are averaged to obtain an effective output. To make the detection results more accurate, the weight of LSTM will be optimally tuned by the proposed opposition learning-based aquila optimization (OLAO) model. The MUStARD dataset is a multimodal video corpus used for automated sarcasm Discovery studies. Finally, the effectiveness of the proposed approach is proved based on various metrics.