Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems by Kai Zhan, Cong Wang, Xigui Zheng, Chao Kong, Guangming Li, Wei Xin, Longhe Liu

Get full text

NMT-translation – basic models, quality assessment by I. A. Borunov

Subjects: Get full text

Reinforcement Learning-Based Generative Security Framework for Host Intrusion Detection by Yongsik Kim, Su-Youn Hong, Sungjin Park, Huy Kang Kim

“…Based on the extracted keywords, the pre-trained Seq2Seq model generate rules according to the reward calculation method in reinforcement learning. …”
Get full text

Chinese semantic and phonological information-based text proofreading model for speech recognition by Meiyu ZHONG, Peiliang WU, Yan DOU, Yi LIU, Lingfu KONG

“…To study the influence of Chinese Pinyin on detecting and correcting text errors in speech recognition, a text proofreading model based on Chinese semantic and phonological information was proposed.Five Pinyin coding methods were designed to construct the character-Pinyin embedding vector that was employed as the input of the Seq2Seq model based on gated recurrent unit.At the same time, the attention mechanism was adopted to extract the Chinese semantic and phonological information of sentences to correct speech recognition errors.Aiming at the problem of insufficient labeled corpus, a data augmentation method was introduced, which could automatically obtain annotated corpora by exchanging the initials or finals of Chinese Pinyin.The experimental results on AISHELL-3’s public data show that phonological information is conducive to the text proofreading model to detect and correct text errors after speech recognition, and the proposed data augmentation method can improve the error detection performance of the model.…”
Get full text

Urban Traffic Flow Forecast Based on FastGCRNN by Ya Zhang, Mingming Lu, Haifeng Li

“…Specifically, we use FastGCN unit to efficiently capture the topological relationship between the roads and the surrounding roads in the graph with reducing the computational complexity through importance sampling, combine GRU unit to capture the temporal dependency of traffic flow, and embed the spatiotemporal features into Seq2Seq based on the Encoder-Decoder framework. Experiments on large-scale traffic data sets illustrate that the proposed method can greatly reduce computational complexity and memory consumption while maintaining relatively high accuracy.…”
Get full text

Multi-step multivariate forecasting of transmission power in NPPs using operational and meteorological data by Jaeseok Yoo, Young-jin Oh, Nam-hyun Kim, Soo-ill Lee, Jaepil Ko

“…In this study, we explored how to effectively handle the long-term dependence problem and various data characteristics to increase the forecasting accuracy of transmission power in NPPs by introducing a Seq2Seq model with an encoder-decoder structure and an attention mechanism, beyond traditional time series deep learning models, especially LSTM. …”
Get full text

Automatical sampling with heterogeneous corpora for grammatical error correction by Shichang Zhu, Jianjian Liu, Ying Li, Zhengtao Yu

“…Finally, we enhance typical Seq2Seq and Seq2Edit grammatical error correction models with pre-trained language models and design a model ensemble algorithm for integrating the advantages of heterogeneous models and weighted samples. …”
Get full text

Artificial intelligence-driven ensemble deep learning models for smart monitoring of indoor activities in IoT environment for people with disabilities by Munya A. Arasi, Hussah Nasser AlEisa, Amani A. Alneil, Radwa Marzouk

“…For the detection of indoor activities, the proposed MOEM-SMIADP model utilizes an ensemble of three classifiers, namely the graph convolutional network model, long short-term memory sequence-to-sequence (LSTM-seq2seq) method, and convolutional autoencoder. Eventually, the hyperparameter tuning is accomplished by an improved coati optimization algorithm to enhance the classification outcomes of ensemble models. …”
Get full text