☆ 4.7 Article

Muformer: A long sequence time-series forecasting model based on modified multi-head attention

KNOWLEDGE-BASED SYSTEMS (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals

Yuxin Zhang et al.

Summary: Nowadays, multi-sensor technologies are widely used in various fields, generating a large amount of multivariate time-series data. Unsupervised anomaly detection on multi-sensor data is critical but challenging due to the need to capture spatial-temporal correlation and distinguish between normal, abnormal, and noisy data. This paper proposes a novel deep learning-based algorithm called CAE-M, which characterizes spatial dependence using a deep convolutional autoencoder and temporal dependence with a memory network. Experimental results on HAR and HC datasets show that the proposed approach outperforms existing methods.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Discovering emotion and reasoning its flip in multi-party conversations using masked memory network and transformer

Shivani Kumar et al.

Summary: Efficiently identifying a speaker's emotional changes in a multi-party conversation is crucial for designing conversational agents that resemble humans. This paper introduces a novel task called Emotion-Flip Reasoning (EFR), which aims to identify past utterances that trigger a speaker's emotional state to flip. By utilizing the MELD dataset and introducing new labels, our models demonstrate improved performances in emotion recognition and emotion-flip reasoning tasks.

KNOWLEDGE-BASED SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Adaptive Temporal-Frequency Network for Time-Series Forecasting

Zhangjing Yang et al.

Summary: This paper proposes a novel adaptive temporal-frequency network (ATFN) for mid- and long-term time series forecasting. The model combines deep learning networks and frequency patterns to learn the trend feature and capture dynamic periodic patterns of time series data. The experimental results demonstrate that the ATFN has promising performance and strong adaptability for long-term time-series forecasting.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Visual affordance detection using an efficient attention convolutional neural network

Qipeng Gu et al.

Summary: This paper introduces a novel convolutional neural network architecture for pixel-wise affordance detection, which achieved better performance in experiments compared to traditional methods by integrating attention mechanism and up-sampling layer.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep Transformer modeling via grouping skip connection for neural machine translation

Yachao Li et al.

Summary: In this paper, a deeper Transformer encoder is proposed by organizing encoder layers into multiple groups, connected via a grouping skip connection mechanism, to build a deep Transformer encoder with up to 48 layers. Experimental results show that the proposed deep Transformer model significantly outperforms the baseline on machine translation tasks and is easy to implement.

KNOWLEDGE-BASED SYSTEMS (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Hierarchical Memory Decoder for Visual Narrating

Aming Wu et al.

Summary: This article introduces a novel memory decoder for visual narrating, which uses multi-modal fusion and multiple memory layers to better capture long-term information and generate accurate descriptions.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Application of variational mode decomposition and chaotic grey wolf optimizer with support vector regression for forecasting electric loads

Zichen Zhang et al.

Summary: Accurate electric load forecasting is crucial for the efficiency of power system operation. Hybrid intelligent computing methods and swarm-based algorithms, along with the SVR model, show promising results in solving convergence issues. The proposed VMD-SVR-CGWO model outperforms other models in forecasting accuracy based on numerical examples from two electric load data sets.

KNOWLEDGE-BASED SYSTEMS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

DSTP-RNN: A dual-stage two-phase attention-based recurrent neural network for long-term and multivariate time series prediction

Yeqi Liu et al.

EXPERT SYSTEMS WITH APPLICATIONS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

CNN-FCM: System modeling promotes stability of deep learning in time series prediction

Penghui Liu et al.

KNOWLEDGE-BASED SYSTEMS (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Convolutional Reconstruction-to-Sequence for Video Captioning

Aming Wu et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2020)

添加到收藏夹

Article Economics

DeepAR: Probabilistic forecasting with autoregressive recurrent networks

David Salinas et al.

INTERNATIONAL JOURNAL OF FORECASTING (2020)

添加到收藏夹

Article Computer Science, Hardware & Architecture

NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm

Xiaoliang Dai et al.

IEEE TRANSACTIONS ON COMPUTERS (2019)

添加到收藏夹

Article Statistics & Probability

Forecasting at Scale

Sean J. Taylor et al.

AMERICAN STATISTICIAN (2018)

添加到收藏夹

Article Computer Science, Information Systems

A Tensor-Based Information Framework for Predicting the Stock Market

Qing Li et al.

ACM TRANSACTIONS ON INFORMATION SYSTEMS (2016)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Energy Time Series Forecasting Based on Pattern Sequence Similarity

Francisco Martinez-Alvarez et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2011)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A unifying framework for detecting outliers and change points from time series

J Takeuchi et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2006)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.