Asynchronous dual-pipeline deep learning framework for online data stream classification

Lara-Benítez, Pedro; Carranza-García, Manuel; García-Gutiérrez, Jorge; Riquelme, José C.

doi:10.3233/ica-200617

Cited by 47 publications

(29 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dilation consists of skipping d values between the inputs of the convolutional operation, as can be seen in Figure 4c. The complete dilated causal convolution operation over consecutive layers can be formulated as follows [36]:…”

Section: Temporal Convolutional Neural Networkmentioning

confidence: 99%

Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting

et al. 2020

Self Cite

View full text Add to dashboard Cite

Modern energy systems collect high volumes of data that can provide valuable information about energy consumption. Electric companies can now use historical data to make informed decisions on energy production by forecasting the expected demand. Many deep learning models have been proposed to deal with these types of time series forecasting problems. Deep neural networks, such as recurrent or convolutional, can automatically capture complex patterns in time series data and provide accurate predictions. In particular, Temporal Convolutional Networks (TCN) are a specialised architecture that has advantages over recurrent networks for forecasting tasks. TCNs are able to extract long-term patterns using dilated causal convolutions and residual blocks, and can also be more efficient in terms of computation time. In this work, we propose a TCN-based deep learning model to improve the predictive performance in energy demand forecasting. Two energy-related time series with data from Spain have been studied: the national electric demand and the power demand at charging stations for electric vehicles. An extensive experimental study has been conducted, involving more than 1900 models with different architectures and parametrisations. The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.

show abstract

Section: Temporal Convolutional Neural Networkmentioning

confidence: 99%

Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, their capacity to adapt directly to the data without any prior assumptions provides significant advantages when dealing with little information about the time series. 10 With the increasing availability of data, more sophisticated deep learning architectures have been proposed with substantial improvements in forecasting performances. 11 However, there is the need more than ever for works that provide a comprehensive analysis of the TSF literature, in order to better understand the scientific advances in the field.…”

Section: Introductionmentioning

confidence: 99%

An Experimental Review on Deep Learning Architectures for Time Series Forecasting

Lara-Benítez

Carranza-García

Riquelme

2021

Int. J. Neur. Syst.

Self Cite

326

118

View full text Add to dashboard Cite

In recent years, deep learning techniques have outperformed traditional models in many machine learning tasks. Deep neural networks have successfully been applied to address time series forecasting problems, which is a very important topic in data mining. They have proved to be an effective solution given their capacity to automatically learn the temporal dependencies present in time series. However, selecting the most convenient type of deep neural network and its parametrization is a complex task that requires considerable expertise. Therefore, there is a need for deeper studies on the suitability of all existing architectures for different forecasting tasks. In this work, we face two main challenges: a comprehensive review of the latest works using deep learning for time series forecasting and an experimental study comparing the performance of the most popular architectures. The comparison involves a thorough analysis of seven types of deep learning models in terms of accuracy and efficiency. We evaluate the rankings and distribution of results obtained with the proposed models under many different architecture configurations and training hyperparameters. The datasets used comprise more than 50,000 time series divided into 12 different forecasting problems. By training more than 38,000 models on these data, we provide the most extensive deep learning study for time series forecasting. Among all studied models, the results show that long short-term memory (LSTM) and convolutional networks (CNN) are the best alternatives, with LSTMs obtaining the most accurate forecasts. CNNs achieve comparable performance with less variability of results under different parameter configurations, while also being more efficient.

show abstract

“…The increase in availability and quality of remote sensing data provided by modern multi-modal sensors has allowed pushing the state-of-the-art in many computer vision tasks. The data provided by high-resolution cameras and proximity sensors have helped to develop more powerful machine learning models that have achieved unprecedented results in visual recognition problems [1]. These developments have significantly improved the perception systems used in many applications such as autonomous driving [2,3], security surveillance [4], or land monitoring [5].…”

Section: Introductionmentioning

confidence: 99%

On the Performance of One-Stage and Two-Stage Object Detectors in Autonomous Vehicles Using Camera Data

et al. 2020

Self Cite

View full text Add to dashboard Cite

Object detection using remote sensing data is a key task of the perception systems of self-driving vehicles. While many generic deep learning architectures have been proposed for this problem, there is little guidance on their suitability when using them in a particular scenario such as autonomous driving. In this work, we aim to assess the performance of existing 2D detection systems on a multi-class problem (vehicles, pedestrians, and cyclists) with images obtained from the on-board camera sensors of a car. We evaluate several one-stage (RetinaNet, FCOS, and YOLOv3) and two-stage (Faster R-CNN) deep learning meta-architectures under different image resolutions and feature extractors (ResNet, ResNeXt, Res2Net, DarkNet, and MobileNet). These models are trained using transfer learning and compared in terms of both precision and efficiency, with special attention to the real-time requirements of this context. For the experimental study, we use the Waymo Open Dataset, which is the largest existing benchmark. Despite the rising popularity of one-stage detectors, our findings show that two-stage detectors still provide the most robust performance. Faster R-CNN models outperform one-stage detectors in accuracy, being also more reliable in the detection of minority classes. Faster R-CNN Res2Net-101 achieves the best speed/accuracy tradeoff but needs lower resolution images to reach real-time speed. Furthermore, the anchor-free FCOS detector is a slightly faster alternative to RetinaNet, with similar precision and lower memory usage.

show abstract

Asynchronous dual-pipeline deep learning framework for online data stream classification

Cited by 47 publications

References 55 publications

Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting

Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting

An Experimental Review on Deep Learning Architectures for Time Series Forecasting

On the Performance of One-Stage and Two-Stage Object Detectors in Autonomous Vehicles Using Camera Data

Contact Info

Product

Resources

About