scholarly journals FilterNet: A Many-to-Many Deep Learning Architecture for Time Series Classification

2020 ◽  
Author(s):  
Robert D. Chambers ◽  
Nathanael C. Yoder
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Activity Recognition ◽  
Sensor Data ◽  
Time Series Classification ◽  
Discrete Events ◽  
Segmentation Accuracy ◽  
Model Size ◽  
Classification Tasks

We present and benchmark FilterNet, a flexible deep learning architecture for time series classification tasks, such as activity recognition via multichannel sensor data. It adapts popular CNN and CNN-LSTM motifs which have excelled in activity recognition benchmarks, implementing them in a many-to-many architecture to markedly improve frame-by-frame accuracy, event segmentation accuracy, model size, and computational efficiency. We propose several model variants, evaluate them alongside other published models using the Opportunity benchmark dataset, demonstrate the effect of model ensembling and of altering key parameters, and quantify the quality of the models’ segmentation of discrete events. We also offer recommendations for use and suggest potential model extensions. FilterNet advances the state of the art in all measured accuracy and speed metrics on the benchmarked dataset, and it can be extensively customized for other applications.

scholarly journals FilterNet: A Many-to-Many Deep Learning Architecture for Time Series Classification

2020 ◽  
Author(s):  
Robert D. Chambers ◽  
Nathanael C. Yoder
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Activity Recognition ◽  
Sensor Data ◽  
Time Series Classification ◽  
Discrete Events ◽  
Segmentation Accuracy ◽  
Model Size ◽  
Classification Tasks

We present and benchmark FilterNet, a flexible deep learning architecture for time series classification tasks, such as activity recognition via multichannel sensor data. It adapts popular CNN and CNN-LSTM motifs which have excelled in activity recognition benchmarks, implementing them in a many-to-many architecture to markedly improve frame-by-frame accuracy, event segmentation accuracy, model size, and computational efficiency. We propose several model variants, evaluate them alongside other published models using the Opportunity benchmark dataset, demonstrate the effect of model ensembling and of altering key parameters, and quantify the quality of the models’ segmentation of discrete events. We also offer recommendations for use and suggest potential model extensions. FilterNet advances the state of the art in all measured accuracy and speed metrics on the benchmarked dataset, and it can be extensively customized for other applications.

scholarly journals FilterNet: A Many-to-Many Deep Learning Architecture for Time Series Classification

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2498 ◽  
Author(s):  
Robert D. Chambers ◽  
Nathanael C. Yoder
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Activity Recognition ◽  
Short Term Memory ◽  
Sensor Data ◽  
Time Series Classification ◽  
Discrete Events ◽  
Segmentation Accuracy ◽  
Model Size

In this paper, we present and benchmark FilterNet, a flexible deep learning architecture for time series classification tasks, such as activity recognition via multichannel sensor data. It adapts popular convolutional neural network (CNN) and long short-term memory (LSTM) motifs which have excelled in activity recognition benchmarks, implementing them in a many-to-many architecture to markedly improve frame-by-frame accuracy, event segmentation accuracy, model size, and computational efficiency. We propose several model variants, evaluate them alongside other published models using the Opportunity benchmark dataset, demonstrate the effect of model ensembling and of altering key parameters, and quantify the quality of the models’ segmentation of discrete events. We also offer recommendations for use and suggest potential model extensions. FilterNet advances the state of the art in all measured accuracy and speed metrics when applied to the benchmarked dataset, and it can be extensively customized for other applications.

scholarly journals Cloud Load Estimation with Deep Logarithmic Network for Workload and Time Series Optimization

2021 ◽  
Vol 3 (3) ◽  
pp. 234-248
Author(s):  
N. Bhalaji
Keyword(s):  
Time Series ◽  
Cloud Computing ◽  
Deep Learning ◽  
Extreme Points ◽  
Learning Approach ◽  
Load Estimation ◽  
Learning Method ◽  
Network Computing ◽  
Noise Interference

In recent days, we face workload and time series issue in cloud computing. This leads to wastage of network, computing and resources. To overcome this issue we have used integrated deep learning approach in our proposed work. Accurate prediction of workload and resource allocation with time series enhances the performance of the network. Initially the standard deviation is reduced by applying logarithmic operation and then powerful filters are adopted to remove the extreme points and noise interference. Further the time series is predicted by integrated deep learning method. This method accurately predicts the workload and sequence of resource along with time series. Then the obtained data is standardized by a Min-Max scalar and the quality of the network is preserved by incorporating network model. Finally our proposed method is compared with other currently used methods and the results are obtained.

Human Activity Recognition from Body Sensor Data using Deep Learning

2018 ◽  
Vol 42 (6) ◽  
Author(s):  
Mohammad Mehedi Hassan ◽  
Shamsul Huda ◽  
Md Zia Uddin ◽  
Ahmad Almogren ◽  
Majed Alrubaian
Keyword(s):  
Deep Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Human Activity Recognition ◽  
Sensor Data

scholarly journals Edge4TSC: Binary Distribution Tree-Enabled Time Series Classification in Edge Environment

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 1908
Author(s):  
Chao Ma ◽  
Xiaochuan Shi ◽  
Wei Li ◽  
Weiping Zhu
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Classification Accuracy ◽  
Time Series Data ◽  
Series Representation ◽  
Series Data ◽  
Feature Engineering ◽  
Time Series Classification ◽  
Binary Distribution ◽  
New Time

In the past decade, time series data have been generated from various fields at a rapid speed, which offers a huge opportunity for mining valuable knowledge. As a typical task of time series mining, Time Series Classification (TSC) has attracted lots of attention from both researchers and domain experts due to its broad applications ranging from human activity recognition to smart city governance. Specifically, there is an increasing requirement for performing classification tasks on diverse types of time series data in a timely manner without costly hand-crafting feature engineering. Therefore, in this paper, we propose a framework named Edge4TSC that allows time series to be processed in the edge environment, so that the classification results can be instantly returned to the end-users. Meanwhile, to get rid of the costly hand-crafting feature engineering process, deep learning techniques are applied for automatic feature extraction, which shows competitive or even superior performance compared to state-of-the-art TSC solutions. However, because time series presents complex patterns, even deep learning models are not capable of achieving satisfactory classification accuracy, which motivated us to explore new time series representation methods to help classifiers further improve the classification accuracy. In the proposed framework Edge4TSC, by building the binary distribution tree, a new time series representation method was designed for addressing the classification accuracy concern in TSC tasks. By conducting comprehensive experiments on six challenging time series datasets in the edge environment, the potential of the proposed framework for its generalization ability and classification accuracy improvement is firmly validated with a number of helpful insights.

scholarly journals DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn

2019 ◽  
Vol 149 ◽  
pp. 91-104 ◽  
Author(s):  
Roberto Interdonato ◽  
Dino Ienco ◽  
Raffaele Gaetano ◽  
Kenji Ose
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Classification ◽  
View Point
Sign in / Sign up

Export Citation Format

Share Document