LA-ESN: A Novel Method for Time Series Classification

Shen, Hui; Min, Liu; Hu, Jiyong; Li, Ping; Peng, Yali; Yi, Yugen

doi:10.3390/info14020067

Cited by 6 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On top of that, decision tree models can handle various types of data with less data preparation needed. However, when the tasks come to time series examination, one-dimension convolutional neural networks (1D-CNNs) have gained a lot of attention and have been widely adopted [22,27,[33][34][35]. Instead of applying some sort of noise filtering or smoothing techniques before the analysis, convolutional neural networks provide an effective way to learn the smoothing parameters.…”

Section: Discussionmentioning

confidence: 99%

Identification and Classification of Human Body Exercises on Smart Textile Bands by Combining Decision Tree and Convolutional Neural Networks

Koo

Nguyen

Kim

2023

Sensors

View full text Add to dashboard Cite

In recent years, human activity recognition (HAR) has gained significant interest from researchers in the sports and fitness industries. In this study, the authors have proposed a cascaded method including two classifying stages to classify fitness exercises, utilizing a decision tree as the first stage and a one-dimension convolutional neural network as the second stage. The data acquisition was carried out by five participants performing exercises while wearing an inertial measurement unit sensor attached to a wristband on their wrists. However, only data acquired along the z-axis of the IMU accelerator was used as input to train and test the proposed model, to simplify the model and optimize the training time while still achieving good performance. To examine the efficiency of the proposed method, the authors compared the performance of the cascaded model and the conventional 1D-CNN model. The obtained results showed an overall improvement in the accuracy of exercise classification by the proposed model, which was approximately 92%, compared to 82.4% for the 1D-CNN model. In addition, the authors suggested and evaluated two methods to optimize the clustering outcome of the first stage in the cascaded model. This research demonstrates that the proposed model, with advantages in terms of training time and computational cost, is able to classify fitness workouts with high performance. Therefore, with further development, it can be applied in various real-time HAR applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Identification and Classification of Human Body Exercises on Smart Textile Bands by Combining Decision Tree and Convolutional Neural Networks

Koo

Nguyen

Kim

2023

Sensors

View full text Add to dashboard Cite

show abstract

Chemical process fault detection and trend analysis based on KESN

Cao,

Cheng,

Deng

et al. 2024

Can J Chem Eng

View full text Add to dashboard Cite

Fault detection has great significance for chemical process safety with the development of science and technology. The conventional echo state network‐based fault detection method does not highlight key fault features, and cannot forecast future fault trend after the occurrence of faults. For the above problems, a chemical process fault detection and trend analysis strategy based on key feature enhanced echo state network (KESN) is proposed. First, dynamic features are extracted by a detecting echo state network. Then, a weighting strategy is designed to enhance key features and increase fault detection rates. After detecting a fault, independent component analysis is utilized to extract independent key features. Future fault trend is forecasted based on the forecasting multi‐KESN. Simulation results on the Tennessee Eastman process demonstrate the effectiveness of the proposed method.

show abstract

Enhancing the chimp optimization algorithm to evolve deep LSTMs for accounting profit prediction using adaptive pair reinforced technique

Yang,

Wu,

Zeng

2023

Evolving Systems

View full text Add to dashboard Cite

Accurately predicting accounting profit (PAP) plays a vital role in financial analysis and decision-making for businesses. The analysis of a business’s financial achievements offers significant insights and aids in the formulation of strategic plans. This research paper focuses on improving the chimp optimization algorithm (CHOA) to evolve deep long short-term memory (LSTM) models specifically for financial accounting profit prediction. The proposed hybrid approach combines CHOA’s global search capabilities with deep LSTMs’ sequential modeling abilities, considering both the global and temporal aspects of financial data to enhance prediction accuracy. To overcome CHOA’s tendency to get stuck in local minima, a novel updating technique called adaptive pair reinforced (APR) is introduced, resulting in APRCHOA. In addition to well-known conventional prediction models, this study develops five deep LSTM-based models, namely conventional deep LSTM, CHOA (deep LSTM-CHOA), adaptive reinforcement-based genetic algorithm (deep LSTM-ARGA), marine predator algorithm (deep LSTM-MPA), and adaptive reinforced whale optimization algorithm (deep LSTM-ARWOA). To comprehensively evaluate their effectiveness, the developed deep LSTM-APRCHOA models are assessed using statistical error metrics, namely root mean square error (RMSE), bias, and Nash–Sutcliffe efficiency (NSEF). In the validation set, at a lead time of 1 h, the NSEF values for LSTM, LSTM-MPA, LSTM-CHOA, LSTM-ARGA, LSTM-ARWOA, and deep LSTM-APRCHOA were 0.9100, 0.9312, 0.9350, 0.9650, 0.9722, and 0.9801, respectively. The results indicate that among these models, deep LSTM-APRCHOA demonstrates the highest accuracy for financial profit prediction.

show abstract

LA-ESN: A Novel Method for Time Series Classification

Cited by 6 publications

References 37 publications

Identification and Classification of Human Body Exercises on Smart Textile Bands by Combining Decision Tree and Convolutional Neural Networks

Identification and Classification of Human Body Exercises on Smart Textile Bands by Combining Decision Tree and Convolutional Neural Networks

Chemical process fault detection and trend analysis based on KESN

Enhancing the chimp optimization algorithm to evolve deep LSTMs for accounting profit prediction using adaptive pair reinforced technique

Contact Info

Product

Resources

About