LA-ESN: A Novel Method for Time Series Classification
نویسندگان
چکیده
Time-series data is an appealing study topic in mining and has a broad range of applications. Many approaches have been employed to handle time series classification (TSC) challenges with promising results, among which deep neural network methods become mainstream. Echo State Networks (ESN) Convolutional Neural (CNN) are commonly utilized as TSC research. However, ESN CNN can only extract local dependencies relations series, resulting long-term temporal dependence needing be more challenging capture. As result, encoder decoder architecture named LA-ESN proposed for tasks. In LA-ESN, the composed ESN, obtain matrix representation. Meanwhile, consists one-dimensional (1D CNN), Long Short-Term Memory (LSTM) Attention Mechanism (AM), information global from Finally, many comparative experimental studies were conducted on 128 univariate datasets different domains, three evaluation metrics including accuracy, mean error rank exploited evaluate performance. comparison other approaches, produced good results.
منابع مشابه
a time-series analysis of the demand for life insurance in iran
با توجه به تجزیه و تحلیل داده ها ما دریافتیم که سطح درامد و تعداد نمایندگیها باتقاضای بیمه عمر رابطه مستقیم دارند و نرخ بهره و بار تکفل با تقاضای بیمه عمر رابطه عکس دارند
An Effective Method for Imbalanced Time Series Classification: Hybrid Sampling
Most traditional supervised classification learning algorithms are ineffective for highly imbalanced time series classification, which has received considerably less attention than imbalanced data problems in data mining and machine learning research. Bagging is one of the most effective ensemble learning methods, yet it has drawbacks on highly imbalanced data. Sampling methods are considered t...
متن کاملAdapting ELM to Time Series Classification: A Novel Diversified Top-k Shapelets Extraction Method
ELM (Extreme Learning Machine) is a single hidden layer feed-forward network, where the weights between input and hidden layer are initialized randomly. ELM is efficient due to its utilization of the analytical approach to compute weights between hidden and output layer. However, ELM still fails to output the semantic classification outcome. To address such limitation, in this paper, we propose...
متن کاملA Method for DMUs Classification in DEA
In data envelopment analysis, anyone can do classification decision units with efficiency scores. It will be interesting if a method for classification of DMUs without regarding to efficiency score is obtained. So in this paper, the classification of Decision Making Units (DMUs) is done according to the additive model without being solved for obtaining scores efficiency. This is because it ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Information
سال: 2023
ISSN: ['2078-2489']
DOI: https://doi.org/10.3390/info14020067