Novel measures based on the Kolmogorov complexity for use in complex system behavior studies and time series analysis

AbstractWe propose novel metrics based on the Kolmogorov complexity for use in complex system behavior studies and time series analysis. We consider the origins of the Kolmogorov complexity and discuss its physical meaning. To get better insights into the nature of complex systems and time series analysis we introduce three novel measures based on the Kolmogorov complexity: (i) the Kolmogorov complexity spectrum, (ii) the Kolmogorov complexity spectrum highest value and (iii) the overall Kolmogorov complexity. The characteristics of these measures have been tested using a generalized logistic equation. Finally, the proposed measures have been applied to different time series originating from: a model output (the biochemical substance exchange in a multi-cell system), four different geophysical phenomena (dynamics of: river flow, long term precipitation, indoor

Download Full-text

Long-Term Data Traffic Forecasting for Network Dimensioning in LTE with Short Time Series

Electronics ◽

10.3390/electronics10101151 ◽

2021 ◽

Vol 10 (10) ◽

pp. 1151

Author(s):

Carolina Gijón ◽

Matías Toril ◽

Salvador Luna-Ramírez ◽

María Luisa Marí-Altozano ◽

José María Ruiz-Avilés

Keyword(s):

Time Series ◽

Deep Learning ◽

Time Series Analysis ◽

Data Traffic ◽

Medium Term ◽

Short Term ◽

Traffic Forecasting ◽

Series Analysis ◽

Radio Planning

Network dimensioning is a critical task in current mobile networks, as any failure in this process leads to degraded user experience or unnecessary upgrades of network resources. For this purpose, radio planning tools often predict monthly busy-hour data traffic to detect capacity bottlenecks in advance. Supervised Learning (SL) arises as a promising solution to improve predictions obtained with legacy approaches. Previous works have shown that deep learning outperforms classical time series analysis when predicting data traffic in cellular networks in the short term (seconds/minutes) and medium term (hours/days) from long historical data series. However, long-term forecasting (several months horizon) performed in radio planning tools relies on short and noisy time series, thus requiring a separate analysis. In this work, we present the first study comparing SL and time series analysis approaches to predict monthly busy-hour data traffic on a cell basis in a live LTE network. To this end, an extensive dataset is collected, comprising data traffic per cell for a whole country during 30 months. The considered methods include Random Forest, different Neural Networks, Support Vector Regression, Seasonal Auto Regressive Integrated Moving Average and Additive Holt–Winters. Results show that SL models outperform time series approaches, while reducing data storage capacity requirements. More importantly, unlike in short-term and medium-term traffic forecasting, non-deep SL approaches are competitive with deep learning while being more computationally efficient.

Download Full-text

Comparison of parametric and non-parametric time-series analysis methods on a long-term meteorological data set

Central European Geology ◽

10.1556/24.60.2017.011 ◽

2017 ◽

Vol 60 (3) ◽

pp. 316-332 ◽

Cited By ~ 6

Author(s):

Tímea Kocsis ◽

Ilona Kovács-Székely ◽

Angéla Anda

Keyword(s):

Time Series ◽

Time Series Analysis ◽

Meteorological Data ◽

Data Set ◽

Series Analysis ◽

Analysis Methods ◽

Non Parametric

Download Full-text

Are all the word ranking methods the same?

International Journal of Modern Physics C ◽

10.1142/s0129183121501448 ◽

2021 ◽

pp. 2150144

Author(s):

Elham Najafi ◽

Alireza Valizadeh ◽

Amir H. Darooneh

Keyword(s):

Complex System ◽

Time Series ◽

Spatial Distribution ◽

Time Series Analysis ◽

Complex Networks ◽

Rank Correlation ◽

Ranking Methods ◽

Series Analysis ◽

Maximum Value

Text as a complex system is commonly studied by various methods, like complex networks or time series analysis, in order to discover its properties. One of the most important properties of each text is its keywords, which are extracted by word ranking methods. There are various methods to rank words of a text. Each method differently ranks words according to their frequency, spatial distribution or other word properties. Here, we aimed to explore how similar various word ranking methods are. For this purpose, we studied the rank correlation of some important word ranking methods for number of sample texts with different subjects and text sizes. We found that by increasing text size the correlation between ranking methods grows. It means that as the text size increases, the associated word ranks calculated by different ranking methods converge. Also, we found out that the rank correlations of word ranking methods approach their maximum value in the case of large enough texts.

Download Full-text