Combining time series prediction models using genetic algorithm to autoscaling Web applications hosted in the cloud infrastructure

An accurate, reliable and stable air quality prediction system is conducive to the public health and management of atmospheric ecological environment; therefore, many models, individual or hybrid, have been implemented widely to deal with the prediction problem. However, many of these models do not take into consideration or extract improperly the period information in air quality index (AQI) time series, which impacts the models’ learning efficiency greatly. In this paper, a period extraction algorithm is proposed by using a Luenberger observer, and then a novel period-aware hybrid model combined the period extraction algorithm and tradition time series models is build to exploit the comprehensive forecasting capacity to the AQI time series with nonlinear and non-stationary noise. The hybrid model requires a multi-phase implementation. In the first step, the Luenberger observer is used to estimate the implied period function in the one-dimensional AQI series, and then the analyzed time series is mapped to the period space through the function to obtain the period information sub-series of the original series. In the second step, the period sub-series is combined with the original input vector as input vector components according to the time points to establish a new data set. Finally, the new data set containing period information is applied to train the traditional time series prediction models. Both theoretical proof and experimental results obtained on the AQI hour values of Beijing, Tianjin, Taiyuan and Shijiazhuang in North China prove that the hybrid model with period information presents stronger robustness and better forecasting accuracy than the traditional benchmark models.

Download Full-text

Application of the nonlinear time series prediction method of genetic algorithm for forecasting surface wind of point station in the South China Sea with scatterometer observations

Chinese Physics B ◽

10.1088/1674-1056/25/11/110502 ◽

2016 ◽

Vol 25 (11) ◽

pp. 110502 ◽

Cited By ~ 1

Author(s):

Jian Zhong ◽

Gang Dong ◽

Yimei Sun ◽

Zhaoyang Zhang ◽

Yuqin Wu

Keyword(s):

Genetic Algorithm ◽

Time Series ◽

South China Sea ◽

South China ◽

Time Series Prediction ◽

Surface Wind ◽

Prediction Method ◽

Nonlinear Time Series ◽

The South China Sea ◽

China Sea

Download Full-text

An Optimized Method of Wind Speed Prediction with Support Vector Machine and Genetic Algorithm

International Journal of Circuits, Systems and Signal Processing ◽

10.46300/9106.2021.15.24 ◽

2021 ◽

Vol 15 ◽

pp. 212-217

Author(s):

Guan-fa Li ◽

Wen-sheng Zhu

Keyword(s):

Genetic Algorithm ◽

Time Series ◽

Support Vector Machine ◽

Wind Speed ◽

Power System ◽

Prediction Models ◽

Optimization Method ◽

Support Vector ◽

Wind Speed Prediction ◽

Speed Prediction

Due to the randomness of wind speed and direction, the output power of wind turbine also has randomness. After large-scale wind power integration, it will bring a lot of adverse effects on the power quality of the power system, and also bring difficulties to the formulation of power system dispatching plan. In order to improve the prediction accuracy, an optimized method of wind speed prediction with support vector machine and genetic algorithm is put forward. Compared with other optimization methods, the simulation results show that the optimized genetic algorithm not only has good convergence speed, but also can find more suitable parameters for data samples. When the data is updated according to time series, the optimization range of vaccine and parameters is adaptively adjusted and updated. Therefore, as a new optimization method, the optimization method has certain theoretical significance and practical application value, and can be applied to other time series prediction models.

Download Full-text

Prognosis of Chronic Renal Syndrome by Classification and Progression Using Temporal Abstraction

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.j9927.0981119 ◽

2019 ◽

Vol 8 (11) ◽

pp. 53-58

Keyword(s):

Genetic Algorithm ◽

Time Series ◽

Renal Disease ◽

Prediction Model ◽

Prediction Models ◽

Series Data ◽

Support Vector ◽

Temporal Abstraction ◽

Graphic Data ◽

Lab Test

Chronic renal syndrome is defined as a progressive loss of renal function over period. Analysers have make effort in attempting to diagnosis the risk factors that may affect the retrogression of chronic renal syndrome. The motivation of this project helps to develop a prediction model for level 4 CKD patients to detect on condition that, their estimated Glomerular Filtration Rate (eGFR) stage downscale to lower than 15 ml/min/1.73 m². End phase renal disease, after six months accumulating their concluding lab test observation by assessing time affiliated aspects. Data mining algorithm along with Temporal Abstraction (TA) are confederated to reinforce CKD evolvement of prognostication models. In this work a inclusive of 112 chronic renal disease patients are composed from April 1952 to September 2011 which were extracted from the patient’s Electronic Medical Records (EMR). The information of chronic renal patients are collected in a big spatial info-graphic data. In order to analyse these info-graphic data, it is significant to detect the issues affecting CKD deterioration and hence it becomes a challenging task. To overcome this challenge, time series graph has been generated in this project work based on creatinine and albumin lab test values and reports of the time period. The presence of CKD diagnostic codes are transformed into default seven digit default format of International Classification of Disease 10 Clinical Modification (ICD 10 CM). Feature selection is performed in this work based on wrapper method using genetic algorithm. It is helpful for finding the most relevant variables for a predictive model. High Utility Sequential Rule Miner (HUSRM) is used here to address the discovery of CKD sequential rules based on sequence patterns. Temporal Abstraction (TA) techniques namely basic TA and complex TA are used in this work to analyse the status of chronic renal syndrome patients. Classification and Regression Technique (CART) along with Adaptive Boosting (AdaBoost) and Support Vector Machine Boosting (SVMBoost) are applied to develop the CKD in which the progression prediction models exhibit most accurate prediction. The results obtained from this work divulged that comprehending temporal observation forward the prognostic instances has escalated the efficacy of the instances. Finally, an evaluation metrics namely accuracy, sensitivity, specificity, positive likelihood, negative likelihood and Area Under the Curve (AUC) are helps to evaluate the performance of the prediction models which are designed and implemented in this project. Key Words: CKD, progression, time series data, genetic algorithm, sequential rules, TA classification and prediction model.

Download Full-text

Airline Delay Time Series Differentials

International Journal of Aviation Systems Operations and Training ◽

10.4018/ijasot.2014070105 ◽

2014 ◽

Vol 1 (2) ◽

pp. 64-76

Author(s):

Ronald Wesonga ◽

Fabian Nabugoomu ◽

Brian Masimbi

Keyword(s):

Time Series ◽

Prediction Models ◽

Time Series Prediction ◽

Model Development ◽

Differential Analysis ◽

Management Styles ◽

Flight Delays ◽

Daily Data ◽

Passenger Travel ◽

Time Series Modelling

Flight delays affect passenger travel satisfaction and increase airline costs. The authors explore airline differences with a focus on their delays based on autoregressive integrated moving averages. Aviation daily data were used in the analysis and model development. Time series modelling for six airlines was done to predict delays as a function of airport's timeliness performance. Findings show differences in the time series prediction models by airline. Differential analysis in the time series prediction models for airline delay suggests variations in airline efficiencies though at the same airport. The differences could be attributed to different management styles in the countries where the airlines originate. Thus, to improve airport timeliness performance, the study recommends airline disaggregated studies to explore the dynamics attributable to determinants of airline unique characteristics.

Download Full-text

An Evolutionary Framework for Nonlinear Time-Series Prediction with Adaptive Gated Mixtures of Experts

Artificial Intelligence and Integrated Intelligent Information Systems ◽

10.4018/978-1-59904-249-7.ch007 ◽

2011 ◽

pp. 114-138

Author(s):

André L.V. Coelho ◽

Clodoaldo A.M. Lima ◽

Fernando J. Von Zuben

Keyword(s):

Machine Learning ◽

Genetic Algorithm ◽

Time Series ◽

Intelligent System ◽

Time Series Prediction ◽

Integrated Approach ◽

Nonlinear Time Series ◽

Learning Problems ◽

Automatic Design ◽

Hybrid Intelligent System

A probabilistic learning technique, known as gated mixture of experts (MEs), is made more adaptive by employing a customized genetic algorithm based on the concepts of hierarchical mixed encoding and hybrid training. The objective of such effort is to promote the automatic design (i.e., structural configuration and parameter calibration) of whole gated ME instances more capable to cope with the intricacies of some difficult machine learning problems whose statistical properties are time-variant. In this chapter, we outline the main steps behind such novel hybrid intelligent system, focusing on its application to the nontrivial task of nonlinear time-series forecasting. Experiment results are reported with respect to three benchmarking time-series problems, and confirmed our expectation that the new integrated approach is capable to outperform, both in terms of accuracy and generalization, other conventional approaches, such as single neural networks and non-adaptive, handcrafted gated MEs.

Download Full-text

Real coded genetic algorithm for fuzzy time series prediction

10.1063/1.5008700 ◽

2017 ◽

Cited By ~ 3

Author(s):

Shilpa Jain ◽

Dinesh C. S. Bisht ◽

Phool Singh ◽

Prakash C. Mathpal

Keyword(s):

Genetic Algorithm ◽

Time Series ◽

Time Series Prediction ◽

Fuzzy Time Series ◽

Real Coded Genetic Algorithm

Download Full-text

Bandwidth Utilization Prediction in LAN Network Using Time Series Modeling

Iraqi Journal of Computer Communication Control and System Engineering ◽

10.33103/uot.ijccce.19.2.9 ◽

2019 ◽

pp. 78-89

Keyword(s):

Time Series ◽

Network Traffic ◽

Network Performance ◽

Prediction Models ◽

Time Series Prediction ◽

Bandwidth Utilization ◽

Research Issues ◽

Network Traffic Analysis ◽

Network Bandwidth ◽

And Performance

monitoring the behavior of computer networks is essential for problem identification and optimal management. Part of this behavior to be monitored is the utilization of the network bandwidth. Several techniques are used to model and forecast network traffic such as time series models, modern data mining techniques, soft computing approaches, and neural networks are used for network traffic analysis and prediction. Efficient bandwidth utilization and optimization are very interesting research issues in effective networks because bandwidth is one of the most required and expensive Internet components needed today. It is generally known that the higher the bandwidth available, the better the network performance, thus an essential aid for network design and bandwidth wastage control and a need for traffic models which can capture the characteristics is necessary. In this paper, a time series prediction models were proposed for LAN office network bandwidth utilization. The proposed prediction models are tested by using evaluation metrics used in time series such as MSE and performance evaluation plot. Testing results show that the proposed models can enhance the detection of bandwidth traffic and provide an efficient tool for bandwidth utilization.

Download Full-text