An ARIMA‐ANN Hybrid Model for Time Series Forecasting

Wang, Li; Haofei, Zou; Su, Jia; Li, Ling; Chaudhry, Sohail S.

doi:10.1002/sres.2179

Cited by 124 publications

(80 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ARIMA [8] and ES [9] are two classical time series forecasting methods which have been introduced in Section 1. The former builds the forecasting model based on the lag value and random error term value.…”

Section: Discussion and Comparisonsmentioning

confidence: 99%

“…By analyzing the time dependent relationship of security events, we can forecast the future situation. Autoregressive integrated moving average (ARIMA) [8] and exponential smoothing (ES) [9] are two classic time series forecasting methods, which require a stable time series. Only when the data fit the normal distribution can obtain better prediction results.…”

Section: (1) Spatial-time Sequence Based Methods (Sts)mentioning

confidence: 99%

“…By combining this function in our model, we can get a more reliable estimate. Combining with (8), the exploitability probability on the age of the vulnerability V which is still unpatched in the current network is as follows:…”

Section: Attack Capacity Metricmentioning

confidence: 99%

See 2 more Smart Citations

Quantitative Method for Network Security Situation Based on Attack Prediction

Zhang

Liu

et al. 2017

Security and Communication Networks

View full text Add to dashboard Cite

Multistep attack prediction and security situation awareness are two big challenges for network administrators because future is generally unknown. In recent years, many investigations have been made. However, they are not sufficient. To improve the comprehensiveness of prediction, in this paper, we quantitatively convert attack threat into security situation. Actually, two algorithms are proposed, namely, attack prediction algorithm using dynamic Bayesian attack graph and security situation quantification algorithm based on attack prediction. The first algorithm aims to provide more abundant information of future attack behaviors by simulating incremental network penetration. Through timely evaluating the attack capacity of intruder and defense strategies of defender, the likely attack goal, path, and probability and time-cost are predicted dynamically along with the ongoing security events. Furthermore, in combination with the common vulnerability scoring system (CVSS) metric and network assets information, the second algorithm quantifies the concealed attack threat into the surfaced security risk from two levels: host and network. Examples show that our method is feasible and flexible for the attack-defense adversarial network environment, which benefits the administrator to infer the security situation in advance and prerepair the critical compromised hosts to maintain normal network communication.

show abstract

Section: Discussion and Comparisonsmentioning

confidence: 99%

Section: (1) Spatial-time Sequence Based Methods (Sts)mentioning

confidence: 99%

See 1 more Smart Citation

Quantitative Method for Network Security Situation Based on Attack Prediction

Zhang

Liu

et al. 2017

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…ARIMA is originally proposed by Box and Jenkins [31], which is a very popular model for time series analysis and forecasting [32], [33]. It collects past values of the same variable and develops a model to describe their underlying relationships.…”

Section: Arima Modelsmentioning

confidence: 99%

Personalized Qos Prediction Using Time Series Forecasting and Collaborative Filtering

Hu¹,

Peng²,

Hu³

et al. 2016

STSC

View full text Add to dashboard Cite

Quality of Service (QoS) has been widely used for web service recommendation and selection. Since QoS information usually cannot be predetermined, how to make personalized QoS prediction precisely becomes a big challenge. Time series forecasting and Collaborative Filtering (CF) are two mainstream technologies for QoS prediction. However, existing time series forecasting approaches based on AutoRegressive Integrated Moving Average (ARIMA) models do not take new observations as a feedback to revise QoS forecasts. Moreover, they only focus on forecasting QoS values for each individual web service. Service users' personalized factors are not considered. CF facilitates personalized QoS evaluation, but rarely models the temporal dynamics of QoS values. To address the limitations of existing approaches, this paper proposes a novel personalized QoS prediction approach considering both the temporal dynamics of QoS attributes and the personalized factors of service users. Our approach seamlessly combines CF with an improved time series forecasting method, which uses Kalman filtering to compensate for defects of ARIMA models. Additionally, we design a prototype system for QoS dissemination over the Internet, thus providing a necessary infrastructure for the implementation of personalized QoS prediction. Finally, we conduct experiments to study the effectiveness of our approach. Experimental results show our approach can improve QoS prediction accuracy significantly.

show abstract

“…Cuando se analizaron los 18 artículos seleccionados, se encontró que únicamente tres propuestas consideran un proceso diferente al autorregresivo: Khashei and Bijari [24], Tseng, Yu and Tzeng [29], Zhang [30], y Wang et al [48].…”

Section: Factores De Calidadunclassified

Methodological Advances in Artificial Neural Networks for Time Series Forecasting

Cogollo

Velásquez

2014

IEEE Latin Am. Trans.

View full text Add to dashboard Cite

Objective: The aim of this paper is to analyze the development of new forecasting models based on neural networks using the guidelines of the synthesis method, systematic literature review. Method: We used the systematic literature review method employing a manual search of papers published on new neural networks models in the time period 2000 to 2013. Results: Only 19 studies meet all the requirements of the inclusion criteria. Of these, only three proposals considered a neural networks model using a process different to the autoregressive. Conclusion: Although studies relating to the application of neural network models were frequently present, we find that the studies proposing new forecasting models based on neural networks with a theoretical support and a systematic procedure for the construction of model, were scarce in the time period 2000-2013.

show abstract

An ARIMA‐ANN Hybrid Model for Time Series Forecasting

Cited by 124 publications

References 43 publications

Quantitative Method for Network Security Situation Based on Attack Prediction

Quantitative Method for Network Security Situation Based on Attack Prediction

Personalized Qos Prediction Using Time Series Forecasting and Collaborative Filtering

Methodological Advances in Artificial Neural Networks for Time Series Forecasting

Contact Info

Product

Resources

About