Implementation of SARIMA algorithm in understanding cybersecurity threats in university network.
Currently, there are few studies on cybersecurity threats risk assessment in the university network. This research aims to fill the gaps by identifying cybersecurity threats through a quantitative study conducted in selected university. This study aims to investigate the use of predictive analysis b...
保存先:
| 主要な著者: | , , , , |
|---|---|
| フォーマット: | 論文 |
| 言語: | English |
| 出版事項: |
ASR Research India
2022
|
| 主題: | |
| オンライン･アクセス: | http://eprints.utm.my/104227/1/NorkhushainiAwangGathanALNarayanaSamyNoorHafizahHassan2022_ImplementationofSARIMAAlgorithm.pdf http://eprints.utm.my/104227/ https://www.journalppw.com/index.php/jpsp/article/view/5110/3326 |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 要約: | Currently, there are few studies on cybersecurity threats risk assessment in the university network. This research aims to fill the gaps by identifying cybersecurity threats through a quantitative study conducted in selected university. This study aims to investigate the use of predictive analysis by looking at network packets in the university network. We proposed a prediction model using Time Series Analysis (TSA) whereby data is gathered from the selected university network firewall. Conducting a risk assessment is a very important activity in an organization. The results of the risk assessment process can help network admin to make decisions in managing risks. The risk assessment also important because university network have many systems to be protected from cybersecurity threats. With risk assessment, network admin can manage the risks and prevent before cybersecurity threats interrupt the whole system in the university network. In this research, we adapted quantitative methods to analyze risk. Moreover, there are few studies on risk assessment prediction at university network. In building predictive models, we implemented the Seasonal Autoregressive Integrated Moving Average (SARIMA) method for time series forecasting with univariate data containing trends and seasonality. SARIMA has built a predictive model by looking at several variables namely seasonal autoregressive order, seasonal difference order, seasonal moving average order and also the number of time steps for a single seasonal period. The conclusion from this study shows that byusing SARIMA algorithm, the researcher get the best prediction value in order to get a small Root Mean Squared Error (RMSE) value |
|---|