Pub Date : 2011-09-01DOI: 10.1109/cis.2011.6169133
D. Mirikitani, Lahcen Ouarbya, Lisa Tsui, Eamonn Martin
Recurrent neural networks (RNNs) have been used for modeling the dynamics of the Dst index. Researchers have experimented with various inputs to the model, and have found improvements in prediction accuracy using measurements of the interplanetary magnetic field (IMF) taken from the Advanced Composition Explorer satellite. The output of the model is the one hour ahead forecasted Dst index. Previous models have used gradient information, usually gradient descent, for optimization of RNN parameters. This paper uses the IMF inputs (that have been found to work well) to the RNN and uses a Genetic algorithm for training the RNN. The proposed model is compared to a model used in operational forecasts which relies on solar wind data and IMF parameters, as well as a model which uses IMF data only. Both of the comparison models were trained with gradient descent. A series of geomagnetic storms that so far have been difficult to forecast are used to evaluate model performance. It is shown that the proposed evolutionary method of training the RNN outperforms both models which were trained by gradient descent.
{"title":"Improving forecasts of geomagnetic storms with evolved recurrent neural networks","authors":"D. Mirikitani, Lahcen Ouarbya, Lisa Tsui, Eamonn Martin","doi":"10.1109/cis.2011.6169133","DOIUrl":"https://doi.org/10.1109/cis.2011.6169133","url":null,"abstract":"Recurrent neural networks (RNNs) have been used for modeling the dynamics of the Dst index. Researchers have experimented with various inputs to the model, and have found improvements in prediction accuracy using measurements of the interplanetary magnetic field (IMF) taken from the Advanced Composition Explorer satellite. The output of the model is the one hour ahead forecasted Dst index. Previous models have used gradient information, usually gradient descent, for optimization of RNN parameters. This paper uses the IMF inputs (that have been found to work well) to the RNN and uses a Genetic algorithm for training the RNN. The proposed model is compared to a model used in operational forecasts which relies on solar wind data and IMF parameters, as well as a model which uses IMF data only. Both of the comparison models were trained with gradient descent. A series of geomagnetic storms that so far have been difficult to forecast are used to evaluate model performance. It is shown that the proposed evolutionary method of training the RNN outperforms both models which were trained by gradient descent.","PeriodicalId":286889,"journal":{"name":"2011 IEEE 10th International Conference on Cybernetic Intelligent Systems (CIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134359783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-09-01DOI: 10.1109/CIS.2011.6169140
J. Nehinbe, F. Adebayo
New dimensions to computer misdemeanors such as information leakages, masquerading, electronic fraud, deformation of corporate cultures and identities through fallacious electronic publicities are alarming across the globe. Hence, corporate organizations are facing serious challenges in coming up with security frameworks that will adequately safeguard their assets and liabilities on a daily basis. Unfortunately, corporate assets have several inherent vulnerabilities while available forensic computer scientists, forensic accountants, laws and litigation that will restrict illegal activities over the web are weak because of the discrepancies in the regulatory activities of different countries to cite a few. Thus, this paper presents a critical review of emerging challenges in auditing digital logs. The review provides useful guidelines that can be used to improve computer usage across the globe and to ultimately lessen the success rate of computer related frauds in corporate organizations.
{"title":"Audit and research challenges in digital forensics","authors":"J. Nehinbe, F. Adebayo","doi":"10.1109/CIS.2011.6169140","DOIUrl":"https://doi.org/10.1109/CIS.2011.6169140","url":null,"abstract":"New dimensions to computer misdemeanors such as information leakages, masquerading, electronic fraud, deformation of corporate cultures and identities through fallacious electronic publicities are alarming across the globe. Hence, corporate organizations are facing serious challenges in coming up with security frameworks that will adequately safeguard their assets and liabilities on a daily basis. Unfortunately, corporate assets have several inherent vulnerabilities while available forensic computer scientists, forensic accountants, laws and litigation that will restrict illegal activities over the web are weak because of the discrepancies in the regulatory activities of different countries to cite a few. Thus, this paper presents a critical review of emerging challenges in auditing digital logs. The review provides useful guidelines that can be used to improve computer usage across the globe and to ultimately lessen the success rate of computer related frauds in corporate organizations.","PeriodicalId":286889,"journal":{"name":"2011 IEEE 10th International Conference on Cybernetic Intelligent Systems (CIS)","volume":"17 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126069886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：