Lucas P. Queiroz, Francisco Caio M. Rodrigues, J. Gomes, Felipe T. Brito, Iago C. Brito, Javam C. Machado
{"title":"基于混合高斯分布的硬盘故障检测","authors":"Lucas P. Queiroz, Francisco Caio M. Rodrigues, J. Gomes, Felipe T. Brito, Iago C. Brito, Javam C. Machado","doi":"10.1109/BRACIS.2016.036","DOIUrl":null,"url":null,"abstract":"Being able to detect faults in Hard Disk Drives (HDD) can lead to significant benefits to computer manufacturers, users and storage system providers. As a consequence, several works have focused on the development of fault detection algorithms for HDDs. Recently, promising results were achieved by methods using SMART (Self-Monitoring Analysis and Reporting Technology) features and anomaly detection algorithms based on Mahalanobis distance. Nevertheless, the performance of such methods can be seriously degraded when the normality assumption of the data does not hold. As a way to overcome this issue, we propose a new method for fault detection in HDD based on a Gaussian Mixture Model (GMM). The proposed method is tested in a real world dataset and its performance is compared to three other HDD fault detection methods.","PeriodicalId":183149,"journal":{"name":"2016 5th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Fault Detection in Hard Disk Drives Based on Mixture of Gaussians\",\"authors\":\"Lucas P. Queiroz, Francisco Caio M. Rodrigues, J. Gomes, Felipe T. Brito, Iago C. Brito, Javam C. Machado\",\"doi\":\"10.1109/BRACIS.2016.036\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Being able to detect faults in Hard Disk Drives (HDD) can lead to significant benefits to computer manufacturers, users and storage system providers. As a consequence, several works have focused on the development of fault detection algorithms for HDDs. Recently, promising results were achieved by methods using SMART (Self-Monitoring Analysis and Reporting Technology) features and anomaly detection algorithms based on Mahalanobis distance. Nevertheless, the performance of such methods can be seriously degraded when the normality assumption of the data does not hold. As a way to overcome this issue, we propose a new method for fault detection in HDD based on a Gaussian Mixture Model (GMM). The proposed method is tested in a real world dataset and its performance is compared to three other HDD fault detection methods.\",\"PeriodicalId\":183149,\"journal\":{\"name\":\"2016 5th Brazilian Conference on Intelligent Systems (BRACIS)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 5th Brazilian Conference on Intelligent Systems (BRACIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/BRACIS.2016.036\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 5th Brazilian Conference on Intelligent Systems (BRACIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BRACIS.2016.036","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Fault Detection in Hard Disk Drives Based on Mixture of Gaussians
Being able to detect faults in Hard Disk Drives (HDD) can lead to significant benefits to computer manufacturers, users and storage system providers. As a consequence, several works have focused on the development of fault detection algorithms for HDDs. Recently, promising results were achieved by methods using SMART (Self-Monitoring Analysis and Reporting Technology) features and anomaly detection algorithms based on Mahalanobis distance. Nevertheless, the performance of such methods can be seriously degraded when the normality assumption of the data does not hold. As a way to overcome this issue, we propose a new method for fault detection in HDD based on a Gaussian Mixture Model (GMM). The proposed method is tested in a real world dataset and its performance is compared to three other HDD fault detection methods.