The Research And Implement Of IPTV Fault Diagnosis Based On Data Mining

With the rapid development of multimedia communications,more and more users enjoy the Internet Protocol Television(IPTV)service at home.The IPTV operators try their best to support high-quality programs and smooth video streaming transmission in order to guarantee the excellent user's experience.Meanwhile,the operations face more and more pressure because they have to solve the difficulties and failures which come from varying degrees and different levels daily.Therefore,how to accurately and objectively assess the quality of IPTV service and timely maintain the IPTV networks has become a research hotspot in the current sense.This paper proposes a novel quality assessment scheme for IPTV operation and maintenance.It is an integrated system to make the IPTV network fault location diagnosis more efficiently and accurately.Specifically,the potential user complaint and potential warning facility are integrated for constructing the IPTV service quality assessment system.When handling the determination of the potential warning facility,objective Quality of Experience(QoE)indicators reflecting users' viewing behaviors are considered and integrated with traditional Quality of Service(QoS)indicators.In this paper,the main contents of the research on IPTV fault location diagnosis are presented as follows:On the one hand,this paper proposes an integrated poor-quality equipment prediction model to find the potential relationship between elected set-top boxes(STB)indicators and network conditions.The target is to make the IPTV network fault diagnosis more accurately and efficiently,especially for the sudden pause or blurred screen.The integrated poor-quality model consists of indicator,record and user model.Firstly,as a novel feature selection algorithm,the poor-quality indicator model is proposed for replacing existing ones in decision tree generation and pruning.It is in charge of selecting the effective indexes from candidate STB indicators.Secondly,the poor-quality record model,which based on our proposed decision tree algorithm,has responsibility for adjustment of threshold values in order to meet the needs of higher accuracy rate with lower misjudgment ratio.Finally,the poor-quality user model takes customer's viewing time parameter into account,which can reflect end user's quality of experience objectively.The experiment results show that the prediction for poor-quality user model can reach up to 83.25%.On the other hand,in imbalanced IPTV dataset,the traditional algorithm performs not well in terms of predicting the user's complaint.For this problem,this paper combines traditional network parameters that influence the network quality of service(QoS)with MOS score that objectively reflects the quality of experience(QoE)to predict user's complaint.And then we propose an improved algorithm based on the existing ODR-BSMOTE-SVM algorithm for the defect that over-sampling algorithm will produce noise.Besides,there is not any optimization for kernel parameters.Firstly,under-sampling algorithm,over-sampling algorithm and data cleaning algorithm are applied to process the original imbalanced dataset.Then,through searching for the approximate optimal value by adaptive variable kernel parameters,classification effect is ultimately improved.Experimental results show that this method performs better than traditional standard support vector machine(SVM)and ODR-BSMOTE-SVM algorithm in predicting user's complaint.