Dr. Ye Ouyang of Verizon Wireless

Scalable and diagnosable are the two most crucial needs for voice call quality assessment in mobile networks. However, while these two requirements are widely accepted by mobile carriers, they do not receive enough attention during the development. Current related research mainly focuses on audio feature analysis, which is costly, sensitive to language and tones, and infeasible to be applied to mobile networks. This work revisits this problem, and for the first time explores wireless network, the causal factor that directly impacts the mobile voice quality but yet lacks of attention for decades. We design CrowdMi, a wireless analytics tool that model the mobile voice quality by crowdsourcing and mining the network indicators of cellphones. CrowdMi mines hundreds of network indicators to build a causal relationship between voice quality and network conditions, and carefully calibrates the model according to the widely accepted POLQA voice assessment standard. We implement a light-load CrowdMi Client App in Android smartphones, which automatically collects data through user crowdsourcing and outputs to the CrowdMi Server in our data center that runs the mining algorithm. We conduct a pilot trial in VoLTE network in different geographical areas and network coverages. The trial shows that the CrowdMi does not require any additional hardware or human effort, and has very high model accuracy and strong diagnosability.

Biography: Dr. Ye Ouyang is a Distinguished Member of Technical Staff-Mobile Network & Device Analytics at Verizon Wireless USA Headquarters. He has over 12 years experience in telecommunications industry, working on the forefront of cutting edge wireless and big data analytics field. Dr. Ouyang’s research lies in big data analytics and quantitative modeling for wireless networks, with a focus on 2G/3G/4G LTE network performance, network capacity, traffic patterns, user behaviors, and network and device service quality etc. by leveraging data analytics, network simulation, statistical modeling, machine learning, and data mining techniques. He holds a Bachelor of Engineering from Southeast University in Nanjing, China, a Master of Science from Tufts University in Massachusetts, USA, and a Doctor of Philosophy from Stevens Institute of Technology in New Jersey, USA. In 2012-2013, Dr. Ouyang as Co-Principal was awarded telecom research funding by White House, the office of Science and Technology and National Science Foundation (NSF). He authored 20+ academic papers, 3 book chapters, and 7 US Patents. Dr. Ouyang is also a columnist of SINA Technology, which is the largest online media portal in China. He serves as Chair for Big Data Analytics Session in IEEE WOCC and WTS Conference, and TPC and reviewer for many leading academic journals and transactions.

Address:Verizon Wireless , , New Jersey, United States

Dr. Tan Yan of NEC Labs America, USA

Biography: Dr. Tan Yan received Ph.D. and Master of Science Degree from Department of Computer Science, NJIT, supervised by Dr. Guiling Wang and Bachelor of Engineering from Southeast University in Nanjing, China. He currently is a Research Staff Member in NEC Labs America. His research focuses on network analytics, mobility data mining and network planning. He has published 10+ research papers in top conferences and journals, and is the first author of three IEEE Transactions

Address:NEC Labs America, , United States