Time series anomaly detection with event correlation to reduce MTTR of WiFi issues
First, I’ll examine the effectiveness of using a statistical approach with time series network data to detect anomalies. This approach, combined with event correlation, enables us to detect several classes of network problems, which I will discuss in detail.
Mutual information to apply WiFi service levels and predict network success
In this section of the talk, I discuss taking unstructured data from the wireless edge and converting it into domain-specific metrics. The mutual information data science technique can then be applied to determine which network features are the most likely to cause success or failure. We will look at mutual information expressed in terms of the entropy between two random variables and how it can be used to find the root cause of a client user experience problem.
Unsupervised machine learning for highly accurate indoor location
For RSSI based location solutions, there is a model needed that maps RSSI to distance, often referred to as the RF path loss model. Typically, this model is learned by manually collecting data, known as fingerprinting. For large venues and given the fact that mobile devices have different RF characteristics, fingerprinting is not practical. In this section, I will discuss how the unsupervised machine learning data science technique can use noisy RSSI data from directional BLE antenna arrays to learn the RF path loss model.
Bob is CTO and co-founder of Mist, a pioneer in smart wireless networking for the smart device era.
Bob started his career in wireless at Metricom (Ricochet wireless network) developing and deploying wireless mesh networks across the country to connect the first generation of Internet browsers. Following Metricom, Bob co-founded Airespace, a start-up focused on helping enterprises manage the flood of employees bringing unlicensed Wi-Fi technology into their businesses. Following Cisco’s acquisition of Airespace in 2005, Bob became the VP/CTO of Cisco enterprise mobility and drove mobility strategy and investments in the wireless business (e.g. Navini, Cognio, ThinkSmart, Phunware, Wilocity, Meraki). He also drove industry standards such as Hot Spot 2.0 and market efforts such as Cisco’s Connected Mobile Experience. He holds more than 15 patents.