Presented By O'Reilly and Cloudera
Make Data Work
December 1–3, 2015 • Singapore

IoT and Real-time conference sessions

Tuesday, December 1

Add to your personal schedule
1:30pm–5:00pm Tuesday, 12/01/2015
Location: 324 Level: Intermediate
Patrick McFadin (DataStax)
Average rating: ****.
(4.40, 5 ratings)
This tutorial is all about managing large volumes of data coming at your data center fast and continuously. If you don't have a strategy, then allow me to help. Amazing Apache Project software can make this problem a lot easier to deal with. Spend a few hours and learn about how each part works, and how they work together. Your users will thank you. Read more.

Wednesday, December 2

Add to your personal schedule
11:00am–11:40am Wednesday, 12/02/2015
Location: 324 Level: Intermediate
Amy Shi-Nash (Singtel)
Average rating: ****.
(4.00, 9 ratings)
This talk will broach the topic of how DataSpark has created an innovative way of understanding people and what is important to them, by leveraging advanced data science and the wealth of data in an aggregated manner, while adhering to high standards of data privacy. Read more.
Add to your personal schedule
11:50am–12:30pm Wednesday, 12/02/2015
Location: 324 Level: Intermediate
Thomas Holleczek (Singtel)
Average rating: ****.
(4.36, 11 ratings)
We present a traffic measurement system that monitors subway and expressway traffic from telco location data. Read more.
Add to your personal schedule
1:30pm–2:10pm Wednesday, 12/02/2015
Location: 324 Level: Intermediate
Sean Zhong (Previously Intel)
Average rating: ****.
(4.00, 1 rating)
GearPump is an akka based framework that processes real time data across a DAG of actors. Its data delivery is highly scalable with at least once data delivery guarantees. Read more.
Add to your personal schedule
2:20pm–3:00pm Wednesday, 12/02/2015
Location: 324 Level: Intermediate
Tags: iot, geo
Masaru Dobashi (NTT DATA Corporation), Yoshitaka Suzuki (IHI Corporation)
Average rating: ***..
(3.43, 7 ratings)
We are developing a platform to process massive sensor data obtained from social infrastructures and industrial machinery all over the world, in order to achieve advanced safety management. In this session, we'll talk about the capability of Spark to realize time-series data processing, the best practices of application development, and realistic lessons on operating Spark on YARN. Read more.
Add to your personal schedule
4:00pm–4:40pm Wednesday, 12/02/2015
Location: 324 Level: Intermediate
Tags: iot
Danielle Dean (Microsoft)
Average rating: ****.
(4.50, 6 ratings)
Predictive maintenance is a technique to predict when an in-service machine will fail so that maintenance can be planned in advance. This talk introduces the landscape and challenges of predictive maintenance applications in the industry. Through a real-world example, the talk also illustrates how to formulate a predictive maintenance problem with three machine learning models. Read more.
Add to your personal schedule
4:50pm–5:30pm Wednesday, 12/02/2015
Location: 324 Level: Intermediate
Tags: telecom
Arshak Navruzyan (Startup.ML)
Average rating: ***..
(3.89, 9 ratings)
Like most large internet sites, Telecom networks are constantly under attack by highly sophisticated fraudsters. Historically, carriers have tried to isolate fraudulent behavior through complex rules. However, increasingly there is a need to use machine learning algorithms that can keep up with the changing face of Telecom fraud. Read more.

Thursday, December 3

Add to your personal schedule
11:00am–11:40am Thursday, 12/03/2015
Location: 324 Level: Intermediate
Tags: telecom
Albert Bifet (Huawei), Silviu Maniu (Huawei)
Average rating: ****.
(4.17, 6 ratings)
Real-time analytics are becoming increasingly important to telecommunication operators due to the large amount of data that flows through their networks. Drawing from our experience at Huawei, we present StreamDM, a new open source data mining and machine learning library on top of Spark Streaming. We will present its implemented advanced methods, and demonstrate its ease of use and extensibility. Read more.
Add to your personal schedule
11:50am–12:30pm Thursday, 12/03/2015
Location: 324
Reynold Xin (Databricks)
In this talk, we introduce a recent effort in Spark to employ randomized algorithms for a number of common, expensive methods: membership testing, cardinality, stratified sampling, frequent items, quantile estimation. Read more.
Add to your personal schedule
1:30pm–2:10pm Thursday, 12/03/2015
Location: 324 Level: Intermediate
Markus Kirchberg (Deep Labs Pte. Ltd.)
Average rating: ***..
(3.67, 6 ratings)
In this talk, we will first take a look at current IoT standards, solutions, and common challenges; change management; and near real-time decision-making capabilities that are yet to be adequately addressed. Read more.
Add to your personal schedule
2:20pm–3:00pm Thursday, 12/03/2015
Location: 324 Level: Intermediate
Eric Frenkiel (MemSQL)
Average rating: ***..
(3.33, 9 ratings)
Eric Frenkiel, CEO/cofounder, MemSQL, will demonstrate a prototype of a futuristic smart city where all household energy devices are tracked in real-time. He will show the challenges, design choices & architecture required to enable urban planners/energy companies to see what is possible for efficient energy consumption through a real-time data pipeline combining Kafka+Spark+an in-memory database. Read more.
Add to your personal schedule
2:20pm–3:00pm Thursday, 12/03/2015
Location: 328-329 Level: Intermediate
Fangjin Yang (Imply)
Average rating: ****.
(4.33, 3 ratings)
Organizations frequently rely on dedicated query layers, such as relational databases and key/value stores, for faster query latencies; but these technologies suffer many drawbacks for analytic use cases. In this session, we discuss examine using Druid to power applications designed to analyze sensor data, and why the architecture is well suited for different use cases in “smart cities”. Read more.
Add to your personal schedule
4:00pm–4:40pm Thursday, 12/03/2015
Location: 324 Level: Intermediate
Tags: telecom
Average rating: **...
(2.00, 3 ratings)
The fast evolution of services and mobile terminals combined with the aggressive competition between mobile operators is driving a continuous upgrade of the radio access network (RAN). This upgrade process is expensive and time consuming, and it scales with the number of base stations. This talk stresses the importance of the customer and proposes a new methodology for an efficient RAN upgrade. Read more.
Add to your personal schedule
4:50pm–5:30pm Thursday, 12/03/2015
Location: 324 Level: Intermediate
Majken Sander (TimeXtender), Joerg Blumtritt (Datarella)
Average rating: ****.
(4.00, 4 ratings)
Algorithms are what make things "smart." More or less arbitrary, subjective decisions are regularly built into our connected things, when we choose a certain method or set parameters. These underlying value judgments imposed on users are hardly present in the privacy discussion or business point of view. However, they may be more important than the more obvious data collection and security. Read more.