O’REILLY、INTEL AI主办

English中文
将人工智能用起来
2019年6月18-21日
北京,中国

Using deep learning and time-series forecasting to reduce transit delays

This will be presented in English.

Mark Ryan (IBM), Alina Li Zhang (Skylinerunners)
14:5015:30 Thursday, June 20, 2019

必要预备知识 (Prerequisite Knowledge)

- basic to intermediate machine learning - conceptual familiarity with deep learning

您将学到什么 (What you'll learn)

- applying time-series forecasting in machine learning - applying machine learning to resolve fundamental transit issues

描述 (Description)

Toronto is unique among North American cities for having a legacy streetcar network as an integral part of its transit system. The streetcars are icons of the city and make a unique contribution because of their passenger capacity and zero emissions. However, because most of the streetcar network shares streets with other vehicles, and because unlike buses streetcars cannot move around obstacles or be quickly towed away if they break down,
streetcar delays have a disproportionate on gridlock.

This session will demonstrate an approach that uses time-series forecasting and deep learning to predict streetcar delays.

- First, the nature of the problem will be described in more detail, including the economic impact of streetcar-triggered gridlock on Canada’s largest city.
- Next, we’ll describe the development environment we used to tackle the problem.
- Then we’ll describe the source data and cleansing process, with a focus on the challenges and opportunities of dealing with “wild data”. We’ll describe the essential points of time-series forecasting and how we applied it conjunction with
deep learning.
- Finally, we’ll share the results of our analysis, including practical recommendations for Toronto’s transit authority (the TTC) to resolve the problem of streetcar delays so that the city can continue to enjoy the character and soul of our unique street railway for the rest of the 21st century.

Data Source: https://www.toronto.ca/city-government/data-research-maps/open-data/open-data-catalogue/#e8f359f0-2f47-3058-bf64-6ec488de52da

Photo of Mark Ryan

Mark Ryan

IBM

Mark has had an interest in machine learning and artificial intelligence since doing a Masters at University of Toronto in the 80s. Currently he works at IBM and is responsible for shepherding customers to a variety of database products, including IBM Integrated Analytics System, which includes a full-blow machine learning environment: DSX. Mark’s interests in machine learning include deep learning on structured data and NLP.

Photo of Alina Li Zhang

Alina Li Zhang

Skylinerunners

Alina Zhang is Data Scientist at Skylinerunners Corporation and certified as Google Cloud Professional Data Engineer. She has authored [articles](https://medium.com/@alina.li.zhang) on Machine Learning, Exploratory Data Analysis, Data Visualization, etc.
Alina is driving Skylinerunners to provide small business with AI solutions. She applies Machine Learning models on user behavior analysis, recommendation system, and time series forecasting.
Before joining Skylinerunners, Alina was data scientist in Nobul. She was driving Nobul to evolve real estate in the cloud with Machine Learning technology to a variety of problems including property listing prediction, real estate chatbot with natural language processing, customer’s behavioral clustering, etc.
She worked for IBM as a software developer and WLM component owner of IBM DB2. Alina holds a Master Degree in Computer Science from Western University, where her research focused on high performance computing and Truncated Fourier Transform.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)