Who should attend
- Professionals who have done analytics for some years and realised that there are gaps/issues in data preparation and analytics processes when it comes to IoT data.
- IoT professionals who plan to embark upon analytics journey in their organisation and want to approach analytics in a structured manner to design and better handle analytics on IoT data.
- Beginners who are learning how to perform analytics activities and need more explicit guidance from experienced professionals, on how to engage in IoT analytics exercises properly, with a focus on upstream processes for IoT.
- Participants who have successfully completed “NICF-Big Data Engineering for Analytics (SF)” or have equivalent knowledge.
- Python knowledge is strongly desirable, participants with no prior Python knowledge is encouraged to attend NICF- Python for Data, Ops and Things (SF) course.
About the course
In the last few years, continuous streaming of data from sensors has emerged as one of the most promising data sources, fuelling a number of interesting developments in “Internet of Things (IoT)”. This continuous streaming of information must be coupled with a means to analyse the data and create the corresponding analytics models, and put these models back to the edge nodes in IoT network. Given the fast pace of change to connected devices and the perspective of data science, one needs to understand and explore feature engineering of IoT or sensor data.
This course will equip analytics professionals and managers with an understanding of how data are ingested, transformed, the addition of constructed new fields and the removal of distracting fields. These are done with the knowledge of how the representation model operates, making it easy for Machine Learning model for different output representation.
The main objective of this course is to provide participants with a practical understanding of Feature Engineering and skills of analysing IoT data and use them effectively to obtain analytics insights.
Upon completion of the course, students will be able to:
- Design suitable strategy on harnessing IoT analytics to create business value.
- Classify and contextualise different architectural solutions to deal with feature analytics pertinent to IoT.
- Evaluate various major cloud vendors in the market and their services/libraries/framework for IoT analytics.
- Identify a framework to classify processing and decisions in the cloud and/or edge using cognitive computing (Machine Learning/Deep Learning) libraries for a given business case.
- Understand and use various data sources, data visualisations and insight generation techniques to create intelligence.
- Understand domain specific variation needed for feature engineering while applying to final solution developed using analytics.
What Will Be Covered
- Managing data ingestion, storage and processing via data lakes
- Selecting optimal time window for aggregating sensor data
- Application of well-known data mining algorithms for IoT data
- Practical business use cases of end-to-end solution with IoT analytics
- Demonstration of the Economics of IoT analytics
Liu Fan currently lecturers in the Software Systems Practice in the areas of software engineering, big data engineering and data analytics. She received her Ph.D Ph.D. degree from School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore. Prior to joining ISS, ...
Senior Analytics professional with 20 years’ experience in management roles driving value from analytics, leveraging big data to generate actionable insights and increased revenues. Proven record of establishing, building from scratch the analytics and campaign function of HDFC Bank (leading ban...
Read more about Business Analytics
Because of COVID-19, many providers are cancelling or postponing in-person programs or providing online participation options.
We are happy to help you find a suitable online alternative.