AI News, Data Science for Internet of Things methodology - Evolving CRISP-DM - Part Two
- On Wednesday, October 17, 2018
- By Read More
Data Science for Internet of Things methodology - Evolving CRISP-DM - Part Two
You can find the first post describing the initial steps of the methodology on Data Science Central This new post focus on continuous improvement, following the design and deployment of the architecture and the model.
While hardware is unchanged for a certain period of time, software gets updated often, bringing new capabilities to the devices, which can be used to solve the problem defined initially.
However, it the methodology has been implemented in an agile way, then the initial implementation is only a first step good enough, but definitely not the last step of implementation. This continuous improvement phase is split into four activities:
Given the categories of factors listed above, the rate of review to conduct the improvement activities is very specific to those factors.
Whether we decide to revise the model on a regular period or when a given event occurs (often an unexpected result / behavior), we need to collect information on the current state.
For instance, if we are looking at an industrial analytics application that predicts pressure based on a set of diverse parameters coming from sensors, we want to collect the time series of all the data coming from the sensors, the time series of the actual pressure points and the predicted time series by the model we initially designed.
Whatever the rationale behind the continuous improvement process, collecting this data ensures that we have a sound foundation for reviewing the work done previously, and construct a new dataset.
For instance a device may have sensors that were not initially programmed in its firmware, like an industrial device initially providing only temperature information, which is upgraded to provide pressure in addition of temperature.
The implications of changing the architecture can be far reaching, and doing so should be done with care, otherwise we may not be doing continuous improvement but we have to start from scratch instead.
This list is by no means exhaustive, but for all these reasons we need to re-analyze the problem at hand and rework on the model, using the new dataset that has been created (either in the first phase or in the second phase depending on whether we have additional data in the data streams).
We won’t go through again here, just reminding that the model should be assess both from a statistical point of view (minimizing bias and variance and trading-off precision and recall) and that it can indeed solve the problem (impact on the KPIs we have defined).
- On Thursday, June 4, 2020
Architecture Components - Introduction (Google I/O '17)
Writing robust Android apps can be challenging, between complex lifecycle issues, unreliable mobile networks, and constrained device capabilities. Mistakes in ...
Data Modeling for BigQuery (Google Cloud Next '17)
BigQuery is a different data warehouse, permitting new approaches to data modeling. To get the most out of this system, Dan McClary and Daniel Mintz examine ...
Android Jetpack: what's new in Architecture Components (Google I/O '18)
This session will cover the state of the art in Android app architecture: all the new features and updates that have been added to Android Architecture ...
3.2 - LTE RAN Architecture - UMTS - Introduction
In previous Generations, the base stations were controlled by a central device. In 2G, it was the base station controller, and in 3G it was the RNC. In LTE, this ...
H.265 (HEVC) vs H.264 (AVC) Compression: Explained!
What is H.265 (HEVC)? Why is it better quality than H.264 (AVC), especially for 4K? Do your devices support H.265? This video will explain all of the questions ...
Lecture 15 | Efficient Methods and Hardware for Deep Learning
In Lecture 15, guest lecturer Song Han discusses algorithms and specialized hardware that can be used to accelerate training and inference of deep learning ...
20. Mobile Phone Security
MIT 6.858 Computer Systems Security, Fall 2014 View the complete course: Instructor: Nickolai Zeldovich In this lecture, Professor ..
Small Deep Neural Networks - Their Advantages, and Their Design
Deep neural networks (DNNs) have led to significant improvements to the accuracy of machine-learning applications. For many problems, such as object ...
Inside Azure datacenter architecture with Mark Russinovich - BRK3347
Microsoft Azure has achieved massive, global scale, with 50 announced regions consisting of over 100 datacenters, and it is growing fast. It delivers the promise ...
EVPN for Everyone Else Evolved Campus Core
Technical difficulties with audio & video. Today when you hear someone talk about EVPN/VXLAN it's more than likely in the context of a DataCenter.