Predictive Analytics Role in Water Treatment’s Sustainability and Reliability
The Current Energy Dilemma in Water Treatment The critical component of water and waste treatment processing is the common architecture of electric motors and controls. In the United States, the treatment process is driven by electric motor-driven devices, including energy-intensive pumps. Studies and publications from the past ten years demonstrate that the energy efficiency of […]
Projecting Mission Success and Safety: Freya’s Mission Readiness Dashboard
Our impact is measured in how we equip clients with predictive models and decision tools to be more effective, efficient, and safe in their operations. We employ data strategies to fuel condition-based maintenance models and customize dashboard tools so that clients are making data-driven decisions. We are most acutely focused on these project goals in […]
Hackathon: Freya Team takes on a Visual Computing
Towards the end of 2021, Freya hosted a hackathon that split the team into two separate factions asked to solve a distinct set of computer vision problems. The resulting days allowed for collaboration and problem solving that really got the data science juices flowing. Two Real-World Problems Each team had a unique task however both […]
An Overview of the Data Pipeline – From Raw Data to Visual Insight
Before becoming a data scientist, the way data appeared on a web page seemed like magic (to be honest some parts of the process still feel that way!), but having been involved in many aspects of the data pipeline at Freya Systems I wanted to share an overview of this process. The goal of the […]
What is the Difference Between Software Development and Enterprise Software Development?
According to IBM Research: “Software development refers to a set of computer science activities dedicated to the process of creating, designing, deploying and supporting software.” Software itself is the set of code that tells a device what to do. The software could be for an individual job function or a departmental function. Enterprise software development […]
Creating a Dual Axis Plot with ggplot2
The Goal As a data scientist you often find yourself creating a notebook documenting a new model or an update to an existing model. Recently in this particular situation I was analyzing how my model was performing within windows of time throughout the prediction window. I wanted a visualization to show these results. The Problem […]
Using the Weibull Distribution to Understand Component Reliability
Component Reliability Analysis Much of our work involves determining the reliability of components, where we want to understand how long they will last before failure. We use statistical analysis to predict these failures in terms of the expected number of hours used, miles driven, etc. Say we are given data on vehicle components and how […]
Data Manipulation in R – Part 2: dplyr
This post is part 2 of a series on Data Manipulation in R. In part 1, my colleague showed the uses of the data.table package. In this part I will explore the dplyr package using the same examples used in part 1. What is dplyr? dplyr is a package for the R programming language and […]
Using Leaflet with data from the Yelp API
I was recently doing a project utilizing the Yelp API and analyzing restaurant data through R. Leaflet proved to be very helpful in providing interactive maps to visualize data. It didn’t hurt that the maps were very easy to generate and customize as well. In this post I’ll go through some of the uses I […]
What is Sentiment Analysis? Bringing Emotion into Computing
If you had to sort reviews on a website and there were no ratings attached to it: how would you know if it was good or bad? Would it be valuable for organizations to understand the public sentiment around key issues? Are consumers frustrated over an underperforming part that has slipped under the radar of […]
