Looking at the root causes and potential approaches we can take to solve one of the biggest problems with modern transportation

Image source

In the US alone, 17.4 billion hours are wasted sitting in traffic. During this time, over 3 billion additional gallons of fuel are emitted into the atmosphere (which is ~2% of the 134 billion gallons of gasoline consumed by Americans each year).

Furthermore, traffic congestion worsens as cities grow. Considering by 2050 13% of the worlds population is expected to shift from suburban/rural areas to urban cities, traffic congestion is expected to increase at astronomical rates.

Take Los Angeles for example, a metropolitan area of ~90,000km2 which has more roadway miles than all of Canada (~10M km2). Traffic in LA…

17th Century philosopher Rene Descartes

Everyone has problems. Whether you forgot to complete yesterday’s math homework or just had a huge fight with your sibling, problems are an inevitable part of a person’s life. However, problems aren’t a bad thing. Its the fact people aren’t willing to foster solutions to their issues which is the true hindrance.

Simply put, people hate effort. And effort is required to create solutions to problems. To avoid creating solutions, people tend to draw conclusions like: “I’m just not naturally talented” or “I have a bad teacher”.

So what’s the solution to this. Well, it’s rather simple: logic.

Logic (läjik)…

A simple and digestible deep dive into the theory behind Hourglass Networks for human pose estimation

Human Pose Estimation (source)

A man is running at you with a knife. What do you do? Well, most people will only have one thought in mind: RUN. Well, why would you run? Because after observing this man’s aggressive posture, you can conclude that he wants to harm you. And since you want to live to see tomorrow, you decide to run as fast as you possibly can.

Well, how are you able to do all this complex analysis in mere seconds? Well, you’re brain just did something called human pose estimation. …

Source (here)

Go from zero to hero guide to building a Lane Line Detection algorithm in OpenCV

Lane line detection is one of the essential components of self-driving cars. There are many approaches to doing this. Here, we’ll look at the simplest approach using Hough Transform. Alright, let’s dive into it!


So before we get started, we need a place to write our code. The IDE (environment) that I recommend is Jupyter Notebooks. It has a nice, minimalistic interface yet is really powerful at the same time. Also, Jupyter Notebooks are awesome for visualizing data. Here’s the download link:

Now that you have Anaconda installed and Jupyter is working, let’s get some data! You can download the…

Ever watched those motivational videos that said, “Your comfort zone is your enemy”, or said, “you are confined by the walls you build yourself”.

I’ve been there. I used to watch those videos every single day. And while yes, what they are saying is true, I never actually went outside of my comfort zone. Heck, by watching those videos, my comfort zone was getting smaller.

In fact, here’s how things used to take place

  • I’d come across a motivational video
  • Feel really good after watching it
  • Make plans to start something big, like runs every morning
  • First day, I crush…

Writing a CNN that classifies over 43 types of road signs in the Keras framework

Process of classifying road signs (source)

There are so many different types of traffic signs out there, each with different colours, shapes and sizes. Sometimes, there are two signs may have a similar colour, shape and size, but have 2 totally different meanings. How on earth would we ever be able to program a computer to correctly classify a traffic sign on the road? We can do this by creating our very own CNN to classify each different road sign for us.

Downloading the Data

In this tutorial, we’ll use the GTSRB dataset, a dataset with over 50,000 images of German Traffic Signs. There are 43 classes (43 different…

Convolutional Neural Networks demystified without any of the fancy tech jargon!

A convolutional neural network that recognises people and objects (Source)

Cars can recognize road signs. Facebook knows your best friends names. You can use your face to unlock your phone. This is all done by magic.

I’m just joking, there is no magic here, just plain, old math. But serious talk though, all the stuff I just mentioned are examples of a convolutional neural network.

But before diving into the code for a convolutional network, let’s get an understanding of what a convolutional neural network (CNN) is and how it works.

Part 0: What is a CNN? Why should we use it?

So why would we use a CNN over another type of neural network, say, a multi-layer perceptron? This is…

A simple algorithm that will allow Survey Monkey to gather much more valuable and accurate data

Survey Monkey is one of the main players in the survey industry. Both Ryan and Chris Finley, founders of Survey Monkey, have come a long way since the company started in 1999. Through their mission to create a more efficient and cheaper platform for online surveys, they created a $2 billion company and gave the online survey industry a place in the market.

Despite Survey Monkey’s massive success, there is still a problem with surveys. Think about it. How many times have you taken a survey? Ten, fifty, a hundred times? Probably more than you can remember. But, how many…

How people in the future will make money by selling their DNA on the Blockchain.

Source (steemit.com)

Blockchain. It’s one of the hottest emerging techs out today. It’s already disrupting the investing and banking sectors, and it is predicted to become a $23 Billion industry by 2023. The applications of blockchain are endless. However, one application of Blockchain really sparked my interest (and hopefully yours): Selling Your DNA on the Blockchain.

Yeah, you read that right. In the future, you will be able to sell your DNA on the blockchain. But to really understand how this will become a reality, let’s also dive into the field of genomics.

A Short Stroll into Genomics

Genomics is all about the study of our DNA…

The part of Self-Driving Cars that no one ever talks about

Whenever you say “Self-Driving Cars”, people automatically think “AI”, “machine learning”, “back to the future” or “Elon Musk”. But the one thing that no one ever thinks of is: “Sensors”. Yeah, I know you probably weren’t expecting that (the title maybe gave it away).

LIDAR and RADAR are just as important as all the fancy algorithms are to a self-driving car, just that people don't want to care as much about the nuts and bolts behind self-driving cars. …

Nushaine Ferdinand

A big AI and car guy. I write on transportation, urban development, deep learning and that sorta stuff.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store