We all know voice-powered applications are increasing in number and effectiveness, due to better NLP models and consumer home hardware like Alexa or Home.
According to Google, 27% of the online global population is using voice search on mobile, the trend is rising and effectively, once you start to use it, it becomes very fast and natural.
So, for a personal project I’m developing (more on this in few weeks), I decided to build a vocal interface to perform some actions and my needs were:
Live as if you were to die tomorrow. Learn as if you were to live forever (Mahatma Gandhi)
The is no better way to start talking about learning than this quote by Gandhi.
The act of learning should be a constant and endless process, it makes us grow, discover new horizons, becoming more complete as human beings.
But I realized, through the years, facing new learning challenges for fun and working necessities, that be able to learn in a better way is something that can be improved and this is possible only when there is complete awareness of the pursued…
In a previous story, I tried to resolve how to find if an exercise is executed in a correct form, using OpenPose to gather exercise data and Dynamic Time Warping to compare the exercise execution with a correct one as a baseline.
This time I added the following other components to greatly enhance the overall experience:
This is a graphical representation…
Italy is, unfortunately, one of the most impacted countries by the pandemic disease, so I’m trying to find some insights in the available data about it.
I’m using data available from the official git repository of “Protezione Civile” that is updated daily, available here.
The used code to perform this analysis can be found here.
If you want to run the notebook directly just follow this link: https://mybinder.org/v2/gl/acalax%2Fcovid-19-eda-italy/master?filepath=eda_italy.ipynb
The notebook will download the data, so you can always have updated graphs!
A disclaimer: I’m not attempting to predict or model anything, just looking at the data and build some graphs…
I’m a big fan of a bodyweight approach and generally of doing workouts, but I don’t like too much going to the gym.
Besides, in this time of forced lockdown due to Coronavirus, it could be useful to try a different way to approach fitness and training.
So I asked myself: is there a way to use Machine Learning in this area? Can I join two passions together to make something useful?
One of the main problems is having a way to validate the correctness of an exercise, so I did some experiments and tried an approach and found that…
Recently, I had the opportunity to deal with crypto exchange public data and this allowed me to visually explore the data using Plotly libraries, one of the best visualization tools available, as it will enable us to have general interactive graphs without worrying about coding part — like I used to do with Bokeh.
If you’re using notebooks for analysis, to keep things clean, I suggest you write helper functions on a .py file and then import it.
I’ll share the code, so you’ll be able to see how Plotly works and adapt it to use with your data
Recently, I had the opportunity to build a PoC (Proof of Concept — a demo) to resolve a specific computer vision problem and it was a cool experience, so why not share it?
The goal of the demo was to detect in real-time, having as input a video stream from a camera, if a specific object — a fake id card — has fingers on it, covering information that could be used, for example, in OCR tasks once the frame is achieved.
In other words, a system that can help to automate the capture of id document being confident all…
We all have to learn new things, for work or fun (great when eventually there’s a match) and everyone probably has developed an approach about this.
But what if we can “ultralearn”, learning how to learn better and not just in theory, but with direct experience from successful people that achieved incredible results in this context?
To me, this is like a superpower, allowing us to learn faster, better and giving to all the process stability and repeatability.
If this sounds appealing, Ultralearning by Scott Young is the book to read.
The author used not just his impressive direct experiences…
In this article, we’ll see how to use a couple of cool things together to create and host a simple website.
If you need to set up a simple website, like a personal site, brochureware, a landing page or something similar, there are easy solutions to consider, maybe less famous respect specific services or standard applications, but bringing the same results.
In tech — but is something valid everywhere — there is no one fits solution, but the best choice is derived as a tradeoff from the context, the needs, the expected outcome and the available resources — time, skills…
Let me introduce you an old ETL companion: its acronym is PDI, but it’s better known as Kettle and it’s part of the Hitachi Pentaho BI suite.
With Kettle is possible to implement and execute complex ETL operations, building graphically the process, using an included tool called Spoon.
I implemented a lot of things with it, across several years (if I’m not wrong, it was introduced in 2007) and always performed well.
So let me show a small example, just to see it in action.
The simplest way is to download and extract the zip file, from here. …