Smart Insight

This post is the final chapter of my experiments with the simulation. Here I will point out the conclusions we can get from running each test.  Again, please note that the simulation does not completely simulate the human and virus behaviour and it is based on known assumptions and probabilities. Therefore, some tests can have a different outcome from real life. However, we can infer some risky behaviours to avoid in our daily life. Image created by Rawpixel Images. Submitted for United Nations Global Call Out To Creatives Every health authorities states we should wear a mask, wash our hands or use alcohol gel, avoid crowded places, to be 2 meters apart from other people. Well, after running several tests in my simulation I can say they are completely right! If you do not trust them for some reason, please look to the results I got ( here ).  We are now starting another spread. The vaccine against COVID-19 spread. I really hope it does not have any serious side effects. I ...

Here I will present some tests and analyze them to find out some COVID-19's behaviours.  Again, please note the simulation is a simple model where the outputs can be different from the ones in the real world.  Image created by Underway Studio. Submitted for United Nations Global Call Out To Creatives Tablets| Computers, Tablets & Components |Desktops| Laptop Accessories| Laptops I suggest you use the simulation yourself and tweak the configurations file to better understand the simulation's behaviour.  By using the config.yaml file to change some of the simulation parameters we can test different case scenarios to better understand the spread of the virus.  Sometimes we mislead ourselves by taking someone's statement as the absolute truth and that leads us to some mistakes. And you know, against COVID-19 any mistake counts and can get you and your loved ones in real danger. So I will show some tests results and analyse them in th...

This "project" started with my curiosity about the covid-19 spread around the world. In my own country, and after everyone knows all health authorities' rules, the virus is now attacking harder than never before. Why the virus still continues to spread? This is one of my big questions. So I did this simulation-like project to study the influences of people behaviours in the overall number of infected people. As an example, evaluating the influence of 50% of the people within an area not wearing a mask, or not respecting the social distance as we should. Stop The Spread. Image created by Hazem Asif. Submitted for United Nations Global Call Out To Creatives  To build the simulation I used the python programming language and the Object-oriented programming paradigm. I did not use any python library to build the simulation environment itself. It is just two classes to represent the Agents and the Simulation. Classes Simulation The class that stores the list of agents in the...

In the Reinforcement Learning field, we face ourselves with the exploration and exploitation words.  Moreover, many articles talk about the exploration vs exploitation trade-off.  What do they mean? Why is this a thing in RL?  Does this relationship have a big impact on the RL algorithms' outcome? Figure 1 - Should I choose the well-known path or give a try to a new one? Photo by Jens Lelie on Unsplash Exploration Exploration is when the agent explores new steps and/or actions to find if other state-action pairs yield a better reward from the environment. You can explore the whole world, or a sample of it to find out the rewards you can get.   Imagine the case where you need to lunch somewhere in your city. You have two options, in the first one you go to the same restaurant you always go with that tasty food you like. The other option is choosing a different restaurant and only after being there you find out if the food is better, equal or worst.   The...

Today's post will introduce you to the model-free methods of Reinforcement Learning (RL). To have a model of the environment we need to store all the states and actions. To do so, we are limited to the infrastructure limits, that means we need to find another approach when the environment is too big and with too many variables. Therefore, model-free approaches can handle the problems where the world is too big to fit our infrastructures. To better comprehension, the Q-Learning algorithm will be presented and explained. Robot infinite environment - Photo by Dominik Scythe on Unsplash Terminologies Figure 1 - Agent-environment interaction Agent  — The learner and the one that makes actions. The agent's goal is to maximise the cumulative reward across a set of actions and states. Action  — A set of actions which the agent can perform. Different environments allow the agent to perform distinct kinds of actions. The set of all valid actions in a given environment is usu...

Today's post is about a Machine Learning area,  the Reinforcement Learning (RL). This article seeks to summarise the principal types of algorithms used for reinforcement learning. Here we will get an overview of the existing RL methods on an intuitive level. In further posts, we will go into more detail and code examples. Robot - Photo by Photos Hobby on Unsplash As other Artificial Intelligence's approaches, RL is not a new thing. The first studies and developments dating back to the 1850s and further advances on mid-1950s, where Richard Bellman has a huge impact [1]. Now, we are achieving several advances in the area and improving the results year after year. Reinforcement learning is nowadays the most virtuous way to suggest or find the machine’s creativity. Please note, different from human beings, theses algorithms can fetch experience from millions of parallel simulations if they are running on a powerful infrastructure. Terminologies Figure 1 - Agent-environment...

We all know AI is helping us to give several steps ahead in some differentiated sectors. Many scientists point out that AI is leading us to a new industrial revolution. I have the same belief. AI is increasingly improving our world in all aspects. Today's topic is how AI is helping us in the mobility scope. Mobility - VCI, Portugal We are seeing a very significant amount of investments in the automotive industry to apply AI-based algorithms. The self-driving cars are becoming more reliable due to those investments. However, AI is not strictly applied to drive the vehicle. Mobility - VCI, Portugal We see lots of other car features using AI. Some examples are  the emergency brake systems, adaptative cruise control, read traffic signals to identify the allowed velocity, driving monitoring systems to check if the driver is distracted, systems to adjust the vehicle settings such as temperature, mirrors and seat position , and so forth. These features are improving global mobilit...