ESR13: Using truck sensors for road pavement performance investigation

Hello crew! How are you doing? I hope you had a wonderful Easter break with your family and friends. Today, I have great news for you. I am just back from Italy where I spent my Easter break with my girlfriend and my relatives and attended my first International Conference on behalf of TRUSS ITN. The event was the 1 st International Congress on Transport Infrastructures & Systems (TIS) 2017 organized in Rome (Italy) by the AIIT (Italian Association of Transport Engineers) in collaboration with many public and private international sponsors. It was great, and it was attended by experts from all over the world. For me, it was the opportunity for introducing the initial findings of my study, receiving their comments and suggestions about the current work and future development of the project. I presented my work related to road asset management in the Session 17 of the congress. The title of the work presented in Rome is: “A big data approach to assess the influence ...

Hi crew, Are you alright? Today I want to talk with you one more time about Machine Learning (ML). In fact, last week I attended an interesting seminar about possible applications of these techniques. The seminar has been given by the TRL Academy, here in TRL, and for me, it was a good opportunity to introduce myself, my project, and to share ideas about possible optimization algorithms and techniques, for a topic which is completely new for road asset management. In my previous posts, I showed you how ML works, giving particular attention to Artificial Neural Networks and Random Forests . As I already mentioned, these techniques are used nowadays in a number of applications in Science, and actually, also lots of apps installed on our mobiles use similar methods to make our life easier. In fact, based on the ability of these techniques to recognize patterns in large datasets, weather forecasts, banks, social media, among many others, use ML to improve precision and reliabil...

Hi crew, I hope you are doing well! Have you noticed that I changed a bit the layout of the blog? Do you like the new style? However, let’s focus now on the topic of this new (and amazing!) post! Today I want to share with you my experience of the first weeks of secondment that I spent in TRL Ltd… moreover, I would like also to discuss with you a bit about Italian food. Tasty?? Ehm, interesting eh? But let’s start from the main topic of the post: my secondment in TRL. As you probably know, this is my second experience in secondment (the first one was in Microlise last year ) and it is part of my PhD project. This experience will be useful for me and my research, for improving my knowledge about road conditions monitoring, road maintenance strategies, road pavements life-cycle assessment, and for the interpretation of the results of my study so far. TRL is the acronym of Transportation Research Laboratory. In TRL engineers, consultants and technical speciali...

Hi crew! Today an amazing post introducing the Random Forests method is waiting for you to be read! Yep, I know, I promised this post a long time ago but seriously crew: I had no time for it! Random Forest is a machine learning method mainly used for classification and regression purposes. These kind of statistics basically learns from a training set of data and gives answers associated to new data based on what the algorithm learnt. Yep crew it sounds very similar to what Artificial Neural Networks do. In fact, also Artificial Neural Networks is a machine learning method used for regression analysis. However the two methods are based on slightly different concepts. From the historical point of view, the first concepts behind the theory of "Random Forests" are introduced for the first time by Ho in 1995 [2][3], but it is only in 2001 that they are defined as we currently know them by Breimann [1]. The algorithm itself is based on the theory of Decision Trees … ...

Hi crew! Here I am with another post for my blog! I hope you are all doing well, that you spent nice holidays with people you care, and that your 2017 started in the best of ways! So far, the start of 2017 was a quite busy period for me, however, lot of work causes also lots of news for you crew. Therefore  I am sorry for the delay with keep you update but because of meetings, deadlines and holidays, it was really difficult for me to write anything on the blog. My apologies crew! Last week for example I went in Barcelona. Did you know that? … No, crew it was not for holidays… It was because of work! Actually I should say that we went in Barcelona. In fact, it was the 2 nd TRUSS ITN training week organized at the Universitat Politècnica de Catalunya , and all the ESRs attended the meeting. We presented the latest achievements in our projects and it was also the opportunity to share ideas within researchers and experts. We attended many lectures focused on seism...

Hey crew, Are you alright? Are you ready for reading a new post? Alright, let’s start then! Almost a month ago I started my secondment in Microlise Ltd . As I already mentioned in the past: Microlise is one of the two companies that is involved within my project. They are experts in truck fleet management and they collect and analyse data from large truck fleets for helping their customer in maximising utilisation, increasing efficiency, and improving economy and safety for their fleets. Fig.1 – The Microlise Ltd logo. How is it going here in Microlise? Well, I have to say that working in the company has pros and cons. The cons are mainly related to the timing: I have to wake up at 6:00am every morning and it takes 1 hour-ish by bus to get to  Eastwood, where Microlise is located. Then, I go back home very late (sometimes I come back home after 6:30pm). Fig. 2 – No crew, it is not that terrible! ;) This means that quite often I’m tired, and ...

Hey crew! Are you ready for a new post?! Here we go then! Today I’m going to introduce you to a more technical topic. In fact, we are going to talk about machine learning and Artificial Neural Networks (ANNs) in particular. Machine learning is a subfield of computer science which aims to give computers the ability to do something without being explicitly programmed for doing that. Originally, it comes from the study of pattern recognition and computational learning theory in artificial intelligence. Exploring the study and construction of algorithms that can learn from experience (historical data), the algorithm operates by building a model from example inputs in order to make data-driven predictions or decisions. ANN is just a branch of Machine Learning. They are data processing paradigms inspired by the way the biological nervous system process information in human beings (Biological Neural Networks, BNNs). Usually they are used to estimate or approximate functions t...