Latest Post

The Power of Prediction in Industry​

by
Entrada blog
Logo Original Forcast

The Power of Prediction in Industry

by Adolfo Navarro Mena

Questions to be resolved:

  • What are predictive algorithms?
  • What is possible to predict through them?
  • How does that impact the smooth running of the industry?
  • What technologies has Forcast developed in this area?

Introduction

What would have been the fate of Rose and Jack if the Titanic technical team had had a modern system to predict the appearance of icebergs? We will never know, but what we are sure of is that with a better predictability the captain could have made a faster and more assertive decision, favoring the protagonists in a better way.

The previous example makes us reflect on the way our decisions impact; But, what would it be like if we had more tools to know what the future will be like? Probably centuries ago the prediction was something associated with the occult or esotericism, but with the passage of time the prediction has become something more common and accessible than many believe. And by common, we do not mean the Octopus Paul, who “supposedly” had the ability to guess the outcome of football matches during the 2010 World Cup, is somewhat more complex and is related to the new technological capabilities of the 4th industrial Revolution.

What is Data Processing?

Data mining, also called knowledge discovery in databases, in computer science, is the process of discovering patterns in large volumes of data. The field combines statistical tools and artificial intelligence (such as neural networks and machine learning) with database congestion to analyze large digital collections, known as a data set.

Source: Enciclopedia Británica, 2020. 

Data determines our decisions

“We know that data is the new oil,” says Fernando Castillo, Forcast’s operations manager; However, not all the information produced by a company is in good condition to be used or to deliver positive results, says the expert; But, thanks to the new capabilities of the various algorithms coming from computer engineering, today industrial processes can be carried out with a greater number of advantages in the face of the adversities of large-scale production.

Through what technologies is the above possible?

The machinery used for mining, agriculture, or other industries produces enormous volumes of information full of relationships that multiply and extend in various directions. Something that, according to Fernando Castillo, is difficult to be analyzed by human beings since it would take too long and, in most cases, it would be impossible to carry out. However, today we have various computer systems that are highly capable of using all that information produced and giving new answers to operators to make intelligent decisions for the benefit of a company. It is what is known as neural networks, the ones that even have memory.

Fernando Castillo (COO Forcast.)

“There are techniques that can focus on predicting anomalies, others on making more complex classifications that directly show production errors. For example, if an engine gets very hot in certain cycles, it is possible to preempt a failure that causes production to stop, ”says Fernando Castillo.

This is possible since we work with algorithms and time series that allow us to evaluate the past and present behavior of the machine to know during production what problems the company will eventually deal with.

“Every time new and better learning architectures are born and with that we are modeling more precisely”, says Fernando Castillo.

Regarding its applications, the COO of Forcast indicates that its scope is very wide, “all industries that have machinery can benefit from predictive algorithms”. This is the case of the bolts used in the structure of SAG mills for mining. Forcast developed and applied a system capable of predicting failure of these metal parts based on their performance history, what does this mean?

Fernando Castillo says that if the bolts of this mining machinery fail, this may mean that a mill does not operate for two full days. With a predictive system, you can know when the best time to do maintenance will be and stopping the operation of the mill is reduced to, for example, two hours. In this way, the company saves millions of pesos in loss.

On the other hand, a greater optimization of resources is also achieved. This is the case of solar energy, which decreases the quality of its energy production due to the weakening of the panels. With predictive algorithms it is not only possible to predict failures but also strategic decisions can be made. For example, postpone the repair of a panel if it still does not have a decisive influence on production and save on emergency maintenance that are much more expensive than scheduled.

Taking the leap towards digital transformation in the industry

For Fernando, all these opportunities are located in the field of digital transformation that the world is experiencing. The possibilities are endless and, in his own words, it is essential that everyone explores how companies can benefit by making use of these technologies and improving the ability to make smart and wise decisions.

Share:

Related Post:

Astronomy and Data Science in Chile… The perfect mix.

by
Astronomía y Data Science
Logo Original Forcast

Astronomy and Data Science in Chile… The perfect mix.

by Cristían Irribarra

Few things are more alluded to in the field of science and technology in today’s news and cultural programs in Chile than Astronomy and Artificial Intelligence (AI). Interestingly, we rarely hear of how both disciplines have symbiotically empowered each other, pushing the edges of the computational paradigm at breakneck speed. The cutting edge in data storage and computing power is updated with each new super telescope to be inaugurated.

Downloading or pre-processing a modest set of astronomical data on a conventional laptop can take hours and even days, an alternative is imperative with the EELT and LSST just around the corner, promising hundreds or perhaps thousands of Terabytes of data per week. Furthermore, the computing power required for an expedited investigation is vastly greater than what can be expected with a personal computer. The management of these huge databases is today the work of Data Centers around the world, giving way to the birth of “Astro-informatics”, at the national level, the first center dedicated to this is ChiVO (Chilean Virtual Observatory).

The cutting edge in data storage and computing power is updated with each new super telescope to be inaugurated.

ChiVO is not only a warehouse with about a Petabyte (that’s a million Gigabytes) of storage capacity, but it also has services and software aimed at facilitating data processing: algorithm libraries for on-line processing, data simulators for the development of AI models, interfaces and manipulators of astronomical images are some of them.

“Data science is growing and in Chile astronomy is, clearly, one of its main drivers. “

It will undoubtedly be interesting to see how the convergence between better and better telescopes, more powerful astronomical instruments and more advanced tools for data processing will cause unprecedented discoveries in both basic science and applied computing, and with Chile as headquarters. AI will be the main driver and the area that benefits the most from this. How exciting it is to think about what kinds of tasks the algorithms of the near future will master with so much data at their disposal!

Share:

Related Post:

Astronomy and Data Science: an elementary relationship

by
Astronomía y Ciencia de Datos: una relación elemental
Logo Original Forcast

Astronomy and Data Science: an elementary relationship ( with great potential for the local economy).

Source: Forcast

Do you remember Katie Bouman? If not, we tell you that she was the scientist who at the beginning of 2019 made a photograph viral on social networks that was taken next to a stack of hard drives, which in total amounted to more than 5,000,000 gigabytes, essential to contain the total data that allowed the creation of the historic first photograph of a black hole.

That milestone, which captivated the press around the world, was just one part of the immense display resulting from the coordination of eight telescopes located in cities around the globe; in addition, it produced large volumes of data that had to be processed through a special algorithm.

This is how dealing with a large amount of information is a task that for astronomers is natural since “astronomy is a science based on data”, as stated by Mauricio Araya, PhD in Computer Science and Academic at the Federico Santa María University, who in turn points out that this analysis cannot be done separately.

“The data must be worked together. Part of that responsibility is handed over to the computer and it is precisely there where the concept of data science comes in, since various systems are developed to automate the obtaining of results ”, she concludes.

Astronomical data as a tool to contribute to development

As a result of its geography and great diversity of biomes, Chile is home to a series of natural laboratories that, according to the book «Natural Laboratories for Chile: Science and Innovation with Advantage» by Clapes UC, are strategic spaces that have a series of characteristics and conditions that allow to attract the attention of world science to do research.

When natural laboratories are located in emerging countries, they provide comparative advantages that cannot be replicated to other places or contexts given their nature. They allow the study, for example, of geophysical phenomena in the field of volcanology, natural disasters or the investigation of local species collaborating with biochemistry.

In the case of Chile, it is common to hear about the unique characteristics at the planetary level of the northern skies, which have managed to attract large astronomical consortia and several of the world’s leading universities such as the Las Campanas Observatory, operated by the Carnegie Institute of the United States, or the Observatory of the University of Tokyo in the city of Atacama (TAO).

In the words of Felipe Larraín, current Minister of Finance, with the comparative advantages of the skies of northern Chile “investments were made in infrastructure for research previously unthinkable in the country (about US $ 5 billion by 2020)”

“In contact with the frontier of knowledge”

Why is it relevant to continue developing this sector? Doctor Mauricio Araya indicates that although this is a very small area, from an economic perspective, “here in Chile we have the best astronomy in the world in terms of observatories, infrastructure and the amount of publications that are made.”

If we compare astronomy with mining, the most developed sector and the one that attracts the most dividends for Chile, Araya argues that even so the latter is not the most advanced compared to mining in other countries. However, Chile has a high level in engineering, instruments and astronomical science.

“Through astronomy we are permanently in contact with the frontier of knowledge, a window to the future to know what the problems will be,” he concludes.

All these elements help us to compose a great puzzle that shows us the importance of this area of ​​knowledge. But there seems to be a missing piece, the one that allows us to understand how valuable astronomy is when considering the other sectors of the local economy. More precisely, what will be the destination of all the knowledge acquired in data management in astronomy considering the other needs of the country?

Using the universe to solve problems on Earth.


Demian Arancibia is an Industrial Civil Engineer and Master in Systems Engineering from Cornell University, United States. His vast experience in the field of national and international astronomy led him to lead the Astroinformatics Initiative of the Ministry of Economy created in 2013.

The program, through various stages and with the support of previous initiatives, helped to determine a series of opportunities for the Chilean State from an economic dimension. The team was voluntarily integrated by prominent experts from national and international universities; Among them, Massimo Tarenghi (Italian physicist and astronomer), María Teresa Ruiz (National Prize for Exact Sciences), Juan Rada (economist), who considered local capacities, the development of a market, among other factors.

Astronomía Icon1

Thanks to the infrastructure it is possible to produce a large amount of high quality information. What Arancibia defines as “data acquisition”.

Astronomía Icon2

These data are a great value since they are knowledge about the universe.

Astronomía Icon4

There is a high level of sophistication to distribute data and the content that is generated to make it accessible.

Astronomía Icon3

This enables new opportunities in the field of data exploration and visualization.

Arancibia indicates that these opportunities (see table) are linked to existing needs in other industries such as banks, mining, or those companies that need to enhance their marketing areas. All, as in astronomy, must process large volumes of information that must be analyzed and visualized.

The above is also shared by Doctor Mauricio Araya. He says that astronomers estimate that the observable universe has more than 100 billion galaxies, so increasingly sophisticated intelligent systems will be needed to deal with the processing of all that information. This ability may well be useful in other areas such as those already mentioned. As an anecdote, Araya says that many high-level professionals, after going through astronomical centers of great relevance, come to work for famous companies such as Spotify, Amazon, among others.

Data management for the economy of the future.

Since 2017, the Ministry of the Economy, through its “Economy of the Future” area and with the preliminary support of the European Southern Observatory (ESO), ALMA and Amazon Web Services, has promoted the creation of the Data Observatory or Data Observatory Foundation, that in the words of the ministers Andrés Couve and José Ramón Valente will have as mission “to receive, process and store the data sets generated in the country, and that, due to their volume, nature and complexity, require curation, exploration, visualization and analysis that facilitates its availability for the development of knowledge, technology and innovation, and its applications for the economy and society ”. [read column] 

This opportunity for Arancibia will help advance towards a new stage that allows undertaking specific projects and initiatives: training of talents, generation of technologies, solving problems.

“A company in collaboration with this initiative and that effectively generates solutions, that addresses the problems of astronomy, has an asset that allows it to sit at the table to carry out projects on a global scale. For example, a company that currently works with the Latam company in its marketing area in Chile could collaborate with the Data Observatory to scale its solutions and be able to work with American Airline, Emirates; in other words, working with an airline that has a greater number of customers ”, he concludes.

The foregoing also impacts the job opportunities of professionals who have specialized in the field of data. Today, many of them work in academia, observatories or public initiatives, but local technology companies are emerging increasingly that are awakening the interest of various industries to solve problems using the most advanced in information technology, and with the support of talents capable of meeting those needs.

Cristián Irribarra is an astronomer from the Universidad Católica de Chile and currently works as a data scientist at Forcast, a company specialized in generating solutions based on data science, artificial intelligence, machine learning, among other technologies.

Cristián’s mission within Forcast is to receive any type of numerical data from companies and from there create a statistical model with computational tools that allow interpreting the behavior of these numbers to infer their future and what things can be obtained.

“If you are given the sales history of a store, in principle you could know how much you sell daily, the amount of profit you will have at the end of the month; However, if you intrude deeper into the data and use special systems you can optimize the product offer, know what prices to raise or lower, how people respond to price changes, how much the consumption of an object will change you in specific in the future, ”says Cristián.

To carry out this work, the expert points out that a database is essential, “that is almost an axiom of the data scientist and artificial intelligence. The more data you have about something, the better the model you use will perform; in addition, you will assign it greater versatility ”.

“Very recently we were making a prototype to detect anomalies in street light poles with cameras; that is, if they are crooked, damaged or otherwise. One of the things that most caught my attention is that we used a system that was pre-made but to interpret other images. He did not know what a post was, but with no more than a thousand images of posts taken with my cell phone, in about 30 minutes the system was able to recognize them ”.

Cristián indicates that this example demonstrates the scope of a correct interpretation of data since systems are becoming more and more powerful, “the story is knowing how to take advantage of it and use it for various industries. If we think only in detection models, there are countless possible applications that we have not yet tested. “

However, in some cases companies have effective information gathering systems, which makes the task easier and faster; in other cases, there are problems in recording the data. For the latter, Cristian indicates that it is Forcast’s task to know how to deal with those gaps and inconsistencies on the part of customers.

“Many times the registry is filled out by hand, or they started doing it recently and they don’t have a correct structure, but regardless of that we use it the same. Whether it’s dirty or not, we get to the final product, this is an essential part of what Forcast does ”, he concludes.

The great contribution of astronomy to solving problems shows us the enormous potential of this area of ​​knowledge in the country. Chile will concentrate 70% of astronomical observations by 2024, so a strategy and the support of various productive sectors are required to take advantage of it. 

Share:

Related Post:

The new revolution of Artificial Intelligence in Digital Marketing​

by
AIDigitalMarketing
Logo Original Forcast

The new revolution of Artificial Intelligence in Digital Marketing

One of the most developed areas within Smart Marketing is the analysis of BigData from machine learning algorithms (Machine Learning). Making use of the immense data repository in the cloud, it is possible to segment and characterize users to make personalized recommendations at the right place and time.

Another area of application of AI in Marketing is advertising testing, with the purpose of measuring the level of impact or effectiveness that it has on the user. A widely used technology here is Biometric Marketing, which basically consists of monitoring the signals of the human body when faced with a certain stimulus. For example, it is possible to follow the path of the human eye and identify the residence time in a particular image.

Customer Service and Retention is another area where Artificial Intelligence will play an important role in the not too distant future. There are already companies that are implementing bots with Artificial Intelligence in order to establish direct communication with the user and offer them personalized options. Digital employees will allow people in the future to focus on what really matters, such as establishing strong and lasting relationships with customers.

Share:

Related Post:

Digital transformation index in Chile: How well are we doing?

by
AIEngineer
Logo Original Forcast

Digital transformation index in Chile: How well are we doing?

Source: CORFO

According to a study led by CORFO, Chile obtained 43 points on a scale from 0 to 100, known as the Digital Transformation Index, going from “Beginner to Digital Intermediate”. The study considered 8 sectors, eight sectors (commerce, food industry, productive industry, construction, communications, services, health, public administration and basic services) and a total of 465 companies.

The study concluded that “the Communications, Health and Services sectors lead the Digital Transformation, while those in the rear positions are the Public Administration and Construction, this last mentioned being the one that registers the lowest level of maturity”.

The components that the study considered are:

  • Leadership towards digital.
  • Vision and digitization strategy.
  • Digitization of processes and decision making.
  • Forms of work, people and digital culture.
  • Technology, data management and digital tools.

The dimension “Forms of work, people and culture” is the one with the highest level of evolution, which indicates that culture allows a transformation to an Intermediate Digital level, from then on culture can be a brake on transformation if it does not evolve along with the other dimensions.

Share:

Related Post:

Artificial Intelligence in the Music Industry

by
IAenlaMúsica
Logo Original Forcast

Artificial Intelligence in the Music Industry

Source: CIDIF

As in other industries, in the field of music, Artificial Intelligence (AI) has the potential to automate services, discover patterns and extract knowledge from a large amount of data.

Scott Cohen is one of the leaders in the music industry who saw the potential in using AI to promote the growth of this industry. According to him, more than 20,000 new music tracks are uploaded to Spotify every day and Artificial Intelligence would serve to make personalized recommendations. AI-generated music playlists are not just based on what you’ve listened to in the past, but what the machine considers to be “good music.”

Now, Artificial Intelligence can not only make personalized recommendations, but can also contribute directly to the creation of new music. Alan Turing, the well-known British programming scientist, was the first to record computer-generated music. Through Machine Learning, an algorithm creates music patterns considered “pleasant” to the human being or that imitate a certain genre.

Today, many are following the Turing legacy. The AIVA software is capable of generating pieces of music according to the feeling that you want to evoke in the listener.

Santiago Velarde, a 29-year-old Peruvian composer, stands out in Amper Music, recognized worldwide for allowing users to create music in a simple way thanks to the use of Artificial Intelligence. This platform allows you to compose music in just a few minutes and in a professional way.

Despite the fact that we saw it far away for a while, today we can already find Artificial Intelligence in the composition of music, live performances and in digital sound processing. This opens up a moral and philosophical debate as to whether a computer can ever replace and improve the work of a human. What do you think?.

Share:

Related Post:

The birth of Smart Cities

by
AISmartCities
Logo Original Forcast

The birth of Smart Cities

Source: CIDIF

Increasingly, city administrations are turning to specialized technologies to attack social, ecological and economic problems. The incipient concept of SmartCity seeks to promote the inclusion of sensors and Big Data through what is known as the Internet Of Things (IoT). The ability to collect information in real time provides a better understanding of how cities evolve, adapt and respond to various conditions.

The areas where the SmartCity concept can be applied are varied. These include government, the economy, the environment, mobility, infrastructure, education and health.

An application with a lot of development within Smart Cities is that of image processing (Computer Vision), which has the purpose of identifying millions of simultaneous events within the urban sphere, such as people, cars, public workers, garbage, accidents , fires and natural disasters. This not only makes it possible to monitor the health of cities in real time, but also to help decision-making by organizations for the public administration.

Although Artificial Intelligence has been used extensively to attack problems of a technological nature, its potential to also contribute in human dimensions, such as Resilience, Security and Sustainability, cannot be set aside.

With the appearance of Covid-2019 we have been able to observe how the so-called Smart Cities have been able to combat the advance of the pandemic. In China, a series of measures have been deployed to control the spread of the virus that are based on the use of Artificial Intelligence and Big Data. The measures range from patrol robots that detect the use of masks in public places to infrared thermometers installed in strategic areas that can measure the temperature of ten people at a time. In South Korea, one of the most acclaimed countries for crisis management, an online coronavirus monitoring system was launched that monitors the behavior of infected patients through the use of surveillance cameras and transaction records based on credit cards. credit.

The use of information within the sphere of SmartCities has opened a debate regarding data privacy and security. The recent appearance of BlockChain technologies seeks to guarantee the transparency and security of the processes through the use of an open and transversal platform. On the other hand, it is also necessary for intelligent systems to work hand in hand with laws to protect privacy and human rights. What do you think?.

Share:

Related Post

Artificial Intelligence for the world of Medicine

by
IAenlaMedicina
Logo Original Forcast

Artificial Intelligence for the world of Medicine

Source: CIDIF

The areas where Artificial Intelligence (AI) can be applied in medicine are wide, ranging from robotic consulting physicians to diagnostic systems using image processing or Computer Vision.

It is said that Medical Artificial Intelligence allows the development of the well-known 4Ps of medicine (Prediction, Prevention, Personalization and Participation) and therefore has the ability to grant greater autonomy to patients.

One field where work with AI has recently started is Gastroenterology. This discipline normally presents a certain difficulty and complexity in the diagnosis, which is why it benefits from the use of Deep Learning algorithms and Neural Network Convolutions to detect abnormal structures, such as colon polyps or gastric cancer.

Another example of the application of AI is found in the diagnosis and treatment of rare diseases. The pharmaceutical company Bayer has teamed up with technology partners to determine the diagnosis of an individual through data on symptoms, causes, test results and images, and in turn, create new drugs through the use of Machine Learning techniques.

Finally, the use of Artificial Intelligence in the planning and monitoring of a surgical intervention is growing. Surgical robots may be able to analyze a large amount of data prior to the operation and guide the surgeon during the intervention in order to favor decision-making that results in a shorter patient stay.

One of the great barriers to the adoption of AI in medicine is the fear of dehumanization. This is largely due to the administrative burden imposed on doctors. However, modern technologies such as ACI and Natural Language Processing seek to solve the administrative burden issue and help doctors focus exclusively on patients.

Although there is a latent fear that AI could replace doctors in the future, the general opinion is that it is best to consider it as a tool with the potential to complement the intelligence of the specialist. What do you think?

Share:

Related Post:

How Artificial Intelligence will transform the Renewable Energy Industry

by
IAEnergíasRenovables
Logo Original Forcast

How Artificial Intelligence will transform the Renewable Energy Industry

Source: El Periódico de la Energía

The consultancy DNV GL has published its latest document “Making renewable energies smarter: benefits, risks and future of artificial intelligence in solar and wind energy”, in which it predicts a growing use of Artificial Intelligence (AI), for which it foresees a $ 3 trillion market by 2024, across the industry, in which it analyzes its current and future potential to accelerate processes in multiple areas of renewable energy development.

The report focuses on the downstream sector and notes that wind and solar plants have already benefited from the widespread development of sensor technology and data analytics. “We look forward to the installation of more sensors, the growth of easier-to-use machine learning tools, and the continued expansion of data analysis, processing and analytics capabilities to create new operational efficiencies,” said Lucy Craig, Director of Technology and Innovation at DNV GL.

The paper expects solar and wind power to further harness the benefits of artificial intelligence in the areas of inspection and troubleshooting, where “autonomous drones with real-time AI support analytics” and “crawling robots that can get close to the surface of a structure”. Ultrasonic transmission, which can be used to penetrate structures and reveal material flaws, will pay off.

Planning and due diligence is another area that DNV GL says can benefit from the increased use of AI: “planning and analysis that today can require many human hours and thousands of documents can be greatly reduced in the future and even improved” .

DNV GL even speaks of a future in which the construction of wind and solar plants will be fully automated and carried out by ‘autonomous driving robots, which in the future may build entire terrestrial or solar wind farms: parts of a wind turbine or solar panels are transported from the factory by autonomous trucks, unloaded by another set of robots, attached to the foundations that other robots have excavated and filled, and assembled by a final set of robots and drones ”.

Despite all this potential, DNV GL points out the risks of such approaches and the danger of relying too heavily on artificial intelligence rather than the deep insights needed to manage such a system. “For the majority of participants in the renewable energy industry,” states the DNV GL press release, “building stable, progressive and reliable artificial intelligence systems requires knowledge and data sets from many different projects.”

Share:

Related Post:

AgroTech: Artificial Intelligence to improve agriculture

by
AIAgroTech
Logo Original Forcast

AgroTech: Artificial Intelligence to improve agriculture

Source: CIDIF

Precision agriculture has been one of the areas that has benefited the most in recent years with the use of Artificial Intelligence. According to the Huerta Digital (https://lahuertadigital.es/agtech-tendences/), among the main trends within the world of Smart Agriculture can be named remote monitoring of crops, robotics and agricultural automation and the area of ​​research and development in genetics and biotechnology.

Within remote crop monitoring, one of AgTech’s most recent forays is the analysis and processing from satellite images. This technology has the potential to monitor droughts and predict harvests in real time over large areas.

Another topic in full development within agricultural monitoring is how to achieve effective control of pests, diseases and other risk factors for Agro. The FuturCrop company implements technologies for the automatic detection of larvae and has declared that its initiative allows a reduction of 30-50% in the use of phytosanitary products in horticultural and fruit trees.

Regarding robotics and automation in agriculture, there are different types of robots for each productive stage, ranging from drones to robotic arms specialized in the harvest of fruits and vegetables.

In short, Artificial Intelligence promises to increase productivity in the agricultural sector by allowing the business to be managed more profitably. In periods of water deficit, such as the one that has plagued a large part of Latin America in recent years, it is essential to have technologies that allow optimizing and increasing the response capacity of this industry.

Share:

Related Post: