News & Politics
André Larente President & CEO DIAGNOS INC. NORTH AMERICA MINING QUÉBEC EDITION PAGE 19 upplying the company's services to the mining industry has led to much activity for DIAGNOS with interest and market excitement continuing to build in its data mining technology. "The objective of the company is to use artificial intelligence to do predictions," says Larente. He goes on to explain that when mining companies are conducting exploration activity, they are often relying on information that fails to narrow down the specific areas of a claim where much sought after resources, such as gold and diamonds, are located. "Ninety-five per cent is thrown away," says Larente. "Usually, we target five per cent of the claim." DIAGNOS has the ability to do that by using technology it has developed that mines the data provided by the companies in question. ”The key is that the DIAGNOS technology is able to complete data mining of an array of existing information in addition to analysing text and images. We can pretty much predict anything if we have data to analyse. The intelligence is buried in the data." explains a confident Larente. At the core of DIAGNOS’ methods are three tools that it describes as: MCubiX-KE (Knowledge Extractor): a data mining toolbox that includes a wide selection of algorithms (decision trees, neural networks, association rules, etc.) and visualisation tools to help bring solutions to the most complex problems. MCubiX-EP (Enterprise Predictor): developed with the end-user in mind. End-user applications can now take full advantage of data mining technologies. Using MCubiX-EP, data mining can be embedded directly into any end-user application thus isolating the end-user from the complexities of modelling and scoring of a database. Data miners develop and fit models with MCubiX-KE and store their models in PMML and or XML format in a central repository. This repository is in turn consulted by the MCubiX-EP modules to obtain the rules established by the data miner in order to score the dataset(s) presented by the host application. CARDS (Computer Aided Resources Detection Software): an application that has been developed to assist scientists and professionals in their search for natural resources. CARDS uses MCubiX-KE's artificial intelligence and pattern recognition algorithms to learn the signatures or finger prints of resource areas with a high economic potential and to automatically detect similar sites across unexploited regions. CARDS uses four steps in its process according to Mr. Larente. First is the data gathering where geophysical data, satellite imagery, field mapping, geochemical, petrological and mine geological data is analysed using CARDS. The tool then completes a model set-up using the MCubiX data mining engine to detect signatures or so-called fingerprints indicating where natural resources are located. Next are the prediction phase and presentation phase, where detailed maps are rendered to allow customers to view the most likely sites for successful exploration. Larente explains that DIAGNOS’ tools are very powerful because they have the ability to analyse a huge amount of data that otherwise would be impossible using conventional methods. "Human beings cannot possibly analyse all of the data that is produced," says Larente. Marketing its services to junior mining companies across the world, DIAGNOS has met success with more than a dozen of those companies now using its technology. One company that is using DIAGNOS services is Diagem International Resource Corp. a Montreal based mining group that is currently conducting diamond exploration in Brazil. Diagem's president, Paulo Alfonso Andreazza, recently sent a letter to André Larente praising CARDS. He writes, "We are very impressed with the capabilities of your CARDS application. As you know, we had over 1,000 anomalies to choose from and the process to identify which target to prioritize is very complex. The DIAGNOS application was able to reduce to 20 targets the focus of the company. This will enable us to move quickly to these areas in our 240 square kilometre property. If this new process is confirmed, it is very evident that the DIAGNOS CARDS application will help us reduce our cost, increase our target selection and time to discover, by a large factor." Mr. Larente says mining companies will enjoy huge savings because mountains of data are analysed more quickly and more accurately. "It will discover the pattern defining the existing drill holes, successful or otherwise," says Larente. Calling its technology a new approach to knowledge extraction, DIAGNOS has been offering its artificial intelligence services to mining companies and more recently also to the oil and TAKING THE BLUFF OUT OF KNOWLEDGE EXTRACTION DIAGNOS Inc. exemplifies the adage work smarter not harder. The high-tech company based in Brossard, Quebec, describes itself as a software corporation that develops and markets knowledge extraction products and services. DIAGNOS was incorporated in 2002, and is headed by André Larente its president and CEO. Mr. Larente has nearly 30 years experience in the high tech business and carries a master's degree related to computer science from Sherbrooke University in 1978. Following his graduation Mr. Larente worked with some of the best known technology companies in the world including Honeywell Information Systems from 1978 to 1990 where his last position was as vice president in charge of sales. Larente has also held positions with Cognos Inc. and Newbridge Networks Corp. With a foundation in computer science complemented by his extensive sales experience, Larente is now determined to move DIAGNOS forward as one of the most innovative artificial intelligence companies in Canada. S Interview by Wes Lafortune Portrait Photography Courtesy of DIAGNOS CARDS.....A WINNING HAND TSX.V: ADK CARDS and mining, .....synonymous to hammer and nails, .....takes the guesswork out of building a brighter and more successful future. The soil type which confirmed the presence of the ADK-13 pipe. Since then, Diagem has found 5 kimberlites out of 6 targets identified by DIAGNOS. DIAGNOS continued on next page gas industry. Using CARDS and MCubiX, a data mining software suite capable of extracting knowledge from historical data and then making predictions that improve business processes and decision making ability DIAGNOS believes it can help mining companies in their search for resources including diamonds, gold, zinc and copper. With the technology consolidation of the past five years, the company is now being noticed by mining companies including Mana SA and Cancor Mines Inc. The company is led by its well motivated president and CEO, André Larente, and a team of talented co-workers including experts in artificial intelligence, mathematics and information technology. With CARDS the company believes it will be able to help mining companies be able to explore for resources in a more timely and cost effective fashion. Based in the province of Quebec, DIAGNOS has a global vision for its company to continue expanding and taking on additional international clients. DIAGNOS is a knowledge extraction company that's taking a new approach to data mining. An approach it hopes will revolutionize the mining industry in Canada and beyond. With the positive reactions from the industry so far, it appears the mining industry is on to something. A program making possible discoveries faster and less expensive,....if they play their CARDS right. DIAGNOS continued from Previous page NORTH AMERICA MINING QUÉBEC EDITION PAGE 20 CARDS, the right hand for the quick witted. The weathered pipe material started to show reddish colors and progressively changed to yellowish green to greenish at 3.5 meters. See the greenish colors here.