Select Page

What is Machine Learning? Machine Learning can be described as the study and construction of algorithms that can learn from and make predictions on data, rather than follow programmed instructions. IoT and Machine Learning are said to go hand in hand.

IoT promotes the data that can help cities predict accidents, give doctors real-time insight into information from bio-chips and pacemakers, and enable optimized productivity across industries through predictive maintenance on equipment and machinery. The possibilities that IoT bring are endless.

The problem is finding ways to analyze the deluge of performance data and information that all these devices create. It’s impossible for humans to review and understand all this data. We need to improve the speed and accuracy of big data analysis in order for IoT to live up to its promise. The only way to keep up with this IoT-generated data and gain the hidden insight it holds is with Machine Learning.

Machine Learning in your business

In an IoT situation, machine learning can help companies take the billions of data points they have and boil them down to what’s really meaningful. The general idea is the same as retail applications – review and analyze the data you’ve collected to find patterns that can be learned from, so better decisions can be made.

For example, a hotel that is paying a worker $16/hour to manually check 16 meters around the property once a day will cost $3,840, and if this person was to check the same meters once per hour to try and decipher changes it would cost $92,160. Imagine checking the meters every minute or every second; it becomes humanly impossible to do so without the use of machine learning. Machine learning can decipher the changes, and workers can then implement the changes to start that next level of predictive maintenance.

John Morrow, CEO of Morrow Consultants, spoke with me about sensor based applications and IoT. He gave me an example of how a hotel property can benefit from vibration sensors in their assets, such as an A/C unit, to help notice changes in the system that can in turn help prevent malfunctions from occurring and making your assets last longer.

John explained, ” The air compressor in the A/C unit, for example, has a rotating shaft that produces a particular motion that sensors can pick up on if it is moving too fast or too slow than its original motion which could mean there is a problem with the system; these vibrations are outside the range that human’s can experience.”

He also mentioned in the a/c unit example that the shaft is just one portion of the whole unit and there could be a number of other sensors monitoring all functions of the machine at once to notice irregularities.

John also discussed the benefits of “wearable internet of things,” such as Googleglass or even Fitbit. The next level of Fitbit would be reporting those stats recorded and immediately sending them over to a doctor for review in cause there could be a problem.

IoT and Machine Learning are allowing us to gather and identify immense amounts of data to make better decisions in all industries of business and life.

Will IoT and Machine Learning take over the work force?

Will machine learning eliminate jobs or is there another industrial revolution starting again? It could be looked at both ways. After analyzing the data to see how many assets need adjusting employees may need to be hired to fix the malfunctions, or since you are eliminating the manual checking, the amount of people could decrease and once maintenance is fixed more routinely less orders may come in for repair.

John Morrow mentioned how people may need to educate themselves more to adjust to the times, where as before the only thing people were competing against were each other and now it is people and robots.

Still, even if robots took over more of the manual labor, people will still need to program them, build them, and fix them. The idea is to grow, learn from mistakes, build off of mistakes, and IoT and machine learning are getting us miles closer through proper implementation.