⬆️ ⬇️

KINETIC: Intel Edison, Gravity, Health, and Savings

The surest way to protect against back injuries when working with weights is to give such work to someone else. But seriously, the correct handling of heavy objects is a whole science. For example, many people know that it is necessary to lift and lower weights with a straight back, so that the main load falls on the legs. Deviation from this rule alone will sooner or later make itself felt, and there are others.



image


Violation of safety at work is transformed into employee injuries and company losses. In 2013, for example, back injuries cost companies in the US $ 70 million. There is a problem, unpleasant and expensive. KINETIC , a New York-based startup that deals with intelligent wearable devices, found a way to use Intel Edison computing modules to create a system that can significantly reduce injuries in dangerous workplaces and save companies huge amounts of money.



KINETIC uses sensors in the device, which is mounted on a belt, as well as well-designed algorithms that help determine whether a person works with weights safely, or so that he looks up to break his back. An additional module, reminiscent of a wristwatch and equipped with a vibration motor, is able to instantly notify an employee that he is performing dangerous actions. For continuous staff development, which means work safety, at the end of the shift, data from devices is collected, uploaded to the cloud service and analyzed. As a result, these data become valuable analytical information, statistical information that can be viewed through a web interface. This analytics can be used, for example, for additional training of employees and to change something in the workplace and make it safer.



How can a small startup, which is only one and a half years old, have been able to quickly develop an industrial-grade IoT device, write programs for it and bring it to the market? Today we, together with the founders of KINETIC, will tell the exciting and inspirational story of this project.

')

How it all began



The CEO and one of the founders of KINETIC, Khaite Elhavari, was educated in biomedical engineering. He wanted to make so that people who work with weights, less suffered from injuries in the workplace. He was reminded of this desire by the way his mother, who worked as a nurse, constantly complained of back pain. This is not surprising: she had to help patients, often completely helpless. This is what he himself says about the project: “I wanted to take technologies that have long been available on the market and introduce them to workplaces, where these technologies can help in reducing industrial injuries.”



He saw movers as “industrial athletes”, so he found something similar to what he wanted to create, among sports devices, such as Nike Plus sneakers. They are equipped with sensors capable of detecting movements, direction of movements, accelerations, rises. On the basis of the data collected, it is possible to determine what a person is doing, calculate the distance traveled, give him recommendations.



“As is the case with any wearable device, or with something that relates to the Internet of things,” says Haytem, ​​“the project has a hardware component that requires special knowledge in design and production. Next are the sensors that collect the data. In order to extract from this data something useful, we need not only knowledge of how to interpret them, but also the ability to clear them of noise and highlight the most important thing. The next stage is the development of the user part of the project. In particular, an information panel with clear analytical information. ”



In order to give life to the project, Khaitem and another project founder, as well as his CTO, Aditya Bessel, an electronics engineer with experience in the development of wearable devices, enlisted the support of a data processing specialist, a software engineer and two mechanical engineers, one of which had manufacturing experience. Let's see what they did.



Getting Started with the Intel Edison Compute Module



The ability to collect data about the actions of workers and give them instant feedback when they deal with weights, risking their health, means that the device must perform calculations in real time.



“This is how you usually automate certain processes in warehouses or factories using portable devices. First, collect data, then send it to the cloud, perform the necessary calculations there. Then transfer the results back. The devices, in turn, somehow react to the accepted results, ”says Haytem.



This idea, applied to the KINETIC goals, has a serious disadvantage. The fact is that not all parts of warehouses or factories can be connected to Wi-Fi networks. The KINETIC team needed a solution that was capable of processing data locally, using the hardware capabilities of the portable device. “The Intel Edison Compute Module played a crucial role in our project,” says Haytem. “It is very compact and at the same time has excellent computational capabilities. Edison is able to process data immediately after it arrives, instantly reacting to dangerous situations, without relying on external services to which you need to connect via Wi-Fi. ”



The Intel Edison, a miniature, energy-efficient device, has a built-in dual-band Wi-Fi adapter. Edison supports Bluetooth 4.0, is equipped with a dual-core Atom processor and an Intel Quark microcontroller. Haytem believes that Edison has provided KINETIC with an excellent multipurpose platform, which, among other things, means the flexibility of the solution. What kind of "flexibility" are we talking about? Here is how the founder of the startup answers this question: “Now we are busy protecting against injuries when working with weights, because they account for the lion's share of claims for compensation from employees. Developing, we want our solutions to be used to analyze other types of work, the improper performance of which is traumatic. ”



The KINETIC wearable device relies on the Intel Edison compute module, working with its sensors, collecting data and storing it in flash memory. The device uses the built-in Edison Wi-Fi adapter to upload data to the cloud. This is done at the end of the shift. Bluetooth is used when additional wearable sensors are added to the solution. It is through BT that they interact with the main module.



Anatomy of devices from KINETIC



The system developed by KINETIC includes two devices. The first, basic, is worn at the waist. It contains, among other things, sensors and a computing module. The second, optional, resembles a wristwatch. It is worn on the wrist, it contains additional sensors and a display. When it is used, both devices work together, collecting more accurate information about the actions of workers.





KINETIC intelligent wearable devices protect workers from back injuries by identifying potentially dangerous actions in real time.



The device, which is worn on the belt, includes a built-in accelerometer and measures acceleration, tilt angle, position in space, using the company's own algorithm. “We observe the movements that the employee makes when he is dealing with weights and is loading the spine,” says Haytem.





The device from KINETIC, which is mounted on the belt. It is capable of autonomous operation and includes sensors and an Intel Edison computing module.



Action modeling



Heitem's experience in the field of biomechanics has played a key role in the development of algorithms to monitor the activities of employees and to determine how safely certain actions are performed.



“A lot has been written about this,” says Haytem. “Over the past 20 years, scientists have developed and published models that describe indicators that are indicators of risk. We found out which indicators work best. ”



Instead of reinventing the wheel, the KINETIC team automated the best it could find. “Usually, ergonomists do this: they stop a person in the process of performing some kind of operation, say, when lifting a heavy box, and, in the literal sense, begin to measure, for example, the back and knee bend, and how far the box is from the waist,” tells Haytem.



For research purposes, all this is very useful, but in the real world, in production, for example, such “manual” measurements are not applicable. According to the founder of the company, thanks to KINETIC, for the first time in history, it became possible to automate such measurements, and, if the risk is too great, to immediately notify the employee.



How does KINETIC find out, for example, that a certain box is held too far from the human body? “To solve this problem, an additional wrist module is used,” explains Haytem. “A device attached to a belt can track the movements and bending of the back. Only with its help a lot can be done. However, if you need more detailed data, for example, you need to know how far the box is from the waist, or if you need to get data on lifting weights above shoulder level, which is considered a very risky business, then you need a module that is attached to the wrist. ”



Behavior change



KINETIC took a lot of effort to create a feedback mechanism, thanks to which workers learn that they are doing something dangerous. “Managers would love the idea of ​​a stun gun. But such feedback will definitely not please the workers, ”Haytem laughs. “And if without jokes, the device on the wrist vibrates like a vibrating alert on the phone when a message arrives. The main goal of feedback is to change dangerous scenarios of behavior to safe ones. ”



The difficulty is also added by the fact that workers, even at the expense of safety, are trying to catch as much as possible. Much here depends on the forms and systems of remuneration. According to Hatem, people are taught to work safely, but often, regardless of what they have been taught, they choose the fastest ways to perform certain actions.



KINETIC wanted to remind employees of what they were taught. In the summer, the company launched a pilot program in several warehouses of companies that operate in the areas of cargo delivery and logistics. This program gave them some important information. “Alerting people about dangerous acts has, in general, proved useful,” says Haytem. “And in order to enhance this effect, workers need to be motivated, they must be allowed to interact with the system, make it understandable.”





The KINETIC device is quite thin, which makes it comfortable to wear on the belt



Workers of the older generation tend to be attentive to occupational safety and health, while younger and stronger people think they are invulnerable. To motivate them all, KINETIC uses a method well known in sports: competition. Namely, records are kept of actions performed at high risk to health that each of the employees performed during the day. Then the results of the workers are compared. The one who performed the most high-risk operations safely receives a small reward.



KINETIC borrowed another idea from consumer wearable electronics: the leaderboard. It allows employees to see what their results are compared to previous working days and to compare their achievements with those of other employees. In KINETIC they say that this idea attracted people, they began to discuss it with each other: “I can’t believe that you broke free”, “We need to get around it”. Work from a boring sequence of actions turned into an exciting competition.





Leaderboard check



In addition, this approach helped to build trust in the team. “When we gave workers access to the leaderboard,” they say at KINETIC, “they were able to see their own and other people's results freely. They understood that they should not worry about the fact that something incomprehensible for them is happening in the depths of our system, but it can somehow influence them. ”



Data processing



Sensors collect data, but, along with the useful signal, there is a lot of noise in this data. “Information from motion sensors is very noisy,” says Aditya Bensal. “We use many traditional signal processing algorithms. Edison's computational power came in handy for solving such problems. ”





Left - noisy sensor performance. According to such data it is difficult to understand how, in fact, a person moves. After processing the signal, it becomes clearly visible when exactly the person bends down (the blue line goes up) and returns to the starting position (the blue line goes down).



A special kind of noise is the actions of the worker himself. Such “noise” arises when a person, for example, eats lunch, waves his hands or does anything that is not related to working with weights. “This brings us back to what has already been touched by Hatem, talking about the algorithms for processing sensor readings and finding out what exactly the employee is busy with,” says Aditya. "We need to drop everything that does not apply to working with weights."



In order to solve this problem, the KINETIC team recorded the activities of workers on video. “We compared the information from the sensors with what was on the video. This was done in order to find out exactly what people are doing and how sensors react to it, ”explained Aditya.



Cloud connection



At the end of the shift, workers install their devices in the charging station. Then all these devices begin to transfer data to the cloud. The project uses the Amazon Web Services API (AWS), which allows you to safely transfer information directly to the cloud service.



The Amazon Elastic MapReduce (EMR) analytical system in real time processes a huge amount of information collected from hundreds of devices and stores them in a database hosted on AWS. After that, the data goes to the KINETIC dashboard, giving managers meaningful, suitable for further work with them, indicators.



Summary of experience



Given the huge amount of data collected, it is not surprising that KINETIC found some interesting patterns in the behavior of workers. “We saw clear bursts of dangerous activity at certain moments of the working day,” Haytem said. “At one factory, this happened right before the lunch break and shortly before the work was completed. We think this suggests that people are trying to have time to do more before a break or before the end of a shift. ”



“Imagine that you are the head of the security service,” he continued. “You are collecting data on high-risk actions performed by company employees. Then you decide to introduce a new training program or spend money on more convenient and safe equipment of workplaces. After the introduction of innovations, you should see a change in performance. If there is no difference, then what you have done has not changed anything. This allows you to assess the real impact on the situation of measures to improve security. Until now, the only way to understand whether the innovation is working or not was simply waiting and evaluating the change in the number of injuries. ”



Contributing to the community: workshops



Haytham Elhavari and Aditya Bensal are actively involved in the life of the developer community, exploring new ideas, supporting talented newbies and helping others bring their development to the market. They do this by organizing monthly seminars in New York.



“We talk about the experience gained, how to bring the product to the market, about building a brand. We pay attention to production, ”says Haytem. These events every month attract more than 200 people, moreover, the list of members includes about 3,000 developers. On this occasion, Khaitem notes: "I suppose this indicates an increase in the popularity of hardware start-ups."



Aditya agrees: “I am conducting seminars on embedded systems here in New York. They are less focused on business. These seminars are dedicated mainly to software and the technical community. Many companies are represented at the events, including Intel. This shows the size of the community formed around the embedded systems in New York. "



Results



Intel has made a significant contribution to the IoT community. This, for example, the support that the company provides to those who are interested in Intel Edison. KINETIC is one example. Intel's participation played an important role in their project, helped to quickly develop an intelligent wearable device that connects to the cloud, to launch it on the market. Assistance, in particular, was in answering technical questions and in supporting the program part of the project. The Intel Edison Compute Module was the ideal choice for locally collecting and processing data and sending them safely to the AWS cloud for analysis.



KINETIC actively participates in the Intel Development Zone forums. "Whenever we encounter a problem and find its solution, we immediately publish the answer," they say in the company.



KINETIC fulfills the noble mission of increasing occupational safety and reducing costs. The company, without exaggeration, protects the "ridge of the economy." KINETIC paved the way for IoT solutions based on Intel Edison compute modules, sensors, and AWS cloud services, where until now the security technologies had helmets, metal-toed safety boots and safety glasses.

Source: https://habr.com/ru/post/369475/



All Articles