Intelligent ‘postcards’ from the Edge: Machine learning model usage

5/5 (2)

5/5 (2)

Organisations have found that it is not always desirable to send data to the cloud due to concerns about latency, connectivity, energy, privacy and security. So why not create learning processes at the Edge? 

What challenges does IoT bring?

Sensors are now generating such an increasing volume of data that it is not practical that all of it be sent to the cloud for processing. From a data privacy perspective, some sensor data is sensitive and sending data and images to the cloud will be subject to privacy and security constraints.

Regardless of the speed of communications, there will always be a demand for more data from more sensors – along with more security checks and higher levels of encryption – causing the potential for communication bottlenecks.

As the network hardware itself consumes power, sending a constant stream of data to the cloud can be taxing for sensor devices. The lag caused by the roundtrip to the cloud can be prohibitive in applications that require real-time response inputs.

Machine learning (ML) at the Edge should be prioritised to leverage that constant flow of data and address the requirement for real-time responses based on that data. This should be aided by both new types of ML algorithms and by visual processing units (VPUs) being added to the network.

By leveraging ML on Edge networks in production facilities, for example, companies can look out for potential warning signs and do scheduled maintenance to avoid any nasty surprises. Remember many sensors are linked intrinsically to public safety concerns such as water processing, supply of gas or oil, and public transportation such as metros or trains.

Ecosystm research shows that deploying IoT has its set of challenges (Figure 1) – many of these challenges can be mitigated by processing data at the Edge.

Challenges of IoT Deployment

Predictive analytics is a fundamental value proposition for IoT, where responding faster to issues or taking action before issues occur, is key to a high return on investment. So, using edge computing for machine learning located within or close to the point of data gathering can in some cases be a more practical or socially beneficial approach. 

In IoT the role of an edge computer is to pre-process data and act before the data is passed on to the main server. This allows a faster, low latency response and minimal traffic between the cloud server processing and the Edge. However, a better understanding of the benefits of edge computing is required if it has to be beneficial for a number of outcomes.

Perception on Edge Analytics in IoT Users
AI Research and Reports

If we can get machine learning happening in the field, at the Edge, then we reduce the time lag and also create an extra trusted layer in unmanned production or automated utilities situations. This can create more trusted environments in terms of possible threats to public services.

What kind of examples of machine learning in the field can we see?

Healthcare

Health systems can improve hospital patient flow through machine learning (ML) at the Edge. ML offers predictive models to assist decision-makers with complex hospital patient flow information based on near real-time data.

For example, an academic medical centre created an ML pipeline that leveraged all its data – patient administration, EHR and clinical and claims data – to create learnings that could predict length of stay, emergency department (ED) arrival models, ED admissions, aggregate discharges, and total bed census. These predictive models proved effective as the medical centre reduced patient wait times and staff overtime and was able to demonstrate improved patient outcomes.  And for a medical centre that use sensors to monitor patients and gather requests for medicine or assistance, Edge processing means keeping private healthcare data in-house rather than sending it off to cloud servers.

Retail

A retail store could use numerous cameras for self-checkout and inventory management and to monitor foot traffic. Such specific interaction details could slow down a network and can be replaced by an on-site Edge server with lower latency and a lower total cost. This is useful for standalone grocery pop-up sites such as in Sweden and Germany.

In Retail, k-nearest neighbours is often used in ML for abnormal activity analysis – this learning algorithm can also be used for visual pattern recognition used as part of retailers’ loss prevention tactics.

Summary

Working with the data locally on the Edge, creates reduced latency, reduced cloud usage and costs, independence from a network connection, more secure data, and increased data privacy.

Cloud and Edge computing that uses machine learning can together provide the best of both worlds: decentralised local storage, processing and reaction, and then uploading to the cloud, enabling additional insights, data backups (redundancy), and remote access.

More Insights to tech Buyer Guidance
0
EU Getting Increasingly Serious about Data Protection

5/5 (1)

5/5 (1)

The Hamburg State Commissioner for Data Protection and Freedom of Information (HmbBfDI) imposed a fine of USD 41.3 million on Swedish MNC, Hennes & Mauritz (H&M) for illegal surveillance of employees in H&M Germany’s service centre at Nuremberg.

The data privacy violations reportedly began in 2014 when the company started collecting employee data including their personal information, holidays, medical records, informal chats and other private details. It was found that the information was unlawfully recorded and stored; and was further opened to managers. The violations were discovered in October 2019 when due to a computing error the data became accessible company-wide for a short span.

Ecosystm Principal Analyst Claus Mortensen says. “This is one of those cases that are so blatant that you cannot really say it is setting a precedent for future cases. All the factors that would constitute a breach of the GDPR are here: it involves several types of data that shouldn’t be collected; poorly managed storage and access control; and to finish it all off, a data leak. So even though the fine is relatively high, H&M should probably be happy that it was not bigger – the GDPR authorises fines of up to 4% of a company’s global annual turnover.”

Mortensen adds, “It should also be said that H&M has handled the aftermath well by accepting full blame and by offering compensation to all affected employees. It is possible that these intentions were considered by the HmbBfDI and prevented an even higher fine.”

The penalty on the Swedish retailer is the highest in Germany linked to the General Data Protection Regulation (GDPR) legislation since it came into effect in 2018 and the second highest throughout the continent. Last year, France’s data protection watchdog fined Google USD 58.7 million for not appropriately disclosing data collection practices to users across its services to personalise advertising.

Talking about the growing significance of fines for data breaches, Ecosystm Principal Advisor Andrew Milroy says, “To be effective, GDPR needs to be enforced consistently across the board and have a significant impact. It is too easy to ‘corner cut’ data protection activities. Some breaches may not have an operational impact. For this reason, the cost of being caught needs to be sufficiently large so that it makes commercial sense to comply.”

According to Milroy, “The sizeable fine meted out to H&M together with the publicity it has generated shows that the regulators are serious about GDPR and enforcing it. Other regulators around the world need to make sure that their jurisdictions don’t become ‘soft touches’ for malicious actors.”

EU Proposing New Data Sharing Rules

We are also seeing the European Union (EU) make moves to regulate digital services and customer data use by technology providers, as part of the European Union Digital Strategy. The EU is drafting new rules under the Digital Services Act to force larger technology providers to share their customer data across the industry, to create an even playing field for smaller providers and SMEs. The aim is to make the data available to all for both commercial use and innovation. This is being driven by the EU’s antitrust arm, aimed to reduce the competitive edge tech giants have over their competition and they may be banned from preferential treatment of their own services on their sites or platforms. The law, which is expected to be formalised later this year, is also expected to prohibit technology providers from pre-installing applications or exclusive services on smartphones, laptops or devices. The measures will support users to move between platforms without losing access to their data.


Click below to get data and insights on our cybersecurity study
Get Started

2