2017 Q2 Sabisu User Group – Agenda sneak peak

Following the success of our January User Group we’re been looking forward to the next one on May 11th and we’re excited to be able to share with you a sneak peak of the agenda.

If you can’t make it in person, we’d be delighted if you could join via web conferencing.


09:00 – 09:30 Coffee, Cake and Chat

09:30 – 09:50  Introductions & Review

09:50 – 10:20  Forthcoming Features: Introducing Machine Learning (Dr Tim Butters)

10:20 – 10:45  Case Study : A presentation by CropEnergies AG

10:45 – 11:00  Interlude (more coffee, cake and chat)

11:00 – 11:30 Case Study: A presentation by SABIC UK

11:30 – 12:00 Q&A and customer suggestions 

Why should you get involved?

  • Get insight into how other customers get value out of Sabisu
  • First hand look at new and upcoming platform features
  • Provide valuable feedback on how you use Sabisu
  • Drive platform development to suit your needs
  • Get to know the Sabisu team

How do you get involved?

Simply email laura.ticehurst@sabisu.co or lynsey.nicholson@sabisu.co and we’ll send you an invitation.

When and Where?

11th May, 2017  9am -12pm

The Wilton Centre, Wilton, TS10 4RF.

Or via web conference.

Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.

Posted in Press Release | Tagged , | Leave a comment

Introducing the Sabisu Handover Log

We’ll shortly be making the Handover Log available to all users in Sabisu.

The Handover Log will provide you with a one stop for any and all handovers; shift handovers, project teams, or anywhere one user/group needs to pick up where another left off.

You can create a Handover Log to take notes in a meeting and assign actions to users. The log can then be used as a working document to monitor progress.

handover log

For example, a Shift Handover Log is common in the process industries to give updates to the next shift on duty and handover any outstanding actions or concerns. This is a great use-case.

Sometimes projects will work back-to-back, with two people working the same role. The Handover Log ensures that the handover is complete and high quality without the need for a face to face meeting, or where that might be difficult.

You can add in current Actions or create new ones and in the next few days we’ll add file attachments too.

handover log 2

Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.


Posted in Release Notes | Tagged , , | Leave a comment

Machine Learning in Sabisu – Finding Patterns in Data

Machine learning allows users to leverage the inherent information contained within large datasets. This is not the top level information that is the raw data itself, but rather the secondary information that can be extracted through the elucidation of hidden patterns.

There are two forms of machine learning; supervised and unsupervised.

Supervised learning requires a labelled dataset, where different classes of behaviour are identified beforehand. This data is then fed into the machine learning algorithms, allowing them to learn the differentiating factors between these classes. Once this is done, a model is produced which can now be used to classify brand new data, predicting what class it belongs to from the original set. This classification process is used for tasks such as handwriting recognition, where a system will learn what the different letters look like using huge labelled datasets that contain different writing styles. The system can then “read” handwritten documents it has never seen before, identifying letters with incredible accuracy. This is how many countries sort their post, using handwriting recognition systems to read postcodes and route the letters to the correct regions.

However, in many cases labelled datasets aren’t available. Industrial process plants contain a large amount of data, often in the form of time series. These time series encapsulate the state of the plant at a very fine granularity but for a continuous process it is rarely straightforward to interrogate this data. Using unsupervised machine learning techniques it is possible to automatically separate different modes of operation by analysing the time series. An example of this is shown in figure 1, where the top panels show process data, and the bottom panels show how unsupervised machine learning has segregated this data into different operational modes.

Feature Detection

Figure 1A. Unsupervised learning identifies the different modes of behaviour by identifying patterns in the data. This can be used to identify similar behaviour in the future, or search the historical data for similar occurrences.


Figure 1B. Zooming in on individual features we can see the boundaries between the different behaviour as the colours change in the lower panel.

Processing in the Cloud

Machine learning is all about Big Data, and efficiently extracting value from this data. It is therefore natural to build machine learning solutions in the cloud, which provides seamless scaling of processing power to meet the demands of the data. Sabisu uses a variety of cloud technologies such as Amazon’s Elastic Map Reduce, Spark, and the Spark-ML libraries to ensure rapid processing of even the largest datasets. Data noise is always a concern in any time-series processing application. Sabisu has developed a set of custom aggregators in Python and Scala to ensure the best results from real-world data.

Simplifying Machine Learning

You don’t have to be an expert to use Sabisu’s machine learning solutions. On the contrary, the finer implementation details are abstracted from users to allow you to concentrate on the thing that really matters; the results!

Sabisu will handle all of the pre-processing and calibration required to make the most of this advanced technology, meaning all you have to do is select the data you want to analyse.

Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.

Posted in Operational Excellence, Operational Intelligence | Tagged , , , | Leave a comment

Dynamically update your widgets

New updates to the Sabisu Pipeline mean you’re now able to query Widget data from a Pipeline Data component. This means that you can now have a Pipeline that can be dynamically updated via another Widget on a Page, e.g., from a user-selected list.

Why is this useful?

This makes Pipeline generated Widgets as flexible as any traditionally built Widget. It means end-users with no programming knowledge can link Widgets together.

You could use this to, say, compare data over a period of time and in different instances so you can analyse the data to spot anomalies and patterns.

query a widget with pipeline

How do I do it?

To get set up you could get in touch and we’ll provide you a list Widget ready to go, so all you need to do is set up the pipeline:

create a query with pipeline

Or you could build your own Widget in the Sabisu Builder, then set up your acquisition within the Sabisu Pipeline to use it:

using builder

Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.


Posted in Release Notes | Tagged , | Leave a comment

Share Sabisu everywhere

You can now embed Sabisu Widgets into any web page.

This makes it easy to embed Sabisu into intranet pages, blogs, SharePoint, digital signage…anywhere that takes HTML.

The embedded widget will update with data as if it was in the Sabisu platform. Any user that needs to analyse the data or see it in contact can simply click the Sabisu logo to be taken into the platform proper.

To start embedding your Sabisu Widgets simply navigate to the widget tab menu and hit “Get Shareable Link”

shareable link

We have embedded a Sabisu widget into the blog post below. If you login to your Sabisu account you’ll see the data.

We’ve set Widgets free but they’re still super-secure; only users with appropriate access can see them. If you have a Sabisu account and you’re logged in to Sabisu, the Widget will automatically load, however if you don’t have an account or you’re not logged in you will be asked to sign in.

If you don’t have a Sabisu account….get in touch!


Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.

Posted in Release Notes | Tagged , , | Leave a comment

Problem? Highlight & huddle with Sabisu Events

Sabisu now allows you to highlight a chart area and create an event, instantly notifying everyone in the Community that there’s something they need to know about.

As soon as you create the Event, it’ll be visible on the chart, the Widget Working View Notes, Community Notes and the Community Stream.

The Event could be anything; a sudden spike in the furnace pressure for example, or costs rising due to an unforeseen circumstance. If you find an Event needs more investigation you can assign an Action to the relevant person directly on the Notes stream.


Rather than just a new type of Note, Events represent a new class of metadata capture for Sabisu which allows our machine learning algorithms to recognise repeating Events and inform you one has occurred or is about to occur. It will also analyse data using to be able to advise you when an event is likely to happen again. Watch this space.

Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.

Posted in Release Notes | Tagged , , | Leave a comment

Another little improvement to Sabisu Actions

Sabisu Actions continues to be a valuable and well-used part of the platform, so we’re continuing to make minor, continual revisions to improve usability.

This week we’ve added an auto-complete feature to make life a bit easier, increase speed of entering new actions and improve the quality of Actions data.

It can be hard to keep track of your actions especially when you raise similar ones and want to find all those relating to, say,  “EHSS”.

We’ve added in a drop down to the Category field so can you see similar categories used previously, saving you having slightly different categories that are hard to keep track of. This will make it easier for you to search for associated Categories.

Auto complete on actions

Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.

Posted in Release Notes | Leave a comment

Why was Sabisu not affected by the Amazon Web Services S3 outage?

It’s all about the architecture being fault tolerant by design.

On February 28th, 2017, Amazon Web Services lost S3 in the US-East region, which is basically a huge datacenter in Northern Virginia.

You can read their full explanation here but it all came down to human error compounded by the scale of S3 usage across the internet – only AWS has the figures but some estimates put the number of sites affected by this one outage at 150,000.

S3 is a great place to put all kinds of data. Sabisu uses it to store raw files of all kinds from customers; MS Excel, highly structured raw process and sensor data, images, fragments of documents and so on. Right now Sabisu has many terabytes of data split into various S3 buckets of structured and unstructured data.

A good chunk of that is in US-East and was taken out by the S3 outage. So what happened?

Well, nothing much.

If you were a user working with the Sabisu browser client, you’d be totally unaware. All the cloud Sabisu Units continued to operate as they run their own integral storage and redundancy.

Customers with a hybrid-cloud implementation linked to US-East would have found their Appliance aggregating data locally, waiting for S3 to come back. No problem. It’s exactly what it’s designed to do if connection is lost, or connection quality dips.

Of course customers running an On-Premise implementation would have seen no effect at all. Their servers are lightly tethered to Sabisu Central but as with Units, it has it’s own redundancy arrangements.

If you were a customer with a Unit in US-East, publishing an MS Excel document through Go, then perhaps you’d have seen a slight delay as Go tried to write to S3.

We monitored Sabisu performance throughout the outage and it there were no problems to report and indeed, none were reported.

Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.

Posted in Uncategorized | Leave a comment

Towards total self-service; filtering data in Pipelines

With Sabisu Pipeline Directory you can use any data from anywhere – sometimes you need a little precision in choosing it.

We’ve added filtering into Pipelines. Simply add a data object into the data lane then add a filter in the Filters and Calculations lane below. The filter allows you to limit the result of the data based on standard comparators (contains, =, <, >, etc.) and output this data onto a chart. You can apply filters to any data; project, process, sensor, or enterprise data.

This means you can easily reduce the dataset to that which is required or eliminate some anomalous data that is skewing your results.

Follow these simple steps to apply a filter – in this example, showing the results in a chart:

  • Select Pipeline click on ‘+’ in the Calculations & Filters lane
  • Click on Filter, select the tag you wish to manipulate and then click Add filter
  • Choose the results you wish to view whether this is a value or a time stamp then hit Save
  • Add a Chart into the Do lane and then make sure you only select the manipulation you have just applied.
  • Deploy the widget to your page.
  • Further configuration changes can be made directly to charts by clicking on the Pipelines tab in the Widget Working View.

Filters on Pipelines

Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.

Posted in Release Notes | Tagged , , , | Leave a comment

Can you get your project back on track?

We’ve just released a new analytics tool in Widget Working View designed for project s-curves. It works with both cost and progress information and calculates recovery measures.

Firstly it will calculate the required rate for recovery within a month. This is usually the shortest recovery period that makes sense but even then, often it’s too short and results in an unrealistic ramp in project spend or progress.

It also calculates a recovery period based on the maximum rate seen in the baseline or planned value. As the baselines and approved plans are rarely intentionally unrealistic, it makes sense to use them as an indicator of maximum possible productivity.

Plotting both these values on a project s-curve allows an informed decision to be made.

S curve

Of course, this isn’t the whole story. As the project nears completion we’d expect to see the s-curve flatten off. These analytics will be updated to include that natural slowing of progress in the next few weeks.

Contact Us

We’re always interested in hearing from you with any comments or suggestions, feel free to get in touch.

Posted in Release Notes | Tagged | Leave a comment