The construction industry isn’t known for being a beacon of innovation. I’m sure they would forgive us for saying that.

But there’s always room for new technology and we know one local company leading the way.

Operance, founded by Ian Yeo and Scott Pilgrim, are a software and consultancy provider specialising in Building Information Modelling or BIM as it’s commonly known.

We spoke to Ian about how tech like theirs is changing how buildings are built everywhere. It has the potential to save lives and increases efficiency throughout the construction process.

They’re a C4DI success story and to top it off they make a pretty good claim to having one of the best offices in the building.

Before we go any further, you’re probably wondering, what exactly is it that Operance (formally known as Bimsense) do?

Well, in Ian’s own words, “BIM is an acronym for Building Information Modelling. This has quite a few components. So, a 3D model created by an architect or an engineer, is one part of BIM. It’s a real central core part of BIM. But it’s also about information and making that information digital, throughout the construction process.”

“So, you will have an architect’s model. But you can also have, say, an Excel spreadsheet that becomes part of that overall model of a building.”

Thanks Ian. BIM has the potential to be a complete digital footprint of a building, its components, uses, specifications and more.

Operance don’t just do BIM – they offer other services too. They originally formed as a consultancy service for contractors and large estate owners, which is still part of what they do, but they also have an increasing range of software tackling facilities management, operations, and maintenance.

Tying it all together is an exciting concept known as the Golden Thread.

Simply put the Golden Thread is ‘the ability to track decisions throughout the life of a project.’ In other words, Operance empowers users by ‘identifying a thread all the way through design, construction, and the use of the building to know what’s happening to the material of the building and the products.’

The Golden Thread of building safety information is a digital document containing an accurate and up-to-date record of building data that spans the entire lifecycle of old and new facilities.

The term featured heavily in the final report of the Independent Review of Building Regulations and Fire Safety, which was led by Dame Judith Hackett in 2017 after the Grenfell Tower tragedy.

New building legislation requires developers to provide this Golden Thread of information, which spans the entire lifecycle of old and new facilities.

Whilst this new demand for a breadth and depth of information places additional pressure on developers, housing associations and estate managers, the Golden Thread helps us to create safer, more efficient spaces for people to live – which, in our eyes, can only be a positive outcome.

But what does the Golden Thread mean for you and how are you going to deliver it?

We’ve outlined everything you need to know about the Golden Thread in this article below, alternatively, here’s a short video explainer…

The responsibility of the Golden Thread changes as the project progresses through two different phases: the Design and Construction Phase and the Occupational Phase.

During the Design and Construction phase, the development of the Golden Thread of building information is the responsibility of the ‘Dutyholder’.

The dutyholder may be fulfilled by either an individual or an organisation/legal entity. A dutyholder can hold more than one role in a building project. Some examples of dutyholders include:

• Client
• Principal Designer
• Designer
• Principal Contractor
• Contractor
• Building Safety Manager

The information gathered by the project team is verified by the dutyholder at the end of specific ‘Gateways’ during and at the end of the Design and Construction phase.

The dutyholder must present the Golden Thread when registering the building with the Building Safety Regulator (BSR) so they can successfully obtain a Building Assurance Certificate (BAC).

The responsibility for the Golden Thread changes when you reach the Occupation Phase of the project.

The ongoing development of the information package throughout its lifecycle becomes the responsibility of a new dutyholder who becomes the named ‘Accountable Person (AP)‘.

They are responsible for registering existing and new occupied buildings and applying for a Building Assurance Certificate and is required to comply with all the statutory obligations on an ongoing basis.

The AP is the dutyholder during the Occupation phase. They may be an individual, partnership or corporate body and there may be more than one Accountable Person for a building.

The AP nominates a Building Safety Manager (BSM) to continue maintaining and updating the information to record the ongoing safety of the building.

The BSM can be either an individual or organisation that must have the organisational capability and relevant skills, knowledge, experience and behaviours to support the Accountable Person in the day-to-day management of fire and structural safety in the building.

Find out more about who is responsible for your Golden Thread: Access the guide.

Learn more about who you should appoint as your dutyholder and accountable person (AP).

The Golden Thread is required for all high-rise buildings (HRB) – residential buildings with a height of 18 metres or more.

In the future, this is likely to extend to include smaller buildings and asset-specific information.

Every time a building is changed or maintained, information reflecting those changes needs to be recorded.

The Golden Thread of building information is currently being defined as part of the Ministry of Housing, Communities and Local Government (MHCLG) sponsored ‘Golden Thread Initiative’ project.

The Operance team is invited to participate in the project and share our experience and software to help define the information requirements and provide the first working example for the Golden Thread.

The final requirements of the Golden Thread will be defined in secondary legislation.

Tap here to receive a notification from us.

What we know now is that your Golden Thread needs to contain accurate, up-to-date information about the design, construction and ongoing maintenance of buildings.

It’s likely that the legislation will require information about:

• Building Safety
• Fire Safety
• Structural Safety

However, it’s anticipated that, over time, more information will be required, such as Asset Information for assets that don’t fall within one of the above categories.

The Golden Thread is essentially a digital way of working that enables a systematic, controlled approach to construction, refurbishment and management of occupied buildings, to manage building safety information.

The best way to comply is to create a standardised digital package to make sure all your buildings and the assets within your estates develop uniform building safety information.

We’d recommend creating and controlling this data at the component level (the assets and elements of which make up the building) in three ways:

• What – What information is required. Use templates and checklists to define and audit standardised information.
• When – The timing of when and who supplies the information. Software platforms such as Operance O&M linked to master project programmes need to be used to plan and coordinate your information in a timely manner.
• Where – Where the information is stored. Implement an easy-to-use, open format and non-proprietary software (meaning that information and data can be easily accessed and shared between other digital platforms).

The specifics of what you need to include in your Golden Thread depends on the phase of your project. Below is a breakdown of the two Golden Thread phases and specific gateways at which you need to supply information.

Before construction can commence, the dutyholder must submit key Golden Thread information to the Building Safety Regulator.

This information includes but is not exclusive to:

• Specifications – detailed construction products, materials and component information, including important fire performance capabilities.
• Plans relating to how fire and structural safety risks will be managed.
• Models – digital 3D BIM representations of the building ‘as planned’.
• Fire Statement – details on fire service access and fire fighting water accessibility, which forms the foundation of the fire and emergency file.
• Construction Control Plan – how compliance with Building Regulations will be achieved and how changes will be controlled and recorded.

Major changes affecting any of the above items in relation to safety need to be agreed upon with the principal designer and client and approved by the Building Safety Regulator (BSR) in advance.

In order to obtain and validate the information in a timely manner, the new Building Safety Bill process includes the introduction of three ‘Gateways‘:

• Gateway 1: before achieving planning permission.
• Gateway 2: before construction begins.
• Gateway 3: before handover.

The gateways are compliance ‘hard stops’, which require the responsible dutyholder to demonstrate to the new Building Safety Regulator (BSR) how they are actively managing risk. If they do not adequately comply, the BSR can stop the project from proceeding to the next stage of development.

The gateways during the Concept, Design and Construction phases align with the eight RIBA Plan of Works 2020 stages as follows:

The key golden thread information listed above must be submitted to the Building Safety Regulator (BSR) before the planning application is submitted.

The updated key Golden Thread information listed above must then be re-submitted to the Building Safety Regulator (BSR) before construction begins.

The updated key information is again presented by the dutyholder. Once the final gateway approval certificate is obtained, the Design and Construction phase dutyholer hands over their specific duties to the Accountable Person (AP). This ensures that the regulatory requirements beyond the gateways are met during the next stage: the Occupation Phase.

With all the information updated and reviewed throughout the Design and Construction Phase, the Golden Thread is presented to the Building Safety Regulator (BSR) for review. Once satisfied, the BSR issues a Building Assurance Certificate (BAC), which permits occupation.

Note: This certificate could include certain conditions, such as requiring last-minute test certificates before a certain date. The certificate and safety case (identification of hazards and how to control inherent risks) is subject to review every five years.

Your responsibility for the Golden Thread never stops. It’s an ever-evolving process that spans across the facility’s full life story.

The Golden Thread is not something you can develop and complete, you can not employ someone to create it and ‘hand it over’. In fact, the recording and updating of building safety information continue up until the final decommissioning and demolition of the building.

Our ‘Operance 4-Step Golden Thread Plan’ breaks down the process of developing the golden thread and in doing start creating a digital estate into four simple, easy to follow steps.

Note: This certificate could include certain conditions, such as requiring last-minute test certificates before a certain date. The certificate and safety case (identification of hazards and how to control inherent risks) is subject to review every five years.

Your responsibility for the Golden Thread never stops. It’s an ever-evolving process that spans across the facility’s full life story.

The Golden Thread is not something you can develop and complete, you can not employ someone to create it and ‘hand it over’. In fact, the recording and updating of building safety information continue up until the final decommissioning and demolition of the building.

Step 1 – Define:

To help organisations take the first step, our Operance information managers develop your organisation information requirements. They help understand your owners, operators and occupiers in-use information needs and create a tailored set of requirements using the expected building safety bill requirements as a foundation.

Step 2 – Curate:

Our award-winning Operance BIM team then helps curate your digital building information on both legacy and new buildings ensuring information is accurate, complete and fit for use.

Step 3 – Access:

Operance O&M is the first purpose-built desktop application to define, curate, audit and maintain the golden thread in one place. It is a common data environment (CDE), O&M coordination tool and supply chain database solution in one. It provides an immutable ‘quantum ledger’, built on blockchain technology, to produce a secure lifecycle record of high-quality building safety and asset information.

Step 4 – Maintain:

Our user-friendly Operance FM mobile application enables owners, operators and occupiers to easily search, share, update and use your building safety and asset information for simple property and facilities management. Our Smart HUG (Home User Guide) extension also enables tenants to access information in line with new building safety legislation.

Bimsense, the company house listed name of Operance has been named the third most exciting tech company in the Business Cloud Tech 50 rankings for Yorkshire and Humberside. Business Cloud provides daily updates on the latest technology and innovation news from the UK and receives approximately 11.8K visitors and 12,974 page impressions per day. Operance, based at the Centre for Digital Innovation [C4DI] in Hull, is one of 6 Hull based businesses to be named in the regionally recognised Tech50 list and is ranked number 1 in Hull. The firm, which recently secured a £250,000 investment and currently undergoing rapid expansion with 10 new employees joining in the next year confirms that this is the first time they have been entered into the Tech 50.

Tim Mutlow, CTO of Operance, said: “I have kept a keen eye on the Tech50 list for a couple of years now. Having seen other familiar C4DI based businesses successfully making the cut, it is clearly one of the strongest regional tech company rankings around”. “Our nomination came as a complete surprise but then receiving as many votes as we did from Business Cloud readers is incredibly humbling and provides an amazing feeling that our team’s creativity and innovation is being recognised in this way.” “It is important to me as CTO that our technology and of course the team behind it, from the UX designers to the developers, and the wider team take the well earned credit for this highly placed ranking. Attempting to organise the world’s building information is not a simple task, I believe you need great people first and foremost in order to build great technology to create something that can be seen as game-changing. “All tech organisations are in a ‘war for talent’ nowadays, so they can attract and retain the best people to build the best products and features for their customers. Being recognised as an exciting tech company obviously helps with this as we build our tech reputation and we can’t wait to show everyone how exciting the future will be too. “Thanks and praise must go to all of the wonderful people who make up the growing Operance family and to our customers whose patronage, loyalty, and constant feedback keeps us passionate that we are doing something amazing and important and keeps us moving forward as a business.”

To speak to one of the team for more information, call 0800 464 3316.

Scott Pilgrim   scott.pilgrim@bimsense.co.uk   0113 3281282   Twitter   LinkedIn

The £250,000 funding is from NPIF – Mercia Equity Finance, which is managed by Mercia Asset Management and is part of the Northern Powerhouse Investment Fund. The news is a breakthrough for the Operance smart building information and facilities management software, which we believe will revolutionise the construction industry through the use of digital technology.

It will enable our parent company, Bimsense, to commercialise Operance and create 10 new jobs over the next two years. The funding marks a major milestone in the development of Bimsense, which was launched four years ago by Ian Yeo and Scott Pilgrim, who had become frustrated by the traditional approach to building design, construction and management. Since then Bimsense has advised property owners, developers and contractors on major developments throughout the UK on how to reduce project risks, while helping to digitally transform their operations. At the same time Bimsense has been continually developing the Operance software to make buildings safer, healthier and more efficient.

Based at the Centre for Digital Innovation (C4DI) tech hub in Hull, Bimsense specialises in building information modelling (BIM), which allows construction projects to be digitally built, before they are physically built, in order to address issues normally identified on site or after completion. BIM helps save time and money, improve quality and reduce potential safety risks, while the data it provides also enables building owners to operate and maintain buildings efficiently over the long term. BIM is widely accepted as the best way to achieve the Government’s aim of reducing construction and operating costs by a third, and is in line with the Grenfell Tower report’s recommendation to create a digital lifecycle record. The new funding will be used to develop further and commercialise Operance, which helps meet this challenge by creating a “golden thread” – a digital audit trail covering the entire history of facilities, enabling better decision making and increased accountability.

Ian Yeo, CEO of Bimsense, said: “We’re delighted and excited to secure this investment to deliver our long-term ambition of digitising and ‘humanising’ building information to help create safer, healthier places for people to live, work and spend their leisure time. “We know the devastating effects that poor, mismanaged information and ill-informed decisions can have on people’s lives. This funding helps us to tackle these issues, by enabling project teams to develop better quality information for end-users to access in a really easy, user-friendly way.”

Maurice Disai, Investment Associate at Mercia, said: “Although construction and property management is the fourth biggest contributor to GDP, it is one of the least digitised sectors. The Operance system could have a huge impact in terms of reducing costs and improving safety and quality of life for building users. “The proof of concept version of this software has already generated a great deal of interest within the industry by showing the cost and performance benefits of using a digital building information platform. The funding will allow Bimsense to further enhance the product and bring it to market.”

Stephen Parnaby OBE, Chair of the Humber Local Enterprise Partnership, said: “We are delighted to see another Humber business benefit from the Northern Powerhouse Investment Fund, which continues to bring vital finance to the region’s businesses. This funding will not only create additional local employment and opportunities within the supply chain, but will also help many other construction companies through its innovative software.”

Mark Wilcockson, of the British Business Bank, said: “Since its launch in 2017, NPIF’s impact on businesses has been wide-ranging, providing funding to launch new products, employ new staff, enter new markets and acquire new facilities. We are pleased that NPIF is continuing to unlock the Humber’s growth potential by supporting small growing businesses with vital investment, particularly those that have the potential to revolutionise their respective sector.” The Northern Powerhouse Investment Fund project is supported financially by the European Union using funding from the European Regional Development Fund (ERDF) as part of the European Structural and Investment Funds Growth Programme 2014-2020 and the European Investment Bank. We would like to take this opportunity to thank our funding partners for their support for our exciting vision and look forward for delivering on the game-changing potential of Operance.

Scott Pilgrim   scott.pilgrim@bimsense.co.uk   0113 3281282   Twitter   LinkedIn

If Data Is The New Oil, Then BIM Is the Combustion Engine…and it’s about to seize up!

How Data Science, Artificial Intelligence and Machine Learning can enable quality BIM. 

In this article, Ian Yeo kindly shares his Bimshow Live 2020 script on how Data Science, Artifical Intelligence (AI), Machine Learning and Deep Learning can enable quality BIM.

Ian provides real in-depth insight into how he uses coding and data science tools, along with a link to the presentation itself via Slideshare and numerous links to the various resorces and platforms we use at both Operance and Bimsense to create, collate, and provide quality BIM data for the benefit of Operance users.

Reccomended Tools

Global Data

Data and information has always been a big part of our lives, but the ease in generating new information and at which we can access this information is making data ever more important (and in many cases essential);

• Data is or should be driving decision making in business and government. 
• The amount of data we are producing has never been greater than it is now. 
• The forecast for the volume of data that we are due to create this year is 50.5 zetabytes (from statista.com), and one zetabyte is 1021 bytes or a 1 with 21 zeros after it. Or 1 trillion Gigabytes.
• The 50.5 zetabytes from this year alone, is equivalent to all the data that we ever produced before 2016.
• This all means that the digital universe has doubled every 2 ½ years. It’s predicted that in the future the doubling of data will reduce to every 2 years, so in 2022 we will generate over 100 zetabytes (100 trillion gigabytes).
• This doubling of data is giving us exponential growth.

This means that if we want to take control of data, there is never a better time to do it and taking control will enable you to gain from the available benefits.

BIM Data

So how does the exponential growth in the data universe directly impact upon us our work and BIM? Firstly our everyday work and our processes are becoming increasingly more digital and increasingly online by using new tools.

As an industry we are finding and generating new sources of information, for example in a relatively short time we have spawned a whole new industry of scanning and modelling existing buildings, which is all based upon gathering millions of geometric data points.

BIM clients want increasingly more data than ever in onerous EIRs. Long gone are the days when the physical building and a couple of ring binders of paperwork were enough to complete a project, we now also handover a whole suite of digital information, often including a digital version (or model representation) of the completed building.

If you carry out repetetive workflows that can be defined in clear steps then it’s almost certain that you can automate it.

Coding can be really beneficial. Coding, when you break it down is just a process of providing a clear sequence of instructions. The instructions are provided in a predefined format and that format is the language. I believe that coding and just simple coding when combined with your expertise can be your superpower!

IFC

It’s common now for EIR’s to require KPI reporting on either model graphical quality or data quality. As an example, an EIR requires that a model uses uniclass classifications and requires a percentage of the completeness of objects and spaces with classifications.

On the surface this appears to be an easy problem, but classifications mean different things to different people and to the application that generated the IFC file, it can be a classification in the strict IFC format. Or what about classifications from the the revit COBie plugin or some other bespoke approach? If an EIR isn’t explicit then it could be that all of those are acceptable.

We wanted our solution to be repeatable and automated, so we use Jupyter Notebooks with Python and Pandas;

1. We produce a Pandas data frame from an IFC file (this does require some adjustments, to make it work, but again, once you have this setup this one process can be reused for all other IFC file work).
2. Then, by a series of Pandas filters we obtain a list and a count of the number of model objects.
3. We then look at objects that have IFC Uniclass classifications and combine this with objects that have classifications through a property or attribute (these steps are not simple, it’s not one to jump into as a trial project) and if a designer uses a different method for classification we just add a couple more rules or instructions (and over time we have a robust method of that covers most method for classifying objects). 

We have an approach where we want to be as flexible as possible, we think there are project benefits in letting teams use the efficient processes that they have evolved rather than change, because we want data in a certain way or format.

It’s actually far easier to setup and run a script than to change a bespoke data type or format into a client or end-user-specific format that is provided, that the data being generated using tried and tested techniques is consistent, and reliable. We use this approach with the BIM data for Operance, afterall, why would we want to exclude models, just because they don’t follow a precise (but arbitrary) format?

What this means is that we have an automated approach where we link to a model, run the script and receive an output of the progress of the classifications. Which goes into a report which again is automated. But as this method uses keyword searches to obtain classifications as properties or attributes, it’s also extendable for obtaining other data such as manufacturer. And then extendable again to search for data for say maintainable assets which have a predefined classifications.

COBie

There are so many automations that we have that involve COBie, most using pandas within a Jupyter notebook where each sheet of a COBie file is imported as a separate data frame. Some of the automated checks are simple such as checking for and removing duplicates, adding documents for asset types and checking for the correct data formats. One that is slightly more complex involves manufacturers and obtaining contact information.

We take a manufacturer name and use various automated searches to find contact information for each manufacturer, their address, a standard contact email and telephone number. This uses a couple of APIs (to find a business address and telephone number), a bit of web crawling (for a standard contact email address), various checks to validate the data, combining all this information together and then saving it back into a COBie file contact sheet.

This doesn’t always produce the correct information, I would say on average 1 in 20 contacts have to be amended, but that means that the other 19 are fully automated. This includes adding the correct manufacturer contact email address to the individual assets types.

We also have also automated the generation of the COBie documents for maintainable assets, all we ask is that the file name that we receive from the contractors has a reference to the asset model number. The script then looks into the folder with the documents and populates the cobie.documents sheet. With other simple scripts for zones and systems.

The more that we use these automations the more valuable they become, every time we are increasing our return on investment.

BCF

We use Solibri as our preferred tool for model checking, from which we export the checks as BCF issues, which allows the project team, with the BIMcollab plugin) to view them in Revit or Archicad. We also provide an Excel export for those that only wish to view a summary of the checks. This is a really useful workflow and an effective way to collaborate.

But, how often do you find that this happens? Say the models just don’t federate correctly (there are various reasons why this doesn’t happen and I’ll not get into the ins and outs of federation) and that the best solution is for the models to always federate correctly. What I will explain is how we manipulate the BCF issues to work collaboratively even if we have different elevations. We want to find solutions to keep the team doing what they are good at.

The different model heights can be solved by establishing the offset error and adjusting the location in Solibri. We can then do the model check and generate all the BCF issues.

The problem comes when the designer with the incorrect model height attempts to view the BCF issues in their model. In the example the models were adjusted by 81.507m which means that the BIMcollab BCF will try to view the issue 81.507m away from the position of the model.

Now BCF issues are just just text files inside various folders within a zip file, and given a .bcf file extension rather than .zip. So with a jupyter notebook running python (and a couple of useful python packages) we have written rules to unzip the bcf file, list and open each file, read the content and then adjust all elevations references by the 81.507m. The content is then saved and repacked into a zip file

All of this is done within a saved jupyter notebook and after linking to the bcf file and providing the height adjustment it’s all fully automated. Of course, once we have this setup it can be extended, to add other useful data to the BCF, for example we have added revit BATIDs of the objects for designers who are not permitted to use the BIMcollab plugin, to enable them to view the objects involved in the issue.

All of those automations that we looked at (and of course all the automations that you are now going to develop and use) are amazing, they enable us to work more efficiently, they will help you to free up time for the creative work that we as humans, rather than machines, are uniquely placed do. 

But all of these automations only enable us to work better, more efficiently and more reliably with our data. Essentially, doing more of the same.

The next step on the data ladder is to use all this data to gain insights and to inform decision making. For example, how do we assess whether a design is optimised for well being, or for space utilisation or CO2 emissions or how can we assess the likelihood of whether a project will finish on time and within budget.

For answers to questions like these where the number of different factors (or variables) are enormous and their interactions are too complex for us to understand the normal tools available to us are just not good enough.

Machine Learning

What we need to do is to use AI and in particular Machine Learning (ML) and a certain type of machine learning known as Deep Learning (DL). This involves us gathering the increasingly large amounts of data and analysing it using state of the art techniques. Deep learning has within the space of 3 or 4 years transformed the accuracy, reliability and quality of AI.

I’m aware that the idea of AI for most people is either something very scary that’s going to take over our lives on route to the apocalypse or is something that has benefits but is only accessible by the tech giants (the google, apple, facebooks and amazons). Neither of those views are correct.

On the first point, machine learning just aggregates lots of data to develop a machine learning model. Once a model has been produced, it takes an input and provides a result. The result is purely what the model assesses as the most likely result. And the most likely result is assessed using all the previous examples which used to make up the machine learning model, what it learnt from. Now I’m quite certain that that deep learning, which is by far the best AI technique that we have isn’t going to result in AI apocalypse, at least not anytime soon.

On the second point AI and machine learning is only for the tech giants. The tech giants are undoubtedly using and benefiting from AI. But the principles of machine learning were developed in academia, this means that it is available to all of us.

And better still there are machine learning tools available to us all. And guess what, most of them can be used in a Jupyter Notebook, using Python, a Pandas dataframe and open source machine learning packages.

Doing Artificial Intelligence

Before we finish here are a couple of examples that we have. The examples are in their early stages of implementation, but they have got to an acceptable level of accuracy for our internal use.

Building on our ability to assess model objects for Uniclass classifications, we have a machine learning model that automatically applies a classification for objects. 

It assesses either an architectural or building services model and then takes data about the object such as IFC type, the object dimensions, the location relative to floor level, the name of the object and 10 other variables. And provides the most likely Uniclass product classification for the object. And it does this using a combination of what is called natural language processing for the object name and a tabular model for the remaining data.

We are using this internally, when we receive a client model for use within Operance which has no or very few classifications. But in theory this could be extended through plugins to directly apply classifications within Revit.

And then finally we have our Operance AI Object Detection where you can take a photo of a building asset, such as a door or a light fitting or a boiler and assess what it is from 130 defined Uniclass products. Go ahead, have a go yourself!

This uses a groundbreaking technique called transfer learning. Transfer learning builds directly on top of some of the largest available data sets (in this case imagenet which has some 14 million images in more than 20,000 categories.) and then adds our new data which for the initial learning uses around 100 images for each of the 130 building asset categories. During training and validation or the model we get an accuracy of around 86%. Which a few years ago would have been viewed as a cutting edge.

To give you an idea of how good this is, a highly cited academic paper from 2016 achieved an accuracy of 85% on just 20 different categories and these were very broad and different categories such as boat, bird and bike. Rather than the quite narrow and similar building assets such as a consumer unit compared to a distribution board and external louvre and an internal ventilation grille.

And this technology is accessible to all of us. Consider how object detection could be integrated into an automated assessment of progress, or assist with labelling site photographs or recording evidence of completed work.

As an industry we are contributing to the exponential increase in data and we we need to use our data more efficiently, but more importantly we need harness the data to gain not just incremental improvements but the step changes that this data can enable

If you want to find out more in your own time, we have provided a webpage where you can find out more and start your journey to turbo charge your BIM engine. This includes some of the best available learning resources (many of which are free) starting from learning the basics at code academy through to learning the cutting edge deep learning techniques from fastai. Plus links to enable you to install all the software.

Imagine if each of you could combine your unique expertise with the power of deep learning, and this expertise is available to other experts,  in no time at all we will have something far more valuable than the sum of the parts, something that will enable us to make real changes to real people.

Thank you for reading this article, my email address is ian.yeo@bimsense.co.uk, I welcome your conversation!

If Data is the New Oil, BIM is the Combustion Engine: Slideshare

[/vc_column_text][/vc_column][vc_column width=”1/6″][/vc_column][/vc_row][vc_row full_width=”stretch_row” css=”.vc_custom_1582656145705{margin-top: 0px !important;margin-bottom: 0px !important;border-top-width: 0px !important;border-bottom-width: 0px !important;padding-top: 0px !important;padding-bottom: 20px !important;}” el_id=”Links”][vc_column width=”1/6″][vc_empty_space][/vc_column][vc_column width=”2/3″][evlt_heading main_heading_text=”Further reading” main_heading_font_size=”18px” main_heading_color=”#26292c” main_heading_css=”font-weight:700 !important;line-height:37px !important;” css=”.vc_custom_1582195822893{margin-top: 0px !important;margin-bottom: 0px !important;border-top-width: 0px !important;border-bottom-width: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”][vc_column_text css=”.vc_custom_1582651810390{margin-top: 0px !important;margin-bottom: 0px !important;border-top-width: 0px !important;border-bottom-width: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

• How to automate the boring stuff: Automate the Boring Stuff
• Learn to code for free: Codecademy (for some really good introductory lessons to python, that require no setup and can run in your browser)
• Learn to code, gain a new skill: Treehouse (another good learning resource with some free courses)
• The world’s largest web developer site: W3schools (provides a reference for most common python commands plus other languages).
• Open-source software, standards, and services: Jupyter (the easiest way to get up and running with jupyter notebooks is to use Anaconda).
• A couple of good starter guides for jupyter notebooks, including how to install: https://realpython.com/jupyter-notebook-introduction/ and https://www.dataquest.io/blog/jupyter-notebook-tutorial/.
• Online community to learn and share​ ​knowledge: Stackoverflow (the no.1 place for answers!).
• The world’s most popular data science platform: Anconda (provides a graphical interface for installing and accessing jupyter notebooks on both windows and macOS).
• Improve your Python skills and deep learning applications: Google Collab (as an alternative to running jupyter notebooks directly on your laptop, use this to get a notebook located in the cloud, up and running in a matter of seconds. Although, this does have the disadvantage of making it harder to access your local file and data).
• The open source deep learning framework from facebook PyTorch https://pytorch.org/ , we don’t directly use PyTorch but instead use the FastAI version https://docs.fast.ai/ which provides a simpler way to access the package