Artificial intelligence isnât just about T-800s and Skynet or best known as the boogeyman that haunted Stephen Hawkingâs dreams. AI, and everything included under that broad umbrella, is already at work every day to make our lives easier. Machine learning, although not as exciting as other forms of AI, is one of the most helpful and ubiquitous AI applications in use.
Many people think artificial intelligence and machine learning are synonymous with one another, but that isnât the case. Where AI is a broad term denoting the entire concept of erudite machines, machine learning is a specific application of AI more closely related to data mining or statistics. It is a subset of AI that takes data, feeds it to a computer program, and then learns from that data to create a model and, ultimately, a prediction.
Â
See Also:Â McKinsey: When it comes to AI adoption, construction should look to other industries for lessons
Â
But what exactly does learning mean in this context? According to a widely quoted definition from Tom Mitchell, a professor in the Machine Learning Department in the School of Computer Science at Carnegie Mellon University, âA computer program is said to learn from experience âEâ with respect to some class of tasks âTâ and performance measure âPâ if its performance at tasks in âT,â as measured by âP,â improves with experience âE.ââ In short, a computer program is said to have learned if it can improve the outcome of a specific task based on the past experience it has been provided with.
Â
Data streams are crucial to success with machine learning. Here, Perkins+Will created space utilization data visualizations to track and learn from how building occupants use spaces in a building or campus.
Â
Machine Learning in Architecture
At WeWork, a company that specializes in creating co-working and office spaces, machine learning is being used to better determine the correct amount of meeting rooms in a given office building to avoid the stressors for employees associated with there being too few meeting rooms, or the inefficiency of wasted space associated with there being too many.
WeWork uses data about the floor plan of an office and about how past office spaces they have worked on are actually used by employees to train a machine learning system known as a neural network.
The network processes the data it is shown over and over and begins to recognize patterns and learn how employees use the meeting rooms.
After the network has been properly trained, a model is formed. This model is then provided with an input example (e.g., the number of employees or meeting rooms) to create a prediction. It is this prediction that will inform WeWork of the best number of meeting spaces to include in the design and how often they will actually be used.
The more data the neural network is given, the better the model will become and the more accurate the predictions will be. In other words, experience âEâ (the data) is improving the performance measure âPâ (accuracy of predicted occupancy of the meeting rooms vs. the actual occupancy) of the task âTâ (predicting how many meeting rooms are needed based on previously unseen data).
This process creates a feedback loop: buildings provide data that is used to generate a prediction, which informs the design of a more-efficient, better-designed building. That building then provides better data, which will refine the prediction to create an even better building. The machines continue to get smarter and the buildings continue to improve.
WeWork has calculated that machine learning is about 40% more accurate in terms of estimating the predicted occupation of the meeting rooms versus the actual occupation (known as the prediction bias) as compared to human designers. This percentage should only increase as more data is collected and fed into the neural network, and the loop proceeds along its continuous path.
In similar fashion, ZGF Architects is exploring machine learning statistical techniques to build models that identify how specific design elements contribute to overall occupant satisfaction in addition to space use. ZGF uses data it collects on its own, but also incorporates client data from space utilization sensors, GPS tracking, ID badges, and conference room bookings.
âWith more data, the more we can zero in on the factors most responsible for, say, why a certain conference roomâs characteristics make it more successful than those of another conference room,â says Tim Deak, a Workplace Strategist with ZGF. âWeâll also be able to say, with some confidence, how well we can expect a particular design articulation to fare in a similar project setting.â
The process is a combination of high-tech machine learning applications and good old-fashioned gumshoe intuition.
Â
Perkins+Willâs machine learning efforts focus on computer vision and natural language processing to reach what it refers to as âextended intelligence.â Courtesy Perkins+Will.
Â
A picture says a thousand words
The ever-important data that fuels machine learning doesnât just have to be numbers and statistics. Machines can also be trained with images.
ZGF is currently developing a classification tool that will use machine learning to improve how the firm conducts occupancy studies. Before ZGF begins designing a project, the firm evaluates clientsâ existing spaces to better understand how they are being used. This data is then used to inform the team of the best ways to optimize the new project so employees will make the best use of their space.
The current process for accomplishing this task is as straightforward and nontechnical as it gets; the design team will walk the floors to observe and manually tally each employeeâs furniture and equipment setup.
âFor larger client offices, this can take days and multiple people,â says Dane Stokes, Design Technology Specialist with ZGF. âWith machine learning, we intend to drastically streamline the process.â
In the new, streamlined process, designers will capture video of the employee workspaces and use it to train machines to automatically classify the items shown. The tool uses Googleâs robust photo data set to categorize everything from the number of monitors on an employeeâs desk to the specific brand of keyboard or chair used.
If the employee is using an office chair that isnât in Googleâs library, thatâs where the beauty of machine learning comes in. âIf a clientâs preferred brand of office chair isnât in Googleâs library, we will capture 360-degree videos of the chair and train our machines to recognize it,â says Stokes. The next time the machine comes across that chair it will be recognized and categorized immediately. This is referred to as supervised learning. According to Stokes, this process will help save time and money by âvastly reducing the number of human inputs needed, while helping us produce better designs in the future.â
Â
ZGF Workplace Strategist Tim Deak (left) and Design Technology Specialist Dane Stokes (right) share a screenshot of a custom-designed application for facial recognition. The same technology is being used to develop a machine learning tool that will be used to conduct ZGFâs occupancy studies. Courtesy ZGF.
Â
From artificial intelligence to extended intelligence
Most of the current AI and machine learning efforts at Perkins+Will focus on computer vision and natural language processing to reach what it refers to as âextended intelligence,â according to Satya Basu, an Advanced Insights Analyst with P+W.
Computer vision allows graphic outputâa massively critical part of the deliverables of the design processâto be rendered into feature-rich, machine-readable content, which is the first step in generating structured data at scale for both supervised and unsupervised learning.
Next, machine learning processes are leveraged for classification and clustering analyses of projects with different features that can be further blended or combined. Natural language processing is also leveraged on the combined output of labels, features, and descriptions to generate intelligent query and suggestion models.
Â
Machine Learning Glossary
Data set. A collection of examples
Example. One row of a data set. An example contains one or more features and possibly a label.
Feature. An input variable used in making predictions
Label. In supervised learning, the âanswerâ or âresultâ portion of an example
Model. The representation of what a machine learning system has learned from the training data
Neural network. A model that is composed of layers (at least one of which is hidden) consisting of simple connected units followed by nonlinearities
Prediction. A modelâs output when provided with an input example
Prediction bias. A value indicating how far apart the average of predictions is from the average of labels in the data set
Supervised learning. Training a model from input data and its corresponding labels
Training. The process of determining the ideal parameters comprising a model
Unsupervised learning. Training a model to find patterns in a data set, typically an unlabeled data set
Â
Related Stories
AEC Tech | Apr 30, 2024
Lack of organizational readiness is biggest hurdle to artificial intelligence adoption
Managers of companies in the industrial sector, including construction, have bought the hype of artificial intelligence (AI) as a transformative technology, but their organizations are not ready to realize its promise, according to research from IFS, a global cloud enterprise software company. An IFS survey of 1,700 senior decision-makers found that 84% of executives anticipate massive organizational benefits from AI.Â
AEC Innovators | Apr 26, 2024
National Institute of Building Sciences announces Building Innovation 2024 schedule
The National Institute of Building Sciences is hosting its annual Building Innovation conference, May 22-24 at the Capital Hilton in Washington, D.C. BI2024 brings together everyone who impacts the built environment: government agencies, contractors, the private sector, architects, scientists, and more.Â
BIM and Information Technology | Mar 11, 2024
BIM at LOD400: Why Level of Development 400 matters for design and virtual construction
As construction projects grow more complex, producing a building information model at Level of Development 400 (LOD400) can accelerate schedules, increase savings, and reduce risk, writes Stephen E. Blumenbaum, PE, SE, Walter P Moore's Director of Construction Engineering.
AEC Tech | Mar 9, 2024
9 steps for implementing digital transformation in your AEC business
Regardless of a businesses size and type, digital solutions like workflow automation software, AI-based analytics, and integrations can significantly enhance efficiency, productivity, and competitiveness.
AEC Tech | Feb 28, 2024
How to harness LIDAR and BIM technology for precise building data, equipment needs
By following the Scan to Point Cloud + Point Cloud to BIM process, organizations can leverage the power of LIDAR and BIM technology at the same time. This optimizes the documentation of existing building conditions, functions, and equipment needs as a current condition and as a starting point for future physical plant expansion projects.Â
AEC Innovators | Feb 28, 2024
How Suffolk Construction identifies ConTech and PropTech startups for investment, adoptionÂ
Contractor giant Suffolk Construction has invested in 27 ConTech and PropTech companies since 2019 through its Suffolk Technologies venture capital firm. Parker Mundt, Suffolk Technologiesâ Vice PresidentâPlatforms, recently spoke with Building Design+Construction about his companyâs investment strategy.Â
AEC Tech | Jan 24, 2024
4 ways AEC firms can benefit from digital transformation
While going digital might seem like a playground solely for industry giants, the truth is that any company can benefit from the power of technology.
AEC Tech | Jan 8, 2024
What's driving the surge of digital transformation in AEC today?
For centuries, the AEC industry has clung to traditional methods and legacy processesâseated patterns that have bred resistance to change. This has made the adoption of new technologies a slow and hesitant process.
Digital Twin | Jul 31, 2023
Creating the foundation for a Digital Twin
Aligning the BIM model with the ownerâs asset management system is the crucial first step in creating a Digital Twin. By following these guidelines, organizations can harness the power of Digital Twins to optimize facility management, maintenance planning, and decision-making throughout the buildingâs lifecycle.
Digital Twin | Jul 17, 2023
Unlocking the power of digital twins: Maximizing success with OKRs
To effectively capitalize on digital twin technology, owners can align their efforts using objectives and key results (OKRs).