Associative Trails


A selection of thoughts, notes on other people's thoughts, experiences with APIs, tips, tricks, and other stuff.

Migrating a Coldfusion application to Microsoft Azure - setting up a data source
Setting up an encrypted data source for Azure SQL services

Setting up a Coldfusion data source that points to an Azure SQL database is a bit more complicated than usual.

 Read more
Classifying content in bulk
Notes from colleagues about the client contact
The classification, tagging and metadata management of large content repositories should not be a chore

As Eckersley O'Callaghan added more and more content to their intranet, they found keeping it all classified, tagged and linked together was becoming a majorly time-consuming task. Our bulk editing interface made it easy for them.

 Read more
Dealing with short signoff delays in Sling
Notes from colleagues about the client contact
A short delay in signing off needn't bring the whole process to a grinding halt

Following client feedback, we added an extra option in the signoff process to avoid enquiries having to wait while international credit checks and other lengthy approval decisions were made.

 Read more
Responding to prospective client emails promptly and with confidence
Notes from colleagues about the client contact
Sling gives you immediate access to all the important information, without leaving Outlook

By embedding useful contact information directly in Outlook, Sling lets you quickly decide the next step, efficiently capture all the details of a new lead and immediately begin the process of following it up.

 Read more
Deep Learning Architect - Classification for Architectural Design through the Eye of Artificial Intelligence (2018)
Notes on a 2018 paper by Yuji Yoshimura, Bill Cai, Zhoutong Wang, and Carlo Ratti

Using a convolutional neural network to recognise top-level architects' individual styles. Almost 70% or architects can be distinguished with 80% accuracy. 20,000 sample images by 34 past Prisker Prize winners.

 Read more
Architectural Drawings Recognition and Generation through Machine Learning (2018)
Notes on a 2018 paper by Weixin Huang and Hao Zheng

A generative adversarial network to superimpose coloured rectangles on architectural floor plans based on room type (Bedroom, kitchen, etc.). Worked really well for some rooms - it even picked up a few mistakes in the human labelling.

 Read more
OPTIMISING IMAGE CLASSIFICATION - Implementation of Convolutional Neural Network Algorithms to Distinguish Between Plans and Sections within the Architectural, Engineering and Construction (AEC) Industry (2019)
Notes on a 2019 paper by Alessandra Fabbri, M. Hank Haeusler, and Yannis Zavoleas

An attempt to build a convolutional neural network to classify 1000 images into 3 categories. Accuracy peaked at 82%, no hyperparameter tuning was performed.

 Read more
Drawing Recognition. Integrating Machine Learning Systems into Architectural Design Workflows (2020)
Notes on a 2020 paper by Lachlan Brown, Michael Yip, Nicole Gardner, M. Hank Haeusler Haeusler, Nariddh Khan, Yannis Zavoleas, and Christina Ramos

Development of a convolutional neural network for the recognition and labelling of rooms within floor plan images of multi-residential apartments. Trains on 454 floor plan images sorting into 6 categories - claims the results were "satisfactory".

 Read more
Classification of Building Information Model (BIM) Structures with Deep Learning (2018)
Notes on a 2018 paper by Francesco Lomio, Ricardo Farinha, Mauri Laasonen, and Heikki Huttunen

A comparison of different machine learning methods and their accuracy in categorising building use. The deep learning models came out on top, with the model based on ResNet50 performing particularly well. 240 images were used to train the models to sort into three categories.

 Read more
 Jump to top