Published in Towards Data Science·PinnedImage Clustering Implementation with PyTorchLine-by-Line Tutorial Implementation of a Deep Convolutional Neural Network for the Clustering of Mushroom Photos — Supervised image classification with Deep Convolutional Neural Networks (DCNN) is nowadays an established process. With pre-trained template models plus fine-tuning optimization, very high accuracies can be attained for many meaningful applications — like this recent study on medical images, which attains 99.7% …Clustering17 min read
Published in Bioeconomy.XYZ·Sep 1, 2021Patenting as A Business ActSo you have created something innovative. Is it time to call up a patent lawyer? Maybe, maybe not. — The act of trying to obtain a patent — patenting — is one act among many a business can take in competition with other acts as patenting requires both time and money. …Patents35 min read
Published in Bioeconomy.XYZ·Jun 23, 2021The Bioeconomy of Emerging Cancer TherapyPatent Data Analysis and Concept Graph Mining As Means to Learn About Commercial R&D — Patents are essential to gain a foothold in competitive markets of biotechnology and to bring a product to customers. A significant amount of research and development normally precede the creation of the biological product, and for the financial accounting to add up positive, patents have become indispensable to applied biotechnology.Patents18 min read
Published in Towards Data Science·Dec 10, 2020Responses to COVID-19 in Taipei and London — As Revealed By Bike SharingA Spatiotemporal Analysis of Urban Open Data — When, where and how frequent bike rentals take place in a city bike-share system reflect the dynamics of the city. Public bike-share systems are part of the shorter distance transportations of humans in urban transport. …Covid 1913 min read
Published in Towards Data Science·Jun 10, 2020London Bike Ride Forecasting with Graph Convolutional NetworksEnd-to-End PyTorch Deep-Learning from Concept to Validation — A recent addition to the roster of deep-learning methods is the Graph Convolutional Network (GCN). Like its renowned ancestor, the Convolutional Neural Network (CNN), learnable convolution operations are key as a vast number of non-linear relations are strung together between known input and predicted output. …Machine Learning21 min read
Published in Towards Data Science·Mar 17, 2020The Social Graphs in Viral GrowthMeans to Reason About Collective Outcomes from Interpersonal Interactions: Computer Simulations of Mathematical Models — At the time of writing, the coronavirus disease COVID-19, caused by the virus SARS-CoV-2, is spreading over the globe. The virus spreads from a contagious person to another person, and after a time of incubation, the spread might continue to yet another person. In one view of the matter, the…Graph Theory16 min read
Published in Towards Data Science·Feb 24, 2020Countries That Make and Trade PaperDiscovery by Data Visualization for Major Global Industry 1998–2018 — To put it very simply, paper is produced from pulp. Pulp, in turn, is produced from wood, and to a lesser extent straw, bamboo, cotton and other natural sources of fibre. …Data Visualization12 min read
Jan 28, 2020What to Learn From a Doer’s Manifesto On InnovatingReview of Luis Perez-Breva’s Book on Innovating — Innovation is the process of creating something new. But at its genesis, no thing about an innovation is new. That is the starting point of Luis Perez-Breva’s book Innovating — A Doer’s Manifesto from 2016. The book evolved from workshops at MIT on innovating. The title offers two clues to…Innovation10 min read
Published in Towards Data Science·Feb 6, 2019Toronto on Fire in Data, Part 2Modelling Extreme Events and Their Wild Randomness — In this second of a two-part series on fire data analysis from Toronto between 2011 and 2016, I analyze the severity of fires addressed by the Toronto Fire Services (TFS). …Data Science9 min read
Published in Towards Data Science·Feb 6, 2019Toronto on Fire in Data, Part 1Fire Incidents Analysis by Segmentation & Poisson in Practice — Each year the Toronto Fire Services (TFS) are dispatched to between 9,000 and 10,000 fires in the city of 2.7 million inhabitants. The severity ranges from minor fires in grass or rubbish to major fires in warehouses or residential high-rises. …Data Science10 min read
