Skip to content

Research and writing

AI in a factory should start from a real problem and real data. The research and articles here come from my own work.

M.Sc. in Digital Technology

Predictive Work Order Management for Semiconductor Production Using the Random Forest Algorithm

Pisarn Boonnuk and Walisa Romsaiyud

KMUTNB Journal of Information Technology (TCI Tier 1), Vol. 23 No. 1, January–June 2027

Accepted for publication after review by three experts

Read the article

Random Forest99.97%F1 98.9%Hist Gradient Boosting96.65%F1 77.46%Logistic Regression79.62%F1 24.19%colour = accuracy, grey = macro F1

AI articles: principles and practice

Published

Floor-First: my way to change an organization, six weeks at a time

A faster take on enterprise architecture: one day on the floor, one decision, an AI-drafted worksheet, a slice in use within two weeks, and a blueprint that fills up from real work.

Published

Enterprise architecture, part 2: business and applications, fitted to the job

Capabilities versus processes, five application design activities, balancing user, business and system, and a table for choosing app types in a factory.

Published

Enterprise architecture, part 4: technology, change and governance

The technical reference model, change management, architecture contracts, how to change the organization so the blueprint is used, and a first-year plan for a factory.

Published

Guide: retire paper forms for a mobile app in five steps

A small-business method, from picking the first form and watching real use to running beside paper and retiring it, with a checklist.

Published

Technology is only one of six dimensions

Six dimensions of reshaping management for digital transformation, with real examples from a factory moving off paper and a small farm.

Published

Building systems with AI: fast without breaking

Six rules from practice: plan first, tests first, verify on the real thing, security now, small reversible steps, people accountable.

Published

AI in the factory starts with the data you already have

Five principles from practice: start from a decision, reuse existing data, measure fully, deploy where people work, keep people in charge.

Published

An edge + cloud smart farm that survives an internet outage

Separate control from analysis, keep data in the right place, and let the board own safety.