# Timothy Wong

> Timothy Wong: UK-based data science, machine learning and AI engineering professional. Chartered Statistician (CStat) and Chartered Engineer (CEng).

Timothy (Tim) is an AI/ML professional with over ten years of experience in big data, data science, and analytics applications. His experience spans multiple sectors, including energy, telecommunications, defense and national security. He has a strong, proven track record of delivering complex AI/ML applications in enterprise environments and has led teams of experienced engineers. Tim is also a published researcher in ML and a frequent conference speaker. He is professionally qualified as both a Chartered Statistician (CStat) and a Chartered Engineer (CEng).

## Profile

- [Biography](https://timothywong731.github.io/): Data Science, Machine Learning and AI Engineering
- [TIM-360M: Transformer Inference Model](https://timothywong731.github.io/projects/): A 360M-parameter small language model, trained end-to-end on consumer-grade hardware.
- [linkedin.com/in/timothywong731](https://www.linkedin.com/in/timothywong731)
- [github.com/timothywong731](https://github.com/timothywong731)
- [orcid.org/0000-0003-1943-6448](https://orcid.org/0000-0003-1943-6448)
- [arxiv.org/a/0000-0003-1943-6448](https://arxiv.org/a/0000-0003-1943-6448)
- [x.com/timothywong731](https://x.com/timothywong731)
- [huggingface.co/timothywong731](https://huggingface.co/timothywong731)
- [ollama.com/timothywong731](https://ollama.com/timothywong731)

## Publications

- [Mobile Coverage Analysis using Crowdsourced Geolocation Data](https://timothywong731.github.io/publication/geolocation) (arXiv pre-print (cs.AI), 2025): Effective assessment of mobile network coverage and the precise identification of service weak spots are paramount for network operators striving to enhance user Quality of Experience (QoE). This p...
- [Recurrent Auto-Encoder Model for Large-Scale Industrial Sensor Signal Analysis](https://timothywong731.github.io/publication/sensor) (19th International Conference on Engineering Applications of Neural Networks (EANN 2018), 2018): Recurrent auto-encoder model summarises sequential data through an encoder structure into a fixed-length vector and then reconstructs the original sequence through the decoder structure. The summar...

## Patents

- [Determining Operating State from Complex Sensor Data](https://timothywong731.github.io/patents/rae/): A method of detecting an operating state of a process, system or machine based on sensor signals from a plurality of sensors is disclosed. The method comprises receiving sensor data, the sensor dat...
- [Method of Utility Usage Analysis](https://timothywong731.github.io/patents/flexiscore/): A method and apparatus for analysing utility consumption at a utility supply location is described. The method comprises the steps of: receiving utility consumption data corresponding to utility co...
- [Method and system for detecting anomalies in energy consumption](https://timothywong731.github.io/patents/theft/): A method of detecting conditions indicative of energy meter tampering, meter faults or energy loss (e.g. due to energy theft) is disclosed. The method includes receiving energy consumption data fro...

## Talks

- [Agentic AI Systems for Cloud Migration: Embeddings, Orchestration, and Azure Integration](https://timothywong731.github.io/talks/earl2026) (EARL 2026 (Enterprise Application of the R Language), 2026): Modern cloud migrations require analysing vast volumes of source code, documentation, and architectural metadata, tasks that exceed the limits of manual review and often obscure critical dependenci...
- [Using Linear Programming for Route Planning and Job Scheduling](https://timothywong731.github.io/talks/earl2024) (Enterprise Application of the R Language, 2024): Efficiently managing travel and job scheduling for multiple workers across various locations presents a significant operational challenge. We use a Linear Programming (LP) model to optimise route p...
- [Large-Scale Time Series Forecasting in Apache Spark](https://timothywong731.github.io/talks/earl2019) (EARL 2019 (Enterprise Application of the R Language), 2019): Accurately forecasting power demand is important for securing energy supply. Time series forecasting methods and other machine learning algorithms can be used to create energy forecasts. We have de...
- [Signal Analysis using Deep Learning](https://timothywong731.github.io/talks/hkml2018) (Hong Kong Machine Learning Meetup, 2018): Deep learning models can be used to extract representations for multidimensional time series data. We have used a sensors dataset collected from a large-scale industrial facility to illustrate this...
- [Modelling Field Operation Capacity using Generalised Additive Model and Random Forest](https://timothywong731.github.io/talks/user2018) (The Conference for Users of R (useR!) 2018, 2018): In any customer-facing business, accurately predicting demand ahead of time is of paramount importance*. Workforce capacity can be flexibly scheduled at local area accordingly. In this way, we can ...
- [Generalised Additive Model for Gas Boiler Breakdown Demand Prediction](https://timothywong731.github.io/talks/erum2018) (European R User Meeting 2018 (eRum), 2018): At British Gas, we operate a service and repair business with more than 6,000 qualified engineers ready to serve customers who are urgently in need across the country. Predicting demand accurately ...
- [Deep Neural Network Training and Applications](https://timothywong731.github.io/talks/bristol2018) (Bristol Data Scientists Meeting, 2018): Deep learning models can be used to extract representations for multidimensional time series data. We have used a sensors dataset collected from an industrial-scale compresssor unit to illustrate t...
- [Text Mining for Preventative Maintenance](https://timothywong731.github.io/talks/koln2017) (Köln R User Group, 2017): Large-scale industrial processes are normally comprised of thousands and thousands of individual components which are vulnerable to breakdown. Maintenance of these components is the key to reduce u...
- [Analysing High-Frequency Industrial Component Failure using Text Mining Techniques](https://timothywong731.github.io/talks/earl2017) (EARL 2017 (Effective Application of the R Language), 2017): Centrica plc is an energy service company and its Exploration and Production (E&P) division currently operates several gas production assets across the world. A largescale production asset usua...
- [Parallelised Time Series Spike Detection using R on the Hadoop Platform](https://timothywong731.github.io/talks/user2017) (The Conference for Users of R (useR!) 2017, 2017): Smart meters records continuous stream of electricity consumption for each and every supply point across the United Kingdom. Energy suppliers are interested in understanding customer’s consumption ...
- [Multi-seasonal Time Series Modelling using Recurrent Neural Nets](https://timothywong731.github.io/talks/earl2016) (EARL 2016 (Effective Application of the R Language), 2016): The ability to foresee what’s about to happen is crucial to the success of energy companies like Centrica. For instance, predicting the number of boiler breakdown on any given day allows us to ensu...

## Tutorials

- [Geospatial Optimization](https://timothywong731.github.io/tutorials/geospatial_optimization): This tutorial provides a Linear Programming (LP) approach to determine where stationary sensors should be placed to maximize coverage in a defined area while respecting constraints on sensor count ...
- [Textual Inversion for Stable Diffusion](https://timothywong731.github.io/tutorials/textual_inversion): This tutorial provides a comprehensive guide on using Textual Inversion with the Stable Diffusion model to create personalized embeddings. It covers the significance of preparing diverse and high-q...
- [Using Linear Programming for Route Planning and Job Scheduling](https://timothywong731.github.io/tutorials/scheduling): Efficiently managing travel and job scheduling for multiple engineers across various locations presents a significant operational challenge. We use a Linear Programming (LP) model designed to optim...
- [Linear Programming for Optimal Resources Allocation](https://timothywong731.github.io/tutorials/resourceoptimisation): Using Linear Programming (LP) solver to allocate resources to geographical regions. This generalised example shows how to dynamically allocate engineers to local areas, while satisfying business co...

## Teaching

- [Renewable Energy Systems](https://timothywong731.github.io/teaching/renewables-rhul-2020) (Royal Holloway, University of London, 2020): This guest lecture covers the basics of Transmission and Distribution, and the Balance Mechanism (BM) from a supplier perspective. It also covers demand estimation methodology, especially the Non-H...
- [Business Analytics in R](https://timothywong731.github.io/teaching/r-training) (Various Locations, 2018): R is an open source language for statistical programming. It is widely used among statisticians, academic researchers, and business analysts across the world. This is a three days workshop for busi...