# DSTI TechBlog: ideas, systems and projects worth examining . Canonical HTML: https://dsti.school/techblog This Markdown copy is generated from the same DSTI static-site build as the canonical HTML page. It is intended for machine readability and concise retrieval. DSTI  / TechBlog  — research, engineering and work in progress Faculty research, student-built datasets, alumni work in the field, and engineering decisions from inside DSTI School of Engineering. Each article begins with something real: a model, a paper, a repository, a system or a difficult trade-off. > **Figure caption:** Applied Mathematics for AI Models, optimisation and statistical reasoning ![A fitted model curve through observations, with a tangent vector and the area under the curve](https://dsti.school/assets/dsti-techblog-hero-applied-mathematics.07b35d0aa8.svg) > **Figure caption:** Digital Engineering for AI Layered inference graph · forward pass ![A layered inference graph with input, hidden and output nodes, highlighting one forward path](https://dsti.school/assets/dsti-techblog-hero-digital-engineering.94ca5eeb87.svg) 8 substantial articles now published 4 editorial voices across faculty, students, alumni and Team DSTI Open evidence papers, repositories, datasets and engineering records where available ## Published work Equal-weight editorial cards keep the focus on the work itself. Sort by contributor group, or move across research, projects and engineering practice. [Students Cloud data architecture Data engineering · electric vehicles When automotive market analysis becomes a data-engineering problem A Google Cloud workflow connecting vehicle sales, powertrain components, suppliers, pricing and market addressability. Google-Cloud BigQuery electric-vehicles NL Nicolas Len · Data Engineering student at DSTI at the time of the project Read the project account →](https://dsti.school/techblog/cloud-database-electric-vehicle-powertrain-analysis)[Alumni Open-source R R · pharmacological data From complex drug databases to reproducible R workflows How dbparser turns DrugBank, OnSIDES and TWOSIDES into consistent, traceable R objects for reproducible research. R dbparser pharmacovigilance MA Mohammed Ali · DSTI alumnus Read the article →](https://dsti.school/techblog/dbparser-pharmacological-data-r-package)[Faculty AI is tech Semantic Web · knowledge graphs When a link carries meaning Knowledge graphs, Linked Data and open standards: how explicit meaning changes the architecture of AI systems. Semantic-Web Linked-Data knowledge-graphs FG Pr Fabien Gandon Read the article →](https://dsti.school/techblog/semantic-web-linked-data) [Faculty AI is maths Data assimilation · physical models When the model already knows the physics Why intelligent systems should combine observations, optimisation and physical models instead of relearning nature from scratch. data-assimilation optimisation hybrid-ai JB Pr Jacques Blum & Pr Didier Auroux Read the article →](https://dsti.school/techblog/data-assimilation-physics-models) [Students Open dataset & benchmark Multilingual AI · idiom interpretation Building IdiomX: language beyond the literal A reproducible multilingual dataset and four-task benchmark for detecting, retrieving and interpreting idioms across English, Arabic and French. NLP multilingual-ai open-data AS Ayman Ali Sharara · MSc in Data Science & AI Explore the project →](https://dsti.school/techblog/idiomx-multilingual-idiom-understanding) [Alumni IEEE Big Data Cup 2025 Responsible AI · temporal modelling Predicting mental health risk through social media A first-place approach combining LLM post classification with lightweight temporal modelling to forecast an unseen future risk level. LLMs ordinal-classification responsible-ai JC Jannic Alexander Cutura · DSTI alumnus Read the research account →](https://dsti.school/techblog/predicting-mental-health-risk-social-media) [Faculty AI is maths Random Forest · big data Scaling a random forest without losing the statistics Why scaling Random Forest models can change the statistics, and how out-of-bag error and variable importance became VSURF. Random-Forest VSURF machine-learning CM Dr Christine Malot and co-authors Read the article →](https://dsti.school/techblog/random-forest-big-data-machine-learning) [Team DSTI Engineering systems Web architecture · verified delivery Rebuilding dsti.school: eighteen months on the road, three weeks at the keyboard How international field insight became a deterministic, multilingual and AI-portable publishing system without losing the human reasons for building it. web-engineering schema.org AI-portability SC Sébastien Corniglion · Team DSTI Read the engineering account →](https://dsti.school/techblog/rebuilding-dsti-school-spring-2026) ## What the TechBlog covers AI, maths and modelling Methods, assumptions, evaluation and the science beneath intelligent systems. Data and software systems Architecture, deployment, validation, reproducibility and operational trade-offs. Student and alumni projects Work that has become a dataset, repository, paper, product or professional contribution. Engineering education How research, teaching and practice meet inside a specialist school of engineering. ### Have a technical story worth documenting? Students, alumni, faculty and Team DSTI can propose an account grounded in real work, evidence and lessons learned. [Propose an article](https://dsti.school/contact)