I’m Imran Shahriar, a structural engineering graduate from UTM (CGPA 3.74) and current MSc student at METU, funded by the YTB Outstanding Merit Scholarship. My thesis focuses on real-time anomaly detection and occupant comfort modeling in tall buildings using SHM, unsupervised machine learning, and mobile app integration. I have previously done peer-reviewed research work in big data analytics of smart cities. I offer remote project support and prototyping services at the intersection of structural health monitoring, data-driven modeling, and smart infrastructure systems. This is ideal for graduate students, research groups, or urban tech startups seeking fast, targeted help with analytics, comfort modeling, or SHM app development.
At SHMatic, I provide digital SHM workflows — from FEM integration and anomaly detection to comfort modeling and academic support. I focus on safe, research-driven, software-based solutions — no hardware installation or safety certification require
I’ve developed structural monitoring workflows for high-rise buildings exposed to wind and seismic activity, combining unsupervised learning, ISO comfort criteria, and mobile app integration. I use clean code, clear visuals, and structured documentation to make sure even complex outputs are intuitive and actionable.
A list of my certifications can be found here:
✔️ SHM-focused thesis under Assoc. Prof. Dr. Ozan Cem Çelik (METU)
Clean vibration or acceleration time-series
Extract RMS, peak, dominant frequency, standard deviation
Visualize trends, detect outliers, prepare datasets for modeling
Build and apply anomaly detection models on clean datasets
Show results with graphs + confidence thresholds
Explain fuzzy membership logic and uncertainty handling
Apply ISO 10137 formulas to RMS acceleration
Simulate occupant comfort zones by floor
Provide visual summaries of comfort class (A–C)
Build a working Flutter UI (with Firebase or dummy JSON)
Features: 1–5 comfort rating, floor select, alert popup
Create a 1-minute walkthrough video or mock install
Build real-time or interactive dashboards
Simulate vibration + wind + comfort feedback + alert overlay
Add dropdowns/sliders for testing scenarios
Help MSc/PhD students write, edit, or structure your SHM/ML methods
Build code snippets, figures, or data tables for publication
Perform structural analysis and design using ETABS and STAAD.Pro for buildings, frames, and foundations
Apply load combinations and checks based on international standards (TBEC 2018, Eurocode, ASCE 7-22) for academic, educational, or exploratory studies.
Deliver structural models, calculation reports, and drawings for academic or professional use
Convert hand-drawn sketches or PDF plans into clean, layered AutoCAD (DWG) drawings
Standardize line weights, layers, hatches, and dimensions for structural/architectural clarity
Set up layout sheets (A1, A3) with title blocks and annotations, and export as print-ready PDF or DWG
Turn raw Excel/Python data into clean dashboards (e.g., material usage, loads, structural response)
Use Power BI / Python / Streamlit to make insights interactive
Build detailed finite element models in Abaqus and SCIA Engineer for structural analysis, load simulations, and stress–strain evaluation
Develop coordinated BIM models in Autodesk Revit with accurate geometry, clash detection, and integrated architectural–structural elements
Generate analysis reports, 3D views, and layout sheets - tailored for academic or professional use
In a 216-meter tall building experiencing intermittent lateral wind anomalies without visible damage, I developed an unsupervised anomaly detection system using autoencoders. After cleaning and standardizing 6DOF acceleration data (3 translational, 3 rotational), I trained the model to learn normal structural behavior and flag deviations based on reconstruction error. This approach enabled near real-time anomaly detection and reduced false positive rates by approximately 40% compared to traditional threshold-based methods.
To address the lack of user-facing tools for capturing perceived comfort during structural events, I developed a mobile application using Flutter and Firebase. The app collects floor-specific feedback from occupants, sends real-time alerts during wind or seismic triggers based on acceleration thresholds, and links user responses to corresponding time-series SHM events. This created a two-way communication channel between residents and the building’s monitoring system, and was successfully deployed as a field-ready prototype for future user studies.
Synthetic Wind-Response Generator + Anomaly Detection
Comfort Threshold Explorer Dashboard (ISO 10137)
Mode Shape Visualizer Using FEM/Modal Analysis Theory
Noise Detection in SHM Signals
... and with your patronage, many more successful projects to come!
More on Projects
🧩 Need help with a data-heavy SHM project?
💻 Want to convert a research method into a working prototype or publishable figure?
📊 Or just want to explore how ML fits into your thesis or digital twin?
Book a free 20-min consultation. Send: goal • data sample • deliverables • deadline → Book now!
Outputs for research/education; licensed review required for design use.
⚖️ SHMatic Disclaimer
SHMatic provides digital workflows, simulations, data analytics, and academic/research support in Structural Health Monitoring (SHM), FEM/BIM, and comfort modeling. These services are intended for educational, exploratory, and research purposes only. SHMatic does not provide licensed professional engineering services, structural certification, or safety-critical approvals. All outputs should be reviewed and verified by a licensed engineer before being used in design, construction, or regulatory contexts.