Apply now
Master'sData, AI, Simulation & Analytics Applications open

Master’s in Time Series, Signals and Edge AI Engineering

Online master's programme of 1,900 hours in time series, signals and edge AI: 12 modules covering discrete signals and systems, digital filtering, time-series analysis, deep learning for series, feature extraction, edge AI hardware, model optimisation, on-device deployment, edge-cloud systems and device security, with an assigned technical tutor.

Duration1900 h
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

Take the controls.

Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Analyse discrete signals in the time and frequency domains.

02

Design efficient digital filters for embedded systems.

03

Model time series with statistical and deep learning methods.

04

Optimise models through quantisation, pruning and distillation.

05

Deploy inference models on microcontrollers.

06

Design distributed edge-cloud architectures with MLOps.

07

Ensure the security of smart devices in line with European regulations.

Profile

Who it's for

  • Embedded AI engineers running inference on microcontrollers and edge modules.
  • Signal processing engineers working with sensor, audio and vibration data.
  • IoT systems developers building connected products and device fleets.
  • Time-series data scientists focused on forecasting and anomaly detection.
  • Firmware engineers adding machine learning to resource-constrained devices.
  • Edge-cloud architects designing hierarchical IoT platforms.
  • Engineering or science graduates aiming to move into consumer electronics.
Standards & tools

What you'll work with

  • ETSI EN 303 645 (cybersecurity for consumer IoT devices)
  • IEC 62443-4-2 (industrial cybersecurity: technical requirements for components)
  • Regulation (EU) 2024/2847 (Cyber Resilience Act) (cybersecurity requirements for products with digital elements)
  • Regulation (EU) 2024/1689 (AI Act) (European Artificial Intelligence Regulation)
  • Directive 2014/53/EU (radio equipment) (Radio Equipment Directive)
  • IEEE 1451.0 (smart transducer interface standard)
  • ISO/IEC 30141 (IoT reference architecture)
  • TensorFlow Lite Micro
  • Edge Impulse
  • MATLAB Signal Processing Toolbox
  • STM32Cube.AI
  • Python with SciPy and statsmodels
Syllabus

12 modules · 1900 h

  1. 1.1Sampling and the Nyquist-Shannon theorem
  2. 1.2Quantisation and converter resolution
  3. 1.3Linear time-invariant systems
  4. 1.4Convolution and impulse response
  5. 1.5The Z-transform and stability
  6. 1.6The discrete Fourier transform
  7. 1.7Power spectral density
  8. 1.8Noise and signal-to-noise ratio
  9. 1.9Typical signals from embedded sensors
  10. 1.10Lab: spectral analysis of accelerometer signals
  1. 2.1FIR filters and the window method
  2. 2.2Butterworth and Chebyshev IIR filters
  3. 2.3Linear phase and group delay
  4. 2.4Decimation and interpolation
  5. 2.5Filters in fixed-point arithmetic
  6. 2.6The linear Kalman filter
  7. 2.7The extended Kalman filter
  8. 2.8Inertial sensor fusion
  9. 2.9Efficient implementation on microcontrollers
  10. 2.10Practical: fixed-point IIR filter on Cortex-M
  1. 3.1Stationarity and unit root tests
  2. 3.2Autocorrelation and partial autocorrelation
  3. 3.3STL decomposition of trend and seasonality
  4. 3.4ARIMA and SARIMA models
  5. 3.5Exponential smoothing and ETS
  6. 3.6State-space models
  7. 3.7Multivariate series and VAR
  8. 3.8Time-based validation and backtesting
  9. 3.9Forecast error metrics
  10. 3.10Lab: SARIMA forecasting of electricity consumption
  1. 4.1LSTM and GRU recurrent networks
  2. 4.2Temporal convolutional networks
  3. 4.3Transformers for time series
  4. 4.4Time-series foundation models
  5. 4.5N-BEATS and N-HiTS
  6. 4.6Probabilistic forecasting with quantiles
  7. 4.7Time-series classification
  8. 4.8Temporal data augmentation
  9. 4.9Self-supervised learning on time series
  10. 4.10Practical: human activity classification with a 1D CNN
  1. 5.1Statistical and spectral features
  2. 5.2The discrete wavelet transform
  3. 5.3MFCC coefficients for audio
  4. 5.4Spectrograms and image representation
  5. 5.5tsfresh and similar libraries
  6. 5.6Feature selection for the edge
  7. 5.7Computational cost per feature
  8. 5.8On-device normalisation
  9. 5.9Sliding windows and overlap
  10. 5.10Workshop: feature pipeline for keyword spotting
  1. 6.1ARM Cortex-M and RISC-V microcontrollers
  2. 6.2Embedded NPU and TPU accelerators
  3. 6.3Jetson platforms and edge modules
  4. 6.4FPGAs for inference
  5. 6.5Memory, power and thermal constraints
  6. 6.6MEMS sensors and interfaces
  7. 6.7In-sensor processing
  8. 6.8MLPerf Tiny benchmarks
  9. 6.9Platform selection by use case
  10. 6.10Case study: comparison of platforms for embedded vision
  1. 7.1Post-training integer quantisation
  2. 7.2Quantisation-aware training
  3. 7.3Structured and unstructured pruning
  4. 7.4Knowledge distillation
  5. 7.5Efficient architecture search
  6. 7.6ONNX and TensorFlow Lite formats
  7. 7.7TVM and similar compilers
  8. 7.8Latency and memory profiling
  9. 7.9The trade-off between accuracy and power consumption
  10. 7.10Lab: INT8 quantisation of a time-series network
  1. 8.1The TensorFlow Lite Micro workflow
  2. 8.2CMSIS-DSP and CMSIS-NN
  3. 8.3Integration with real-time operating systems
  4. 8.4Static memory management
  5. 8.5OTA model updates
  6. 8.6Validation on hardware
  7. 8.7On-device debugging and tracing
  8. 8.8Power consumption and low-power modes
  9. 8.9Firmware security
  10. 8.10Practical: deploying a model on a Cortex-M4 board
  1. 9.1Lightweight anomaly detection
  2. 9.2Compact autoencoders for microcontrollers
  3. 9.3Embedded short-term forecasting
  4. 9.4Acoustic event detection
  5. 9.5Gesture recognition
  6. 9.6Vibration monitoring at the edge
  7. 9.7Adaptive on-device thresholds
  8. 9.8On-device learning
  9. 9.9Selective data aggregation and transmission
  10. 9.10Workshop: embedded vibration anomaly detector
  1. 10.1Hierarchical edge, fog and cloud architectures
  2. 10.2MQTT and CoAP protocols
  3. 10.3Device fleet management
  4. 10.4Federated learning at the edge
  5. 10.5Synchronisation and intermittent connectivity
  6. 10.6Device twins
  7. 10.7MLOps for the edge
  8. 10.8Telemetry and model monitoring
  9. 10.9Scalability and costs
  10. 10.10Lab: device fleet with model updates
  1. 11.1IoT device cybersecurity according to ETSI EN 303 645
  2. 11.2Industrial cybersecurity according to IEC 62443-4-2
  3. 11.3The Cyber Resilience Act
  4. 11.4Data privacy at the edge
  5. 11.5Adversarial attacks on embedded models
  6. 11.6Functional safety and AI
  7. 11.7Electromagnetic compatibility and CE marking
  8. 11.8Hardware reliability in the field
  9. 11.9The AI Act and embedded systems
  10. 11.10Case study: threat analysis of a smart sensor
  1. 12.1Defining the signal problem
  2. 12.2Data acquisition and preparation
  3. 12.3Designing the signal pipeline
  4. 12.4Model training
  5. 12.5Optimisation for the target hardware
  6. 12.6On-device deployment and validation
  7. 12.7Power and latency measurements
  8. 12.8Conclusions and future work at the edge
  9. 12.9Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

100% online training on the SEIUM campus, with downloadable materials, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so the programme fits around your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is TensorFlow Lite Micro, Edge Impulse, MATLAB Signal Processing Toolbox, STM32Cube.AI and Python with SciPy and statsmodels, in free, academic or evaluation versions. Real procedures are studied, such as vibration monitoring with inference on a microcontroller, keyword spotting on low-power devices and embedded energy consumption forecasting. Assessment is continuous by module, plus the final Master's Thesis.

Standards covered: ETSI EN 303 645, IEC 62443-4-2, Regulation (EU) 2024/2847 (Cyber Resilience Act), Regulation (EU) 2024/1689 (AI Act), Directive 2014/53/EU (radio equipment), IEEE 1451.0, ISO/IEC 30141.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of ETSI EN 303 645, IEC 62443-4-2 and the Cyber Resilience Act applied to real cases, not as a theoretical annex.
Industry software:TensorFlow Lite Micro, Edge Impulse, MATLAB Signal Processing Toolbox, STM32Cube.AI and Python with SciPy and statsmodels, in free, academic or evaluation versions.
Master's Thesis with defence:an edge AI project, from data acquisition and signal pipeline design to model optimisation, on-device deployment and power and latency measurements, defended before a panel.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Acquire the signals
Define the signal problem and acquire and prepare the sensor data.
Design the signal pipeline
Apply filtering and feature extraction suited to the target device.
Train and optimise
Train the model and quantise it to INT8 for the target hardware.
Deploy on the device
Deploy the model on a Cortex-M board and measure power and latency.
Master's Thesis
Present the validated edge AI system and future work, defended before a panel.
Career opportunities

Where this takes you

Embedded AI engineerSignal processing engineerIoT systems developerTime-series data scientistFirmware engineerEdge-cloud architect
Admissions & scholarships

Requirements

  • University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
  • Internet connection and a computer capable of running the programme software.
  • English sufficient to read technical standards.

Ready to start?

Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.

Apply now Scholarships
FAQ

Frequently asked questions

The programme totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with TensorFlow Lite Micro, Edge Impulse, MATLAB Signal Processing Toolbox, STM32Cube.AI and Python with SciPy and statsmodels, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.

A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.

Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.

A university degree in engineering, science or architecture (or equivalent professional experience), a computer able to run the software and English sufficient to read technical standards.

Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.

Keep exploring

Related programmes

See all in Data, AI, Simulation & Analytics
Master's9,970 $

Master’s in Causality and Experimentation Engineering

Online master's programme of 1,900 hours in causality and experimentation: 12 modules covering causal frameworks, causal graphs, classical design of experiments, online A/B testing, complex experiments,…

1900 hOnlineData, AI, Simulation & Analytics
Master's9,970 $

Master’s in Reinforcement Learning, Control and Safe AI Engineering

Online master's programme of 1,900 hours in reinforcement learning, control and safe AI engineering. 12 modules covering sequential decision-making, deep RL, model-based learning, classical and modern…

1900 hOnlineData, AI, Simulation & Analytics
Master's6,610 $

Master’s in Optimisation under Uncertainty Engineering

Online master's programme of 1,900 hours in optimisation under uncertainty: 12 modules covering uncertainty in decision-making, scenario models, two-stage and multi-stage stochastic programming, chance constraints, robust…

1900 hOnlineData, AI, Simulation & Analytics
Master’s in Time Series, Signals and Edge AI EngineeringEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Master’s in Reinforcement & Imitation Learning for Control EngineeringView programme →Master’s in Real-Time Analytics and Stream Processing EngineeringView programme →Master’s in Multiphysics Co-Simulation & FMI EngineeringView programme →Master’s in Privacy, Federated and Graph EngineeringView programme →Master’s in Factory and Supply Chain Digital Twins Engineering — Discrete-Event Simulation, WIP/OEE and What-IfView programme →Master’s in Reinforcement Learning, Control and Safe AI EngineeringView programme →

All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.