Apply now
Postgraduate DiplomaData, AI, Simulation & Analytics Applications open

Diploma in Multimodal Pipelines and Synchronization

Online postgraduate diploma of 800 hours in multimodal pipelines and synchronisation: 8 modules covering multimodal data, time synchronisation with IEEE 1588 (PTP) and IEEE 802.1AS (gPTP), capture and logging, processing pipelines, dataset preparation and real-time multimodal inference, with an assigned technical tutor.

Duration6–8 months
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

Characterise data from different modalities and their requirements.

02

Synchronise sensors using precision time protocols.

03

Log multi-sensor data reliably and reproducibly.

04

Build batch and streaming multimodal processing pipelines.

05

Prepare coherent multimodal datasets for machine learning.

06

Deploy multimodal inference that meets latency requirements.

07

Operate and govern pipelines with quality and security.

Profile

Who it's for

  • Multimodal data engineers building capture and processing chains.
  • Embedded systems engineers working with synchronised sensors.
  • MLOps engineers deploying multimodal models in production.
  • Perception engineers combining cameras, LiDAR, audio and other signals.
  • Data pipeline architects who need precise time alignment across sources.
  • Robotics engineers logging and replaying multi-sensor data.
  • Engineering or science graduates looking to move into the automotive sector.
Standards & tools

What you'll work with

  • IEEE 1588-2019 (PTP) (Precision Time Protocol for networked clock synchronisation)
  • IEEE 802.1AS-2020 (gPTP) (generalised PTP for time-sensitive networks)
  • ASAM MDF 4.2 (measurement data format for logged sensor and bus data)
  • ISO 23150:2023 (data communication between sensors and data fusion unit in vehicles)
  • ISO/IEC 5259-2:2024 (data quality measures for analytics and machine learning)
  • Regulation (EU) 2016/679 (GDPR) (General Data Protection Regulation)
  • SMPTE ST 2059-2 (PTP profile for professional broadcast applications)
  • ROS 2
  • GStreamer
  • NVIDIA DeepStream
  • Apache Kafka
  • Foxglove
Syllabus

8 modules

  1. 1.1Image, audio, text and signal modalities
  2. 1.2Characteristics of each modality
  3. 1.3Heterogeneous sampling rates
  4. 1.4Sensor data and event logs
  5. 1.5Multimodal storage formats
  6. 1.6Storage volume and cost
  7. 1.7Quality according to ISO/IEC 5259
  8. 1.8Metadata and context
  9. 1.9Privacy in multimodal data
  10. 1.10Workshop: inventory of the data sources of an industrial plant
  1. 2.1Clocks, drift and jitter
  2. 2.2The NTP protocol and its limits
  3. 2.3Precision Time Protocol IEEE 1588
  4. 2.4gPTP according to IEEE 802.1AS
  5. 2.5Hardware timestamping
  6. 2.6Hardware triggering and synchronisation
  7. 2.7Post-hoc alignment by correlation
  8. 2.8Interpolation and resampling
  9. 2.9Measuring synchronisation errors
  10. 2.10Lab: camera synchronisation with PTP
  1. 3.1ROS 2 and DDS middleware
  2. 3.2Recording with rosbag2 and MCAP
  3. 3.3The ASAM MDF 4 format
  4. 3.4Logging in vehicles and robots
  5. 3.5Compression of video and point clouds
  6. 3.6Data loss and buffers
  7. 3.7On-board bandwidth and storage
  8. 3.8Deterministic replay of recordings
  9. 3.9Foxglove visualisation tools
  10. 3.10Practical: multi-sensor logging with rosbag2
  1. 4.1Batch and streaming architectures
  2. 4.2Apache Kafka and Flink
  3. 4.3Processing with GStreamer
  4. 4.4Pipelines with NVIDIA DeepStream
  5. 4.5Feature extraction and transformation
  6. 4.6Time-window alignment
  7. 4.7Joins between asynchronous streams
  8. 4.8Backpressure and latency
  9. 4.9Orchestration with Airflow
  10. 4.10Lab: video and audio pipeline with GStreamer
  1. 5.1Multimodal datasets and their organisation
  2. 5.2Synchronised labelling across modalities
  3. 5.3Efficient loaders in PyTorch
  4. 5.4WebDataset and sharded formats
  5. 5.5Consistent data augmentation across modalities
  6. 5.6Handling missing modalities
  7. 5.7Splits without temporal leakage
  8. 5.8Dataset versioning
  9. 5.9Scene catalogues
  10. 5.10Practical: synchronised multimodal dataloader
  1. 6.1End-to-end latency requirements
  2. 6.2Edge inference with Jetson
  3. 6.3Optimisation with TensorRT
  4. 6.4Concurrent execution of models
  5. 6.5GPU resource scheduling
  6. 6.6Synchronisation during inference
  7. 6.7Tolerance to source failures
  8. 6.8Monitoring latency and quality
  9. 6.9Deployment with containers
  10. 6.10Case study: industrial inspection with video and vibration
  1. 7.1Validating synchronisation in production
  2. 7.2Drift detection per modality
  3. 7.3Observability of multimodal streams
  4. 7.4Automated data testing
  5. 7.5Incident management
  6. 7.6Stream security and encryption
  7. 7.7Data protection requirements
  8. 7.8Pipeline documentation
  9. 7.9Operating costs
  10. 7.10Case study: audit of an instrumented-vehicle pipeline
  1. 8.1Definition of sources and requirements
  2. 8.2Synchronisation design
  3. 8.3Data capture and logging
  4. 8.4Processing pipeline
  5. 8.5Dataset preparation
  6. 8.6Real-time inference
  7. 8.7Measurement of latencies and errors
  8. 8.8Conclusions and scaling of the pipeline
  9. 8.9Report and presentation
  10. 8.10Final project: final review with the tutor
Methodology, software & labs

How you'll learn

100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within the intake, so you can combine it with your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is ROS 2, GStreamer, NVIDIA DeepStream, Apache Kafka and Foxglove, in free, academic or evaluation versions. Practical work is based on real procedures for synchronising cameras and sensors with PTP, multi-sensor logging in vehicles and robots, and real-time multimodal inference on edge devices. Assessment is continuous by module, plus the final project.

Standards covered: IEEE 1588-2019 (PTP), IEEE 802.1AS-2020 (gPTP), ASAM MDF 4.2, ISO 23150:2023, ISO/IEC 5259-2:2024, Regulation (EU) 2016/679 (GDPR), SMPTE ST 2059-2.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of IEEE 1588 (PTP), IEEE 802.1AS (gPTP) and ASAM MDF 4.2 applied to real cases, not as a theoretical annex.
Industry software:ROS 2, GStreamer, NVIDIA DeepStream, Apache Kafka and Foxglove, in free, academic or evaluation versions.
Final project:an end-to-end multimodal pipeline, from synchronised capture to real-time inference with measured latencies, reviewed by your tutor.
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.

Sources and requirements
Define the data sources, modalities and latency requirements of the pipeline.
Synchronisation design
Design the time synchronisation scheme with PTP/gPTP and hardware timestamping.
Capture and processing
Log multi-sensor data and build the batch or streaming processing pipeline.
Dataset and inference
Prepare the synchronised dataset and deploy real-time inference on the edge.
Final project
Measure latencies and errors and present the documented pipeline, reviewed by your tutor.
Career opportunities

Where this takes you

Multimodal data engineerEmbedded systems engineerMLOps engineerPerception engineerData pipeline architectRobotics engineer
Admissions & scholarships

Requirements

  • Prior technical training or professional experience in the sector. No university degree is required.
  • An 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 800 hours over 6–8 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with ROS 2, GStreamer, NVIDIA DeepStream, Apache Kafka and Foxglove, 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 final project. 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 are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.

Prior technical training or professional experience in the sector (no university degree required), a computer able to run the programme 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
Postgraduate Diploma1,220 $

Diploma in Robust and Stochastic Optimization

Online postgraduate diploma of 800 hours in robust and stochastic optimisation. 8 modules covering uncertainty modelling, two-stage and multi-stage stochastic programming, chance constraints and CVaR, robust…

6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma1,670 $

Diploma in Partial Twins and Degradation Assessment

Online postgraduate diploma of 800 hours in partial twins and degradation assessment. 8 modules covering physical, reduced-order and hybrid degradation models, Bayesian data assimilation, remaining useful…

6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma1,440 $

Diploma in Value Metrics and Data Monetization

Online postgraduate diploma of 800 hours in data value metrics and monetisation, with 8 modules covering data economics, data value metrics, causal impact measurement, monetisation models,…

6–8 monthsOnlineData, AI, Simulation & Analytics
Diploma in Multimodal Pipelines and SynchronizationEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Diploma in Industrial RAG with Documentation and LogsView programme →Diploma in Technical Storytelling and Dashboard DesignView programme →Diploma in OTA Security and Edge Version ManagementView programme →Diploma in Production Deployment of Solvers and Optimization APIsView programme →Diploma in Anomaly and Attack Detection in GraphsView programme →Diploma in Robust and Stochastic OptimizationView 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.