Active topics for possible student theses and indivudual/team projects.
We will provide all required hardware and sensors. We also have a lab environment with all lab equipment where you can perform development and experiments.
If you are a bachelor student and feel that you can handle some specific master topic, you can take it and contact us at email@example.com for further discussion.
Topics for BSc students
Automate range hood (also known as kitchen hood or vent hood) working process
- When something is being boiled and steam starts to come out from the pot, range hood starts automatically.
- Depending on the amount of steam, it is possible to automatically change the speed of range hood (2-3 steps).
- When boiling is finished and level of humidty decreases close to the range hood, it stops automatically.
- It is possible to switch range hood to manual and automatic mode.
- It is possible to set range hood humidity sensitivity when it starts and stops (be aware – two independent steps named here).
- Take into account that system should to react to slow humidity changes but more sudden changes as usual cooking in the kitchen is.
- Develop hardware to integrate microcontroller and humidity sensor with few buttons and LEDs (for feedback) to a prototype.
- Develop software that functionality is descibed above.
- Write documentation about the prototype. It must contain hardware architecture, schematic, software block diagram and test results (with the list of tests and conditions).
- Additionally for MSc students: Integate thermal sensor to the system to detect potential food burning.
Smart human presence detector (taken)
Sensor should turn on lights only when human enters to the room. If there something else moving (robot cleaner, etc) then lights should keep stiched off.
- Use Omron D6T type thermal sensor and microcontroller to build a prototype.
- Write software to detect human presence in the area of interest.
- Verify your algorithm by collecting data in different situations and provide accuracy results.
Topics for MSc students
Thermal camera based smart home sensor
Human presence detection is usually done with PIR (passive Infrared) sensor. This sensor does not give any information whether person is still in the area of interest but but moving. Our goal is to identify whether the person has fallen or is still present in that area. Therefore we need to develop mode advanced sensor that is equipped with matrix thermal sensor. Additionally we want to validate could this sensor detect early sign of fire in the room. This tasks includes data collection, model development, model validation and possibly schematic design for physical model, including enclosure design and prototyping with 3D printer.
We already have a basic sensor prototype with 4×4 thermal sensor.
- Data communication over NB-IOT network.
- Data is sent out once per 1 minute or immediately in case of alarm.
- There are two types of alarms: person fall detection, early fire detection.
- Data is sent out using MQTT protocol in JSON format.
- Sensor is battery powered and minimizing power consumption is essential part of the development.
- Enclosure must be designed to change batteries easily.
- Sensor is placed stationary on the wall or to the upper corner of the wall-ceiling.
- Sensor should detect falling in the following conditions
- In the living room distance up to 4-5 meters from the sensor
- Sensor should detect early fire.
- Data collection for algorithm development
- Prepare use-case descriptions, where and how is data collected.
- Develop software to perform data collection and validation.
- Perform data collection for each scenario. Multiple collections for each scnenario are necessary
- Note: You will need to perform experiments with different thermal sensors: 4×4 sensor, 8×8 sensor and 32×32 sensor. Possibly simultaneously.
- Clean up and prepare collected data, label it for usage and algorithm development.
- Expected outcome is a report of performed experiments, processed data for each experiment.
- Algorithms development
- Fall detection algorithm development
- Early fire-detection algorithm development.
- Expected outcome is comparison of results with different sensors running your model and description of the model in pseudo-code.
- Custom designed hardware development. (Could be excluded if hardware engineer is not in the group)
- Expected outcome 1 is a schematic design and PCB layout of sensors, bill of materials.
- Expected outcome 2 is a manufactured PCB and prototype with soldered components that has passed electrical tests and can be programmed.
- Device enclosure development (2-3 iterations with tests)
- Expected outcome is 3D design file of the enclosure and 3D printed enclosure that fits the designed electronics.
- Algorithm validation, accuracy and sensitivity analysis. Algorithm improvements and tunings.
- Expected outcome is algorithm integrated into the prototype that is validated with one fall-detection use cases and one early fire-detection use-cases.
Garage door opening and closing detection algorithm development
Develop neural network model that detects garage door operational status. Door is opened by motor lifting a door up and closed lifting door down. It is possible to stop opening or closing at any time moment by pressing the button. To detect door movement a 3-axis accelerometer is used that measures movements with 100Hz frequency.
Examples of abnormal behaviour of a door
- Movement is not smooth
- Vibrations during the moving
- Door stopped too early until got fully open or closed because of
- One side of the door is blocked
- Door has hit something during the movement
- Door moving speed is different (too fast or slow)
- Someone/something is hanging on the door while door is moving
- Door has damaged
- Door has faulty mechanical parts
- We will provide you several datasets that simulate opening and closing cycles.
- Datasets contain different cycles when door is opening/closing normally or has different faults.
- Dataset features we see useful to use:
- door movement speed
- door movement direction
- door movement linearity
- door movement duration
- door movement starting acceleration until constant speed
- door movement deceleration until stopped
- door vibrations (amplitude and frequency)
- Develop features based on accelerometer data that are listed here or develop your own feature that is not listed here.
- Develop a (machine learning) model based on this available data. Your model should have single output to indicate the status of the door.
- Convert your model for using it on STM32 microcontroller (STM32F429 Discovery Kit) for demonstration with the integrated accelerometer.
- Particular development board has also
- integrated 64Mbit SDRAM
- 2.4′ touchscreen LCD
- 3-axis accelerometer.
- Particular development board has also
- Validate your model with test data and make calculations that include
- Algorithm computational complexity
- Amount of RAM this model needs
- Model accuracy
Vessel cargo plan generation with machine learning algorithm
We have developed smart card deck solution to automate cargo loading and unloading process between the port and vessel during years long R&D project with one of the largest ferry operator in Baltic region. Among other developments we have automated cargo planning on the vessel that has always been done manually. Placing a vehicle to the vessel there are a lot of constraints that are important:
- Vehicle dimensions, weight, type
- The order when they arrive to the vessel
- Priority and VIP classes, dangerous vehicles, etc
- Ship stability system to keep vessel in balance during the (un)loading
Current vehicle placement algorithm is based on different constraints. There is a need for an algorithm that can learn over time about each departure. There is a dataset about 5000 departures that consists information what kind of vehicle is placed on which card deck an on which location. This data could be used for teaching the algorithm
- Research about input data, ship constraints, priorities and other data required to take into account for cargoplan generation.
- Develop a machine learning model to use for cargo plan generation
- Prepare dataset for training
- Train algorithm and validate its accuracy.
Facial recognition with embedded hardware
We have a facial recognition model that has been used for some time in smart elevator project that recognizes and learns all new faces automatically. We need to improve the model accuracy and modify it to run it on embedded hardware. This requires understanding the model and trying to find ways to optimize its speed and size.
- Find optimal hardware configuration that could handle high resolution camera image and could perform real-time facial recognition.
- Take the existing facial recognition algorithm and find methods how to increase its accuracy. Test its accuracy after model tuning.
- Implement the algorithm on embedded hardware and optimize the model to speed it up (if needed).
Camera based person tracking and location detection on embedded hardware (taken)
We need to detect the person location in the field of camera and track his or her movement. Location of the person is calculated based on the camera location. Detection of the person an be done with image processing or person detection methods and it is up to the student to decide which way to choose. Model must work on embedded hardware and must therefore be lightweight. Person location tracking should be either in real-time or near real-time. This solution is intended to work indoor situations.
- Research about possible methods how to perform person detection on embedded hardware and implement one of those methods and make experiments to validate the accuracy in different conditions.
- Research about possible methods how to map person location based on the camera. Implement one method and validate the accuracy in different conditions.
Camera based person activity classification on embedded hardware (taken)
We need to develop a human tracking and activity classification model that can run on embedded hardware to process all data locally. Camera is used indoor, located at the corner of the room. Goal is to predict activity detection for any time moment.
- Research about person activity classification methods that are suitable for using on embedded hardware
- Implement chosen activity classification algorithm on embedded hardware (Jetson Nano or similar)
- Perform experiments for different types of activities and calculate accuracy for each activity type and with different camera configurations.
- You may also need to use pose detection models like posenet.
- On-device, Real-time Body Pose Tracking with MediaPipe BlazePose
Radar and camera based object detection for critical infrastructure (taken)
- Research questions:
- Research possible radar and camera hardware solutions for object detection.
- Develop a model how to perform object detection and classification using both sensors.
- Develop software for selected hardware and perform initial tests for experiments.
- Perform experiments and analyze results.