Thesis and Internsips

Here you can find a list of available Bachelor and Master thesis available, along with internships. There may be also novel projects available, so please check with me if you are interested in the topics I work on.

General rules for taking an internship or thesis work with me

I am always happy to work with Bachelor and Master students, and I am glad that you are considering one of the topic I propose. Undergoing a thesis work is a key step in your education, and it is a challenging yet rewarding experience. The following rules are meant to be a guideline so that both you and me can carry the project in an efficient manner.

  • Take your time: a good bachelor thesis requires around 4 months, while a Master thesis can take 6 months or even more. If you are interested in one or more topics, ask in advance, even if you have not finished your exams yet. Moreover, if you are interested in one of the topics listed in this pages, say it upfront.
  • Be efficient with communication: when reporting your work, one email per month is too few, one per day is too much. Be efficient in what you communicate and how you do so.
  • I am not gdb (or similar): do not send me code saying “it does not work”. Explain what you have tried, on what circumstances you experience any problem. Be proactive, be clear.
  • How to write: we will use LaTeX, which may seem difficult at the beginning but you will benefit a lot from it at the later stages. A good tool to share the thesis work is Overleaf.
  • The Internship/thesis is YOUR responsibility: I will not remind you about deadlines, documents to fill, bureaucracy and alike. It is your responsibility to perform these tasks.

Topics

Internet of Things and Web of Things

B.Sc. or M.Sc.TitleAbstractPartnersTopics
BachelorWoT aggregatorDevelop a library which enables the development of WoT controllers able to extend their description with single devices servicesUNIBOWoT, MQTT, CoAP
Thesis in progress
Master
Efficient ECG reconstruction at the EDGEDevelop a an efficient framework which reconstructs and classifies ECG of patients at the EDGEUCI IrvineIoT, e-Health, Neural Networks
Bachelor/MasterMQTT with multiple retention messagesDevelop and test an MQTT broker which enables an extension of the protocol to allow multiple messages to be retained. For a Master thesis, also integrate traffic recognition.IoT, Protocols, MQTT
BachelorExtending the WoT with computation servicesLeverage the WoT definition to extend it towards providing a standardized approach to computing service.CNRartificial intelligence, Web of Things
Bachelor/MasterJoining Context Awareness and PrivacyDevelop a system that makes it possible to evaluate the service quality and privacy issues of a system at design time. These translates into designing a system which abstracts the data needed for both the service to run and the privacy issue to appear, to be able to bridge the gap between the two worlds.context awareness, IoT, privacy
BachelorLocal computation to prevent data leaksExplore the trade-off between service quality and data privacy in ubiquitous systems, when part of the computation can be done locally.UNIBOIoT, application development, privacy
Bachelor/MasterSimulator and Emulator system for IoTDevelop a novel system which makes it possible to realize mixed real and simulated testbeds, where each device can be real or simulated on the PC. There is the need to use docker containers to emulate real performance.UCI IrvineIoT, application development
Bachelor/MasterDevelopment of an autonomous smart home Web of Things architectureLeveraging artificial intelligence techniques and personal smart home hubs, design an architecture which makes it possible to deploy models which can automatically fulfil services requested by users.CNRIoT, WoT, reinforcement learning
Bachelor/MasterDesign and development of a flexible anomaly detection framework for Industry 4.0Anomaly detection is a wide used technique in Industry 4.0 to cover a multitude of services. Right now it is difficult to provide a flexible system which can be easily reconfigured. The objective of the thesis is to fill this gap.DIGIBELT Srlindustry 4.0, application development, artificial intelligence
BachelorPerformance analysis of TinyMLAnalyze the performance of TinyML on different low-power microcontrollersIoT, performance evaluation
Bachelor/MasterIndoor Localization with WiFiDesign and implement algorithms to perform indoor localization through WiFi fingerprinting and triangulationIoT, Indoor Localization

Activity Recognition

B.Sc. or M.Sc.TitleAbstractPartnersTopics
Thesis in progress
Bachelor
Texting and Driving Recognition with Front CameraIdentify whether users are texting and driving using the smartphone front cameraUNIBO, UCI IrvineActivity recognition, Neural Networks
Bachelor/MasterActivity recognition with Continual LearningGiven a dataset of inertial data, perform activity recognition with personalization on the user, leveraging Continual LearningUNIPIContext aware computing, activity-recognition, IoT
Bachelor/MasterActivity recognition with Few Shot LearningGiven a dataset of inertial data, perform activity recognition with personalization on the user, leveraging Few Shot LearningContext aware computing, activity-recognition, IoT
BachelorIdentification of users from inertial sensorsIdentify user based on how they walk, run, and in general perform activities. A complete dataset is already available.Development, sensors, IoT, activity-recognition
Bachelor/MasterSurvey on context awareness tasks and servicesSurvey thesis about the different tasks available in context aware systems. Tasks must be categorized based on data needed, precision, task objective.IoT, context awareness, artificial intelligence

Crowdsensing and Data Science

B.Sc. or M.Sc.TitleAbstractPartnersTopics
BachelorAlternative routes from GPS dataLeveraging open GPS datasets, the goal of this project is to determine whether there are multiple routes in a city which are used by drivers to reach a common point, depending on the time of the day, weather conditions and other parameters.data analysis, openstreetmap
BachelorDetermine the economical benefits of crowdsensingCompute the costs to deploy and maintain an infrastructure to sense specific data. Then it is possible to determine what is the price someone is allowed to pay to users if the same data is obtained through crowdsensing. The system should leverage open data and real parameters.UNIBOcrowdsensing, iot, reward
MasterParticipatory Crowdsensing analysisThrough the use of available data, this work should assess whether user habits exists in participatory crowdsensing.Crowdsensing, data science

Privacy

B.Sc. or M.Sc.TitleAbstractPartnersTopics
BachelorEvaluate different techniques to improve k-anonymityEvaluate different techniques to improve the privacy resilience of datasets.k-anonymity, privacy
MasterLeverage k-anonymity to divide data and improve privacyDivide and anonymyze for k-anonimity. Identify clusters which are hard to separate with k-anonimity and separate them.IMDEA Networksk-anonymity, privacy
MasterIdentify and exploit common points in datasetsDevelop a version of k-anonymity which balances the amount of information which is kept secret and stored locally on a device and the information which is instead shared publicly.IMDEA Networksk-anonymity, privacy
Thesis in progress
Master
Privacy resilience of datasets based on few certaintiesAssess the resilience of datasets against identification attacks, when certainties about the users are gathered through other sourcesRMITprivacy, graph theory
Bachelor/MasterJoining Context Awareness and PrivacyDevelop a system that makes it possible to evaluate the service quality and privacy issues of a system at design time. These translates into designing a system which abstracts the data needed for both the service to run and the privacy issue to appear, to be able to bridge the gap between the two worlds.context awareness, IoT, privacy
Thesis in progress
Bachelor
Local computation to prevent data leaksExplore the trade-off between service quality and data privacy in ubiquitous systems, when part of the computation can be done locally.UNIBOIoT, application development, privacy
MasterUnderstanding how routine habits may uncover privacy issuesStarting from user datasets about routine habits, understand how patterns can highlight specific habits and understand possible issues with the privacy of users.UCI Irvinegraph theory, privacy