Property:OneLineSummary
From ISLAB/CAISR
Jump to navigationJump to searchC
Design and implement synchronized multi-pattern formation (circle, square, hexagon, spiral) for 2–6 Crazyflie drones using Lighthouse positioning and ROS 2/Crazyswarm2, with smooth formation transitions and quantified accuracy/synchronization. +
Courteous robot guide for visitors to an intelligent home +
Cross-Spectrum Ocular Identity Recognition via Deep Learning +
D
Addressing the challenges of data imbalance in Federated Learning +
A study of feature selection and distance measures for clustering big number of categories (>1000) and novelty detection in warehouse environment. +
Data analysis in collaboration with WirelessCar +
Data mining for fault diagnostics in cyberphysical systems +
Data muling services over a constellation of aircraft +
Develop a coordination control between a mobile robot and drone for movement and sharing data of the environment +
develop a machine learning framework for activity recognition and energy consumption forecasting, in collaboration with Volvo Group +
Active Learning to improve data efficiency for LiDAR point Cloud Segmentation +
Designing a deep model that uses decision trees instead of artificial neurons +
In this project, the candidate is supposed to implement a deep graph network that receives a set of graphs as input and returns the predicted next upcoming graph(s). +
The candidate will implement a neural network to detect spatial relations between objects in the scene. For instance, the book is on the table or the spoon is in the cup. +
Construct and optimise Recurrent Neural Networks for industrial applications on machine prognostics; Augmenting industrial data for supervised learning +
In this project, deep clustering will be used on the logged vehicle data (LVD) to find the best representation of vehicles’ operation to explain the behavior of the vehicles over time. +
Deep feature analysis and extraction on Logged Vehicle data for the task of predictive maintenance +
This project is about applying supervised/unsupervised methods of feature selection on Logged Vehicle data (LVD) from Volvo trucks and investigate the contribution in model construction for different predictive maintenance tasks +
Deep learning and Back Order Solutions +
The purpose of this thesis is analyzing a ferry dataset to identify the most optimal path using deep-net. +