Goal: The principal objective of this project is to compile and store complex secure applications in the Internet of Things devices with limited computational resources. This process is carried out by integrating encryption, machine learning, and real-time operative system algorithms. Therefore, IoT devices will have the ability to make their own decisions and handle the data to improve their performance.
Goal: In the traditional food transaction, there are many problems, such as lack of trust between customers and businesses, and the information of food trade is easy to tamper. Also, the food industry has realized the great potential of the IoT. In this sector, limited food resources must be managed responsibly to feed as many people as possible. IoT techniques can be used to monitor the entire food supply chain and improve environmental monitoring and control, enabling to monitor crops via sensors, e. g., to detect diseases at an early stage \cite{stach2020}. Smart farming depends on IoT devices to acquire data from environmental conditions from crops and take decisions by machine learning techniques. Typical applications use a few sensors and send data to the cloud repositories. It is a very know-process; however, in an industrial application, when crops are in large fields and different types, it is necessary to develop multiple IoT devices such as wireless sensor networks and mobile robots that send information by sensors and cameras can be implemented.
Goal: The principal project goal is to implement machine learning techniques inside an embedded system (ES) with limited resources. Therefore is necessary to do data cleansing and dimensionality reduction algorithms inside of ES to reduce the computational load and memory ram used for the microprocessor.
The embedded systems acquire data for different sensors applied in areas such: bio-signals, agriculture, education, among others.
Goal: Goal: The objective of this project is to link the field of dimensionality reduction (DR) with that of information visualization (IV), in order to harness the special properties of the latter within DR frameworks. In particular, the properties of controllability and interactivity are of interest, which should make the DR outcomes significantly more understandable and tractable for the (no-necessarily-expert) user. These two properties allow the user to have the freedom to select the best way for representing data. Then, in other words, it can be said that the goal of this project is to develop a DR framework that facilitates an interactive and quick visualization of data representation to make more intelligible the DR outcomes, as well as to allow users modifying the views of data according to their needs in an affordable way.
Goal: The principal project goal is to implement machine learning techniques inside an embedded system (ES) with limited resources. Therefore is necessary to do data cleansing and dimensionality reduction algorithms inside of ES to reduce the computational load and memory ram used for the microprocessor.
The embedded systems acquire data for different sensors applied in areas such: bio-signals, agriculture, education, among others.
Fernando Yépez:
Development and application of heuristic multi-objective optimization methodologies for the control and planning of autonomous vehicle trajectories for the monitoring of environmental conditions in greenhouses. (Ongoing)
Universidad Politécnica de Valencia
Advisor(s): José Vicente Salcedo Romero de Ávila and Paul D. Rosero
Vanessa Alvear:
Hardware accelerators for IoT device analysis in a cloud environment (Ongoing)
Universidad de Salamanca
Advisor(s): Vivian López Batista and Paul D. Rosero
Vanessa Alvear:
Urban Air Pollution Monitoring by Neural Networks and Wireless Sensor Networks Based on LoRa (2020)
Advisor(s): Paul D. Rosero and Jaime Michelena
Universidad Técnica del Norte
Maja Gréta Szász and Kristian Ullum Vind:
Exploration of the application of automatic event detection for on-board satellite processing (2022)
Advisor(s): Sebastian Büttrich and Paul D. Rosero
IT University of Copenhagen
Jacob Søgaard Bøgh
DISCOSAT2: Using machine learning for image selection in constrained small satellite image processing pipelines (2022)
Advisor(s): Julian Charles Philip Priest and Paul D. Rosero
IT University of Copenhagen
Alexander Palsson, Henrik Bellsund, and Emil Krogsgaard:
Smart Farming Robot for Detecting Environmental Conditions in a Greenhouse (2023)
Advisor(s): Paul D. Rosero
IT University of Copenhagen
Booy Vitas Faassen:
A Machine Learning Approach to Identifying Micro-Fractures in Solar Modules (2023)
Advisor(s): Paul D. Rosero
IT University of Copenhagen
Sabrina Fonseca:
Computer Vision for Ocean Exploration: A Study of Data Requirements and Model Adaptation (2023)
Advisor(s): Paul D. Rosero
IT University of Copenhagen
Wei-Jie Wang:
Tiny embedded machine vision for metering (2023)
Advisor(s): Paul D. Rosero
IT University of Copenhagen
Victor Popp:
Efficient ML for CubeSat Environmental Observations (2023)
Advisor(s): Paul D. Rosero
IT University of Copenhagen
Paola Sanipatín:
Recognition of facial expressions through analysis of facial muscle movement patterns using deep learning techniques (2021)
Advisor(s): Paul D. Rosero
Universidad Tecnica del Norte
Wilmer Champutiz:
Pattern recognition of WSN data focused on irrigated by controlled environments of roses on a laboratory scale (2021)
Advisor(s): Paul D. Rosero
Universidad Tecnica del Norte
Cristian Quespaz:
Intelligent route detection vehicle by means of GPS positioning oriented to irrigation by environment at laboratory scale
Advisor(s): Paul D. Rosero
Universidad Tecnica del Norte
Mayra Valencia:
Comparison of dimensionality reduction methods focused on supervised classification algorithms applied to sensor network data.
Advisor(s): Paul D. Rosero
Universidad Tecnica del Norte
Yadira Burbano:
Mobile embedded air quality pattern recognition system in the city of Ibarra (2020)
Advisor(s): Paul D. Rosero
Universidad Tecnica del Norte
Edison Fuentes:
Electronic system for detecting footprint problems using machine learning algorithms (2020)
Advisor(s): Paul D. Rosero
Universidad Tecnica del Norte
Jairo Navarrete:
Prototype GTSB-1 (sign language recognition glove), for people with hearing and language disabilities (2019)
Advisor(s): Paul D. Rosero
Universidad Tecnica del Norte