A5057708000- Fault Detection and Control Systems
- Spectroscopy and Chemometric Analyses
- Water Quality Monitoring and Analysis
- Mineral Processing and Grinding
- Hepatocellular Carcinoma Treatment and Prognosis
- Target Tracking and Data Fusion in Sensor Networks
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Liver physiology and pathology
- Electrical and Bioimpedance Tomography
- Speech Recognition and Synthesis
- Medical Imaging Techniques and Applications
- Pancreatic and Hepatic Oncology Research
- Geochemistry and Geologic Mapping
- Radiation Detection and Scintillator Technologies
- Liver Disease Diagnosis and Treatment
- Advanced Statistical Process Monitoring
- Spectroscopy Techniques in Biomedical and Chemical Research
- Advanced Chemical Sensor Technologies
University of Coimbra
2021-2024
Dow Chemical (United States)
2024
Wastewater treatment plants (WWTPs) are complex systems presenting stochastic, non-linear, and non-stationary behavior, which makes their operational management very challenging. In this context, data collected from distributed sources across the plant play a central role in optimized operation control of WWTPs. However, even when available, use is far trivial due to coexistence asynchronous measurements, with different granularity, measurements quality (precision, accuracy), multimodal...
The operational management of wastewater treatment plants (WWTP) is a complex activity due to the biological phenomena' intricate nature. This complexity hinders adoption first principles approaches, which lack necessary accuracy be adopted in practice. Data-driven methodologies also face significant challenges processing different information sources available. In this work, we present data-driven and model-agnostic data-fusion framework estimate concentration level toxin effluent, using...
The collection of data from multiple sources with distinct modalities and varying levels quality is pervasive in modern industry. Furthermore, associated each source are often different sampling rates, some may not even have a regular acquisition pattern. These aspects pose significant challenges when developing machine learning (ML) models for predicting target variables, such as product properties, or process key performance indicators (KPIs). Data imputation schemes common solution but...
Sensor fusion aims at synergistically combining different estimators of the same target (called sources) to obtain improved predictions. It is known that performance largely affected by quality individual sources. Unlike existing methods which typically rely on a golden standard data source detect and isolate faulty sensors, we here propose new strategy, called mutual error monitoring sources (MEMS), does not existence reference source. The methodology based assumptions are unbiased...
Decision making and operational management of multiple identical units, equipment, or plants (sources) that are geographically distributed becoming increasingly common. Instead developing a classifier for each source, with much less data representativeness the entire population, this work presents unique centralized using federated approach. The can take into account all collected from sources accommodate their local specific structures correlation patterns. approach has built-in capability...