Eve Bélisle

Classification with Quantification for Air Quality Monitoring

In this paper, a fuzzy classification with quantification algorithm is proposed for solving the air quality monitoring problem using e-noses. When e-noses are used in dynamic outdoor environment, the performance suffers from noise, signal drift and fast-changing natural environment. The question is, how to develop a prediction model capable of detecting as well as quantifying gases effectively and efficiently? The current research work has focused either on detection or quantification of sensor response without taking into account of dynamic factors. In this paper, we propose a new model, namely, Fuzzy Classification with Quantification Model (FCQM) to cope with the above mentioned challenges. To evaluate our model, we conducted extensive experiments on a publicly available datasets generated over a three-year period, and the results demonstrate its superiority over other baseline methods. To our knowledge, gas type detection together with quantification is an unsolved challenge. Our paper provides the first solution for this kind.

Truth Discovery in Material Science Databases

Instead of performing expensive experiments, it is common in industry to make predictions of important material properties based on some existing experimental results. Databases consisting of experimental observations are widely used in the field of Material Science Engineering. However, these databases are expected to be noisy since they rely on human measurements, and also because they are an amalgamation of various independent sources (research papers). Therefore, some conflicting information can be found between various sources. In this paper, we introduce a novel truth discovery approach to reduce the amount of noise and filter the incorrect conflicting information hidden in the scientific databases. Our method ranks the multiple data sources by considering the relationships between them, i.e., the amount of conflicting information and the amount of agreement, and as well eliminates the conflicting information. The scalable Gaussian process interpolation technique (SGP) is then applied to the clean dataset to make predictions of materials property. Comprehensive performance study has been done on a real life scientific database. With our new approach, we are able to highly improve the accuracy of SGP predictions and provide a more reliable database.