Periodic Reporting for period 1 - DATAMINE4.0 (Advanced Data Modeling and Analysis Applied to next Generation Industry 4.0 settings and the Internet of Things)
Période du rapport: 2018-01-22 au 2020-01-21
The goal of the DataMining4.0 project is to identify the most promising data mining techniques and its applications in the context of Industry4.0 where incorporation of “intelligent” techniques in industrial processes is a central theme, and to execute several “data project” case studies. In particular, the project objective is to build calibration and optimisation models using advanced statistical and machine learning methods, for applications in which existing methods have been unsatisfactory.
We considered the following applications: 1) food processing - detection of foreign matter in food with help of hyper-spectral imaging, 2) agriculture - forecast of the rice blast disease, and 3) human-robot collaborative application - object detection problem. These applications require very high prediction accuracy, and even a small improvement in the accuracy can have a high impact in a long run (for example, less food waste in food processing application).
We considered the following applications: 1) food processing - detection of foreign matter in food with help of hyper-spectral imaging, 2) agriculture - forecast of the rice blast disease, and 3) human-robot collaborative application - object detection problem. These applications require very high prediction accuracy, and even a small improvement in the accuracy can have a high impact in a long run (for example, less food waste in food processing application).
The results achieved by the project are the following.
1. We developed a novel machine learning model for anomaly detection in hyperspectral images for the application of the detection of foreign matter in food. The model uses the recent advances in the unsupervised machine learning modelling, in particular the use of autoencoders for the purpose of dimensionality reduction.This model was tested in a pre-industrial setting with an IRIS proprietary hyperspectral camera. The tests have shown an improvement over the methods traditionally used in chemometrics.
2.We trained a forecasting model for the detection of the rice blast disease. The model is based on a recurrent neural network, which is one of the state-of-the art models for time series data. Our approach has shown an advantage in several cases over the 'process-based' models traditionally used for this application.
3. We trained an object detection model for a robotic application. We used one of the state-of-the-art model called YOLOv3. The model is a trained on artificial images obtained by a simulator of a robotic application. The study confirmed usefulness of the YOLOv3 model for this kind of images.
The results were disseminated through one published conference paper, submission of two journal papers of which one is published and another one is under the revision process, and a poster presentation on a conference. All mentioned scientific papers were peer-reviewed.
1. We developed a novel machine learning model for anomaly detection in hyperspectral images for the application of the detection of foreign matter in food. The model uses the recent advances in the unsupervised machine learning modelling, in particular the use of autoencoders for the purpose of dimensionality reduction.This model was tested in a pre-industrial setting with an IRIS proprietary hyperspectral camera. The tests have shown an improvement over the methods traditionally used in chemometrics.
2.We trained a forecasting model for the detection of the rice blast disease. The model is based on a recurrent neural network, which is one of the state-of-the art models for time series data. Our approach has shown an advantage in several cases over the 'process-based' models traditionally used for this application.
3. We trained an object detection model for a robotic application. We used one of the state-of-the-art model called YOLOv3. The model is a trained on artificial images obtained by a simulator of a robotic application. The study confirmed usefulness of the YOLOv3 model for this kind of images.
The results were disseminated through one published conference paper, submission of two journal papers of which one is published and another one is under the revision process, and a poster presentation on a conference. All mentioned scientific papers were peer-reviewed.
We have achieved a progress beyond the state of the art for analysis of hyperspectral images in Chemometrics, in particular for anomaly detection in hyperspectral images. This is due to the transfer knowledge from the new advanced techniques in the field of Machine Learning which are not widely known in the field of Chemometrics. Our model have shown very promising results in a pre-industrial setting for detection of foreign matter in food, not only on the surface but also several millimetres in-depth. The use of hyperspectral images with sophisticated image analysis techniques have a potential to improve the food quality control regarding food safety in food processing facilities as well as regarding fraud.