We have worked extensivly in various fields of Photonics, including (but not exclusively) Oxygen Sensing and Food Technology. But we are also working on application of Machine Learning on all kind of photonics use cases.

An overview of our expertise and interests in Sensors.

Research

Computer Vision
- Satellite imaging analysis: land type determination, object as solar panels detection, time development analysis, weather related analysis, etc.
  
  Partners: Lucerne University of Applied Sciences (CH)
- Super resolution techniques in scientific imaging and astrophysics telescope imaging
  
  An example of one of our super resolution algorithms applied to EEMs. We can get an EEM of the quality obtainable in 20 minutes of measurements, by starting from one measured in 2 minutes.
  
  Partners: Zurich University of Applied Sciences (CH), Partners: Max-Planck Institute, Munich, (DE)
- Deblurring Algorithms for imaging and scientific data
  
  Partners: Lucerne University of Applied Sciences (CH), Zurich University of Applied Sciences (CH)
- Excitation and emission matrices analysis (what are EEMs?)
  
  Partners: Zurich University of Applied Sciences (CH)
Artificial Intelligence and Algorithms for Spectroscopy
- We work in several projects in developing algorithms and machine learing approaches for spectroscopy in general. For example we have developed a new algorithm for interference-immune tunable absorption spectroscopy gas sensing by using Fourier Transform in a clever an innovative way. [Michelucci, U., & Venturini, F. (2017). Novel semi-parametric algorithm for interference-immune tunable absorption spectroscopy gas Sensing. Sensors, 17(10), 2281.]
  
  Partners: Zurich University of Applied Sciences
Oxygen Sensing
- we have developed algorithms and have applied machine learning to the problem of oxygen sensing in gases that resulted in 9 publications.
  
  Partners: Zurich University of Applied Sciences (CH)
Food Technology
- We have done extensive research in the application of machine learning (in particular neural networks) to food, and especially to olive oil. We have developed algorithms to classify its quality and to extract important chemical parameters from fluorescence spectra. To achieve this we developed a low-cost sensor that can be used with a Raspberry-Pi to measure fluorescence spectra of oil samples easily and quickly. Several publications on peer-reviewed journals has resulted from years of research in this area.
  
  Partners: Zurich University of Applied Sciences (CH), University of Granada (ES), Politecnico di Torino (IT)
Material Characterisation
- Prof. Dr. Venturini is particulary active in this fields with several years of experience that resulted in multiple publications.
  
  Partners: Zurich University of Applied Sciences (CH)
Sensor development: we develop hardware and software for EDGE sensors that can be deployed and used in rough environments. We are also interested in studying the energy consumption of deep learning and machine learning algorithms on battery operated devices.

Partners: Zurich University of Applied Sciences (CH), Istituto dalle Molle for artificial Intelligence (IDSIA) (CH)

Publications

Food Technology

Venturini, F., Sperti, M., Michelucci, U., Gucciardi, A., M. Martos, V., & Deriu, M. A. (2023). Dataset of Fluorescence Spectra and Chemical Parameters of Olive Oils. Under Review.

[Bibtex]

@article{michelucci-sr-spie,
  title = {Dataset of Fluorescence Spectra and Chemical Parameters of Olive Oils},
  author = {Venturini, Francesca and Sperti, Michela and Michelucci, Umberto and Gucciardi, Arnaud and M. Martos, Vanessa and Deriu, Marco A.},
  journal = {Under Review},
  year = {2023},
  preparation = {true},
  topic = {food}
}

Venturini, F., Sperti, M., Michelucci, U., Gucciardi, A., Martos, V. M., & Deriu, M. A. (2022). Extraction of physicochemical properties from the fluorescence spectrum with 1D convolutional neural networks: Application to olive oil. Journal of Food Engineering, 336, 111198.

[Bibtex]

@article{venturini2023extraction,
  title = {Extraction of physicochemical properties from the fluorescence spectrum with 1D convolutional neural networks: Application to olive oil},
  author = {Venturini, Francesca and Sperti, Michela and Michelucci, Umberto and Gucciardi, Arnaud and Martos, Vanessa M. and Deriu, Marco A.},
  journal = {Journal of Food Engineering},
  volume = {336},
  pages = {111198},
  year = {2022},
  month = sep,
  publisher = {Elsevier},
  selected = {true},
  bibtex_show = {true},
  abbr = {Food},
  topic = {food}
}

Sperti, M., Gucciardi, A., Michelucci, U., Venturini, F., & Deriu, M. A. (2022). Chemical analysis of olive oils from fluorescence spectra thanks to one-dimensional convolutional neural networks. Optical Sensing and Detection VII, 12139.

[Bibtex]

@inproceedings{sperti2022chemical,
  title = {Chemical analysis of olive oils from fluorescence spectra thanks to one-dimensional convolutional neural networks},
  author = {Sperti, Michela and Gucciardi, Arnaud and Michelucci, Umberto and Venturini, Francesca and Deriu, Marco A},
  booktitle = {Optical Sensing and Detection VII},
  volume = {12139},
  year = {2022},
  bibtex_show = {true},
  abbr = {Food},
  topic = {food},
  organization = {SPIE}
}

Arnaud, G., Michelucci, U., Venturini, F., Sperti, M., & Deriu, M. A. (2022). Compact optical fluorescence sensor for food quality control using artificial neural networks: application to olive oil. Optical Sensing and Detection VII, 12139.

[Bibtex]

@inproceedings{arnaud2022compact,
  title = {Compact optical fluorescence sensor for food quality control using artificial neural networks: application to olive oil},
  author = {Arnaud, Gucciardi and Michelucci, Umberto and Venturini, Francesca and Sperti, Michela and Deriu, Marco Agostino},
  booktitle = {Optical Sensing and Detection VII},
  volume = {12139},
  year = {2022},
  bibtex_show = {true},
  abbr = {Food},
  topic = {food},
  organization = {SPIE}
}

Venturini, F., Michelucci, U., Sperti, M., Gucciardi, A., & Deriu, M. A. (2022). One-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge: explainability techniques applied to olive oil fluorescence spectra. Optical Sensing and Detection VII, 12139, 326–333.

[Bibtex]

@inproceedings{venturini2022one,
  title = {One-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge: explainability techniques applied to olive oil fluorescence spectra},
  author = {Venturini, Francesca and Michelucci, Umberto and Sperti, Michela and Gucciardi, Arnaud and Deriu, Marco A},
  booktitle = {Optical Sensing and Detection VII},
  volume = {12139},
  pages = {326--333},
  year = {2022},
  bibtex_show = {true},
  abbr = {Food},
  topic = {food},
  organization = {SPIE}
}

Venturini, F., Sperti, M., Michelucci, U., Herzig, I., Baumgartner, M., Caballero, J. P., Jimenez, A., & Deriu, M. A. (2021). Exploration of Spanish Olive Oil Quality with a Miniaturized Low-Cost Fluorescence Sensor and Machine Learning Techniques. Foods, 10(5). https://doi.org/10.3390/foods10051010
Extra virgin olive oil (EVOO) is the highest quality of olive oil and is characterized by highly beneficial nutritional properties. The large increase in both consumption and fraud, for example through adulteration, creates new challenges and an increasing demand for developing new quality assessment methodologies that are easier and cheaper to perform. As of today, the determination of olive oil quality is performed by producers through chemical analysis and organoleptic evaluation. The chemical analysis requires advanced equipment and chemical knowledge of certified laboratories, and has therefore limited accessibility. In this work a minimalist, portable, and low-cost sensor is presented, which can perform olive oil quality assessment using fluorescence spectroscopy. The potential of the proposed technology is explored by analyzing several olive oils of different quality levels, EVOO, virgin olive oil (VOO), and lampante olive oil (LOO). The spectral data were analyzed using a large number of machine learning methods, including artificial neural networks. The analysis performed in this work demonstrates the possibility of performing the classification of olive oil in the three mentioned classes with an accuracy of 100%. These results confirm that this minimalist low-cost sensor has the potential to substitute expensive and complex chemical analysis.
```
@article{foods10051010,
  author = {Venturini, Francesca and Sperti, Michela and Michelucci, Umberto and Herzig, Ivo and Baumgartner, Michael and Caballero, Josep Palau and Jimenez, Arturo and Deriu, Marco Agostino},
  title = {Exploration of Spanish Olive Oil Quality with a Miniaturized Low-Cost Fluorescence Sensor and Machine Learning Techniques},
  journal = {Foods},
  volume = {10},
  year = {2021},
  number = {5},
  article-number = {1010},
  link = {https://www.mdpi.com/2304-8158/10/5/1010},
  pubmedid = {34066453},
  bibtex_show = {true},
  abbr = {Food},
  topic = {food},
  issn = {2304-8158},
  doi = {10.3390/foods10051010}
}
```

Oxygen Sensing

Venturini, F., Michelucci, U., & Baumgartner, M. (2021). Implementation of multi-task learning neural network architectures for robust industrial optical sensing. Optical Measurement Systems for Industrial Inspection XII, 11782, 117822H.

[Bibtex]

@inproceedings{venturini2021implementation,
  title = {Implementation of multi-task learning neural network architectures for robust industrial optical sensing},
  author = {Venturini, Francesca and Michelucci, Umberto and Baumgartner, Michael},
  booktitle = {Optical Measurement Systems for Industrial Inspection XII},
  volume = {11782},
  pages = {117822H},
  year = {2021},
  bibtex_show = {true},
  abbr = {Sensing},
  topic = {oxygen},
  organization = {International Society for Optics and Photonics}
}

Michelucci, U., & Venturini, F. (2020). New Autonomous Intelligent Sensor Design Approach for Multiple Parameter Inference. Engineering Proceedings, 2(1). https://doi.org/10.3390/engproc2020002096
The determination of multiple parameters via luminescence sensing is of great interest for many applications in different fields, like biosensing and biological imaging, medicine, and diagnostics. The typical approach consists in measuring multiple quantities and in applying complex and frequently just approximated mathematical models to characterize the sensor response. The use of machine learning to extract information from measurements in sensors have been tried in several forms before. But one of the problems with the approaches so far, is the difficulty in getting a training dataset that is representative of the measurements done by the sensor. Additionally, extracting multiple parameters from a single measurement has been so far an impossible problem to solve efficiently in luminescence. In this work a new approach is described for building an autonomous intelligent sensor, which is able to produce the training dataset self-sufficiently, use it for training a neural network, and then use the trained model to do inference on measurements done on the same hardware. For the first time the use of machine learning additionally allows to extract two parameters from one single measurement using multitask learning neural network architectures. This is demonstrated here by a dual oxygen concentration and temperature sensor.
```
@article{engproc2020002096,
  author = {Michelucci, Umberto and Venturini, Francesca},
  title = {New Autonomous Intelligent Sensor Design Approach for Multiple Parameter Inference},
  journal = {Engineering Proceedings},
  volume = {2},
  year = {2020},
  number = {1},
  bibtex_show = {true},
  abbr = {Sensing},
  article-number = {96},
  link = {https://www.mdpi.com/2673-4591/2/1/96},
  issn = {2673-4591},
  topic = {oxygen},
  doi = {10.3390/engproc2020002096}
}
```

Venturini, F., Michelucci, U., & Baumgartner, M. (2020). Deep-learning for multi-parameter luminescence sensing: demonstration of dual sensor. Frontiers in Optics, FTu2B–5.

@inproceedings{venturini2020deep,
  title = {Deep-learning for multi-parameter luminescence sensing: demonstration of dual sensor},
  author = {Venturini, Francesca and Michelucci, Umberto and Baumgartner, Michael},
  booktitle = {Frontiers in Optics},
  pages = {FTu2B--5},
  year = {2020},
  bibtex_show = {true},
  abbr = {Sensing},
  topic = {oxygen},
  organization = {Optical Society of America},
  link = {https://www.osapublishing.org/viewmedia.cfm?uri=FiO-2020-FTu2B.5&seq=0}
}

Venturini, F., Michelucci, U., & Baumgartner, M. (2020). Multi-task learning approach for optical luminescence sensing. Applied Machine Learning Days (AMLD), Lausanne, 25-29 January 2020.

[Bibtex]

@inproceedings{venturini2020multi,
  title = {Multi-task learning approach for optical luminescence sensing},
  author = {Venturini, Francesca and Michelucci, Umberto and Baumgartner, Michael},
  booktitle = {Applied Machine Learning Days (AMLD), Lausanne, 25-29 January 2020},
  bibtex_show = {true},
  abbr = {Sensing},
  topic = {oxygen},
  year = {2020}
}

Venturini, F., Michelucci, U., & Baumgartner, M. (2020). Dual oxygen and temperature sensing with single indicator using multi-task-learning neural networks. Optical Sensing and Detection VI, 11354, 113541C.

@inproceedings{venturini2020dual,
  title = {Dual oxygen and temperature sensing with single indicator using multi-task-learning neural networks},
  author = {Venturini, Francesca and Michelucci, Umberto and Baumgartner, Michael},
  booktitle = {Optical Sensing and Detection VI},
  volume = {11354},
  pages = {113541C},
  year = {2020},
  bibtex_show = {true},
  abbr = {Sensing},
  topic = {oxygen},
  organization = {International Society for Optics and Photonics},
  link = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11354/113541C/Dual-oxygen-and-temperature-sensing-with-single-indicator-using-multi/10.1117/12.2554941.short}
}

Venturini, F., Michelucci, U., & Baumgartner, M. (2020). Dual oxygen and temperature luminescence learning sensor with parallel inference. Sensors, 20(17), 4886.

@article{venturini2020duam,
  title = {Dual oxygen and temperature luminescence learning sensor with parallel inference},
  author = {Venturini, Francesca and Michelucci, Umberto and Baumgartner, Michael},
  journal = {Sensors},
  volume = {20},
  number = {17},
  pages = {4886},
  year = {2020},
  bibtex_show = {true},
  abbr = {Sensing},
  topic = {oxygen},
  publisher = {Multidisciplinary Digital Publishing Institute},
  link = {https://www.mdpi.com/1424-8220/20/17/4886/pdf}
}

Venturini, F., Baumgartner, M., & Michelucci, U. (2019). New approach for luminescence sensing based on machine learning. Optical Data Science II, 10937, 109370H.

@inproceedings{venturini2019new,
  title = {New approach for luminescence sensing based on machine learning},
  author = {Venturini, Francesca and Baumgartner, Michael and Michelucci, Umberto},
  booktitle = {Optical Data Science II},
  volume = {10937},
  pages = {109370H},
  year = {2019},
  bibtex_show = {true},
  abbr = {Sensing},
  topic = {oxygen},
  organization = {International Society for Optics and Photonics},
  link = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/10937/109370H/New-approach-for-luminescence-sensing-based-on-machine-learning/10.1117/12.2508969.short}
}

Michelucci, U., & Venturini, F. (2019). Multi-task learning for multi-dimensional regression: application to luminescence sensing. Applied Sciences, 9(22), 4748.

@article{michelucci2019multi,
  title = {Multi-task learning for multi-dimensional regression: application to luminescence sensing},
  author = {Michelucci, Umberto and Venturini, Francesca},
  journal = {Applied Sciences},
  volume = {9},
  number = {22},
  pages = {4748},
  year = {2019},
  bibtex_show = {true},
  abbr = {Sensing},
  topic = {oxygen},
  publisher = {Multidisciplinary Digital Publishing Institute},
  link = {https://www.mdpi.com/2076-3417/9/22/4748/pdf}
}

Michelucci, U., Baumgartner, M., & Venturini, F. (2019). Optical oxygen sensing with artificial intelligence. Sensors, 19(4), 777.

@article{michelucci2019optical,
  title = {Optical oxygen sensing with artificial intelligence},
  author = {Michelucci, Umberto and Baumgartner, Michael and Venturini, Francesca},
  journal = {Sensors},
  volume = {19},
  number = {4},
  pages = {777},
  year = {2019},
  publisher = {Multidisciplinary Digital Publishing Institute},
  link = {https://www.mdpi.com/1424-8220/19/4/777/pdf},
  bibtex_show = {true},
  topic = {oxygen},
  abbr = {Sensing}
}

Spectroscopy Algorithms

Michelucci, U., & Venturini, F. (2017). Novel semi-parametric algorithm for interference-immune tunable absorption spectroscopy gas Sensing. Sensors, 17(10), 2281.

[Bibtex]

@article{michelucci2017novel,
  title = {Novel semi-parametric algorithm for interference-immune tunable absorption spectroscopy gas Sensing},
  author = {Michelucci, Umberto and Venturini, Francesca},
  journal = {Sensors},
  volume = {17},
  number = {10},
  pages = {2281},
  year = {2017},
  publisher = {Multidisciplinary Digital Publishing Institute},
  bibtex_show = {true},
  topic = {mltheory},
  abbr = {Algorithms}
}

Table of Contents

Research

Publications

Food Technology

Oxygen Sensing

Spectroscopy Algorithms