Nuova ricerca

DANIELE GOLDONI

Dottorando
Dipartimento di Ingegneria "Enzo Ferrari"

Home |


Pubblicazioni

2024 - Machine learning and data augmentation methods for multispectral capacitance images of nanoparticles with nanoelectrodes array biosensors [Articolo su rivista]
Lombardo, F; Pittino, F; Goldoni, D; Selmi, L
abstract

A large number of technology applications still remain where Artificial Intelligence techniques, carefully tailored to the specific application needs, could provide performance benefits to hardware technologies. One such area is biosensing with innovative complementary-metal-oxide-semiconductor nanocapacitor arrays. These sensors operate as powerful imaging platforms but, despite the advancements in the field, the knowledge necessary for precise and robust interpretation of their response to analytes is still largely lacking.In this work, we leverage the ability of Machine Learning methods for computer vision to construct precise and robust models in different operation scenarios. By recognizing the similarity between multifrequency capacitance maps and multispectral images, we identified optimal Machine Learning algorithms to accurately estimate the size of analytes measured by the nanoelectrode array biosensor.As a relevant case study, we focus on measurements of the radius of dielectric spherical nano-particles dispersed in deionized water and phosphate buffer saline. The performance of large, established image-processing neural networks is compared to that of less complex, purposely developed ones. Sizable training data sets are generated by accurate finite element simulations of the sensor response combined with measured data. An excellent accuracy, comparable to traditional sizing technology, is achieved for the task of providing a quantitative measure of the nano-particle radius when the latter is comparable to the pitch of the pixels in the array. We report a size median error below 15% in all scenarios when a few percent of measured data samples is added to the simulation-based training data set.

2023 - Approaches for Nanoparticles Size Estimation with CMOS-based Nano-Capacitors Array Biosensor [Abstract in Atti di Convegno]
Goldoni, Daniele; Lombardo, Federico; Pittino, Federico; Rovati, Luigi; Selmi, Luca
abstract

2023 - Blood-pH Optical Measurement: A Model to Compensate for the Effects of Temperature [Articolo su rivista]
Goldoni, Daniele; Ferrari, Alberto; Piccini, Mattia; Cattini, Stefano; Molinari, Riccardo; Rovati, Luigi
abstract

2023 - Estimation of Analyte's Vertical Positions above the Surface of Nanocapacitor Array Biosensors [Relazione in Atti di Convegno]
Goldoni, Daniele; Ongaro, Claudio; Orazi, Leonardo; Rovati, Luigi; Selmi, Luca
abstract

2023 - Towards Continuous Nano-Plastic Monitoring in Water by High Frequency Impedance Measurement with Nano-Electrode Arrays [Articolo su rivista]
Goldoni, D.; Rovati, L.; Selmi, L.
abstract

We explore the potentiality of high frequency impedance measurements with CMOS nano-electrode arrays for nano-plastic pollutant particles monitoring in water. This technology offers benefits as nano-scale resolution, high parallelization, scalability, label-free single particle detection, and automatic measurements without operator intervention. Simple models are proposed for size and concentration estimation. The former integrates measurements of adjacent electrodes and shows uncertainty comparable to the nominal one with mean prediction error lower than 45 % down to 50 nm radius. The latter accounts for noise in the definition of the sensing volume. We report a worst-case concentration error lower than a factor 1.7 under stationary and continuous flow, which demonstrates the potential of this technology for automated measurements.

2022 - A simple Temperature Correction Technique for a Blood-pH Sensor in Extracorporeal Circulation: a Preliminary Investigation with PBS [Abstract in Atti di Convegno]
Goldoni, Daniele; Ferrari, Alberto; Piccini, Mattia; Cattini, Stefano; Rovati, Luigi
abstract

2022 - A simple method for the preliminary analysis and benchmarking of automotive LiDARs in fog [Relazione in Atti di Convegno]
Cassanelli, D.; Cattini, S.; Di Loro, G.; Di Cecilia, L.; Ferrari, L.; Goldoni, D.; Rovati, L.
abstract

The vast multitude of LiDAR systems currently available on the market makes the need for methods to compare their performances increasingly high. In this study, we focus our attention on the development of a method for the analysis of the effects induced by the fog, one of the main challenges for Advanced Driver Assist Systems (ADASs) and autonomous driving. Large experimental setups capable of reconstructing adverse weather conditions on a large scale in a controlled and repeatable way are certainly the best test conditions to analyze and compare LiDARs performances in the fog. Nonetheless, such large plants are extremely expensive and complex, therefore only available in a few sites in the world. In this study, we thus propose a measurement method, a data analysis procedure and, an experimental setup that are extremely simple and inexpensive to implement. The achievable results are reasonably less accurate than those obtainable with large plants. Nevertheless, the proposed method can allow to easily and quickly obtain a preliminary estimate of the performance in the presence of fog and a rapid benchmarking of different LiDAR systems.

2022 - Towards a Temperature Compensated Model for a Blood-pH Sensor in Extracorporeal Circulation [Relazione in Atti di Convegno]
Goldoni, D.; Ferrari, A.; Piccini, M.; Cattini, S.; Rovati, L.
abstract

Under physiological conditions, the body maintains blood pH within the very narrow range [7.36, 7.44] pH. Small deviations from this range can reveal the onset of pathological states. In this work the performances of a real-time, non-invasive pH measuring sysem for extracorporeal circulation (ECC) are analyzed. In particular, this study focuses on the analysis of the effects that temperature of the measurand may have on the error in estimating blood pH. Indeed, the sensor is based on the analysis of the fluorescence produced by HPTS, which is known to vary with temperature. The extent of such a variation, however, depends on various factors, including the chemical environment. Blood temperature in ECC is often thermostated at 37 °C. Nevertheless, there are treatments in which the blood temperature is varied by a few Celsius degrees, generally reduced, from the physiological temperature of 37 °C. Therefore, the first objective of this study was to evaluate whether a modest reduction in temperature, that is a few Celsius degrees, introduce an error such as the measuring system no longer conforms to the maximum permissible measurement error of ±0.04 pH. Once verified that the temperature-induced error could exceed the limit of ±0.04 pH, a correction factor for temperature compensation was investigated and its robustness to unevenness in the sensor production was explored. The results obtained from this preliminary study performed using Phosphate Buffer Saline (PBS) showed how the addition to the measuring system of a temperature sensor can effectively allow to maintain the measurement error within the ±0.04 pH range, even when the temperature of the measurand decreases by a few degrees from the physiological temperature of 37 °C.