Radio-Frequency-Identification-Based Intelligent Packaging: Electromagnetic Classification of Tropical Fruit Ripening

Occhiuzzi, Cecilia; D'Uva, N.; Nappi, S.; Amendola, S.; Giallucca, Chiara; Chiabrando, V.; Garavaglia, Luigi; Giacalone, Giovanna; Marrocco, Gaetano

doi:10.1109/map.2020.3003212

Cited by 30 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high observed variability among fruits further confirms the non-full reliability of the time-based classification methods currently employed [20] and the value of the proposed strategy. Compared to the previous works [18], the present monitoring platform demonstrated to be capable of retrieving the very early stages of the ripening process (in which the variations of the electromagnetic signals are limited), and hence the trolley can be effectively adopted in the industrial sector, where operators are generally interested in producing fruits ready to be distributed to the consumers rather than ready-to-be-eaten by the consumers [18].…”

Section: Discussionmentioning

confidence: 99%

“…2), whose slope is randomly affected by the fruit variability, the harvest conditions, and by the environmental parameters during the storage. According to the SH levels, four classes (C) of ripening can be considered [18] based on the thresholds {T H n } = {0.9, 0.8, 0.7} (Table I). Typically, at ambient temperature and without forced environmental conditions, the fruits reach the last ripening class in 5-7 days.…”

Section: Rationalementioning

confidence: 99%

“…Thanks to the current advances in RFID-based automatic monitoring of objects [16] and even of people [17], the authors recently proposed the use of RFID technology for monitoring the ripening of avocado packaged for final customer distribution in stores [18]. The system comprises intelligent packaging integrating a single passive UHF RFID tag and a customized reader.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Monitoring of Fruit Ripening Rooms by UHF RFID Sensor Network and Machine Learning

Occhiuzzi,

Camera,

D'Orazio

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Accelerated ripening through the exposure of fruits to controlled environmental conditions and gases is nowadays one of the most assessed food technologies, especially for climacteric and exotic products. However, a fine granularity control of the process and consequently of the quality of the goods is still missing, so the management of the ripening rooms is mainly based on qualitative estimations only. Following the modern paradigms of Industry 4.0, this contribution proposes a nondestructive RFID-based system for the automatic evaluation of the live ripening of avocados. The system, coupled with a properly trained automatic classification algorithm based on Support Vector Machines (SVMs), can discriminate the stage of ripening with an accuracy greater than 85%.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Rationalementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Monitoring of Fruit Ripening Rooms by UHF RFID Sensor Network and Machine Learning

Occhiuzzi,

Camera,

D'Orazio

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [19], they proposed a piecewise nonlinear curve fitting (PWCF) procedure to maintain and present the spectral features of the hyperspectral images, and the error-correcting output code-based support vector machine (ECOC-SVM) was adopted to address the apple bruise grading problem. In [20], they utilized a Radio-frequency identification (RFID) tag as an electromagnetic transducer to convert the chemical-physical change of avocados into a modulation of the electromagnetic parameters when the avocados are ripening. The electromagnetic parameters were fed into a decision trees model to classify the ripeness level of avocados.…”

Section: Related Workmentioning

confidence: 99%

Support Vector Machine and YOLO for a Mobile Food Grading System

Zhu,

Spachos

2021

Preprint

View full text Add to dashboard Cite

Food quality and safety are of great concern to society since it is an essential guarantee not only for human health but also for social development, and stability. Ensuring food quality and safety is a complex process. All food processing stages should be considered, from cultivating, harvesting and storage to preparation and consumption. Grading is one of the essential processes to control food quality. This paper proposed a mobile visual-based system to evaluate food grading. Specifically, the proposed system acquires images of bananas when they are on moving conveyors. A two-layer image processing system based on machine learning is used to grade bananas, and these two layers are allocated on edge devices and cloud servers, respectively. Support Vector Machine (SVM) is the first layer to classify bananas based on an extracted feature vector composed of color and texture features. Then, the a You Only Look Once (YOLO) v3 model further locating the peel's defected area and determining if the inputs belong to the mid-ripened or well-ripened class. According to experimental results, the first layer's performance achieved an accuracy of 98.5% while the accuracy of the second layer is 85.7%, and the overall accuracy is 96.4%.

show abstract

“…ISPs arise in free-space imaging, biomedical diagnostics [2]- [6], subsurface and ground penetrating radar (GPR) investigations [7]- [10], non-destructive testing and evaluation (NDT/NDE) [11]- [14], and through-the-wall imaging (TWI) [15]- [17]. Recently, microwave imaging techniques, based on inverse scattering (IS) formulations, have been also successfully applied to innovative contexts such as, for instance, food quality assessment [18]- [20]. However, solving an ISP is not a trivial task and it poses several challenges due to the intrinsic complexity of the scattering phenomena in the microwave regime described by the Maxwell's equations.…”

Section: Introductionmentioning

confidence: 99%

Learned Global Optimization for Inverse Scattering Problems -- Matching Global Search with Computational Efficiency

Salucci¹,

Poli²,

Rocca³

et al. 2021

Preprint

View full text Add to dashboard Cite

The computationally-efficient solution of fully non-linear microwave inverse scattering problems (ISPs) is addressed. An innovative System-by-Design (SbD) based method is proposed to enable, for the first time to the best of the authors' knowledge, an effective, robust, and time-efficient exploitation of an evolutionary algorithm (EA) to perform the global minimization of the data-mismatch cost function. According to the SbD paradigm as suitably applied to ISPs, the proposed approach founds on (i) a smart re-formulation of the ISP based on the definition of a minimum-dimensionality and representative set of degrees-of-freedom (DoFs) and on (ii) the artificial-intelligence (AI)-driven integration of a customized global search technique with a digital twin (DT) predictor based on the Gaussian Process (GP) theory. Representative numerical and experimental results are provided to assess the effectiveness and the efficiency of the proposed approach also in comparison with competitive state-of-the-art inversion techniques.

show abstract

Radio-Frequency-Identification-Based Intelligent Packaging: Electromagnetic Classification of Tropical Fruit Ripening

Cited by 30 publications

References 33 publications

Automatic Monitoring of Fruit Ripening Rooms by UHF RFID Sensor Network and Machine Learning

Automatic Monitoring of Fruit Ripening Rooms by UHF RFID Sensor Network and Machine Learning

Support Vector Machine and YOLO for a Mobile Food Grading System

Learned Global Optimization for Inverse Scattering Problems -- Matching Global Search with Computational Efficiency

Contact Info

Product

Resources

About