scholarly journals Vibrational Spectroscopy Coupled to a Multivariate Analysis Tiered Approach for Argentinean Honey Provenance Confirmation

Foods ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1450
Author(s):  
Tito Damiani ◽  
Rosa M. Alonso-Salces ◽  
Inés Aubone ◽  
Vincent Baeten ◽  
Quentin Arnould ◽  
...  
Keyword(s):  
Data Fusion ◽  
Cost Benefit ◽  
Classification Performance ◽  
Spectroscopic Techniques ◽  
Food Authentication ◽  
Prediction Ability ◽  
Fast Screening ◽  
Level Data ◽  
Ft Raman Spectroscopy ◽  
High Level

In the present work, the provenance discrimination of Argentinian honeys was used as case study to compare the capabilities of three spectroscopic techniques as fast screening platforms for honey authentication purposes. Multifloral honeys were collected among three main honey-producing regions of Argentina over four harvesting seasons. Each sample was fingerprinted by FT-MIR, NIR and FT-Raman spectroscopy. The spectroscopic platforms were compared on the basis of the classification performance achieved under a supervised chemometric approach. Furthermore, low- mid- and high-level data fusion were attempted in order to enhance the classification results. Finally, the best-performing solution underwent to SIMCA modelling with the purpose of reproducing a food authentication scenario. All the developed classification models underwent to a “year-by-year” validation strategy, enabling a sound assessment of their long-term robustness and excluding any issue of model overfitting. Excellent classification scores were achieved by all the technologies and nearly perfect classification was provided by FT-MIR. All the data fusion strategies provided satisfying outcomes, with the mid- and high-level approaches outperforming the low-level data fusion. However, no significant advantage over the FT-MIR alone was obtained. SIMCA modelling of FT-MIR data produced highly sensitive and specific models and an overall prediction ability improvement was achieved when more harvesting seasons were used for the model calibration (86.7% sensitivity and 91.1% specificity). The results obtained in the present work suggested the major potential of FT-MIR for fingerprinting-based honey authentication and demonstrated that accuracy levels that may be commercially useful can be reached. On the other hand, the combination of multiple vibrational spectroscopic fingerprints represents a choice that should be carefully evaluated from a cost/benefit standpoint within the industrial context.

scholarly journals Data Fusion of Fourier Transform Mid-Infrared (MIR) and Near-Infrared (NIR) Spectroscopies to Identify Geographical Origin of Wild Paris polyphylla var. yunnanensis

Molecules ◽  
2019 ◽  
Vol 24 (14) ◽  
pp. 2559 ◽  
Author(s):  
Pei ◽  
Zuo ◽  
Zhang ◽  
Wang
Keyword(s):  
Fourier Transform ◽  
Data Fusion ◽  
Near Infrared ◽  
Geographical Origin ◽  
Spectroscopic Techniques ◽  
Mid Infrared ◽  
Level Data ◽  
Paris Polyphylla ◽  
High Level ◽  
Geographical Origin Traceability

Origin traceability is important for controlling the effect of Chinese medicinal materials and Chinese patent medicines. Paris polyphylla var. yunnanensis is widely distributed and well-known all over the world. In our study, two spectroscopic techniques (Fourier transform mid-infrared (FT-MIR) and near-infrared (NIR)) were applied for the geographical origin traceability of 196 wild P. yunnanensis samples combined with low-, mid-, and high-level data fusion strategies. Partial least squares discriminant analysis (PLS-DA) and random forest (RF) were used to establish classification models. Feature variables extraction (principal component analysis—PCA) and important variables selection models (recursive feature elimination and Boruta) were applied for geographical origin traceability, while the classification ability of models with the former model is better than with the latter. FT-MIR spectra are considered to contribute more than NIR spectra. Besides, the result of high-level data fusion based on principal components (PCs) feature variables extraction is satisfactory with an accuracy of 100%. Hence, data fusion of FT-MIR and NIR signals can effectively identify the geographical origin of wild P. yunnanensis.

A Threat Assessment Method Based on Hierarchies and Modules

2014 ◽  
Vol 18 (1) ◽  
pp. 93-99
Author(s):  
Fang Deng ◽  
◽  
Xinan Liu ◽  
Zhihong Peng ◽  
Jie Chen
Keyword(s):  
Data Fusion ◽  
Threat Assessment ◽  
Assessment Method ◽  
Fusion Technology ◽  
Low Level ◽  
Information Classification ◽  
Level Data ◽  
High Level

With the development of low-level data fusion technology, threat assessment, which is a part of high-level data fusion, is recognized by an increasing numbers of people. However, the method to solve the problem of threat assessment for various kinds of targets and attacks is unknown. Hence, a threat assessment method is proposed in this paper to solve this problem. This method includes tertiary assessments: information classification, reorganization, and summary. In the tertiary assessments model, various threats with multi-class targets and attacks can be comprehensively assessed. A case study with specific algorithms and scenarios is shown to prove the validity and rationality of this method.

High Level Data Fusion on a Multimodal Interactive Applications Platform

2008 ◽  
Author(s):  
Olga Vybornova ◽  
Hildeberto Mendona ◽  
Jean-Yves Lionel Lawson ◽  
Benoit Macq
Keyword(s):  
Data Fusion ◽  
Interactive Applications ◽  
Level Data ◽  
High Level

scholarly journals Conflict resolution using relation classification: High-level data fusion in data integration

2021 ◽  
pp. 14-14
Author(s):  
Zeinab Nakhaei ◽  
Ali Ahmadi ◽  
Arash Sharifi ◽  
Kambiz Badie
Keyword(s):  
Machine Learning ◽  
Conflict Resolution ◽  
Data Integration ◽  
Data Fusion ◽  
Estimated Parameters ◽  
True Value ◽  
Level Data ◽  
Fusion Methods ◽  
Relation Classification ◽  
High Level

The aim of conflict resolution in data integration systems is to identify the true values from among different and conflicting claims about a single entity provided by different data sources. Most data fusion methods for resolving conflicts between entities are based on two estimated parameters: the truthfulness of data and the trustworthiness of sources. The relations between entities are however an additional source of information that can be used in conflict resolution. In this article, we seek to bridge the gap between two important broad areas, relation estimation and truth discovery, and to demonstrate that there is a natural synergistic relationship between machine learning and data fusion. Specifically, we use relational machine learning methods to estimate the relations between entities, and then use these relations to estimate the true value using some fusion functions. An evaluation of the results shows that our proposed approach outperforms existing conflict resolution techniques, especially where there are few reliable sources.

scholarly journals Detecting Food Fraud in Extra Virgin Olive Oil Using a Prototype Portable Hyphenated Photonics Sensor

2020 ◽  
Author(s):  
Yannick Weesepoel ◽  
Martin Alewijn ◽  
Michiel Wijtten ◽  
Judith Müller-Maatsch
Keyword(s):  
Data Fusion ◽  
Olive Oil ◽  
Near Infrared ◽  
Edible Oils ◽  
Virgin Olive Oil ◽  
Extra Virgin Olive Oil ◽  
Food Fraud ◽  
Olive Oils ◽  
Level Data ◽  
High Level

Abstract Background Current developments in portable photonic devices for fast authentication of extra virgin olive oil (EVOO) or EVOO with non-EVOO additions steer towards hyphenation of different optic technologies. The multiple spectra or so-called “fingerprints” of samples are then analyzed with multivariate statistics. For EVOO authentication, one-class classification (OCC) to identify “out-of-class” EVOO samples in combination with data-fusion is applicable. Objective Prospecting the application of a prototype photonic device (“PhasmaFood”) which hyphenates visible, fluorescence, and near-infrared spectroscopy in combination with OCC modelling to classify EVOOs and discriminate them from other edible oils and adulterated EVOOs. Method EVOOs were adulterated by mixing in 10–50% (v/v) of refined and virgin olive oils, olive-pomace olive oils, and other common edible oils. Samples were analyzed by the hyphenated sensor. OCC, data-fusion, and decision thresholds were applied and optimized for two different scenarios. Results: By high-level data-fusion of the classification results from the three spectral databases and several multivariate model vectors, a 100% correct classification of all pure edible oils using OCC in the first scenario was found. Reducing samples being falsely classified as EVOOs in a second scenario, 97% of EVOOs adulterated with non-EVOO olive oils were correctly identified and ones with other edible oils correctly classified at score of 91%. Conclusions Photonic sensor hyphenation in combination with high-level data fusion, OCC, and tuned decision thresholds delivers significantly better screening results for EVOO compared to individual sensor results. Highlights Hyphenated photonics and its data handling solutions applied to extra virgin olive oil authenticity testing was found to be promising.

scholarly journals A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality

2020 ◽  
Author(s):  
Esteban Zuñiga ◽  
Liang Zhao
Keyword(s):  
Betweenness Centrality ◽  
Input Data ◽  
Data Classification ◽  
Classification Performance ◽  
Classification Techniques ◽  
Level Data ◽  
Physical Attributes ◽  
High Level ◽  
Physical Features ◽  
Pure Network

Data classification is a major machine learning paradigm, which has been widely applied to solve a large number of real-world problems. Traditional data classification techniques consider only physical features (e.g., distance, similarity, or distribution) of the input data. For this reason, those are called low-level classification. On the other hand, the human (animal) brain performs both low and high orders of learning, and it has a facility in identifying pat-terns according to the semantic meaning of the input data. Data classification that considers not only physical attributes but also the pattern formation is referred to as high-level classification. Several high-level classification techniques have been developed, which make use of complex networks to characterize data patterns and have obtained promising results. In this paper, we propose a pure network-based high-level classification technique that uses the betweenness centrality measure. We test this model in nine different real datasets and compare it with other nine traditional and well-known classification models. The results show us a competent classification performance.

Sign in / Sign up

Export Citation Format

Share Document