scholarly journals Fuzzy Evaluation Output of Taste Information for Liquor Using Electronic Tongue Based on Cloud Model

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 686 ◽  
Author(s):  
Jingjing Liu ◽  
Mingxu Zuo ◽  
Sze Shin Low ◽  
Ning Xu ◽  
Zhiqing Chen ◽  
...  
Keyword(s):  
Cloud Model ◽  
Electronic Tongue ◽  
Human Perception ◽  
Principal Component ◽  
Cloud Droplet ◽  
Fuzzy Evaluation ◽  
Human Beings ◽  
Digital Output ◽  
Detection Technology ◽  
Evaluative Language

As a taste bionic system, electronic tongues can be used to derive taste information for different types of food. On this basis, we have carried forward the work by making it, in addition to the ability of accurately distinguish samples, be more expressive by speaking evaluative language like human beings. Thus, this paper demonstrates the correlation between the qualitative digital output of the taste bionic system and the fuzzy evaluation language that conform to the human perception mode. First, through principal component analysis (PCA), backward cloud generator and forward cloud generator, two-dimensional cloud droplet groups of different flavor information were established by using liquor taste data collected by electronic tongue. Second, the frequency and order of the evaluation words for different flavor of liquor were obtained by counting and analyzing the data appeared in the artificial sensory evaluation experiment. According to the frequency and order of words, the cloud droplet range corresponding to each word was calculated in the cloud drop group. Finally, the fuzzy evaluations that originated from the eight groups of liquor data with different flavor were compared with the artificial sense, and the results indicated that the model developed in this work is capable of outputting fuzzy evaluation that is consistent with human perception rather than digital output. To sum up, this method enabled the electronic tongue system to generate an output, which conforms to human’s descriptive language, making food detection technology a step closer to human perception.

Evaluation Method of Public Transportation System Based on Fuzzy Cloud Model

2018 ◽  
Vol 10 (4) ◽  
pp. 36-51 ◽  
Author(s):  
Min Tu ◽  
Shiyang Xu ◽  
Jianfeng Xu
Keyword(s):  
Public Transportation ◽  
Evaluation Method ◽  
Cloud Model ◽  
Principal Component ◽  
Transportation System ◽  
Urban Traffic ◽  
Evaluation Methodology ◽  
Fuzzy Evaluation ◽  
The Public ◽  
Public Transportation System

This article describes how the public traffic system evaluation is an important measure to strengthen the management of urban transportation. Many scholars have evaluated the public transportation system, but lack research on different index weights of it. In past models, although the fuzzy assessment method was integrated into an evaluation methodology, its randomness was reflected unclearly. To solve the problems, a fuzzy evaluation of a cloud model is researched. Firstly, the corresponding weights of all indexes are calculated by analytic hierarchy process (AHP) and a clustering method. Then, the principal component of the indexes is extracted by the principal component analysis. According to the distribution of a principal component and processed with the cloud model, a subordinate degree function was established. Finally, scoring cities by combining the principal component weight and membership cloud matrix and evaluating the public transportation system. Comparing the matter-element analysis and the AHP gray model method, this proposed model in this article can evaluate the performance of different urban traffic systems more practically.

Application of Machine Learning in Animal Disease Analysis and Prediction

2020 ◽  
Vol 15 ◽  
Author(s):  
Shuwen Zhang ◽  
Qiang Su ◽  
Qin Chen
Keyword(s):  
Machine Learning ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Clustering Algorithm ◽  
Principal Component ◽  
Support Vector ◽  
Animal Disease ◽  
Human Beings ◽  
Animal Diseases ◽  
Disease Analysis

Abstract: Major animal diseases pose a great threat to animal husbandry and human beings. With the deepening of globalization and the abundance of data resources, the prediction and analysis of animal diseases by using big data are becoming more and more important. The focus of machine learning is to make computers learn how to learn from data and use the learned experience to analyze and predict. Firstly, this paper introduces the animal epidemic situation and machine learning. Then it briefly introduces the application of machine learning in animal disease analysis and prediction. Machine learning is mainly divided into supervised learning and unsupervised learning. Supervised learning includes support vector machines, naive bayes, decision trees, random forests, logistic regression, artificial neural networks, deep learning, and AdaBoost. Unsupervised learning has maximum expectation algorithm, principal component analysis hierarchical clustering algorithm and maxent. Through the discussion of this paper, people have a clearer concept of machine learning and understand its application prospect in animal diseases.

An Exploration of Provincial Low-Carbon Economy Evaluation System Based on Principal Component-Variable Fuzzy Evaluation

2013 ◽  
Vol 291-294 ◽  
pp. 1562-1567
Author(s):  
Ji Min Hu ◽  
Jian Long Gu ◽  
Chang Cui Hu ◽  
Hai Feng Wang
Keyword(s):  
Evaluation System ◽  
Comprehensive Evaluation ◽  
Principal Component ◽  
Fuzzy Comprehensive Evaluation ◽  
Fuzzy Evaluation ◽  
Low Carbon ◽  
Low Carbon Economy ◽  
Component Variable ◽  
The Status ◽  
Carbon Economy

According to indicators’ information repetition and subjectivity of the indicators’ weight set during the variable fuzzy comprehensive evaluation, Principal Component analysis can help solve the weight of the relative indicators and reduce comprehensive evaluation dimensions of the variable fussy comprehensive evaluation. This paper has made a comprehensive evaluation of the status quo of Yunnan’s low carbon economy development(2005-2009), which turns out to be more practical compared with the mere variable fussy theory analysis, thus, principal component-variable fuzzy evaluation is a kind of feasible way to analyze the regional low carbon development status.

scholarly journals Magnetron Sputtering Thin Films as Tool to Detect Triclosan in Infant Formula Powder: Electronic Tongue Approach

Coatings ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 336
Author(s):  
Cátia Magro ◽  
Margarida Sardinha ◽  
Paulo A. Ribeiro ◽  
Maria Raposo ◽  
Susana Sério
Keyword(s):  
Thin Films ◽  
Infant Formula ◽  
Tap Water ◽  
Milk Powder ◽  
Electronic Tongue ◽  
Principal Component ◽  
Formula Milk ◽  
Straight Line ◽  
Multi Walled Carbon Nanotubes ◽  
Walled Carbon Nanotubes

Triclosan (TCS) is being detected in breast milk and in infants of puerperal women. The harmful effects caused by this compound on living beings are now critical and thus it is pivotal find new tools to TCS monitoring. In the present study, an electronic tongue (e-tongue) device comprising an array of sputtered thin films based on Multi-Walled Carbon Nanotubes and titanium dioxide was developed to identify TCS concentrations, from 10−15 to 10−5 M, in both water and milk-based solutions. Impedance spectroscopy was used for device signal transducing and data was analyzed by principal component analysis (PCA). The e-tongue revealed to be able to distinguish water from milk-based matrices through the two Principal Components (PC1 and PC2), which represented 67.3% of the total variance. The PC1 values of infant formula milk powder prepared with tap water (MT) or mineral water (MMW) follows a similar exponential decay curve when plotted with the logarithm of concentration. Therefore, considering the TCS concentration range between 1015 and 10−9 M, the PC1 values are fitted by a straight line and values of −1.9 ± 0.2 and of 7.6 × 10−16 M were calculated for the sensor sensitivity and sensor resolution, respectively. Additionally, a strong correlation (R = 0.96) between MT and MMW PC1 data was found. These results have shown that the proposed device corresponds to a promisor method for the detection of TCS in milk-based solutions.

Physicochemical, Interaction & Topological Descriptors vs. hMAO-A Inhibition of Aplysinopsin Analogs: A Boulevard to the Discovery of Semi-Synthetic Anti-Depression Agents

2021 ◽  
Vol 22 ◽  
Author(s):  
Rajeev K. Singla ◽  
Ghulam Md Ashraf ◽  
Magdah Ganash ◽  
Varadaraj Bhat G ◽  
Bairong Shen
Keyword(s):  
Model Development ◽  
Principal Component ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Topological Descriptors ◽  
Good Prediction ◽  
Physicochemical Interaction ◽  
Human Beings ◽  
2D Qsar

Background: Neurological disorder, depression is the globally 4th leading cause of chronic disabilities in human beings. Objective: This study aimed to model a 2D-QSAR equation that can facilitate the researchers to design better aplysinopsin analogs with potent hMAO-A inhibition. Methods: Aplysinopsin analogs dataset were subjected to ADME assessment for drug-likeness suitability using StarDrop software before modeled equation. 2D-QSAR equations were generated using VLife MDS 4.6. Dataset was segregated into training and test set using different methodologies, followed by variable selection. Model development was done using principal component regression, partial least square regression, and multiple regression. Results: The dataset has successfully qualified the drug-likeness criteria in ADME simulation, with more than 90% of molecules cleared the ideal conditions including intrinsic solubility, hydrophobicity, CYP3A4 2C9pKi, hERG pIC50, etc. 112 models were developed using multiparametric consideration of methodologies. The best six models were discussed with their extent of significance and prediction capabilities. ALP97 was emerged out as the most significant model out of all, with ~83% of the variance in the training set, the internal predictive ability of ~74% while having the external predictive capability of ~79%. Conclusion: ADME assessment suggested that aplysinopsin analogs are worth investigating. Interaction among the descriptors in a way of summation or multiplication products, are quite influential and yielding significant 2D-QSAR models with good prediction efficiency. This model can be used for the design of a more potent hMAO-A inhibitor having an aplysinopsin scaffold, which can then contribute to the treatment of depression and other neurological disorders.

scholarly journals Anthropomorphization Framework for Human-Object Communication

2007 ◽  
Vol 11 (8) ◽  
pp. 1007-1014 ◽  
Author(s):  
Hirotaka Osawa ◽  
◽  
Jun Mukai ◽  
Michita Imai ◽  
Keyword(s):  
Body Image ◽  
Ubiquitous Computing ◽  
Human Perception ◽  
Body Language ◽  
The Body ◽  
Body Parts ◽  
Human Beings ◽  
Human Object ◽  
Computing Environments ◽  
Ubiquitous Computing Environments

We propose an anthropomorphization framework that determines an object’s body image. This framework directly intervenes and anthropomorphizes objects in ubiquitous-computing environments through robotic body parts shaped like those of human beings, which provide information through spoken directions and body language. Our purpose is to demonstrate that an object acquires subjective representations through anthropomorphization. Using this framework, people can more fully understand instructions given by an object. We designed an anthropomorphization framework that changes the body image by attaching body parts. We also conducted experiments to evaluate this framework. Results indicate that the site at which an anthropomorphization device is attached influences human perception of the object’s virtual body image, and participants in experiments understood several instructions given by the object more clearly. Results also indicate that participants better intuited their devices’ instructions and movement in ubiquitous-computing environments.

scholarly journals Discrimination of Milks with a Multisensor System Based on Layer-by-Layer Films

Sensors ◽  
2018 ◽  
Vol 18 (8) ◽  
pp. 2716 ◽  
Author(s):  
Coral Salvo-Comino ◽  
Celia García-Hernández ◽  
Cristina García-Cabezón ◽  
Maria Rodríguez-Méndez
Keyword(s):  
Copper Phthalocyanine ◽  
Electronic Tongue ◽  
Principal Component ◽  
Sensor System ◽  
Galactose Oxidase ◽  
Milk Analysis ◽  
Layer By Layer ◽  
Additional Information ◽  
Milk Samples ◽  
Calibration Models

A nanostructured electrochemical bi-sensor system for the analysis of milks has been developed using the layer-by-layer technique. The non-enzymatic sensor [CHI+IL/CuPcS]2, is a layered material containing a negative film of the anionic sulfonated copper phthalocyanine (CuPcS) acting as electrocatalytic material, and a cationic layer containing a mixture of an ionic liquid (IL) (1-butyl-3-methylimidazolium tetrafluoroborate) that enhances the conductivity, and chitosan (CHI), that facilitates the enzyme immobilization. The biosensor ([CHI+IL/CuPcS]2-GAO) results from the immobilization of galactose oxidase on the top of the LbL layers. FTIR, UV–vis, and AFM have confirmed the proposed structure and cyclic voltammetry has demonstrated the amplification caused by the combination of materials in the film. Sensors have been combined to form an electronic tongue for milk analysis. Principal component analysis has revealed the ability of the sensor system to discriminate between milk samples with different lactose content. Using a PLS-1 calibration models, correlations have been found between the voltammetric signals and chemical parameters measured by classical methods. PLS-1 models provide excellent correlations with lactose content. Additional information about other components, such as fats, proteins, and acidity, can also be obtained. The method developed is simple, and the short response time permits its use in assaying milk samples online.

Use of an electronic tongue in the assessment of highly diluted systems

2021 ◽  
Vol 10 (36) ◽  
pp. 104-107
Author(s):  
Mateus Silva Laranjeira ◽  
Marilisa Guimarães Lara ◽  
Marco Vinicius Chaud ◽  
Olney Leite Fontes ◽  
Antônio Riul Jr
Keyword(s):  
Ultrathin Films ◽  
Electronic Tongue ◽  
Principal Component ◽  
Original Data ◽  
Relevant Information ◽  
Statistical Correlation ◽  
Layer By Layer ◽  
Layer Technique ◽  
Liquid Systems ◽  
Complex Liquid

Introduction: “Eletronic tongue” is a device commonly used in the analysis of tastants, heavy metal ions, fruit juice, wines and also in the development of biosensors [1-3]. Briefly, the e-tongue is constituted by sensing units formed by ultrathin films of distinct materials deposited on gold interdigitated electrodes, which are immersed in liquid samples, followed by impedance spectroscopy measurements [1]. The e-tongue sensor is based on the global selectivity concept, i.e., the materials forming the sensing units are not selective to any substance in the samples, therefore, it allows the grouping of information into distinct patterns of response, enabling the distinction of complex liquid systems [1]. Aim: Our aim was to use e-tongue system for the assessment the homeopathic medicine Belladonna at different degrees of dilution, in attempt to differentiate highly diluted systems. Methods: Ultrathin films forming the sensing units were prepared by the layer-by-layer technique [4], using conventional polyelectrolytes such as poly(sodium styene sulfonate) (PSS) and poly(allylamine) hydrochloride (PAH), chitosan and poly(3,4-ethylenedioxythiophene) (PEDOT). Homeopathic medicines (Belladonna 1cH, 6cH, 12cH and 30cH) were prepared by dilution and agitation according to Hahnemann´s method [5], using ethanol at 30% (w/w) as vehicle. Experimental data acquisition was conducted by blind tests measurements involving Belladonna samples and the vehicle used in the dilutions. Five independent and consecutive measurements were taken for each solution at 1 kHz, which were further analysed by Principal Component Analysis (PCA), a statistical method largely employed to reduce the dimensionality of the original data without losing information in the correlation of the samples [3]. Results: Figure 1 shows that the five independent measurements are grouped quite closed each other for each solution analysed, with a clear distinction of them. Therefore, it was noticed a change in the observed pattern measured at different days, indicating a reduced reproducibility, although the groups of data could still be identified. Discussion: PCA is a powerful tool highly employed to extract relevant information in the correlation of data analysis of e-tongue systems. PCA plots showed a good statistical correlation of the systems (PC1 + PC2 ³ 90%), with the solutions being straightforwardly distinguished each other and also from the vehicle used. Conclusion: Despite the differences of data obtained along distinct days of analysis, the e-tongue could detect differences among the samples tested, even considering the highly diluted cases studied.

Sign in / Sign up

Export Citation Format

Share Document