scholarly journals Use of Multiple Bacteriophage-Based Structural Color Sensors to Improve Accuracy for Discrimination of Geographical Origins of Agricultural Products

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 986
Author(s):  
Daun Seol ◽  
Daeil Jang ◽  
Kyungjoon Cha ◽  
Jin-Woo Oh ◽  
Hoeil Chung
Keyword(s):  
Agricultural Products ◽  
Support Vector ◽  
Amino Acid Residues ◽  
Discrimination Accuracy ◽  
M13 Bacteriophage ◽  
Color Changes ◽  
Color Sensor ◽  
Improve Accuracy ◽  
Color Sensors ◽  
Unique Individual

A single M13 bacteriophage color sensor was previously utilized for discriminating the geographical origins of agricultural products (garlic, onion, and perilla). The resulting discrimination accuracy was acceptable, ranging from 88.6% to 94.0%. To improve the accuracy further, the use of three separate M13 bacteriophage color sensors containing different amino acid residues providing unique individual color changes (Wild sensor: glutamic acid (E)-glycine (G)-aspartic acid (D), WHW sensor: tryptophan (W)-histidine (H)-tryptophan (W), 4E sensor: four repeating glutamic acids (E)) was proposed. This study was driven by the possibility of enhancing sample discrimination by combining mutually characteristic and complimentary RGB signals obtained from each color sensor, which resulted from dissimilar interactions of sample odors with the employed color sensors. When each color sensor was used individually, the discrimination accuracy based on support vector machine (SVM) ranged from 91.8–94.0%, 88.6–90.3%, and 89.8–92.1% for garlic, onion, and perilla samples, respectively. Accuracy improved to 98.0%, 97.5%, and 97.1%, respectively, by integrating all of the RGB signals acquired from the three color sensors. Therefore, the proposed strategy was effective for improving sample discriminability. To further examine the dissimilar responses of each color sensor to odor molecules, typical odor components in the samples (allyl disulfide, allyl methyl disulfide, and perillaldehyde) were measured using each color sensor, and differences in RGB signals were analyzed.

scholarly journals pIPredict: a computer tool for predicting isoelectric points of peptides and proteins

2015 ◽  
Vol 61 (1) ◽  
pp. 83-91 ◽  
Author(s):  
V.S. Skvortsov ◽  
N.N. Alekseychuk ◽  
D.V. Khudyakov ◽  
I.V. Romero Reyes
Keyword(s):  
Amino Acid ◽  
Posttranslational Modifications ◽  
Support Vector ◽  
Amino Acid Residues ◽  
Computer Tool ◽  
Wide Range ◽  
Vector Machines ◽  
Isoelectric Points ◽  
Peptide Fractionation ◽  
Made In

The data on approximate values of isoelectric point (pI) of peptides obtained during their fractionation by isoelectric focusing can be successfully used for the calculation of the pKa’s scale for amino acid residues. This scale can be used for pI prediction. The data of peptide fractionation also provides information about various posttranslational modifications (PTM), so that the prediction of pI may be performed for a wide range of protein forms. In this study, pKa values were calculated using a set of 13448 peptides (including 300 peptides with PTMs significant for pI calculation). The pKa constants were calculated for N-terminal, internal and C-terminal amino acid residues separately. The comparative analysis has shown that our scale increases the accuracy of pI prediction for peptides and proteins and successfully competes with traditional scales and such methods as support vector machines and artificial neural networks. The prediction performed by this scale, can be made in our program pIPredict with GUI written in JAVA as executable jar-archive. The program is freely available for academic users at http://www.ibmc.msk.ru/LPCIT/pIPredict. The software has also the possibility of pI predicting by some other scales; it recognizes some PTM and has the ability to use a custom scale.

scholarly journals Design of System for Determining Corn Seed Color Quality Standards using the Fuzzy Logic Method through the Localhost Network

2019 ◽  
Vol 8 (1) ◽  
pp. 62-70
Author(s):  
Reksa Nirvana Alam
Keyword(s):  
Fuzzy Logic ◽  
Seed Quality ◽  
Large Diameter ◽  
Quality Standards ◽  
Quality Standard ◽  
Seed Color ◽  
Accuracy Rate ◽  
Corn Seed ◽  
Color Sensor ◽  
Color Sensors

Control of quality standards is very important role in ensuring corn on the market. Corn seed quality standards are determined from the results of  classification process applied. So far, evaluation process of classification of corn seeds quality is still done manually which takes a long time and the quality of product is'nt evenly distributed. So, we need a tool to determine corn seeds quality to improve its quality. This study conducted color readings of corn seeds using  TCS230 color sensors and sorting  diameter of corn seeds using a small, medium, and large diameter sieve machine. The method for classifying quality standard of corn seed color uses fuzzy logic. The test was carried out by taking data from 3 TCS230 color sensors on each diameter of the sieve machine for corn seeds types used are BISI-2 and BIMA-19. The sensor accuracy is known by comparing data from sensor with data from Color Grab application. The reading results of BISI-2 on the color sensor-1 shows an accuracy rate of 0.3%, the color sensor-2 shows an accuracy rate of 0.72%, and the color sensor-3 shows an accuracy rate of 1.76%. For BIMA-19 corn seeds, the reading on color sensor-1 shows an accuracy of 1.11%, the color sensor-2 shows an accuracy of 24.6%, the color sensor-3 shows an accuracy of 1.10%. The results of fuzzy testing on BISI-2 and BIMA-19 showed that quality standard of maize seeds was good at medium and large diameters, while those on small diameters showed poor quality standards.

Improved Support Vector Machine and its Application

2010 ◽  
Vol 20-23 ◽  
pp. 147-153 ◽  
Author(s):  
Zhi Wei Huang ◽  
Jian Zhong Zhou ◽  
Li Xiang Song ◽  
Yong Chuan Zhang
Keyword(s):  
Support Vector Machine ◽  
Comprehensive Evaluation ◽  
Flood Hazard ◽  
Hazard Evaluation ◽  
Support Vector ◽  
Continuous Space ◽  
Svm Model ◽  
Improve Accuracy ◽  
Disaster Situation ◽  
Improved Support Vector Machine

According to the complex and uncertain relationships between indexes and grades of flood hazard evaluation, as well as the deficiency of measured samples, an improved support vector machine (SVM) model was established to improve accuracy and efficiency of calculation. The function that comprehensively evaluated indexes of multi-dimensional disaster situation in one-dimensional continuous space could be realized, and effectively solved the incompatible problems of different evaluation results with single index. The results showed that the model based on improved support vector machine had a better ability of generalization and calculation speed by reduce constraint conditions. It is considered to have a good application prospect in multi-index comprehensive evaluation.

scholarly journals Active Learning for Constrained Document Clustering with Uncertainty Region

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
M. A. Balafar ◽  
R. Hazratgholizadeh ◽  
M. R. F. Derakhshi
Keyword(s):  
Iterative Process ◽  
Clustering Algorithm ◽  
State Of The Art ◽  
Distance Matrix ◽  
Support Vector ◽  
Constrained Clustering ◽  
Similarity Matrix ◽  
Improve Accuracy ◽  
Degree Of Similarity ◽  
Accuracy And Stability

Constrained clustering is intended to improve accuracy and personalization based on the constraints expressed by an Oracle. In this paper, a new constrained clustering algorithm is proposed and some of the informative data pairs are selected during an iterative process. Then, they are presented to the Oracle and their relation is answered with “Must-link (ML) or Cannot-link (CL).” In each iteration, first, the support vector machine (SVM) is utilized based on the label produced by the current clustering. According to the distance of each document from the hyperplane, the distance matrix is created. Also, based on cosine similarity of word2vector of each document, the similarity matrix is created. Two types of probability (similarity and degree of similarity) are calculated and they are smoothed for belonging to neighborhoods. Neighborhoods form the samples that are labeled by Oracle, to be in the same cluster. Finally, at the end of each iteration, the data with a greater level of uncertainty (in term of probability) is selected for questioning the oracle. In order to evaluate, the proposed method is compared with famous state-of-the-art methods based on two criteria and over a standard dataset. The result demonstrates an increased accuracy and stability of the obtained result with fewer questions.

Fast Color Detection with Two-Terminal P-I-I-N Devices

1996 ◽  
Vol 420 ◽  
Author(s):  
T. Neidlinger ◽  
M. B. Schubert ◽  
G. Schmid ◽  
H. Brummack
Keyword(s):  
Dynamic Range ◽  
Spectral Response ◽  
Hole Transport ◽  
Color Sensor ◽  
Color Separation ◽  
Color Detection ◽  
Color Sensors ◽  
Voltage Transients ◽  
Different Color ◽  
Electric Field Profile

AbstractIn order to overcome the intrinsic speed limitation of amorphous silicon nipin color sensors we present an alternative way of achieving bias-controlled spectral sensitivity of two-terminal thin film devices, piin structures with appropriate band gap and thickness of their single layers can be used as photodetectors that are able to sequentially extract different color signals. Color separation is achieved by controlling the absorption and electric field profile across these piin devices, and thanks to the differences in electron and hole transport properties. Because in contrast to nipin devices there is no need for reverting readout voltages for color separation, this type of sensors can be operated at much higher readout frequencies. Spectral response and bias voltage transients have been analysed up to 20kHz, and preliminiary data are presented on the optimization of speed, dynamic range and color separation by varying bandgap and thickness of p- and i-layers. Furthermore a three-color sensor has been realized by introducing an additional intrinsic layer.

scholarly journals SENTIMENT ANALYSIS OF COSMETIC REVIEW USING NAIVE BAYES AND SUPPORT VECTOR MACHINE METHOD BASED ON PARTICLE SWARM OPTIMIZATION

2020 ◽  
Vol 2 (3) ◽  
pp. 169-178
Author(s):  
Zulia Imami Alfianti ◽  
Deni Gunawan ◽  
Ahmad Fikri Amin
Keyword(s):  
Support Vector Machine ◽  
Particle Swarm Optimization ◽  
Sentiment Analysis ◽  
Naive Bayes ◽  
Particle Swarm ◽  
Naïve Bayes ◽  
Support Vector ◽  
Swarm Optimization ◽  
Advantages And Disadvantages ◽  
Improve Accuracy

Sentiment analysis is an area of ​​approach that solves problems by using reviews from various relevant scientific perspectives. Reading a review before buying a product is very important to know the advantages and disadvantages of the products we will use, besides reading a cosmetic review can find out the quality of the cosmetic brand is feasible or not be used. Before consumers decide to buy cosmetics, consumers should know in detail the products to be purchased, this can be learned from the testimonials or the results of reviews from consumers who have bought and used the previous product. The number of reviews is certainly very much making consumers reluctant to read reviews. Eventually, the reviews become useless. For this reason, the authors classify based on positive and negative classes, so consumers can find product comparisons quickly and precisely. The implementation of Particle Swarm Optimization (PSO) optimization can improve the accuracy of the Support Vector Machine (SVM) and Naïve Bayes (NB) algorithm can improve accuracy and provide solutions to the review classification problem to be more accurate and optimal. Comparison of accuracy resulting from testing this data is an SVM algorithm of 89.20% and AUC of 0.973, then compared to SVM based on PSO with an accuracy of 94.60% and AUC of 0.985. The results of testing the data for the NB algorithm are 88.50% accuracy and AUC is 0.536, then the accuracy is compared with the PSO based NB for 0.692. In these calculations prove that the application of PSO optimization can improve accuracy and provide more accurate and optimal solutions

scholarly journals Mango ripeness classification system using hybrid technique

2019 ◽  
Vol 14 (2) ◽  
pp. 859
Author(s):  
Muhamad Farid Mavi ◽  
Zulkifli Husin ◽  
Badlishah Ahmad ◽  
Yasmin Mohd Yacob ◽  
Rohani S. Mohamed Farook ◽  
...  
Keyword(s):  
Image Processing ◽  
Color Image ◽  
Processing Technique ◽  
Image Processing Technique ◽  
Support Vector ◽  
Hybrid Technique ◽  
Single System ◽  
Sample Collection ◽  
Fruit Peel ◽  
Color Changes

<span>Nowadays there are many systems develop for agricultural purposes and most system implemented on the use of non-destructive technique not only to classify but also to determine the fruit ripeness. However, most of the studies concentrates using single technique to assess the fruit ripeness. This paper presents the work on mango ripeness classification using hybrid technique. Hybrid stands for mix or combination between two different elements, thus this study combined two different technique that is image processing and odour sensing technique in a single system. Image processing technique are implemented using color image that is HSV image color method to determine the ripeness of fruit based on fruit peel skin through color changes upon ripening. Whereas, odour sensing technique are implemented using sensors array to determine the fruit ripeness through smell changes upon ripening. The “Harumanis” and “Sala” mango was used for sample collection based on two different harvesting condition that is unripe and ripe were evaluated using the image processing and followed by the odour sensor. Support Vector Machine (SVM) is applied as classifier for training and testing based on the data collected from both techniques. The finding shows around 94.69% correct classification using hybrid technique of image processing and odour sensing in a single system.</span>

scholarly journals Comparison some of kernel functions with support vector machines classifier for thalassemia dataset

2021 ◽  
Vol 10 (2) ◽  
pp. 430
Author(s):  
Ilsya Wirasati ◽  
Zuherman Rustam ◽  
Jane Eva Aurelia ◽  
Sri Hartini ◽  
Glori Stephani Saragih
Keyword(s):  
Kernel Functions ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Medical Field ◽  
Treatment Technology ◽  
Blood Disorder ◽  
Vector Machines ◽  
Improve Accuracy ◽  
Rbf Kernel

<span id="docs-internal-guid-9a30056f-7fff-8ff1-59e1-69f89f4280bd"><span>In the medical field, accurate classification of medical data is really important because of its impact on disease detection and patient’s treatment. Technology, machine learning, is needed to help medical staff to improve accuracy to classify disease. This research discussed some kernel functions, such as gaussian radial basis function (RBF) kernel, Polynomial kernel, and linear kernel with support vector machine (SVM) to classify thalassemia data. Thalassemia is a genetic blood disorder which is also one of the major public health problems. In this paper, there is an explanation about thalassemia, SVM, and some of the kernel functions that serve as a comprehensive source for the next research about this topic. Furthermore, there is a comparison result from three kernel functions to find out which one has the best performance. The result is gaussian RBF kernel with SVM is the best method with an average of accuracy 99,63%. </span></span>

scholarly journals A bioinformatic study of antimicrobial peptides identified in the Black Soldier Fly (BSF) Hermetia illucens (Diptera: Stratiomyidae)

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Antonio Moretta ◽  
Rosanna Salvia ◽  
Carmen Scieuzo ◽  
Angela Di Somma ◽  
Heiko Vogel ◽  
...  
Keyword(s):  
Antimicrobial Peptides ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Amino Acid Residues ◽  
First Line ◽  
Hermetia Illucens ◽  
Active Peptides ◽  
Peptide Database ◽  
Living Organisms ◽  
Hostile Environments

Abstract Antimicrobial peptides (AMPs) play a key role in the innate immunity, the first line of defense against bacteria, fungi, and viruses. AMPs are small molecules, ranging from 10 to 100 amino acid residues produced by all living organisms. Because of their wide biodiversity, insects are among the richest and most innovative sources for AMPs. In particular, the insect Hermetia illucens (Diptera: Stratiomyidae) shows an extraordinary ability to live in hostile environments, as it feeds on decaying substrates, which are rich in microbial colonies, and is one of the most promising sources for AMPs. The larvae and the combined adult male and female H. illucens transcriptomes were examined, and all the sequences, putatively encoding AMPs, were analysed with different machine learning-algorithms, such as the Support Vector Machine, the Discriminant Analysis, the Artificial Neural Network, and the Random Forest available on the CAMP database, in order to predict their antimicrobial activity. Moreover, the iACP tool, the AVPpred, and the Antifp servers were used to predict the anticancer, the antiviral, and the antifungal activities, respectively. The related physicochemical properties were evaluated with the Antimicrobial Peptide Database Calculator and Predictor. These analyses allowed to identify 57 putatively active peptides suitable for subsequent experimental validation studies.

Sign in / Sign up

Export Citation Format

Share Document