scholarly journals A Machine Vision Rapid Method to Determine the Ripeness Degree of Olive Lots

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2940
Author(s):  
Luciano Ortenzi ◽  
Simone Figorilli ◽  
Corrado Costa ◽  
Federico Pallottino ◽  
Simona Violino ◽  
...  
Keyword(s):  
Machine Vision ◽  
Nearest Neighbors ◽  
Calibration Method ◽  
Mobile App ◽  
Harvest Time ◽  
Automatic Assessment ◽  
K Nearest Neighbors ◽  
Olive Ripeness ◽  
Olive Ripening

The degree of olive maturation is a very important factor to consider at harvest time, as it influences the organoleptic quality of the final product, for both oil and table use. The Jaén index, evaluated by measuring the average coloring of olive fruits (peel and pulp), is currently considered to be one of the most indicative methods to determine the olive ripening stage, but it is a slow assay and its results are not objective. The aim of this work is to identify the ripeness degree of olive lots through a real-time, repeatable, and objective machine vision method, which uses RGB image analysis based on a k-nearest neighbors classification algorithm. To overcome different lighting scenarios, pictures were subjected to an automatic colorimetric calibration method—an advanced 3D algorithm using known values. To check the performance of the automatic machine vision method, a comparison was made with two visual operator image evaluations. For 10 images, the number of black, green, and purple olives was also visually evaluated by these two operators. The accuracy of the method was 60%. The system could be easily implemented in a specific mobile app developed for the automatic assessment of olive ripeness directly in the field, for advanced georeferenced data analysis.

scholarly journals Automatic Classification for Fruits’ Types and Identification of Rotten Ones Using k-NN and SVM

2019 ◽  
Vol 15 (03) ◽  
pp. 47 ◽  
Author(s):  
Ann Nosseir ◽  
Seif Eldin A. Ahmed
Keyword(s):  
Texture Feature ◽  
Texture Features ◽  
Nearest Neighbors ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
A Value ◽  
Different Types ◽  
Linear Svm ◽  
Occurrence Matrix

Having a system that classifies different types of fruits and identifies the quality of fruits will be of a value in various areas especially in an area of mass production of fruits’ products. This paper presents a novel system that differentiates between four fruits types and identifies the decayed ones from the fresh. The algorithms used are based on the colour and the texture features of the fruits’ images. The algorithms extract the RGB values and the first statistical order and second statistical of the Gray Level Co-occurrence Matrix (GLCM) values. To segregate between the fruits’ types, Fine, Medium, Coarse, Cosine, Cubic, and Weighted K-Nearest Neighbors algorithms are applied. The accuracy percentages of each are 96.3%, 93.8%, 25%, 83.8%, 90%, and 95% respectively.  These steps are tested with 46 pictures taken from a mobile phone of seasonal fruits at the time i.e., banana, apple, and strawberry. All types were accurately identifying.  To tell apart the decayed fruits from the fresh, the linear and quadratic Support Vector Machine (SVM) algorithms differentiated between them based on the colour segmentation and the texture feature algorithms values of each fruit image. The accuracy of the linear SVM is 96% and quadratic SVM 98%.

System Model for Prediction Analytics Using K-Nearest Neighbors Algorithm

2019 ◽  
Vol 16 (10) ◽  
pp. 4425-4430 ◽  
Author(s):  
Devendra Prasad ◽  
Sandip Kumar Goyal ◽  
Avinash Sharma ◽  
Amit Bindal ◽  
Virendra Singh Kushwah
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Research Work ◽  
Nearest Neighbors ◽  
Machine Learning Algorithms ◽  
System Model ◽  
K Nearest Neighbors ◽  
Prediction Analysis ◽  
Pros And Cons

Machine Learning is a growing area in computer science in today’s era. This article is focusing on prediction analysis using K-Nearest Neighbors (KNN) Machine Learning algorithm. Data in the dataset are processed, analyzed and predicated using the specified algorithm. Introduction of various Machine Learning algorithms, its pros and cons have been discussed. The KNN algorithm with detail study is given and it is implemented on the specified data with certain parameters. The research work elucidates prediction analysis and explicates the prediction of quality of restaurants.

scholarly journals Improving an AI-Based Algorithm to Automatically Generate Concept Maps

2019 ◽  
Vol 12 (4) ◽  
pp. 72
Author(s):  
Sara Alomari ◽  
Salha Abdullah
Keyword(s):  
Text Analysis ◽  
Classification Accuracy ◽  
Concept Maps ◽  
Concept Map ◽  
Nearest Neighbors ◽  
Learning Method ◽  
K Nearest Neighbors ◽  
Intelligent Algorithms ◽  
Effective Learning

Concept maps have been used to assist learners as an effective learning method in identifying relationships between information, especially when teaching materials have many topics or concepts. However, making a manual concept map is a long and tedious task. It is time-consuming and demands an intensive effort in reading the full content and reasoning the relationships among concepts. Due to this inefficiency, many studies are carried out to develop intelligent algorithms using several data mining techniques. In this research, the authors aim at improving Text Analysis-Association Rules Mining (TA-ARM) algorithm using the weighted K-nearest neighbors (KNN) algorithm instead of the traditional KNN. The weighted KNN is expected to optimize the classification accuracy, which will, eventually, enhance the quality of the generated concept map.

scholarly journals PEMILIHAN SEKOLAH TERBAIK DENGAN MENGGUNAKAN METODE K-NEAREST NEIGHBORS DAN TAXONOMIC MATCHER

2019 ◽  
Vol 6 (2) ◽  
Author(s):  
Bidari Ayu Lestari ◽  
Muhammad Hasbi ◽  
Teguh Susyanto
Keyword(s):  
Nearest Neighbors ◽  
Likert Scale ◽  
User Acceptance ◽  
Acceptance Test ◽  
Prospective Students ◽  
K Nearest Neighbors ◽  
Prospective Student ◽  
The Right ◽  
School Selection

The accuracy of choosing the right school is what every prospective student and parent wants. But in making the decision to choose the right school is not easy to do, because many aspects that are not simple must be taken into account. Mistakes in making decisions for prospective students must risk the loss of opportunities. Calculations in choosing a prospective student must be able to measure rationally the level of ability themselves with the quality of the school to be chosen. The quality of the school is determined based on the school's favorite level, the value of school accreditation, facilities owned, and achievements that have been achieved by the destination school. The purpose of this study was to apply the K-Nearest Neighbors (KNN) and Taxonomic Matcher methods to the creation of a system for selecting schools. The results of the development of the school selection application have been running in accordance with its functions and the results of the user acceptance test have been approved because it has a higher value than the answer agreed on the Likert scale which is 4.188571 on a scale of 1-5.Keywords: K-Nearest Neighbors (KNN), Taxonomic Matcher, Choosing a School

Efficiently Producing the K Nearest Neighbors in the Skyline on Vertically Partitioned Tables

2013 ◽  
Vol 3 (2) ◽  
pp. 58-77
Author(s):  
Marlene Goncalves ◽  
Maria-Esther Vidal
Keyword(s):  
State Of The Art ◽  
Property Values ◽  
Hybrid Approach ◽  
Nearest Neighbors ◽  
Query Point ◽  
K Nearest Neighbors ◽  
Speed Up ◽  
Set Of Points ◽  
Nearest Points

Criteria that induce a Skyline naturally represent user's preference conditions useful to discard irrelevant data in large datasets. However, in the presence of high-dimensional Skyline spaces, the size of the Skyline can still be very large, making unfeasible for users to process this set of points. To identify the best points among the Skyline, the Top-k Skyline approach has been proposed. Top-k Skyline uses discriminatory criteria to induce a total order of the points that comprise the Skyline, and recognizes the best or top-k points based on these criteria. In this article the authors model queries as multi-dimensional points that represent bounds of VPT (Vertically Partitioned Table) property values, and datasets as sets of multi-dimensional points; the problem is to locate the k best tuples in the dataset whose distance to the query is minimized. A tuple is among the k best tuples whenever there is not another tuple that is better in all dimensions, and that is closer to the query point, i.e., the k best tuples correspond to the k nearest points to the query that are incomparable or belong to the skyline. The authors name these tuples the k nearest neighbors in the skyline. The authors propose a hybrid approach that combines Skyline and Top-k solutions and develop two algorithms: TKSI and k-NNSkyline. The proposed algorithms identify among the skyline tuples, the k ones with the lowest values of the distance metric, i.e., the k nearest neighbors to the multi-dimensional query that are incomparable. Empirically, we study the performance and quality of TKSI and k-NNSkyline. The authors’ experimental results show the TKSI is able to speed up the computation of the Top-k Skyline in at least 50% percent with respect to the state-of-the-art solutions, whenever k is smaller than the size of the Skyline. Additionally, the authors’ results suggest that k-NNSkyline outperforms existing solutions by up to three orders of magnitude.

MODEL SELECTION, CONFIDENCE AND SCALING IN PREDICTING CHAOTIC TIME-SERIES

2000 ◽  
Vol 10 (06) ◽  
pp. 1407-1422 ◽  
Author(s):  
ERIK M. BOLLT
Keyword(s):  
Time Series ◽  
Systematic Approach ◽  
Additive Noise ◽  
Unbiased Estimate ◽  
Traditional Approach ◽  
Nearest Neighbors ◽  
Confidence Bands ◽  
K Nearest Neighbors ◽  
Taylor’S Series

Assuming a good embedding and additive noise, the traditional approach to time-series embedding prediction has been to predict pointwise by (usually linear) regression of the k-nearest neighbors; no good mathematics has been previously developed to appropriately select the model (where to truncate Taylor's series) to balance the conflict between noise fluctuations of a small k, and large k data needs of fitting many parameters of a high ordered model. We present a systematic approach to: (1) select the statistically significant neighborhood for a fixed (usually linear) model, (2) give an unbiased estimate of predicted mean response together with a statement of quality of the prediction in terms of confidence bands.

scholarly journals Classification of Contaminated Insulators Using k-Nearest Neighbors Based on Computer Vision

Computers ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 112
Author(s):  
Marcelo Picolotto Corso ◽  
Fabio Luis Perez ◽  
Stéfano Frizzo Stefenon ◽  
Kin-Choong Yow ◽  
Raúl García Ovejero ◽  
...  
Keyword(s):  
Computer Vision ◽  
Nearest Neighbors ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
Average Accuracy ◽  
Multi Classification ◽  
Mean Variance ◽  
Insulating Properties

Contamination on insulators may increase the surface conductivity of the insulator, and as a consequence, electrical discharges occur more frequently, which can lead to interruptions in a power supply. To maintain reliability in an electrical distribution power system, components that have lost their insulating properties must be replaced. Identifying the components that need maintenance is a difficult task as there are several levels of contamination that are hard to notice during inspections. To improve the quality of inspections, this paper proposes using k-nearest neighbors (k-NN) to classify the levels of insulator contamination based on images of insulators at various levels of contamination simulated in the laboratory. Computer vision features such as mean, variance, asymmetry, kurtosis, energy, and entropy are used for training the k-NN. To assess the robustness of the proposed approach, a statistical analysis and a comparative assessment with well-consolidated algorithms such as decision tree, ensemble subspace, and support vector machine models are presented. The k-NN showed up to 85.17% accuracy using the k-fold cross-validation method, with an average accuracy higher than 82% for the multi-classification of contamination of insulators, being superior to the compared models.

Quality of Carrots Grown for Processing as Affected by Nitrogen Fertilization and Harvest Term

2009 ◽  
Vol 70 (1) ◽  
pp. 135-144 ◽  
Author(s):  
Marek Gajewski ◽  
Zenon Węglarz ◽  
Anna Sereda ◽  
Marta Bajer ◽  
Agnieszka Kuczkowska ◽  
...  
Keyword(s):  
Nitrogen Fertilization ◽  
Soluble Solids ◽  
Soluble Solids Content ◽  
Carrot Juice ◽  
Harvest Time ◽  
Experimental Station ◽  
Colour Parameters ◽  
Solids Content ◽  
Nitrates Content

Quality of Carrots Grown for Processing as Affected by Nitrogen Fertilization and Harvest TermIn 2007-2008 the effect of nitrogen fertilization and harvest term on quality of two carrot cultivars was investigated. The field experiment was carried out in Żelazna Experimental Station of Warsaw University of Life Sciences. Karotan F1and Trafford F1cultivars, commonly grown for juice industry, were the objects of the experiment. Carrot seeds were sown at the beginning of May. Nitrogen fertilization was applied in five rates, ranged from 0 to 120 kg·ha-1and in two terms — before sowing and in the middle of growing season. Roots were harvested in three terms: mid-September, mid-October and the first decade of November. After harvest there were determined: nitrates (NO3) content in carrot roots and juice, soluble solids, colour parameters of juice in CIE L*a*b*system. The dose and the term of nitrogen fertilization influenced nitrates content in carrots, and the highest NO3concentration was found in carrots fertilized with 120 kg·ha-1of N before sowing. Karotan showed higher nitrates accumulation than Trafford. The content of nitrates in the roots was markedly higher than in carrot juice. Nitrates content in carrots decreased with delaying of harvest time, in opposite to soluble solids content. Soluble solids content and colour parameters of carrot juice were not affected by nitrogen fertilization, but the lowest L*, a*and b*values were observed at the last term of harvest.

Sign in / Sign up

Export Citation Format

Share Document