scholarly journals Detection of Malignancy Associated Changes in Cervical Cell Nuclei Using Feed-Forward Neural Networks

1997 ◽  
Vol 14 (1) ◽  
pp. 31-40 ◽  
Author(s):  
Roger A. Kemp ◽  
Calum MacAulay ◽  
David Garner ◽  
Branko Palcic
Keyword(s):  
Neural Networks ◽  
Discriminant Function ◽  
Severe Dysplasia ◽  
Correct Classification ◽  
Correct Classification Rate ◽  
Classification Rate ◽  
Normal Cells ◽  
Feed Forward ◽  
Linear Discriminant ◽  
Feed Forward Neural Networks

Normal cells in the presence of a precancerous lesion undergo subtle changes of their DNA distribution when observed by visible microscopy. These changes have been termed Malignancy Associated Changes (MACs). Using statistical models such as neural networks and discriminant functions it is possible to design classifiers that can separate these objects from truly normal cells. The correct classification rate using feed‐forward neural networks is compared to linear discriminant analysis when applied to detecting MACs. Classifiers were designed using 53 nuclear features calculated from images for each of 25,360 normal appearing cells taken from 344 slides diagnosed as normal or containing severe dysplasia. A linear discriminant function achieved a correct classification rate of 61.6% on the test data while neural networks scored as high as 72.5% on a cell‐by‐cell basis. The cell classifiers were applied to a library of 93,494 cells from 395 slides, and the results were jackknifed using a single slide feature. The discriminant function achieved a correct classification rate of 67.6% while the neural networks managed as high as 76.2%.

scholarly journals The Use of Artificial Neural Networks and a General Discriminant Analysis for Predicting Culling Reasons in Holstein-Friesian Cows Based on First-Lactation Performance Records

Animals ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 721
Author(s):  
Krzysztof Adamczyk ◽  
Wilhelm Grzesiak ◽  
Daniel Zaborski
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Discriminant Analysis ◽  
Multilayer Perceptrons ◽  
Correct Classification ◽  
Correct Classification Rate ◽  
Classification Rate ◽  
Holstein Friesian ◽  
Artificial Neural ◽  
Friesian Cows

The aim of the present study was to verify whether artificial neural networks (ANN) may be an effective tool for predicting the culling reasons in cows based on routinely collected first-lactation records. Data on Holstein-Friesian cows culled in Poland between 2017 and 2018 were used in the present study. A general discriminant analysis (GDA) was applied as a reference method for ANN. Considering all predictive performance measures, ANN were the most effective in predicting the culling of cows due to old age (99.76–99.88% of correctly classified cases). In addition, a very high correct classification rate (99.24–99.98%) was obtained for culling the animals due to reproductive problems. It is significant because infertility is one of the conditions that are the most difficult to eliminate in dairy herds. The correct classification rate for individual culling reasons obtained with GDA (0.00–97.63%) was, in general, lower than that for multilayer perceptrons (MLP). The obtained results indicated that, in order to effectively predict the previously mentioned culling reasons, the following first-lactation parameters should be used: calving age, calving difficulty, and the characteristics of the lactation curve based on Wood’s model parameters.

scholarly journals Opening the Black Box: the Relationship between Neural Networks and Linear Discriminant Functions

1997 ◽  
Vol 14 (1) ◽  
pp. 19-30 ◽  
Author(s):  
Roger A. Kemp ◽  
Calum MacAulay ◽  
Branko Palcic
Keyword(s):  
Neural Networks ◽  
Decision Making ◽  
Classification Problem ◽  
Black Box ◽  
Discriminant Functions ◽  
Classification Problems ◽  
Statistical Decision ◽  
Feed Forward ◽  
Linear Discriminant ◽  
Feed Forward Neural Networks

Over the last ten years feed‐forward neural networks have become a popular tool for statistical decision making. During this time, they have been applied in many fields, including cytological classification. Neural networks are often treated as a black box, whose inner workings are concealed from the researcher. This is unfortunate, since the inner workings of a neural network can be understood in a manner similar to that of a linear discriminant function, which is the standard tool that researchers use for decision making.This paper discusses feed‐forward neural networks and some methods to improve their performance for classification problems. Their relationship to discriminant functions will be examined for a simple two‐dimensional classification problem.

scholarly journals Physicochemical, Spectroscopic and Chromatographic Analyses in Combination with Chemometrics for the Discrimination of Four Sweet Cherry Cultivars Grown in Northern Greece

Foods ◽  
2019 ◽  
Vol 8 (10) ◽  
pp. 442 ◽  
Author(s):  
Spyridon Papapetros ◽  
Artemis Louppis ◽  
Ioanna Kosma ◽  
Stavros Kontakos ◽  
Anastasia Badeka ◽  
...  
Keyword(s):  
Volatile Compounds ◽  
Sweet Cherry ◽  
Statistical Treatment ◽  
Quality Parameters ◽  
Total Phenolic ◽  
Correct Classification ◽  
Correct Classification Rate ◽  
Northern Greece ◽  
Classification Rate ◽  
Linear Discriminant

A total of 56 sweet cherry samples belonging to four cultivars (Ferrovia, Canada Giant, Lapins, and Germersdorfer) grown in northern Greece were characterized and differentiated according to botanical origin. For the above purpose, the following parameters were determined: conventional quality parameters (titratable acidity (TA), pH, total soluble solids (TSS), total phenolic content (TPC), mechanical properties and sensory evaluation, sugars by High Performance Liquid Chromatography (HPLC), volatile compounds by GC/MS, and minerals by ICP-OES. Statistical treatment of the data was carried out using Multivariate Analysis of Variance (MANOVA) and Linear Discriminant Analysis (LDA). The results showed that the combination of volatile compounds and conventional quality parameters provided a correct classification rate of 84.1%, the combination of minerals and conventional quality parameters 86.4%, and the combination of minerals, conventional quality parameters and sugars provided the highest correct classification rate of 88.6%. When the above four cherry cultivars were combined with previously studied Kordia, Regina, Skeena and Mpakirtzeika cultivars, collected from the same regions during the same seasons, the respective values for the differentiation of all eight cultivars were: 85.5% for the combination of conventional quality parameters, volatiles and minerals; and 91.3% for the combination of conventional quality parameters, volatiles, minerals, and sugars.

scholarly journals A data mining approach for desire and intention to participate in virtual communities

2019 ◽  
Vol 9 (5) ◽  
pp. 3714
Author(s):  
Özerk Yavuz ◽  
Adem Karahoca ◽  
Dilek Karahoca
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Neural Networks ◽  
Virtual Communities ◽  
Correct Classification ◽  
Research Model ◽  
Correct Classification Rate ◽  
Classification Rate ◽  
Data Mining Approach ◽  
Intention To Participate

<span lang="EN-US">The purpose of this study is to investigate performances of some of the data mining approaches while understanding desire and intention to participate in virtual communities and its antecedents. A research model has been developed following the literature review and the model was tested afterwards. In research part of the study, some of the data mining approaches as JRip, Part, OneR Method, Multilayer Perceptron (Neural Networks), Bayesian Networks have been used. Based on the analysis conducted it has been found out that Multilayer Neural Network had the best correct classification rate and lowest RMSE.</span>

scholarly journals Fatty Acid Composition of Cosmetic Argan Oil: Provenience and Authenticity Criteria

Molecules ◽  
2020 ◽  
Vol 25 (18) ◽  
pp. 4080
Author(s):  
Milena Bučar Miklavčič ◽  
Fouad Taous ◽  
Vasilij Valenčič ◽  
Tibari Elghali ◽  
Maja Podgornik ◽  
...  
Keyword(s):  
Fatty Acids ◽  
Fatty Acid ◽  
Discriminant Analysis ◽  
Trans Fatty Acids ◽  
Correct Classification ◽  
Fatty Acid Profiles ◽  
Correct Classification Rate ◽  
Classification Rate ◽  
Argan Oil ◽  
Geographical Regions

In this work, fatty-acid profiles, including trans fatty acids, in combination with chemometric tools, were applied as a determinant of purity (i.e., adulteration) and provenance (i.e., geographical origin) of cosmetic grade argan oil collected from different regions of Morocco in 2017. The fatty acid profiles obtained by gas chromatography (GC) showed that oleic acid (C18:1) is the most abundant fatty acid, followed by linoleic acid (C18:2) and palmitic acid (C16:0). The content of trans-oleic and trans-linoleic isomers was between 0.02% and 0.03%, while trans-linolenic isomers were between 0.06% and 0.09%. Discriminant analysis (DA) and orthogonal projection to latent structure—discriminant analysis (OPLS-DA) were performed to discriminate between argan oils from Essaouira, Taroudant, Tiznit, Chtouka-Aït Baha and Sidi Ifni. The correct classification rate was highest for argan oil from the Chtouka-Aït Baha province (90.0%) and the lowest for oils from the Sidi Ifni province (14.3%), with an overall correct classification rate of 51.6%. Pairwise comparison using OPLS-DA could predictably differentiate (≥0.92) between the geographical regions with the levels of stearic (C18:0) and arachidic (C20:0) fatty acids accounting for most of the variance. This study shows the feasibility of implementing authenticity criteria for argan oils by including limit values for trans-fatty acids and the ability to discern provenance using fatty acid profiling.

Sign in / Sign up

Export Citation Format

Share Document