Abstract

Bees are essential for food production for humans and for the maintenance of natural ecosystems. This paper presents a proposal to predict the health level of honeybee colonies using data from internal and external beehive sensors and from in-loco inspections by beekeepers. The data set was obtained by gathering inspection information and internal and external sensors measurements, based on the date of collection. However, obtaining inspection data frequently is not feasible due to the stress caused to the beehive, especially in periods such as winter, where the beehive becomes more sensitive. As a solution, the beehives health status was obtained through a partitioning clustering method and then validated by in-loco inspection data already obtained. We propose a logistic regression model with an elastic net penalty, which consists of a fusion of lasso (l1) and ridge (l2) methods. We obtained a flexible and robust model compared to the usual logistic regression and a diagnostic tool that can avoid unnecessary inspections and, consequently, reduce the stress of the beehives.

Packages

require(tidyverse)
require(suncalc)
require(ggplot2)
require(ggfortify)
require(wesanderson)
require(ggridges)
require(viridis)
require(knitr)
require(kableExtra)
require(FactoMineR)
require(factoextra)
require(fpc)
require(reshape2)
require(qcc)
require(REdaS)
require(caret)

Preprocessing

## 
##  iter imp variable
##   1   1  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   1   2  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   1   3  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   1   4  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   1   5  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   2   1  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   2   2  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   2   3  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   2   4  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   2   5  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   3   1  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   3   2  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   3   3  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   3   4  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   3   5  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   4   1  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   4   2  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   4   3  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   4   4  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   4   5  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   5   1  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   5   2  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   5   3  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   5   4  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed
##   5   5  Brood_Temp  Hive_Temp  Weight  Ext_Temperature  DewPoint  WindDirection  WindSpeed

hide

Description of dataset

O conjunto de dados foi obtido pela união dos dados de sensores internos, externos e de inspeção através de um algoritmo criado em python na ferramenta google colab. E foi preprocessado (limpeza, consistência, imputação…) no software R.

Algumas informações a respeito do dataset:

Número total de observações: 35855
- Número de observações rotuladas (inspeção associada): 17435
- Número de observações não rotuladas (s/ inspeção associada): 18420
Variables in study
- TurnDay:
  - Type: factor.
  - Description: Turno do dia associado ao horário da medição.
  - Missing Values: 0%.
  - Prevalence: \

Turno	Contagem	%
dia	18107	50.5
noite	17744	49.5

Brood Temp:
- Type: numeric.
- Description: Sensor de temperatura em ºC no centro da colméia.
- Missing Values: 0%.
- Visualization:\
Brood Humidity:
- Type: numeric.
- Description: Sensor de umidade em … no cetro da colméia.
- Missing Values: 0%.
- Visualization:\
Hive Temp:
- Type: numeric.
- Description: Sensor de temperatura em ºC na parede interna da colméia.
- Missing Values: 0%.
- Visualization:\
Hive Humidity:
- Type: numeric.
- Description: Sensor de umidade em … na parede interna da colméia.
- Missing Values: 0%.
- Visualization:\
Weight:
- Type: numeric.
- Description: Sensor de Peso da colméia.
- Missing Values: 0%.
- Visualization:\
Ext Temperature:
- Type: numeric.
- Description: Sensor de temperatura em ºC na parte externa da colméia.
- Missing Values 0%.
- Visualization:\
Dew Point:
- Type: numeric.
- Description: Ponto de Orvalho.
- Missing Values: 0%.
- Visualization:\
Wind Direction:
- Type: numeric.
- Description: Direção do vento.
- Missing Values: 0%.
- Visualization:\
Wind Speed:
- Type: numeric.
- Description: Velocidade do vento.
- Missing Values: 0%.
- Visualization:\
Brood:
- Type: factor.
- Description: Todos os estágios da ninhada presentes em quantidades apropriadas.
- Missing Values: 51.37%.
Bees:
- Type: factor.
- Description: Abelhas adultas suficientes e com boa estrutura etária para cuidar das crias e realizar todas as tarefas da colônia.
- Missing Values: 51.37%.
Queen:
- Type: factor.
- Description: Uma rainha jovem e produtiva, presente.
- Missing Values: 51.37%.
Food:
- Type: factor.
- Description: Quantidade suficiente de água, forrageamento e alimento em estoque disponível.
- Missing Values: 51.37%.
Stressors:
- Type: factor.
- Description: Nenhum estressor aparente presente que poderia levar à redução da população da colônia e/ou afetar seu potencial de crescimento.
- Missing Values: 51.37%.
Space:
- Type: factor.
- Description: Espaço adequado para tamanho esperado da colônia à curto e médio prazo que seja sanitário, defensável e que possua espaço para os ovos.
- Missing Values: 51.37%.
Dataset summary:

##    TurnDay            Brood_Temp     Brood_Humidity    Hive_Temp     
##  Length:35855       Min.   :-3.467   Min.   :22.00   Min.   :-5.744  
##  Class :character   1st Qu.:22.133   1st Qu.:62.00   1st Qu.:21.961  
##  Mode  :character   Median :30.078   Median :67.00   Median :28.544  
##                     Mean   :27.201   Mean   :66.21   Mean   :26.443  
##                     3rd Qu.:33.528   3rd Qu.:71.00   3rd Qu.:33.144  
##                     Max.   :39.950   Max.   :89.00   Max.   :39.928  
##                                                                      
##  Hive_Humidity       Weight        Ext_Temperature     DewPoint      
##  Min.   :19.00   Min.   :  1.034   Min.   :-10.00   Min.   :-10.000  
##  1st Qu.:60.00   1st Qu.: 23.101   1st Qu.:  2.50   1st Qu.:  1.170  
##  Median :66.00   Median : 28.050   Median : 12.80   Median :  7.200  
##  Mean   :65.51   Mean   : 28.011   Mean   : 13.18   Mean   :  8.264  
##  3rd Qu.:72.00   3rd Qu.: 31.724   3rd Qu.: 22.80   3rd Qu.: 17.000  
##  Max.   :93.00   Max.   :129.936   Max.   : 36.00   Max.   : 20.000  
##                                                                      
##  WindDirection     WindSpeed         Brood            Bees      
##  Min.   :  0.0   Min.   : 0.00   Min.   :0.000   Min.   :0.000  
##  1st Qu.:  0.0   1st Qu.: 0.00   1st Qu.:1.000   1st Qu.:1.000  
##  Median : 70.0   Median :15.00   Median :1.000   Median :1.000  
##  Mean   :114.4   Mean   :16.94   Mean   :0.852   Mean   :0.926  
##  3rd Qu.:220.0   3rd Qu.:31.00   3rd Qu.:1.000   3rd Qu.:1.000  
##  Max.   :360.0   Max.   :99.00   Max.   :1.000   Max.   :1.000  
##                                  NA's   :18420   NA's   :18420  
##      Queen            Food         Stressors         Space      
##  Min.   :0.000   Min.   :0.000   Min.   :0.000   Min.   :0.000  
##  1st Qu.:1.000   1st Qu.:1.000   1st Qu.:0.000   1st Qu.:0.000  
##  Median :1.000   Median :1.000   Median :0.000   Median :1.000  
##  Mean   :0.912   Mean   :0.958   Mean   :0.441   Mean   :0.724  
##  3rd Qu.:1.000   3rd Qu.:1.000   3rd Qu.:1.000   3rd Qu.:1.000  
##  Max.   :1.000   Max.   :1.000   Max.   :1.000   Max.   :1.000  
##  NA's   :18420   NA's   :18420   NA's   :18420   NA's   :18420

Classificador para “completar” o conjunto de dados

O Classificador escolhido foi Florestas Aleatórias (Random Forest). Os hiperparâmetros escolhidos foram: * mtry = 5 * splitrule = gini * min.node.size = 1 * num.trees = 200

## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction    1    2    3    4    5    6
##          1  1.6  0.0  0.0  0.0  0.0  0.0
##          2  0.1  3.2  0.0  0.0  0.0  0.0
##          3  0.0  0.0  1.8  0.0  0.1  0.0
##          4  0.0  0.2  0.2 16.4  0.9  0.5
##          5  0.0  0.3  0.4  2.3 45.4  3.1
##          6  0.0  0.0  0.1  0.9  1.8 20.6
##                             
##  Accuracy (average) : 0.8899

Completando o dataset

dataset_predicted <- cbind(dataset_classificador_incompleto[, -11], Code = predict(rf, newdata = dataset_classificador_incompleto))

dataset_completo <- rbind(dataset_classificador_completo, dataset_predicted)

Clustering Analysis

Escolhendo o melhor número de clusters por 2 métodos: Calinski-Harabasz (CH) e Average Silhouette Width (ASW). A escolha se dá pelo número de cluster que maximiza o “score” dos dois métodos, no caso o melhor número de clusters é 2. A técnica de clusterização utilizada no artigo é o CLARA (Clustering Large Applications)

Principal Component Analysis (PCA)

Número de observações: 35855.
Número de variáveis: `9.
Teste de Esfericidade (H0: Variáveis Independentes)

bart_spher(dataset_pca)

##  Bartlett's Test of Sphericity
## 
## Call: bart_spher(x = dataset_pca)
## 
##      X2 = 169022.455
##      df = 36
## p-value < 2.22e-16

Gráfico de Pareto para variância explicada

pareto.chart(summary(pca)$importance[2,])

##      
## Pareto chart analysis for summary(pca)$importance[2, ]
##       Frequency Cum.Freq. Percentage Cum.Percent.
##   PC1   0.36470   0.36470   36.47000     36.47000
##   PC2   0.18867   0.55337   18.86700     55.33700
##   PC3   0.15571   0.70908   15.57100     70.90800
##   PC4   0.10423   0.81331   10.42300     81.33100
##   PC5   0.06538   0.87869    6.53800     87.86900
##   PC6   0.05817   0.93686    5.81700     93.68600
##   PC7   0.03965   0.97651    3.96500     97.65100
##   PC8   0.01255   0.98906    1.25500     98.90600
##   PC9   0.01094   1.00000    1.09400    100.00000

Gráficos de contribuição das variáveis e observações.

dataset_pca <- dataset_completo[, 2:10]
a <- FactoMineR::PCA(dataset_pca)

fviz_pca_var(a, col.var = "contrib",
             gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"), 
             repel = TRUE)

fviz_pca_ind(a,
             geom.ind = "point", # show points only (nbut not "text")
             col.ind = dataset_completo$Code, # color by groups
             addEllipses = TRUE, # Concentration ellipses
             legend.title = "Code Health"
             )

Clustering

Como obtido o número de clusters ideal é 2, assim, iremos agrupar os 6 fatores em dois grupos.

Grupo 1 = 1 Fator e Grupo 2 = 5 Fatores

\[\frac{6!}{5!1!} = 6\text{ combinações}\] * Grupo 1 = 2 Fatores e Grupo 2 = 4 Fatores

\[\frac{6!}{4!2!} = 15\text{ combinações}\] * Grupo 1 = 3 Fatores e Grupo 2 = 3 Fatores

\[\frac{6!}{3!3!2} = 10\text{ combinações}\] Logo, o número total de combinações é \(6+15+10 = 31\).

getCode <- function(soma, comb){
  comb = unlist(strsplit(comb, " "))
  for(i in 1:2){
    arr = as.integer(unlist(strsplit(comb[i], "")))
    if(as.integer(soma) %in% arr){
      code = i
    }
  }
  return(code - 1)
}
combs <- c("1 23456", "2 13456", "3 12456", "4 12356", "5 12346", "6 12345",
           "12 3456", "13 2456", "14 2356", "15 2346", "16 2345", "23 1456",
           "24 1356", "25 1346", "26 1345", "34 1256", "35 1246", "36 1245",
           "45 1236", "46 1235", "56 1234", "123 456", "124 356", "125 346", 
           "126 345", "134 256", "135 246", "136 245", "145 236", "146 235", 
           "156 234")

Ajustando o modelo de Regressão Logística Elastic Net

set.seed(2)
ctrl <- trainControl(method="cv", returnResamp="all", classProbs=TRUE, summaryFunction=twoClassSummary)

for(comb in combs){

  dataset_train <- dataset_classificador_completo %>%
      mutate(index = 1:n()) %>%
      group_by(index) %>%
      mutate(Code = getCode(Code, comb)) %>%
      ungroup() %>%
      mutate(Code = as_factor(Code),
             index = NULL)
  
  levels(dataset_train$Code) <- make.names(levels(factor(dataset_train$Code)))

  glmnet_model <- train(Code~., data = dataset_train, method = "glmnet",
                               preProcess = c("center","scale"),
                               trControl = ctrl, metric = "ROC", 
                               tuneGrid = expand.grid(alpha = seq(0, 1, 
                                                                   by = 0.01),
                                                      lambda = seq(50, 0, 
                                                                   by = -1)))
  glmnet_model
  plot(glmnet_model)
  print(print(confusionMatrix(glmnet_model)))
}

## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.3
##         X1  1.7 98.0
##                             
##  Accuracy (average) : 0.9807
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.3
##         X1  1.7 98.0
##                             
##  Accuracy (average) : 0.9807
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.6  0.2
##         X1  3.1 96.0
##                             
##  Accuracy (average) : 0.9666
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.6  0.2
##         X1  3.1 96.0
##                             
##  Accuracy (average) : 0.9666
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.1
##         X1  2.5 97.4
##                            
##  Accuracy (average) : 0.974
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.1
##         X1  2.5 97.4
##                            
##  Accuracy (average) : 0.974
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.1  0.0
##         X1 19.5 80.4
##                             
##  Accuracy (average) : 0.8047
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.1  0.0
##         X1 19.5 80.4
##                             
##  Accuracy (average) : 0.8047
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 29.0 19.4
##         X1 19.2 32.4
##                             
##  Accuracy (average) : 0.6141
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 29.0 19.4
##         X1 19.2 32.4
##                             
##  Accuracy (average) : 0.6141
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.0
##         X1 24.2 75.8
##                             
##  Accuracy (average) : 0.7582
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.0
##         X1 24.2 75.8
##                             
##  Accuracy (average) : 0.7582
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  1.4  0.4
##         X1  4.0 94.2
##                             
##  Accuracy (average) : 0.9562
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  1.4  0.4
##         X1  4.0 94.2
##                             
##  Accuracy (average) : 0.9562
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.1  0.4
##         X1  4.1 95.3
##                             
##  Accuracy (average) : 0.9548
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.1  0.4
##         X1  4.1 95.3
##                             
##  Accuracy (average) : 0.9548
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.2  0.3
##         X1 21.1 78.4
##                             
##  Accuracy (average) : 0.7855
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.2  0.3
##         X1 21.1 78.4
##                             
##  Accuracy (average) : 0.7855
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 32.2 22.2
##         X1 17.7 27.8
##                             
##  Accuracy (average) : 0.6005
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 32.2 22.2
##         X1 17.7 27.8
##                             
##  Accuracy (average) : 0.6005
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.0
##         X1 25.9 74.1
##                             
##  Accuracy (average) : 0.7412
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.0
##         X1 25.9 74.1
##                             
##  Accuracy (average) : 0.7412
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.7  0.3
##         X1  5.6 93.3
##                             
##  Accuracy (average) : 0.9409
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.7  0.3
##         X1  5.6 93.3
##                             
##  Accuracy (average) : 0.9409
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  1.6  1.0
##         X1 21.7 75.7
##                            
##  Accuracy (average) : 0.773
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  1.6  1.0
##         X1 21.7 75.7
##                            
##  Accuracy (average) : 0.773
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 36.5 25.7
##         X1 15.5 22.3
##                             
##  Accuracy (average) : 0.5879
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 36.5 25.7
##         X1 15.5 22.3
##                             
##  Accuracy (average) : 0.5879
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.3  0.6
##         X1 27.7 71.4
##                             
##  Accuracy (average) : 0.7172
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.3  0.6
##         X1 27.7 71.4
##                             
##  Accuracy (average) : 0.7172
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.3  0.2
##         X1 21.9 77.7
##                             
##  Accuracy (average) : 0.7792
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.3  0.2
##         X1 21.9 77.7
##                             
##  Accuracy (average) : 0.7792
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 33.5 22.6
##         X1 17.2 26.6
##                             
##  Accuracy (average) : 0.6015
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 33.5 22.6
##         X1 17.2 26.6
##                             
##  Accuracy (average) : 0.6015
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.1
##         X1 26.7 73.2
##                             
##  Accuracy (average) : 0.7316
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.1
##         X1 26.7 73.2
##                             
##  Accuracy (average) : 0.7316
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 65.6 29.6
##         X1  2.2  2.6
##                             
##  Accuracy (average) : 0.6818
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 65.6 29.6
##         X1  2.2  2.6
##                             
##  Accuracy (average) : 0.6818
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 14.2 11.1
##         X1 29.6 45.2
##                             
##  Accuracy (average) : 0.5932
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 14.2 11.1
##         X1 29.6 45.2
##                             
##  Accuracy (average) : 0.5932
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 69.7 22.5
##         X1  2.7  5.1
##                             
##  Accuracy (average) : 0.7487
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 69.7 22.5
##         X1  2.7  5.1
##                             
##  Accuracy (average) : 0.7487
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  1.8  0.5
##         X1  6.2 91.5
##                             
##  Accuracy (average) : 0.9331
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  1.8  0.5
##         X1  6.2 91.5
##                             
##  Accuracy (average) : 0.9331
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  3.5  1.8
##         X1 21.5 73.2
##                             
##  Accuracy (average) : 0.7672
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  3.5  1.8
##         X1 21.5 73.2
##                             
##  Accuracy (average) : 0.7672
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 39.8 27.8
##         X1 13.9 18.5
##                             
##  Accuracy (average) : 0.5829
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 39.8 27.8
##         X1 13.9 18.5
##                             
##  Accuracy (average) : 0.5829
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.9  1.5
##         X1 28.7 68.9
##                             
##  Accuracy (average) : 0.6983
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.9  1.5
##         X1 28.7 68.9
##                             
##  Accuracy (average) : 0.6983
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  1.1  1.0
##         X1 22.7 75.1
##                             
##  Accuracy (average) : 0.7625
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  1.1  1.0
##         X1 22.7 75.1
##                             
##  Accuracy (average) : 0.7625
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 37.1 25.5
##         X1 15.4 22.0
##                            
##  Accuracy (average) : 0.591
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 37.1 25.5
##         X1 15.4 22.0
##                            
##  Accuracy (average) : 0.591
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.1  0.2
##         X1 28.4 71.4
##                             
##  Accuracy (average) : 0.7148
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.1  0.2
##         X1 28.4 71.4
##                             
##  Accuracy (average) : 0.7148
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 68.7 30.0
##         X1  0.8  0.5
##                             
##  Accuracy (average) : 0.6925
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 68.7 30.0
##         X1  0.8  0.5
##                             
##  Accuracy (average) : 0.6925
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.0
##         X1 45.5 54.5
##                             
##  Accuracy (average) : 0.5454
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0  0.0  0.0
##         X1 45.5 54.5
##                             
##  Accuracy (average) : 0.5454
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 72.4 22.9
##         X1  1.7  3.0
##                             
##  Accuracy (average) : 0.7541
## 
## Cross-Validated (10 fold) Confusion Matrix 
## 
## (entries are percentual average cell counts across resamples)
##  
##           Reference
## Prediction   X0   X1
##         X0 72.4 22.9
##         X1  1.7  3.0
##                             
##  Accuracy (average) : 0.7541

Clustering and Elastic Net Logistic Regression as Support Tools for Honeybee (Apis mellifera) Colonies Health Diagnosis

Daniel de Amaral

2019-11-10