In the present example, we focus on classifying image using keras-TensorFlow in R. To this end, we selected 20 objects (10 airplanes and 10 cars) from google.com and we apply keras to image recognition.

Many passengers have been experiencing this unpleasant feeling of flight delays, sometimes causing immeasurable damage and inconvenience, leading to fury and frustration. In addition, passengers are not always entitled to compensation due to delays. In civil aviation, a flight is considered late when it arrives or departs 15 or more minutes after the scheduled time. Airlines point to several causes that contribute to flight delays, such as weather conditions, aircraft maintenance problems, security problems, aircraft late arrived for the previous flights and air traffic congestion. The present study aims to apply data visualization tools in order to find insights on dataset. In this context, it is related with Airline On-time Performance data gathered by Bureau of Transportation Statistics (BTS). BTS collect information relating to airline operations, flight delays and airline tickets in the US airline industry. Our analysis will be based on the year 2017 evaluating about 6 million records. The objectives of the present study are as follows: 1. Exploring historical arrival delays at different airlines, airports and daytime schedules, trying to get some information on which airlines or airports are more likely to delay. 2. Study the effect of the cause of the delay. 3. Build a predictive model to predict flight delay.

This data set is analysed in R using 04 algorithms for the prediction of diabetic in pregnant women: 1. Logistic Regression; 2. Decision Tree; 3. Random Forest; 4. Support Vector Machine (SVM) and; 5. Comparison of Model Accuracy.