;gender;age;continent;exp_ai;trust_ai;workplace_ai;risk_awareness;SVM;ANN;Linear Regression;XANN;Random_Forest;Decision_Tree;Best_Model;RT1;RT2;T1;T2;RC1;RC2;Remarks_on_Model
0;2;3;3;1;2;3;3;2;1;6;5;5;4;SVM;2;1;Sensor 12 has a negative impact;I would look closer at the metadata;Sensors;Lifespan;I feel that I am missing more data.   I would have liked more data and more information about the SVM. I would have liked more information on all of the choices to be honest. I found the task somewhat complicated as I have very little knowledge about this subject 
1;2;4;3;1;3;3;3;6;4;6;7;5;5;XANN;3;1;Sensor 12 has a positive influence on the URL for the prediction of the specific turbine, which is smaller than s14 and s4, bu greater than s9.;Yes;features;remaining useful time;Not sure I understand the question. I do not think there is something I missed in the explanations.
2;1;3;3;2;4;4;5;5;5;4;4;5;5;XANN;2;1;It is right behind cycle and id, therefor the most important sensor. ;I would look into all information necessary in order to make such a huge purchase.;sensors;performance;It's really hard for me to say as an outsider, because these things I'm completely unaware of. I have no knowledge in this specific area, I'm reading it for the first time today, so I know nothing of it. I would say you have provided a lot of data, a lot of explanations, so if I had to guess (because I don't know any better), I would say yes, I would feel confident using this model. 
3;1;2;3;2;4;4;4;2;3;4;5;3;3;RF;2;1;I have no idea, the sensors measure service life of turbines, but i have no idea how they are connected to RUL (I thought that data from RUL was combined with data from sensors) ;Sensors;sensors;RUL;nothing.
4;1;2;4;2;2;4;3;5;1;6;5;7;6;RF;2;1;Sensor 12 is the 4th most influential even though most of them have a very alike impact.;Sensor values. They are always the most trustable source for data.;algorithms;RUL;I don't have a lot of background, if any, with machine learning but I would have loved to be told more details on graphics. Some of them are very complex that I doubt my answers. I'd say that, for the most part, a little bit of randomness (as provided with the random forest) should be allowed and help the mean results, as there is always some level of uncertainty for every sensor.
5;2;2;3;2;2;4;3;5;5;5;5;4;4;LR;3;3;Sensor 12 is more precise than sensor 21;Yes, definitely.;behaviors;sensors;I chose this model because It looked easy to understand but it is not, at least for me.
6;2;3;3;2;4;4;4;6;2;6;6;4;5;XANN;2;1;I can see sensor 12 has a positive influence but I would not be able to explain why.;I would need someone that understands the dataset better than me to check these value before I purshase them.;sensors ;remaining useful life;The hidden layers 
7;2;2;3;1;3;2;1;1;2;1;1;1;3;DT;2;3;no idea. Sorry;metadata;settings;sensors;"I didn't understand the explanations in the first place. They are too complex, too complicated; the graphic shown is too small, I can't make anything out of it."
8;2;3;3;2;3;3;3;4;4;4;4;4;4;XANN;3;3;I have no idea. This is far too technical for someone not from a STEM background. I can't even see sensor 12.;Yes;Technical term;useable lifespan;I don't feel confident at all. 
9;1;4;6;2;3;5;2;1;1;1;1;1;1;XANN;2;1;Sensor 12 is the third most important feature;Sensor values. ;Features;Safety;I don’t understand this model at all. 
10;1;2;1;1;3;5;5;5;4;6;4;5;5;XANN;2;1;It has the second highest negative influence on RUL;Sensor values;Sensors ;Remaining useful life;Some Form of confidence in the predictions eg 95% confidence interval on influence or maybe an error estimate eg influence is negative and 100+-5 
11;1;2;3;1;4;4;3;5;5;7;4;5;6;XANN;2;1;It's the most important sensor according to the  Feature importance of all observations  graph. It has a good positive influence;The metadata is the thing that has most influence in its behaviour, therefore I would look closer on the metadata values;values;useful life;If simulations were done to prove that this data is useful or not
12;2;3;3;1;2;3;2;6;4;5;5;4;4;RF;3;3;Turbine needs to be maintained before the flight ;Would look at both ;Model;Function ;Not confident 
13;2;2;3;2;4;5;2;4;3;5;5;5;4;RF;2;1;Sensor 12 has a major influence compared with the majority of the other sensor, except for, sensors 9, 14, and 11, whose importance is higher for the prediction of the RUL.;I could have a look at it, but honestly, I wouldn't understand what those values mean.;sensors;RUL;I would maintain my decision and use this model as a support decision.
14;1;2;3;4;5;5;3;6;1;6;5;3;4;SVM;1;3;The influence of the sensor 12 compared to other turbines is positive.;Yes, I would look at the sensor vaules when purchasing an aircraft.;sensors;RUL;I would use other colours in the graphics for example: red which turns green.
15;1;3;3;2;3;4;3;4;2;5;5;3;4;XANN;2;1;Sensor 12 has positive influence for the prediction of the turbine. In terms of feature importance it is the most important sensor.;Yes, I would look at all the metadata to be sure that turbines are still OK to fly.;sensors;RUL;Although I can understand the concept and find it reasonably readable, some other people may find the ML/AI complicated, and may possibly require a simpler language or some analogies to grasp the concept.
16;1;2;3;2;3;4;2;6;1;6;6;6;7;LR;2;1;Sensor 12 influences positively as it shows from the diagram above as it is one of the 3 axis. (Probably z-axis). Thus as it increases its positive value, more it influences the R.U.L. of the engine.;Of course. It is data that I can probably predict if my investment is safe.   To my intellect it is a better investment to know the possible odds unlike not knowing them at all. (The risk is involved in both situations so I don't see any reason not to know the sensor values.);sensors;R.U.L.;I actually believe that this particular model seems the more reliable to show the (average) R.U.L. of the specific turbine. The tree/forest ones seem to me too unreliable due to their statistic process, the networks seem unfitting for this kind of analysis as they seem much more oriented on trial and error process of thought and the vector, well, I am not that sure how the vector can process the data correctly by looking at the results.
17;2;2;3;1;2;1;2;6;3;5;6;4;4;XANN;3;1;S12 has the 3rd highest model output value compared to the other sensors. ;Yes, I feel it would be helping in knowing the turbines remaining useful life for safety before purchasing any aircraft. ;Sensors ;Lifespan ;I think more examples would be useful with real life scenarios so it’s clear to the consumer just how helpful the model is. This would make it more relatable. 
18;2;2;3;1;3;3;4;5;2;5;4;5;3;SVM;2;3;Sensor 12 tends towards 0.75 as the number of cycles increase.  This type of behavior is not the same for all sensors.;I would look closer to the sensor values and see how they relate instead of looking just at the metadata values individually.;parameters mesured by the sensors;remaining life;I think the model should explain how the combination of every feature is done and how the final result is reached.
19;1;2;3;2;3;4;4;6;5;6;6;6;6;XANN;2;1;Sensor 12.;yes, of course;sensor;performance;The specific and detailed mechanism of the AI work
20;1;4;3;1;3;4;3;6;6;6;6;6;6;RF;3;1;Sensor 12 would give information combined with the other sensors to influence the metadata for different flight conditions.;The metadata would be most useful as this gives a more comprehensive outlook with the combined sensor data.;data;RUL;There will be random events that could occur and so not be predicted and any human interaction that may occur is prone to error.
21;1;2;3;2;4;3;4;5;3;5;5;4;5;XANN;3;1;Sensor 12 has the biggest average impact (out of sensors) on model output magnitude. In this specific case its influence is positive but  sensor 9 has a bigger positive influence on RUL. When calculating other turbines RUL it can have negative influence.;I would compare both sources of information.;features;RUL;Further explanation if the result was calculated for the best or for the worst possible conditionts.
22;1;4;3;1;4;3;2;6;4;6;7;6;5;XANN;2;1;s12 has the highest importance in the data reading  and the second positive influence;i´d look closer the metadata;models;lifetime;Reliability in real cases of the model
23;1;2;3;1;4;4;4;5;2;5;5;3;3;XANN;3;1;According to the graph s12 measures are more important than all other sensor based measures;personally no, but I would definately ask someone with the  know how  to do it for me after doing this study;sensors;RUL;what is this 104.87 represent, what are the units of measurement?
24;2;3;3;1;3;1;3;3;6;5;6;1;1;Blackbox ANN;2;1;Sensor 12 is 12 flight cyckles left before turbine fail?;Yes;Sensor;Specific;Nothing
25;1;2;3;1;4;4;3;7;2;6;7;5;2;XANN;3;1;Sensor 12 has a negative influence on RUL for this specific turbine.;Sensor values. The sensor values would assure me of a good buy, more than the metadata.;Sensors;RUL;Maybe this model applied to a short  common knowledge  example, clearly showing its predictability/forecasting ability.
26;2;2;3;1;3;3;3;4;6;4;6;6;6;SVM;2;3;has a influence because has more cycles  and higher setting;yes because it may be more likely to become faulty;features;RUL;Applied to a situation i am familiar with.
27;2;2;3;2;3;5;4;5;7;3;6;5;4;XANN;2;1;Of all sensors, the state of sensor 12 is the one that most influences prediction. Sensor 12 is the most important feature after cycle  and id;Yes. Given the information previously provided, I would take metadata and sensor values for support in choosing;Features;RUL;More informariam about the data, such as, quantity and data distribution
28;1;2;3;1;4;4;4;5;2;7;5;3;6;LR;2;1;it's relative live expectancy is lower due to the linear combination of sensor 12 and it's respective cycle, which means, that the RUL will get lower if sensor 12 is looked at.;Yes, although one may not understand this correctly the first time they look at it.;models;RUL;Some explanations for some technical terms.
29;1;2;1;1;3;4;2;3;5;6;4;4;4;LR;3;3;It appears that sensor 12 mostly has the same influence regardless of cycles or its value;metadata;sensors;remaining useful life (RUL);The graphs are difficult.
30;2;2;3;2;4;4;3;3;3;6;5;4;5;LR;3;3;Positive influence on the RUL;Sensor values;sensors;RUL;How the feature combinations are added together
31;1;2;3;1;4;4;2;6;2;6;5;3;5;LR;3;3;I don't think there is much of an influence here.;Yes, I think I would.;sensors;inspection;I don't know.
32;1;3;3;2;3;4;3;5;5;6;5;2;4;LR;3;3;The effect on the specific turbine is the same when compared to other turbines.;Sensor values.;values;lifetime;More information.
33;2;2;3;1;3;3;3;5;1;5;5;5;6;XANN;2;2;Sensor 12 has a positive influence on the model output value as it is higher than the model output value;Would look more closely at sensor values as these give you an idea of the wear and tear on the turbine. Metadata just gives you flight conditions;flight conditions;wear and tear;Would like to see more raw data
34;1;3;3;1;2;1;3;6;2;5;4;4;4;SVM;2;3;At the end of the cycle it takes a lower value.;If I don't have other data, then yes.;sensors' value;remaining life;The detailed algotihm with values and critical values.
35;1;2;3;1;3;4;3;2;1;5;2;5;5;LR;2;1;It's in the middle, So it is a dependeble variable.;Yes i would look closer.;sensors;state;A simplified visual representation
36;2;2;3;1;3;4;3;5;1;3;6;3;2;SVM;3;3;I have no idea. It seems that with less cycles the dots are darker and so RUL approaches 0? But I am very unsure about it.;Metadata, it seemed that the most valuable indicator was cycle;factors;RUL;I understand it far less that I thought I did. The color model seemed clear, but perhaps somethin easier like the artificial neural network (with a clear blu = positive and red= negative) would be better. I don't know if the colour mixing or being very separate is better or worse in this model. I also know nothing about AI, perhaps knowing at least something is necessary to understand every one of the models.
37;2;3;3;2;4;4;3;6;3;6;6;6;4;RF;2;1;Sensor 12 is a relatively important feature of all the importance of observation chart. It is showing a cluster of data in the random forest.;I would look at the sensor values.;Sensors;Lifecycles;Personally an worked example to gain experience of interpreting the model would help to give more confidence in interpreting it.
38;1;4;5;2;2;2;4;6;2;6;5;5;3;RF;2;1;Wind turbines have 8000 components rotors 80m long and sit 180m high. Despite this size they use tiny sensors to function despite stresses & vibration.;Yes;Build;RUL;yes
39;1;3;3;1;4;5;3;5;2;7;5;6;6;LR;2;1;I'd need to see the chart more clearly to understand the regression analysis and relationship between S12 and the dependant variable, but it does appear that as the value of S12 increases, the RUL remains static. ;I'd use the sensor data, if the assumption that smaller aircraft behave similar to large ones is correct - the data could therefore be scaled down to account for the smaller plane. ;sensors;RUL;I would feel confident using linear regression because its something I use day to day and I'm familiar with the modelling techniques for it. It does make me slightly biased, however I do think showing correlations between the sensors and various data is the most useful way of predicting performance. The more data thats added, the stronger the model becomes. 
40;2;1;3;2;3;4;3;3;3;4;5;6;5;RF;2;1;There’s no data;Probably not;sensor;state;I don’t real know to be honest, for me there’s something about the way the data is showned
41;2;2;3;5;2;3;3;5;7;5;6;3;6;XANN;2;1;Sensor 12 has a positive influence on the RUL, however not as much as s9. s21,s7 and s11 all have a negative impact on RUL.;Sensors;Sensors;RUL;The explanation has to start simple and build up in complexity like this one. Additionally, the ANN explanation used the neuronal networks as an explanation base which made it easier to understand from the beginning as participants may have prior knowledge of these networks making it easier to relate it to the data presented.
42;2;5;3;2;2;3;1;5;4;2;6;5;4;XANN;1;1;sensor 12 is a positive influence on a specific prerdiction in the dataset presented;yes i would want it to be as safe as possible so would look at all aspects of the aircraft;sensors;positivity;what the sensors are for and what they do
43;1;2;3;1;3;3;2;5;2;5;5;2;2;SVM;2;1;Sensor 12 has a positive influence;Sensor values;measured sensor values;RUL;
44;1;2;4;2;4;3;3;5;3;6;3;6;3;LR;1;1;Sensor 12 predict approximately RUL of the turbine, while for other models the sensor values are dependent and are combined;Yes;Sensor;RUL;Ability to use two or more and get the RUL independent of ither sensor
45;2;2;3;2;3;4;4;5;2;7;3;3;2;LR;2;1;sensor 12 generally slightly improves the RUL of the specific turbine compared to the other turbines.;sensor values;sensors;RUL;a better explanation of the function of the sensors/settings.
46;1;2;3;1;4;4;4;3;1;5;5;4;6;DT;2;3;RULs where sensor 12 is present are lower than the other RULs of the same branch where this sensor does not appear.;If I were to buy an used private aircraft I would look closer to the sensor values because they show in an easier way if the aircraft is in good condition or not.;sensors;performance;Showing a general result as a resume of how every sensor is showing positive or negative results.  Also there is a problem with this support system in this scenario, the numbers are far too small to be read even with the zoom item you supported us. This problem is easily solved and because of that reason I did not have that in count in order to make my decision.
47;1;3;3;1;2;2;2;4;4;4;5;4;4;XANN;3;1;Third most important feature n prediction with a high predictive value;Metadata;features;lifetime;
48;1;2;3;1;2;2;2;4;5;5;6;6;5;XANN;3;1;Sensor 12 has the most positive impact on the RUL apart from Sensor 9. The Mean of Sensor 12 is actually the highest positive however it's overall influence on the RUL seems to be less in actuality than Sensor 9.;I would gues the sensor values as you could argue the variance would be smaller therefore more accurate predictions due to this?;Sensors;RUL;With this one the processing which is hidden, the original dataset so show why/how it comes to the 104.87 result. So you can also see/check to see if you agree with the raw data rust small bits of it.
49;1;2;3;1;4;4;3;5;2;4;6;6;4;SVM;1;1;It has positive influence on the RUL.;I would look closer at the metadata.;n-features;ROL;How much data with n-feature can algorithm support?
50;1;4;3;2;4;4;3;5;6;6;5;6;6;XANN;3;1;Sensor 12 has a positive influence on the prediction of RUL and is the third most important feature of the observations in the data available.;It would be useful to check these metadata values, but I would not base my decision sole on this check as,  behave similar  could hide unforseen relations.;features;RUL;I would fee more confident having a few more examples of the predictions.
51;2;4;3;1;2;3;3;5;1;5;6;3;2;LR;3;2;The data for sensor 12 predicts a RUL of ~175, which is comparable to the other sensors shown.;I would look closer at the metadata than the sensor values, but I would always consider both if I was making such a decision in 'real life';sensors;RUL;I would like to see the complete dataset for all of the sensors and their comparisons to all of the possible settings.  Then I could understand e.g. whether some sensors give much higher or lower readings than others and where the overall RUL result is coming from a bit more comprehensively.
52;1;2;3;1;4;4;3;5;6;6;4;5;6;XANN;2;1;Sensor 12 influence positive on the RUL;I would look closer at the sensor values;sensors;lifecycle;I feel confident in using this model as support system. 
53;1;3;3;2;2;2;3;5;2;5;5;5;4;LR;3;3;The regression line for sensor 12 is nearly horizontal - suggesting that its predictive value is inferior compared with the other turbines.;Probably the metadata - the sensor information doesn't appear to be great.;factors that the sensors measure;RUL;In hindsight I'd have liked to have seen all of the different measures in one plot.  The plot of the different relative contributions provided by the other algorithms was actually very useful.
54;1;3;3;3;3;3;4;5;4;6;6;2;5;Blackbox ANN;1;1;identify if this turbine is available to fly in this conditions recorde by sensor;the turbine functions is regulated by al based that automically decided if the turbine need to maintained before fligth;decisions;maintenance;no
55;2;3;3;3;3;2;3;6;2;5;4;6;5;SVM;3;3;I would say it has equal importance.;Sensor values;sensors;RUL;I miss control values to compare the values obtained in the specific turbine.
56;1;2;3;1;4;5;1;2;3;5;5;6;6;RF;2;1;Details for sensor 12 are not provided in the dataset, but by the feature importance of all observations chart, it can be seen that sensor 12 has the fourthmost relevant result.;Metadata;sensors;RUL;The model provided fits my understanding of AI the best, so I think it'll be the most useful. It also provides the data in a simple graph format, compared to cumbersome datasets.