assignment 2 & 3 Big Data Analysis Implementation in Daily Activities

Big data Analysis implementation in daily activities,
Using a Samsung's Health Tracker app to monitor my daily step's between June and July 2017 and compare it between the other app user .


 it was all started when the app give constant notification about how much the time and distance I've covered when i was walking even on short period of time. and the app also provide me with a monthly report, this report also tells me about the total time, distance & steps that i gain in that month. and i was curious about this report and wanted to analyze more about the information since it is one of big data analysis implementation in daily activities so i picked up two months where at that month is where i spent my summer break on, 

JUNE
at this month it was the beginning of a holiday where i spent a lot of my time outside of my house to do certain activities. as it could be seen on the picture above i spent almost 4 hours on June in total and about 16.86 km in the distance, its a great result in my opinion, because as we could see from the picture my monthly average time of walking was only 2hrs and 39mins so compared to this month it is way above average and the number of steps is way better than the previousa months.     

JULY

July is where most of the walking happened it took 5hrs and 16mins in total of time and covered 23.21km in distance it is the biggest achievement in 2017 for me. but it doesn't end there because i start questioning about how does people my age performed am i below or above the average.

COMPARISON TO OTHERS

this step leaderboard is measured from the amount of time and distance of a person that are spending their time walking in a full year, 5% is being the highest since people at this percentage rarely commute by transportation and at the lowest percentage is 100% where people at this percentage rarely walks or it could be a disabled person which couldn't walk, after i gathered the information about the leaderboard/statistics i was at the 58th rank, this statistic is measured from my age only, that is 19 years old, so i am way below the average where the average of this leaderboard of my age is 45%. but how do i compare to rest of the app users.
significantly my rank increased from 58% to 49% that also means that there is a variety of age that are in this leaderboard from a kid to an elderly could be at this leaderboard even though my rank is higher but it is still below the average an this is the end of the comparison what i got from this simple experiment is even with an unimportant unit such as steps we could get a lot of information such as how much we spent and how much we've covered and how do our performance compared to another, an useless/unnimpotant thing could be important if we see it in many ways and it is all depends on how we managed to use it and how we are able to stand for the complexity of it.    


Komentar

Posting Komentar

Postingan populer dari blog ini

assignment 6 comparison of all 4 method

Decision tree C4.5 C4.5 is an algorithm used to generate a decision tree developed by Ross Quinlan. C4.5 is an extension of Quinlan's earlier ID3 algorithm. The decision trees generated by C4.5 can be used for classification, and for this reason, C4.5 is often referred to as a statistical classifier. Authors of the Weka machine learning software described the C4.5 algorithm as "a landmark decision tree program that is probably the machine learning workhorse most widely used in practice to date". advantages: •  Build models that could easily interpreted •  Easy to implement •  It can use categorical and continuous values •  Deals with noise disadvantages: •   Small variation in data can lead to different decision trees (especially when the variables are close to each other in value) •  Does not work very well on a small training set Naive Bayes In machine learning, naive Bayes classifiers are a family of simple probabilistic c...
Baca selengkapnya

assignment 4 big data (prediksi elektabilitas caleg) solved using rapidminer

Gambar
Rapid Miner is a data science software platform developed by the company of the same name that provides an integrated environment for data preparation, machine learning, deep learning, text mining, and predictive analytics. It is used for business and commercial applications as well as for research, education, training, rapid prototyping, and application development and supports all steps of the machine learning process including data preparation, results visualization, model validation and optimization the reason why i choose rapidminer is because it is easy to use and it responded rapidly based on the instruction that is given, i will do the prediction by using three different models. those models are; decision tree, naive bayes & k-nearest neighbor. prediction using decision tree. Description A decision tree is a tree like collection of nodes intended to create a decision on values affiliation to a class. Each node represents a splitting ...
Baca selengkapnya
 Application of ICT use in schools in Nigeria  The adoption and use of ICTs in schools have a positive impact on teaching, learning, and research. Despite the roles ICTs can play in education, secondary schools in Nigeria have yet to extensively adopt them for teaching and learning. Efforts geared towards integration of ICTs into the secondary school system, have not had much impact. Problems such as poor policy and project implementation strategies, and limited or poor information infrastructure militate against these efforts. In order to ensure that ICTs are widely adopted and used in Nigeria's secondary school system, the following efforts should be taken. Government should ensure that ICT policy statements are translated into reality. An ICT policy implementation commission should be created. This commission should be funded and given the power to provide ICT facilities in the schools and monitor their use. All secondary schools should be made benefic...
Baca selengkapnya