AIT Online Education Camp 2021 Report

Online Education Camp 2021 Report

AIT Online Education Innovation Camp 15th to 28th July 2021 A two-week Online Education & Innovation Camp and Study Tour is organized by AIT through the Office of Special Degree Programs for students of King Mongkut’s Institute of Technology Ladkrabang (KMITL) aiming to expose the students to various areas of specializations. Student participants were from different nationality (Thai-8, Indian-1 and Philippines-1) and educational backgrounds are from Robotics and AI and from Software Engineering. As a precaution to the ongoing pandemic, the classes were held online mode. This is the second AIT Online Education Innovation Camp that was organized successfully on the theme “Ignite, Innovate and Inspire” the young minds of the undergraduate students through state-of-the-art seminars and hands-on sessions in cutting edge technologies. The aim of this camp is to help the students discover their interests, create and launch new ideas and become an inspiration and influencer to the community and also motivate them to pursue higher education. International Education Innovation Camp offered a multi-disciplinary program. Interactive sessions on new trends were delivered by AIT faculty and guest lecturer on – Artificial Intelligence for Human Brain Interaction with Systems, Augmented Reality, Big Data seminar and hands-on using “R”, Satellite/UAV- Remote Sensing, GIS hands-on Site suitability Mapping, Global Navigation Sattelite System, Air pollution mapping using Google Earth Engine, Data Science, Nano-Bioscience, Robotics Trends, Embedded Systems, Social Communicanal Skill workshop, Financial Technologies and Solutions and Information Technologies. As a precaution to the ongoing pandemic, virtual lab visits were arranged to give an opportunity for the students to have an actual visualization of the concept they are learning from the lectures. Laboratories visited include Mangrove Museum, Water Engineering Management Lab and Hydrology Simulation Prototype Models, Ambient Lab, Waste Water Treatment Lab and other EEM Facilities. The students were also given some challenging exercises such as “Building a Campus Information System” and “Noise Pollution Mapping in their Communities” through crowdsourcing Geo-App, they were tasked to create their own resume for job application. Students were ignited by brainstorming sessions to think of innovations for their mini project activity which was on Future Technology in Smart Phones. The students showed great enthusiasm in accomplishing all the given tasks. On July 28, 2021, the closing program and awarding of the certificates. The students were invited to present their respective mini projects. Before the awarding of certificates, students were given the opportunity to present their case studies which made use of the tools and concepts learned from their Camp.

A certificate of completion was awarded to each student and was witnessed by Dr. Somyot Kaitwanidvilai, Dean of Faculty of Enigineering, King Mongkut’s Institute of Technology Ladkrabang (KMITL), Dr. Chaowalit Hamomtree, Director of School of International Interdisciplenary Engineering Programs KMITL, and AIT representatives including the Dean of SET, Prof. Dieter Trau. STUDENT FEEDBACK Student feedbacks were also gathered as a basis of improving the Education Camp Program that is held annually. According to the students, the hands-on exercises on Epicollect using Geo App was very well-appreciated. Students were also fascinated by the information about AI – human brain interaction with computer by Dr. Chaklam. They also had fun creating they resume, professional profile in different platforms and the simulated interview. Students were very interested in processing and working on satellite data and preparing land surface temperature and air pollution maps. Students were interested about nutrition and the importance of food and dietry intake. The seminar in UAV made them think on the possible application that they can do in their respective fields. ORGANIZING TEAM Prof. Nitin Kumar Tripathi Director-Special Degree Programs Asian Institute of Technology [email protected] Mr. Arthur Lance Gonzales Program Officer Special Degree Program Asian Institute of Technology [email protected] Mr. Ranadheer Mandadi Program Coordinator Special Degree Program Asian Institute of Technology [email protected]

PROGRAM SCHEDULE DATE Morning Session Instructor Afternoon Session Instructor (10 AM - 12:00 PM) (1:30 PM – 4 PM) Day-1 Prof Nitin Tripathi Prof. Nitin Kumar Thursday Orientation & Virtual Ranadheer Mandadi GIS – Geographic Tripathi 15th July Campus Tour Mr. Arthur Lance Information Systems Dr. Sarawut Day-2 Global Navigation Mr Prapas Augmented Reality Friday Satellite Systems 16th June Epicollect – Geo App Mr. Ranadheer Hands – On Epicollect Day-3 Training and Mapping Mandadi Saturday 17th July Free Day Relax Day-4 Brain-Computer Dr. Chaklam GIS - Laboratory Session Mr. Ranadheer Sunday Interface Silpasuwanchai Mandadi 18 July Communicational Skill-1 Ms Arlene Gonzalez Innovations in Prof. Nitin Day-5 Dr Mongkol Technology Tripathi Monday Embedded Systems Dr. Rafaelle Ricco 19th July “R-Software” Data Mr. Ranadheer Nano Bioscience Analysis & Hands-on Mandadi Day-6 Session Tuesday Data Science Dr Manukid 20th July Robotics Trends IoT Application for (2:00 to 3:30) Day-7 Health Wednesday Dr. Chutiporn Satellite Remote Dr. Salvatore Anutariya 21st July Sensing (3:30 to 5:00) Virdis Day-8 Prof Nitin Kumar Communicational Ms. Arlene Thursday Tripathi Skill-2 Gonzalez 22nd July Free Day Relax Day-9 Friday Artificial Intelligence Prof. Matt Dailey Google Earth Engine Ms Shivani 23rd July Trends Day-10 Unmanned Aerial Dr. Sanit Arunpold Assignment Prof Nitin Tripathi Saturday Vehicle Hand – on Presentation Mr. Ranadheer 24th July Digital Advancements Mini Innovation Prof. Tripathi Day-11 in Fintech Solutions Ms Aishwarya Kapoor Project Presentation Prof. Dieter Trau Sunday Mr. R. Reddy 25th July by Students Day-12 Monday 26th July Day-13 Tuesday 27th July Day-14 Wednesday 28th July









Asian Institute of Technology Education & Innovation Camp 2021 Epicollect – Geo App Training and Mapping Unique Trees in Bangkok By Piyawud Koonmanee Nithiwat Pattrapong Mohamed Arfan Mohamed Nayas Joseph Leandre B. Derpo Puhnyanuj Smizdhanond On 27-Jul-2021

Questions that we asked: Firstly, we started with the information box, which tells you about the details and goals of this survey. Additionally, we also give a heads up for the person who filled the survey to download an app to identify the plants. The questions are straight forward until it meets \"Do you know about the tree?\" question. At this point, when the person who answer this question \"no\", it will then jump to the \"Description of the tree?\" so that they can give a brief physical information about it. If the answer for this question is \"yes\", it will proceed normally to the name of the tree. Then, we asked for the age of the tree. This can be roughly determined by the height of the tree, or, ask the planter. After we asked for the person to take a picture, we asked them \"how many trees are there?\". If they select \"more than one\", it will then go to the questions that asked for the number of the trees. However, if the person selected \"one\", it will jump to \"Where is it?\" which collects the location data.

Example of the responses:

Clusters map with satellite view of the age of the tree: Heat map based on the number of data collected:

Asian Institute of Technology Education & Innovation Camp 2021 Epicollect5 SOUND POLLUTION MAPPING BY Thaninrath Thiraphotiwat Pattaratorn Soranathavornkul Paramon Kanhasiri Noppasit Kasikijvorakul Chatchai Boonman On 27-Jul-2021

1. Sound Pollution Mapping - Noise pollution, also known as environmental noise or sound pollution, is the propagation of noise with ranging impacts on the activity of human or animal life. It cannot be seen, but it is present nonetheless, both on land and under sea. This is a noise pollution mapping survey for AIT Camp, which will be used for the project. Example of the response:



Heat map based on the number of data collected:

R Assignment Code Result Analysis From the result, it is a linear model of yield in relation of coefficients of elevation, area, latitude and longitude. It appears that latitude and longitude have a very significant relationship to the yield. The more latitude the less yield and the higher the latitude, the lower the yield. The reason that the latitude and longitude have a high correlation might be because of high mineral and nutrients concentration in the soil in the south-eastern area of the samples. The elevation has a very low correlation to the yield might be because that no matter the elevation, the concentration of mineral that is essential to the rice or other crops is very vary. However, the field size is having a negative relation to the yield here maybe something might be wrong with the dataset.

-2600.000000 -2200.000000 -1800.000000 -1400.000000 -1000.000000 -600.000000 0 170 340 1500.000000 1500.000000 680 Meters 2100.000000 2100.000000 KMITL Sa 2 2

atellite Image ¯ 2700.000000 3300.000000 3900.000000 -600.000000 -1000.000000 -1400.000000 -1800.000000 -2200.000000 -2600.000000 2700.000000 3300.000000 3900.000000 Made By Chatchai Boonman Data Collected from Google Earth Pro / Maxar Electronics Imagery Taken : 29/1/2021

726000.000000 730000.000000 734000.000000 738000.000000 742000.000000 746000.000000 750000.000000 School Noise Poll 2288000.000000 2292000.000000 2296000.000000 2300000.000000 2304000.000000 2308000.000000 2312000.000000 2 ¹½ Northwestern Prep ¹½ Elm Elementary 2288000.000000 2292000.000000 2296000.000000 2300000.000000 2304000.000000 2308000.000000 2312000.000000 2 1 cm = 24 km Airport_area POPULATION < 1500 1500 - 2500 2500 - 4500 4500 - 6500 6500 - 7046

lution Contour Map 2316000.000000 2320000.000000 2324000.000000 726000.000000 730000.000000 734000.000000 738000.000000 742000.000000 746000.000000 750000.000000 : Airport noise pollution that affects schools ½¹ Legends ½¹ ¹½ Runways ¹½ ¹½2316000.000000 2320000.000000 2324000.000000 Arterials ¹½ Schools CNEL_65 Airport_area ¹½ Made By Chatchai Boonman 1 centimeter = 2.02 kilometers 024 8 12 Kilometers 16

Puhnyanuj Smizdhanond Linear Regression Analysis by R studio Simple linear regression The graph above is plotted between rice_totalcost(Y) and rice_totalrevenue (X) The Call formula is rice_totalcost ~ rice_totalrevenue. Residuals: Minimum = -8680.6, 1Q = -1740.9, Median = -643.5, Maximum = 16179.9 Coefficient: 1) Intercepts: Estimated = 1.713e+03, Std. error = 3.225e+02, T-value = 5.313, Pr(>|t|) = 2.43e-07 2) rice_totalrevenue: Estimated = 4.511e-01, Std. error = 1.349e-02, T-value = 33.448, Pr(>|t|) < 2e-16 Multiple R-squared is 0.821 and Adjusted R-squared is 0.8202 F-statistic: 1119 on 1 and 244 DF, p-value: < 2.2e-16

The graph above is plotted between hh income (Y) and ag income (X) The Call formula is hh_income ~ ag_income Residuals: Minimum = -8680.6, 1Q = -1740.9, Median = -643.5, Maximum = 16179.9 Coefficient: 1) Intercepts: Estimated = 2.769e+04, Std. error = 3.969e+03, T-value =6.978, Pr(>|t|) = 2.8e-11 2) ag_income: Estimated = 1.194e, Std. error = 1.558e-01, T-value = 7.662 , Pr(>|t|) = 4.3e-13 Multiple R-squared is 0.1939 and Adjusted R-squared is 0.1906 F-statistic: 58.71 on 1 and 244 DF, p-value: 4.304e-13

Multiple linear regression formula = hh_income ~ yield + rice_income + ag_income + field_area Coefficient: 1) Intercepts: Estimated = 25594.3969, Std. error = 8466.8179, T-value = 3.023, Pr(>|t|) = 0.00277 2) yield: Estimated = -3.1337, Std. error = 3.4676, T-value = -0.904, Pr(>|t|) = 0.36705 3) rice_income: Estimated = 0.2670, Std. error = 0.4479, T-value = 0.596, Pr(>|t|) = 0.55162 4) field_area: Estimated = 4654.3138, Std. error = 3019.6757, T-value = 1.541, Pr(>|t|) = 0.12455 Multiple R-squared is 0.2133 and Adjusted R-squared is 0.2003 F-statistic: 16.34 on 4 and 241 DF, p-value: 7.406e-12

± Bolivar Sate 140.000000 340.000000 540.000000 .0000000 -100.000000 -200.000000 -300.000000 -400.000000 -500.000000 -600.000000 -700.000000 -800.000000 140.000000 340.000000 540.000000 0 90 180 360 540 720 Kilometers

ellite Imagery 740.000000 940.000000 1140.000000 .0000000 -100.000000 -200.000000 -300.000000 -400.000000 Text -500.000000 -600.000000 -700.000000 -800.000000 940.000000 By Puhnyanuj Smizdhanond740.000000 1140.000000 Data Collected from Google Earth

Noise Pollution Ma 2300000.000000 2305000.00000 Legend 750000.000000 Schools 745000.000000 Runways Arterials 740000.000000 CNEL_65 Airport_area POPULATION 735000.000000 Less Than 1300 730000.000000 1364 - 1500 1500 - 2500 2500 - 3500 3500 - 7046 Land_Parcels 725000.000000 720000.000000 2300000.000000 2305000.00000 0 2.25 4.5 1 cm = 2 km

apping for Schools 2325000.000000 2330000.000000 2335000.000000 00 2310000.000000 2315000.000000 2320000.000000 / 750000.000000 745000.000000 Northwestern Prep 740000.000000 735000.000000 730000.000000 Elm Elementary 725000.000000 720000.000000 00 2310000.000000 2315000.000000 2320000.000000 2325000.000000 2330000.000000 2335000.000000 9 13.5 18 Kilometers by: Puhnyanuj Smizdhanond m 25 July 2021 Data from AIT Edu-camp

Thaninrath Thiraphotiwat 27-Jul-2021 R-Software Hands-on Code #multiple linear regression multreg <- lm(yield~Field_1_ELEVATION+Field_LATITUDE+Field_LONGITUTE+field_area) Result AIT EDU-INNOVATION CAMP









Mohamed Arfan Mohamed Nayas Introduction to R Assignment II: Correlations: 1) Rice revenue and rice income: Code: plot(rice_totalrevenue, rice_income, xlab = 'rice_totalrevenue', ylab = 'rice_income') abline(lm(rice_income ~ rice_totalrevenue), col = \"blue\") Correlation Test: 0.931616 Graph:

Mohamed Arfan Mohamed Nayas 2) Asset and Field area Code: plot(asset, field_area, xlab = 'asset', ylab = 'field_area') abline(lm(field_area ~ asset), col = \"blue\") Correlation Test: 0.327946 Graph:

Mohamed Arfan Mohamed Nayas 3) Rice Total Cost and Rice Labour Cost Code: plot(rice_totalcost, rice_laborcost, xlab = 'rice_totalcost', ylab = 'rice_laborcost') abline(lm(rice_laborcost ~ rice_totalcost), col = \"blue\") Correlation Test: 0.9822036 Graph:

Chapel Hill, NC, US ± 1400.000000 2400.000000 3400.000000 3500.000000 3000.000000 2500.000000 2000.000000 1500.000000 1400.000000 2400.000000 3400.000000 Agency: USDA 1 centim Vendor: USDA-FSA-PFO Datum: NAD83 0 0.2 0.4 0 Sensor Type: CNR

SA Satellite Imagery 4400.000000 5400.000000 3500.000000 3000.000000 2500.000000 2000.000000 1500.000000 4400.000000 5400.000000 meter = 224 meters 1.6 Done By: 0.8 1.2 Kilometers Mohamed Arfan

Noise Pollution Map 2301000.000000 2308000.000000 2315000.000000 2322000.000000 23290 747000.000000 Ü 740000.000000 ? Northwestern Prep 733000.000000 ? 726000.000000 Elm Elementary ?? ?? ? 719000.000000 ? ? ? ?? ?? ? 712000.000000 2301000.000000 2308000.000000 2315000.000000 2322000.000000 23290

pping nearby Schools 000.000000 747000.000000 740000.000000 733000.000000 0 1.75 3.5 1 cm = 2 km 14 Kilometers 7 10.5 726000.000000 Legend POPULATION 719000.000000 ? Schools Less Than 1500 1500 - 2500 Runways 2500 - 3500 Arterials 3500 - 4500 Noise Contour 4500 - 5500 5500 - 6500 Airport Area 6500 - 7500 ? Noise Pollution & Schools: 000.000000 Research has shown that noise has detrimental effects upon children's performance at school, including reduced memory, motivation, and reading ability. 712000.000000 By: Mohamed Arfan Date: 27-07-2021 Data Given: AIT Edu Camp

Introduction to R Report Paper Joseph Leandre B. Derpo Edu-Camp 2021 AIT-KMITL

Objective The objective of this lab report is to find out if there are any relationship between the gathered data from 25 patients such as the Systolic Blood Pressure, Age, and Weight. A data was collected to determine the relationship between Systolic Blood Pressure (mmHg), Age, and Weight (Pounds) of 25 patients that were selected at random and the data is shown in the table below:

Matrix of Scatter Plots The first column (up and down) is the Systolic Blood Pressure (X-axis) and Age is on y axis, whereas the second column is the Age where X axis is the Age and Y axis is the blood pressure For the second column on the right side of the Sbps (y axis is Sbps and age is on x axis) on the scatterplot, it’s quite scattered so there is almost negligible relationship between the 2 variables. Since there is no pattern, no correlation between the 2 variables (Age has no relationship with SBP) Third to the further right top, the plot there is an increasing trend, so it indicates there is a positive correlation between SBP and weight. As the weight increase, the SBP will also increase.

Correlation Coefficient Matrix • This is used to find out the degree of relationship between the variables. With pearson correlation coefficient being used, it will be able to give information about the magnitude of the correlation between the variables. • Rounded up to 2 decimal points • Correlation between Sbps to Sbps is 1 • Correlation between Sbps to age is 0.01, it is not too much. As it is between 0.00 to 0.20, it is considered no correlation or very small. It is negligible in 0.00-0.20 so there is no correlation or small correlation quantity. • Correlation between Sbps to weight is 0.78, there is a positive strong correlation between Sbps and weight.

Significance of Correlation • The sample size is 25. • The first respective P value of the correlation coefficient between Sbps and age is 0.9645 which is greater than .05 when we look at a 95% level of significance which means we accept it as the null hypothesis which means that there is no correlation between age and SBP. (This was evident from the scatterplot) • For the second P value of the correlation coefficient between SBps and weight is 0.000, it means that it is highly significant. It means there is significant correlation between the two variables.

Multiple Linear Regression • LM function is called for the linear relationship between the variables. The dependent variable is the Sbps, we find out the dependency of age and weight. • The 2 variables are age + weight • We got the Intercept value (75.1344), beta 1 (-0.1202; coefficient of Age), and beta 2 (0.4224; coefficient of weight)

Residuals - • For the minimum and maximum value, the range is too much which means it’s not a good indication because residual value is maybe too high, it indicates there is too much variation in the observed and estimated values of the SBP For the coefficients • T statistic value (T value) is obtained easily from dividing Beta not (Estimated value) and Standard error of Beta not (Std. Error) • The P value of age is 0.384 which means its greater than .05, which means it indicates that the null hypothesis is accepted meaning that age doesnt have any influence on the Sbps so its accepted. • The P value of weight, its 5.44 e-06 which means its really small and less than .05, so the coefficient is significant so we will reject the null hypothesis and shows that weight has a significant influence on Sbps. Residual standard error: 8.639 or 22 DoF, it shows the amount of deviation is present in the residual terms from its mean. For multiple linear regression , its good to use Adjusted R-square instead of R-squared: because when we increase the number of regressors in the model whether the regressor is relevant or irrelevant, it doesnt matter since R-square will always increase. If regressor is irrelevant, then adjusted R-squared will decrease. Age is not significant which means it is irrelevant which means R-squared has increased and adjusted R-squared has decreased. In case of multiple linear regression, it is good to see the adjusted R- squared because the r-squared does not take into the loss of degree of freedom

P-value of F-statistic is lesser than .05 which means it is significant which shows the overall model is significant to our data. For different data set, the 2.5% is of negative type so we don’t have sufficient evidence to interpret the confidence interval whether it is significant or not. (left is lower limit and right is upper limit)

Legend A 6°18'0\"N 6°19'0\"N 6°20'0\"N 6°21'0\"N 6°22'0\"N 6°23'0\"N 6°24'0\"N 6°25'0\"N 6°26'0\"N 6°27'0\"N 6°28'0\"N 6°29'0\"N 6°30'0\"N 6°31'0\"N Schools 94°57'0\"W Runways Arterials 4 CNEL_65 Airport_area POPULATION Less than 1300 2000.000001 - 3000.000000 3000.000001 - 4000.000000 4000.000001 - 5000.000000 5000.000001 - 7046.000000 No rt hw este rn Pre p Elm E lem ent ary 0 12.5 25 50 Kilometers 1 cm = 17 km Made By - Joseph Leandre B. Derpo Date - 20-07- 2021 Data Given - Edu Camp 94°57'30\"W

Airport-Induced Noise Pollution 6°17'30\"N 6°18'30\"N 6°19'30\"N 6°20'30\"N 6°21'30\"N 6°22'30\"N 6°23'30\"N 6°24'30\"N 6°25'30\"N 6°26'30\"N 6°27'30\"N 6°28'30\"N 6°29'30\"N 6°30'30\"N Near School Areas W 94°56'0\"W 94°55'0\"W 94°54'0\"W 94°53'0\"W 94°52'0\"W 94°51'0\"W 94°50'0\"W 94°49'0\"W 94°48'0\"W 94°47'0\"W Northwestern Prep Elm Elementary W 94°56'30\"W 94°55'30\"W 94°54'30\"W 94°53'30\"W 94°52'30\"W 94°51'30\"W 94°50'30\"W 94°49'30\"W 94°48'30\"W 94°47'30\"W