PRE2017 3 Groep14: Difference between revisions

From Control Systems Technology Group
Jump to navigation Jump to search
No edit summary
 
(70 intermediate revisions by 5 users not shown)
Line 19: Line 19:
|}
|}


='''Process'''=
[[Process Group 14]]


='''Week 1'''=
='''Report'''=
= Fun Learning for Kids =
[[Report group 14]]


= Subject =
='''Peer review and Contributions'''=
Enhance knowledge levels of young children through an interactive quiz system. Teachers will be able to tell the system the desired final knowledge level and will be able to see the progress of each child. Furthermore the system has to be able to interact with the children and assess their knowledge levels to create questions on their personal level. In our project we will focus on the quiz and try to create this.
==Peer review==
As all of us have contributed a lot to this project, there was good communication and we do not have any negative remarks about each other, we decided that each of us deserves the same result. This is why we decided on the following peer review results:
* Abby: 7,5
* Christine: 7,5
* Dennis: 7,5
* Ellen: 7,5
* Sophie: 7,5
Of course there is always room for improvement and our project could have been better, which is why we think 7,5 is a good representation of what we have done.


= Users =
==Contributions==
* Children from class 3 - 4 in the Netherlands. The system could later on be changed to fit other age groups that have other knowledge levels, but for this project we focus on this group as the simple math they need to learn here are an easy starting point for the program.
We also had 6 hours of meetings each week, so that makes 7*6 = 42 hours extra for everyone.
* Parents or guardians of these children as they want to know the progress their child or children has made.
* Teachers that can tell the systems what level of knowledge the entire class needs to reach at the end. They also need to be able to see how far each student has gotten.


== User Requirements ==
* Abby
'''children:'''
** State of the art - 10 hours
* learning through a fun program
** Desk research - 5 hours
* competitive, want the highest reward (number of sheep)
** Programming - 40 hours
 
** Wiki - 10 hours
'''parents:'''
* Christine
* want their children to study properly
** State of the art - 10 hours
* want their children to be happy
** Desk research - 30 hours
* want their children to be motivated/interested
** Survey - 15 hours
* want to have more free time as they do not have to tutor as much anymore
** Wiki - 10 hours
* want to check their children's progress
** Program design - 5 hours
 
* Dennis
'''teachers:'''
** State of the art - 10 hours
* let the students learn effectively
** Presentation - 8 hours
* the system has to match the curriculum
** Programming - 45 hours
* easier to check all students' progress
** Wiki - 10 hours
 
* Ellen
= Objective =
** State of the art - 10 hours
Develop a smart quiz program for on a computer/tablet/laptop that can assess knowledge levels of its users and ask questions on their personal boundary so they learn effectively.
** Desk research - 30 hours
 
** Survey - 15 hours
= Approach =
** Wiki - 10 hours
Creating the smart quiz and interface in java.
** Presentation - 5 hours
 
* Sophie
== Intelligent Quiz Master ==
** State of the art - 10 hours
'''Idea.''' Use a set of arithmic questions (addition, subtraction, fractions) since then it is easy for us to check if it makes sense.
** Presentation slides and demo - 5 hours
Also, since most children have difficulties with arithmic this is actually useful.
** Programming - 45 hours
 
** Wiki - 10 hours
Given a set of questions, the quiz master will test the knowledge of a child, and help the child improve by asking the right questions at the right time.
We will build an application that selects the next question to ask the child, based on the previous answers the child gave to previous questions.
The quiz will find the knowledge level of the child and ask questions at the child's knowledge boundary so he can still learn from the question but will not be overwhelmed.
 
The quiz master has to:
 
* Find out the level of knowledge the child has, and ask questions that are on the 'edge' of a childs knowledge in order to improve their knowledge.
* Optionally invent new questions, similar to the already existing questions.
 
In order to do so, we must:
 
* Define '''distance''' (or '''question similarity''') between questions, which questions are of similar difficulty. So cluster questions based on their difficulty. Note that this will vary per child.
* Simulate the (increasing/decreasing) knowledge of different children. (To be able to train our app.)
* Construct a (large enough) data set to use parts of it for training and validation.
* Find out what the next '''right''' question would be. Our app should do this, based on the question similarity for a certain child. Educational/psychological: what are the best questions to ask?
 
== Milestones ==
* Finishing planning
* Summarizing SotA
* Quiz
** Teacher can enter category and boundary (knowledge goal that has to be reached)
** Quiz can generate questions inside category
** Quiz can understand the person's input
** Quiz uses input to generate personal level questions
** Quiz gives results
* Interface
** Results are displayed to child/parent/teacher (they each have their own interface)
** Reward system (for the child, parents can see this as well)
 
== Deliverables ==
Smart quiz program including interfaces for the child who will use the quiz to learn, the parents and the teacher.
 
= Who will do what? Planning =
* '''Abby''' focusses on the quiz programming
* '''Christine''' focusses on the quiz design
* '''Dennis''' focusses on the quiz programming
* '''Ellen''' focusses on the wiki
* '''Sophie''' focusses on the quiz programming
 
'''week 1:'''
* literature search, SotA summary
* make plan
* setup Git
* update wiki
'''week 2:'''
* interaction plan
* quiz plan:
** how to make it smart
** categories
** creating questions
** UML of quiz
* update wiki
'''week 3:'''
* teacher program finished
* parent program finished
* smart quiz has to generate questions inside the categories
* update wiki
'''week 4:'''
* quiz has to read input (parsen?)
* start with letting quiz learn from input
* start with interface for child
* update wiki
'''week 5:'''
* quiz has to learn from input
* interface has to be finished
* update wiki
'''week 6:'''
* quiz has to learn from input
* feedback system in quiz
* reward system in interface
* update wiki
'''week 7:'''
* BUFFER
* start with presentation
'''week 8:'''
* final presentation
 
[[= State of the Art Literature Study =]]
 
== The tutoring system ==
 
=== Technical ===
* These two articles propose methods to find similar questions among a database of questions. The similarity of questions in this article is based on how useful the question to one answer could be to answer a different given question. The methods used here might be useful when we will try to define the distance between questions. <ref> A Topic Clustering Approach to Finding Similar Questions from Large Question and Answer Archives, from http://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0071511&type=printable</ref> <ref> ''Deepa Paranjpe'', Clustering Semantically Similar and Related Questions, from https://nlp.stanford.edu/courses/cs224n/2007/fp/paranjpe.pdf</ref>
 
* There are a lot of approaches to construct a intelligent tutoring system. This paper shows a few key elements to take into account when constructing such a system. The focus is put on making trade-offs, for example productivity vs learnability. <ref>Tom Murray, Authoring Intelligent Tutoring Systems: An analysis of the state of the art, International Journal of Artificial Intelligence in Education, 1999, pp.98-129, from https://telearn.archives-ouvertes.fr/file/index/docid/197339/filename/Murray99.pdf </ref>
 
* On how we can add probabilities to someones response to an answer representing their knowledge. This can be useful when training and testing our intelligent quiz, as we can use this to simulate the responses of a child. For example, a child who thinks they know the answer might give the wrong answer because they are too quick, but in fact they do know the answer. Or a child who does not know the answer might take a correct guess. <ref> Knowledge Spaces, Chapter 7 (p. 142 - 173), from https://link-springer-com.dianus.libr.tue.nl/content/pdf/10.1007%2F978-3-642-58625-5.pdf</ref>
 
* This chapter continues on the previous. It describes how to model a learning path of a human being. This can also be useful when simulating the responses of the children, as children in real life progress while answering questions. <ref> Knowledge Spaces, Chapter 8 (p. 175 - 205), from https://link-springer-com.dianus.libr.tue.nl/content/pdf/10.1007%2F978-3-642-58625-5.pdf</ref>
 
* This paper shows that by using a different take on machine learning, it is possible to train children as we are training computers. This is called machine teaching. The goal is to find the optimal training set, the smallest training set, to achieve the desired effect, which is a group of children whom all know the course material given by the teacher.<ref> Xiaojin Zhu, Machine Teaching: An Inverse Problem to Machine Learning and an Approach Toward Optimal Education, Department of Computer Sciences, University of Wisconsin–Madison, from https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/viewFile/9487/9685 </ref>
 
* Combining Artificial intelligence with tutoring has already been used and researched for several years and is called an intelligent tutoring system. Therefore designing such a program requires you to keep in mind all of the things that have already been done, which can be found in the article. For instance the article gives 8 designing principles such as: provide immediate feedback on errors, and it shows a possible architecture. <ref>Albert T. Corbett, Kenneth R. Koedinger and John R. Anderson, Chapter 37 - Intelligent Tutoring Systems, In Handbook of Human-Computer Interaction (Second Edition), edited by Marting G. Helander, Thomas K. Landauer and Prasad V. Prabhu, North-Holland, Amsterdam, 1997, Pages 849-874, ISBN 9780444818621, https://doi.org/10.1016/B978-044481862-1.50103-5</ref>
 
* "Based on the gathered information the next scene presented to the player should be determined in a way such that the learner is neither unchallenged nor overwhelmed by the complexity of the contained tasks. It should rather be ensured that the learner’s knowledge is steadily increased up to full knowledge mastery." <ref> ''Göbel, S., Wendel, V., Ritter, C., and Steinmetz, R.'', Personalized, Adaptive Digital Educational Games using Narrative Game-based Learning Objects, from ftp://dmz02.kom.e-technik.tu-darmstadt.de/papers/GWRS10_507.pdf</ref> This line perfectly captures what we want to achieve. This paper is about how we can make systems adaptive in such a way that they can adapt to the needs and level of its user.
 
* 80Days is a game that is comparable to what we want to achieve. However this is a full on computer game while we want an interactive home system. The adaptation principle is relatable which is why it could be nice to base our system on this game. <ref> ''Kickmeier-Rust, M.D., Göbel, S., and Albert, D.'', 80Days: Melding Adaptive Educational Technology and Adaptive and Interactive Storytelling in Digital Educational Games, from http://ceur-ws.org/Vol-386/p02.pdf</ref>
 
* In the ELEKTRA game they use unobtrusive knowledge assessment to see the user's level of knowledge. <ref> ''Kickmeier-Rust, M. D., Hockemeyer, C., Albert, D., & Augustin, T.'', Micro adaptive, non-invassive assessment in educational games, from http://css-kti.tugraz.at/research/cssarchive/publicdocs/publications/kickmeier-rust_adaptivity.pdf</ref> They do this by observing the user's behaviour in the game. If we can do something similar but in real life, as a smart home will be able to notice the residents behaviour, we can use this technology to assess the childs level and what he needs from the educational system such that he will get personalized assignments.
 
=== User interface ===
* A learning system with a specific interface has been devised based on the learning-style model by Felder & Silverman, so that different learner preferences are revealed through user interactions with the system. This system notices preferences like global vs sequential or visual vs auditory. <ref> Hyun Jin ChaYong Se KimSeon Hee ParkTae Bok YoonYoung Mo JungJee-Hyong Lee, Learning Styles Diagnosis based on User Interface Behaviors for the Customization of Learning Interfaces in an Intelligent Tutoring System, Creative Design & Intelligent Tutoring Systems Research Center12345, School of Information & Communication Engineering, Sungkyunkwan University, Suwon, Korea, pp 513-524, 2006, from http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.315.881&rep=rep1&type=pdf</ref>
 
* Shows that nowadays the educational aspects in interactive systems is often too separate ("chocolate-covered broccoli") and extrinsic. To create learning systems that work it is important to make them intrinsically motivating. You have to keep in mind that people have to actually use the system, so make it in such a way that they want to. Remember, the primary users will be children. <ref> ''Habgood, M.P.J. and Ainsworth, S.E.'', Motivating children to learn effectively: exploring the value
of intrinsic integration in educational games, from http://shura.shu.ac.uk/3556/1/Habgood_Ainsworth_final.pdf</ref>
 
* A paper that "focuses on feedback of interface agents on student perception. (...) This study focuses on three types of feedback from interface agents to clarify student perception of single feedback and multiple feedback types."  <ref> ''Zhi-Hong Chen, Chih-Yueh Chou
, Shu-Fen Tseng, Ying-Chu Su'', Feedback of Interface Agents on Student Perception: Level, Dialogue, and
Emotion, from https://pdfs.semanticscholar.org/d7d2/5d3ff5f286951486b5b11956cfc0c65619a1.pdf </ref> The results of this study should be taken into account when modeling the way in which our system interacts with users, in order to make it's feedback as effective as possible.
 
* Next, a paper that analyses "the role of digital games in early childhood, especially from the perspectives of learning, literacy and play. (...) The analysis of young children's learning while they are engaged in digital games in informal contexts furthers our understanding of the potential of game-based learning in formal early childhood education settings." <ref> ''Marja Kankaanranta, merja Koivula, Marja-Leena Laakso, Marleena Mustola'', Ditital Games in Early Childhood: Broadening Definitions of Learning, Literacy, and Play, from https://books.google.nl/books?hl=nl&lr=&id=BsVCDgAAQBAJ&oi=fnd&pg=PA349&ots=c-UyQVsRzx&sig=RIrTs2S-MZTh5cirTbIKerQ9M10#v=onepage&q&f=false </ref> The results presented in this chapter can be used in our project to properly design the way in which infants interact with the system, what digital games the system should present, and how.
 
* A book that could possibly be helpful. It proposes design principles of educational virtual worlds of preschool children.  <ref> ''Jana Pejoska'', Design principles of educational virtual worlds for preschool
children, from https://jyx.jyu.fi/dspace/bitstream/handle/123456789/26862/URN:NBN:fi:jyu-2011050210720.pdf?sequence=1 </ref> Especially the principles described in chapter 4 could be applied to the designing of our smart home system.
 
* An interesting paper described a study which "investigated teachers’ perceptions of barriers to using - integrating computers in early childhood settings." Unlike other papers, the viewpoint of this article shifts the view from the developer of the system or the child user to the teachers involved in the process. <ref> ''Kleopatra Nikolopoulou & Vasilis Gialamas'', Barriers to the integration of computers in early childhood settings: Teachers’ perceptions, from https://link.springer.com/article/10.1007/s10639-013-9281-9 </ref> The findings in this study can be used to descibe the effects on teachers when applying a smart home system to enhance child learning.
 
* A paper released in 2010 presents a "device to systematically assess children's orienting behavior in social situations." An set of relevant tests was carried out with "12-36 months old typically developing infants [which] prove usability of the proposed technology." <ref> ''Giuseppina Schiavone & Domenico Formica & Fabrizio Taffoni & Domenico Campolo & Eugenio Guglielmelli & Flavio Keller'', Multimodal Ecological Technology: From Child’s Social Behavior
Assessment to Child-Robot Interaction Improvement, from https://link.springer.com/article/10.1007/s12369-010-0080-9 </ref> This study can be used to aid the social learning aspect of childhood in the proposed smart home system.
 
* This article focusses on whether intelligent tutoring systems are better for learning than conventional classroom teaching. <ref> ''Boulay, B. du'', Can We Learn from ITSs?, from ftp://nozdr.ru/biblio/kolxo3/Cs/CsLn/I/Intelligent%20Tutoring%20Systems,%205%20conf.,%20ITS%202000(LNCS1839,%20Springer,%202000)(ISBN%203540676554)(695s)_CsLn_.pdf#page=27 </ref> This way we can determine an approach for our intelligent quiz, and maybe decide it would be better to make this a classroom program instead of a personal one.
 
* Paper about what is needed for a proper functioning intelligent tutoring system. <ref> ''Sharples, M.'', The design of personal mobile technologies for lifelong learning, from https://pdfs.semanticscholar.org/576d/05b4252914b96e36a2a92d14b754e5c5c4a1.pdf </ref> They are trying to create a personal system in order to continue learning throughout your lifetime, but we can use the requirements that are described.
 
== Smart home ==
* Current smart homes have already integrated a lot of features, for instance sensors in the floor to accurate locate persons or cameras with image analysis. However these systems are far from perfect. They have to improve their computing infrastructure more. <ref> Marie Chan, Daniel Estève, Christophe Escriba, Eric Campo, A review of smart homes—Present state and future challenges, Volume 91, Issue 1, Pages 55-81, ISSN 0169-2607, 2008, from https://doi.org/10.1016/j.cmpb.2008.02.001</ref>
 
* It is possible for a smart home to detect speech and react upon it in crowdy and noisy environments <ref> Michel Vacher, Anthony Fleury, François Portet, Jean-François Serignat, Norbert Noury, Complete Sound and Speech Recognition System for Health Smart Homes: Application to the Recognition of Activities of Daily Living, Domenico Campolo, New Developments in Biomedical Engineering, In-Tech, pp. 645 – 673, 2010, from https://hal.archives-ouvertes.fr/hal-00422576/document </ref>
 
* Smart homes can use their social features to interact with persons. <ref> Marie Chan, Eric Campo, Daniel Estève, Jean-Yves Fourniols, Smart homes — Current features and future perspectives, Maturitas, Volume 64, Issue 2, Pages 90-97, ISSN 0378-5122, 2009, https://doi.org/10.1016/j.maturitas.2009.07.014.</ref>
 
* Paper about using smart homes to learn about human behaviour. <ref> ''Brdiczka, O., Langet, M., Miasonnasse, J., and Crowley, J.L.'', Detecting Human Behavior Models From Multimodal Observation in a Smart Home, from https://pdfs.semanticscholar.org/1fa3/5bbda418228e59ab49bb4aff302701f21583.pdf</ref> This could be used for multiple things in our project like the knowledge assessment mentioned above, or checking whether or not the user (child) has some free time that he can use interacting with the system and thus learning. There is a need for pattern recognition in this behaviour.
 
* We propose some papers related to the way our smart home system should be designed and implemented. First, a paper that: "proposes a model to improve Activity Recognition in smart homes. The proposed technique is based on defining a profile ofr each activity from training datasets. The profile will be used to induce extra features and will help in distinguishing residents' activities." <ref> ''Majdi Rawashdeh, Mohammed GH. Al Zamil, Samer Samarah, M. Shamim Hossain, Ghulam Muhammad'', Micro adaptive, non-invassive assessment in educational games, from https://ac.els-cdn.com/S0167739X17311342/1-s2.0-S0167739X17311342-main.pdf?_tid=bef05bc4-14aa-11e8-abcb-00000aab0f01&acdnat=1518958610_409380ed13eef0bd5bb3b6332b1e9138</ref> This technique can be used in our project to develop the way our smart home recognizes activities of the users of the system.
 
* Related to this, a paper that proposes a way to implement an "Adaptable Infant Monitoring System (...) with minimal cost, knowledge and time to set up". <ref> ''Hong Zhou, Brad Goold'', A Domestic Adaptable Infant Monitoring System Using Wireless Sensor Networks </ref> This technique can be used in the implementation of our smart home, in order to monitor infants using the system, and so prevent accidents, and keep track of the location of the infant. This could (possibly) be combined with the proposed technique above, to also monitor whát the infant is doing.
 
* Now, we propose a paper related to the way the educational aspect of our smart home is designed and implemented. First, a paper that does not seem completely relevant to the project at first. <ref> ''E. Oliver'', Gamification as transformative assessment in
higher education, from http://www.scielo.org.za/pdf/hts/v73n3/55.pdf </ref> However, it discusses "the application of gamification within the environment of education, and more specifically with an emphasis on assessment." This paper "opens the way for the implementation of gamification as a transformative online assessment tool ...", which can be used in our project to determine the way in which our smart home educates and assesses children in a playful manner.
 
* We reference a paper that conducted a study amongst students in a "Smart Home Lab". It describes their findings and argues that, in order to successfully use a Smart Home as a Pedagogical Tool, one must shift from virtual reality simulations to the physical environment, which they call "real virtuality". <ref> ''Antonio Sanchez and Lisa Burnell'', A Smart Home Lab as a Pedagogical Tool, from https://link.springer.com/chapter/10.1007/978-3-642-30171-1_12 </ref> These results can be used to guide the development of a Smart Home as a learning (i.e. pedagogical) tool. Note that, even though the study is focussed on individuals that are outside of our research scope in terms of age, some results might still apply.
 
* A paper that "describes an exploratory investigation into the potential effects of a robot exhibiting an adaptive behaviour in reaction to a child’s interaction". <ref> ''Tamie Salter, Francois Michaud, and Dominic Letourneau'', An Exploratory Investigation into the Effects of Adaptation in Child-Robot Interaction, from https://link.springer.com/chapter/10.1007/978-3-642-03986-7_12 </ref> The conclusions in this article can be useful in describing the effects of using a Smart Home system for learning purposes.
 
* The following paper describes the trend of using robotics technology to support childhood education. It goes into the ethics involved, as well as social acceptance for such technologies. <ref> ''Fumihide Tanaka'', Robotics for Supporting Childhood Education, from https://link.springer.com/chapter/10.1007/978-4-431-54159-2_10 </ref> This chapter from the book "Cybernics" can be used to assess the social acceptance and ethics evolved in creating and deploying the proposed smart home system.
 
= References =
<references/>


='''Coaching Questions'''=
[[Coaching Questions Group 14]]
[[Coaching Questions Group 14]]

Latest revision as of 14:21, 4 April 2018

Student Student Number
Abby Berkers 0951825
Dennis van den Berg 0949036
Sophie van den Eerenbeemt 0954445
Christine Ingwersen 0952530
Ellen Mans 0956433

Process

Process Group 14

Report

Report group 14

Peer review and Contributions

Peer review

As all of us have contributed a lot to this project, there was good communication and we do not have any negative remarks about each other, we decided that each of us deserves the same result. This is why we decided on the following peer review results:

  • Abby: 7,5
  • Christine: 7,5
  • Dennis: 7,5
  • Ellen: 7,5
  • Sophie: 7,5

Of course there is always room for improvement and our project could have been better, which is why we think 7,5 is a good representation of what we have done.

Contributions

We also had 6 hours of meetings each week, so that makes 7*6 = 42 hours extra for everyone.

  • Abby
    • State of the art - 10 hours
    • Desk research - 5 hours
    • Programming - 40 hours
    • Wiki - 10 hours
  • Christine
    • State of the art - 10 hours
    • Desk research - 30 hours
    • Survey - 15 hours
    • Wiki - 10 hours
    • Program design - 5 hours
  • Dennis
    • State of the art - 10 hours
    • Presentation - 8 hours
    • Programming - 45 hours
    • Wiki - 10 hours
  • Ellen
    • State of the art - 10 hours
    • Desk research - 30 hours
    • Survey - 15 hours
    • Wiki - 10 hours
    • Presentation - 5 hours
  • Sophie
    • State of the art - 10 hours
    • Presentation slides and demo - 5 hours
    • Programming - 45 hours
    • Wiki - 10 hours

Coaching Questions

Coaching Questions Group 14

Retrieved from "https://dsdwiki.wtb.tue.nl/index.php?title=PRE2017_3_Groep14&oldid=53836"