Changes for page Test

Summary

• Page properties (1 modified, 0 added, 0 removed)

Details

Page properties

Content

...	...	@@ -1,29 +1,65 @@
	1	+Our robot aims to help delay the stage of dementia or slow down the deterioration of memory. The best situation is that we can test the robot with real PwD and in a relatively long time period to see if this robot really works, which is impossible for our project. So our evaluation performs in a group control way. Participants are divided into two groups, group A with the intelligent one, and group B with the dummy one.
1	1
2	2	= Problem statement and research questions =
3	3
4	4	The main use cases that the evaluation focuses on are UC001: Daily todo list and UC005: Quiz. Based on the claims corresponding to those use cases, we derive the following research questions:
5	5
6		-1. System A: the robot does not do anything
7		-System B: the robot plays music associated with tasks
8		-Research question: Are participants more likely to remember their daily tasks when using system B, compared to system A?
9		-1. System A: the robot plays a song and regardless if the answer is right or not, it switches to a different song.
10		-System B: the robot plays the same song until the user gets it right
11		-Research question: Are participants happier to interact with the robot and more effective at linking tasks to music when using System B, compared to system A?
	7	+1. Are PwD willing to play the quiz?
	8	+1. Are PwD happy to listen to music?
	9	+1. Are PwD happy if they get the correct answer?
	10	+1. Does PwD enhance their memory of the association between music and activities?
12	12
13	13	= Method =
14	14
15		-Our group decided to use a mixed-method approach for the evaluation. Quantitative data will be derived during the experiment such as the number of mistakes the participant makes during the quiz. Moreover, qualitative data expected to be gathered through questionnaires, such as to what extent participants are satisfied with using the robot, is also adopted for evaluation. By measuring these two types of data, we will manage to assess if our claims are achieved and the research questions are answered.
	14	+The control group evaluation is used. One group of participants interacts with a dummy robot and another group interacts with the intelligent robot. The only difference between these two groups is the independent variable - dummy or intelligent robot, which makes our result more reasonable.
16	16
	16	+Besides, Our group decided to use a mixed-method approach for the evaluation.
	17	+
	18	+* Quantitative data will be derived during the experiment such as the number of mistakes the participant makes during the quiz.
	19	+* Qualitative data expected to be gathered through questionnaires, such as to what extent participants are satisfied with using the robot, is also adopted for evaluation.
	20	+
	21	+By measuring these two types of data, we will manage to assess if our claims are achieved and the research questions are answered.
	22	+
17	17	== Participants ==
18	18
19		-Roughly sixteen participants are expected for our evaluation. To validate our research question that the quiz will help people better memorize music-activity links, participants will be divided into two groups, Group A and Group B. Both groups will be asked to memorize certain pairs of music and corresponding activity as prior knowledge. Group A, which is the control group, will not have NAO to assist with learning music-activity links through quizzes while Group B will have him as the experimental group. Details on the tasks assigned to each group will be further described below.
	25	+We invited 19 participants. To validate our research question that the quiz will help people better memorize music-activity links, participants will be divided into two groups, Group A with the intelligent robot(9 participants) and Group B(10 participants) with the dummy robot.
20	20
21	21	== Experimental design ==
22	22
23		-The experiment will be conducted to simulate the reinforcement learning process of musical memory related to daily activities and to investigate if the quiz is indeed able to help with the learning. The group of participants will be divided into 3 subgroups that simulate patients in different stages of dementia. The participants will be given artificial memory loss by forcing them to remember a large number of songs they have to associate with certain activities. From each group one of the participants will be asked to play the caregiver and another participant will take the roll of loved one. With these participants the interactions between the actors will be tested. The interactions are described in the design patterns.
	29	+The experiment will be conducted to simulate the reinforcement learning process of musical memory related to daily activities and to investigate if the quiz is indeed able to help with the learning.
24	24
25		-When the participant playing the role of patient has learned the association between the music pieces and activities the robot will start playing certain pieces of music. The participant has to recall the correct activity associated with the music piece. When this is wrong the loved one can step in and call to remind the
26	26
	32	+=== Evaluation Step ===
	33	+
	34	+First, all participants would sign a consent form that informed them of the usage of the collected data and our goal of evaluations.
	35	+
	36	+==== Step 1 ====
	37	+
	38	+In our prototype, users can personalize the link between music and activities based on their existing intrinsic knowledge. But due to the limited time and requiring a comparable result between groups, in evaluation, we forced 6 pieces of music and activities. Participants listened to the music and were asked the remember the associated activities.
	39	+
	40	+==== Step 2 ====
	41	+
	42	+Participants in two groups would play with the robot for 3 minutes. Participants in group A would play with the intelligent robot and group B would play with the dummy robot.
	43	+
	44	+==== Step 3 ====
	45	+
	46	+In the end, the participants would take a quiz to see how much they remembered. They are also asked to fill in a questionnaire including the feeling of the robot and possible feedback.
	47	+
	48	+==== Questionnaire ====
	49	+
	50	+1. How many questions did you answer correctly? (Points from 0-6)
	51	+1. You feel the robot can help you remember the task. (Agree, Neutral, Disagree)
	52	+1. You feel the robot is annoying. (Agree, Neutral, Disagree)
	53	+1. Based on the given system usability scale, please give our robot a score.(0-100)
	54	+
	55	+Except for the previous questions, we also collect feedback from participants
	56	+
	57	+1. What did you like most about the robot?
	58	+1. What did you dislike most about the robot?
	59	+1. Do you have any further suggestions? (*optional)
	60	+
	61	+
	62	+
27	27	== Tasks ==
28	28
29	29	**Event: Quiz**
...	...	@@ -32,8 +32,8 @@
32	32	<table>
33	33	<tr>
34	34	<td>No.</td>
35		- <td>Group A</td>
36		- <td>Group B</td>
	71	+ <td>Group A with the intelligent robot</td>
	72	+ <td>Group B with the dumb robot</td>
37	37	</tr>
38	38	<tr>
39	39	<td>1</td>
...	...	@@ -42,8 +42,8 @@
42	42	</tr>
43	43	<tr>
44	44	<td>2</td>
45		- <td>Play quiz with the dumb robot for five minutes, which will not correct the participant when wrong answers are given ;</td>
46	46	<td>Play quiz with the smart robot for five minutes, which will correct the participant when wrong answers are given;</td>
	82	+ <td>Play quiz with the dumb robot for five minutes, which will not correct the participant when wrong answers are given;</td>
47	47	</tr>
48	48	<tr>
49	49	<td>3</td>