• Không có kết quả nào được tìm thấy

Download (15MB)

N/A
N/A
Nguyễn Gia Hào

Academic year: 2023

Chia sẻ "Download (15MB)"

Copied!
260
0
0

Loading.... (view fulltext now)

Văn bản

Prediction at an early stage can indicate the performance of students during their academic years. They built their models with 39 inputs representing their socio-economic status, e.g. the distance of the hometown from the university and other data related to their high school grades, such as the quantitative score of the high school on the national scale.

Fig. 1.  Predictive students’ performance framework
Fig. 1. Predictive students’ performance framework

Fuzzy model

Fuzzy sets (crisp inputs and outputs)and membership function

Fuzzy Rule-Based Model (FRBM)

Defuzzification

4 Conclusions and Future Work

Fourth, the value of this work is the fuzzy model that integrates the students' current knowledge in the major in which the student wants to specialize and the predicted final GPA. In addition, we would like to extend this work to add a question-based system that predicts performance and guides students to improve their performance.

5 References

Computers and Education Models for Early Prediction of At-Risk Students in a Course Using Standards-Based Assessment. Computers in Human Behavior Predicting University Students at Risk in a Virtual Learning Environment via a Machine Learning Algorithm.

6 Authors

An Empirical Investigation into Examination of Factors Influencing University Students’ Behavior towards E-

1 Introduction

2 Literature Review

A comprehensive theoretical framework of acceptance and use intent of e-learning by university students is put forward in this study and is largely based on the TAM [13]. Certain descriptive features of the use of E-learning and the chosen constructions were also identified.

3 Research Model and Hypotheses

  • Computer self-efficacy (CSE)
  • Social influence (SI)
  • Enjoyment (ENJ)
  • System interactivity (SIN)
  • Computer anxiety (CA)
  • Technical support (TS)
  • Core TAM constructs

H7: Perceived Usability (PEOU) has a positive effect on the Perceived Usability (PU) of the e-learning system. H8: Perceived ease of use (PEOU) has a positive effect on attitudes towards use (ATT) of the e-learning system.

4 Research Methodology

  • Data collection
  • Study instrument
  • Pilot study
  • Survey structure
  • Participants

To evaluate the outcome of the pilot study, Cronbach's internal reliability alpha test was used, which produced acceptable results for the measurement items. The researcher distributed a single survey: the paper surveys were distributed to students at the universities of the United Arab Emirates (UAE) (N=400).

Table 1.  Constructs and their sources.
Table 1. Constructs and their sources.

5 Findings and Discussion

  • Measurement model analysis
  • Assessment of the measurement model (Outer model)
  • Assessment of structural model (Inner model)
  • Structural model analysis

According to the recommendation, at least half of the measurement variance should be determined by the construct if the AVE score exceeds 0.5. The correlations between the constructs are represented by the download diagonal elements, while the square root of the AVE values ​​can be seen in the bold diagonal table.

Table 3.  Convergent validity results which assures acceptable values (Factor loading,  Cronbach’s Alpha, composite reliability  0.70 & AVE > 0.5)  Constructs  Items  Factor Loading  Cronbach
Table 3. Convergent validity results which assures acceptable values (Factor loading, Cronbach’s Alpha, composite reliability  0.70 & AVE > 0.5) Constructs Items Factor Loading Cronbach's Alpha CR AVE

6 Discussion and Implication

The role of the faculty in the introduction of the e-education system can be evaluated in the following studies. Support for the use of virtual councils in higher education should be offered; however, this type of use should be properly integrated into mainstream educational procedures.

7 References

Park, “An Analysis of the Technology Acceptance Model in Understanding University Students' Behavioral Intention to Use E-Learning,” J. Ross, “Extending the Technology Acceptance Model (TAM) to Examine College Use of Learning Management Systems (LMS) in Higher Education. Educational institutions," J.

8 Authors

He works at the University of Jordan teaching international marketing, consumer behavior and management and marketing research. Dr Rami Aldweeri is an assistant professor at the business school at the University of Jordan, Rami completed his PhD and Masters in Marketing at the University of Malaga and his undergraduate studies at Yarmouk University.

Road Information Collector Using Smartphone for Measuring Road Width Based on Object and Lane

Detection

Object detection

7] stated that the steps that take place in a two-stage detector start with defining a region of interest (ROI) and creating a proposed network, and continue to classify into candidate regions. Common methods used in the single stage detector are Single Shot Detector (SSD), You Only Look Once (YOLO) and RetinaNet.

Lane detection

RetinaNet is built on the basis of several single-phase features, the concept of such anchors in RPN and the feature of the pyramid concept in SSD and FPN. The use of object detection is to recognize the road situation, such as the number of cars, motorcycles and other types of vehicles on the road.

Vanishing point

This approach is used when there are no lane boundaries on the road, especially on an alternative road. It will be used to create an illustration of lane boundaries by defining the left, center and right vanishing points on the road.

3 Design and Implementation

Information gathering

Detailed workflow of the proposed system is designed using Unified Modeling Language (UML) such as series, class and activity diagram. Based on its activity, this proposed system will have four actors (driver, server, database and user).

Fig. 4.  Sequence Diagram
Fig. 4. Sequence Diagram

Information extraction

The width of the road will be obtained from the intersection between the bottom line of the vehicle body and the left and right lane boundaries. Road width will be calculated using new intersections based on new road imagery.

Fig. 8.  Lane Detection Result
Fig. 8. Lane Detection Result

4 Testing

Road width measurement with object and lane detection

The average road width will be used as a comparison to determine the road width detection error rate. This value is acceptable, as the expected road width is between 2.81 and 4.19 m, which can still be used for all types of vehicles.

Road width measurement with vanishing point

Error rate for alley and minor road: Table 1 shows some sample results of measuring the error rate in the category of alley and minor road. Average error rate Road width: Table 3 shows the test result from each road category and grip angle (left side, center and right side).

Fig. 15.   Range Setting Between Camera and Several Points
Fig. 15. Range Setting Between Camera and Several Points

Road category classification

Based on these results, the lowest error rate for each type of road is obtained from the left sides with a range of 10% to 15%. Larger roads make higher error rates due to the perspective effect, thus making the pixel/meter comparison less accurate.

5 Conclusion and Future Works

6 References

A method of lane edge detection based on Canny Algorithm, Chinese Automation Congress (CAC), Jinan, China. A new lane sensing and tracking strategy based on a vehicle's forward monocular camera, IEEE Transactions on Intelligent Transportation Systems, 20(4).

7 Authors

Kuspriyanto is a professor at the School of Electrical Engineering and Informatics, Institut Teknologi Bandung. He is a lecturer at the School of Electrical Engineering and Informatics, Bandung Institute of Technology.

The Akeffa Tutor Application

A New Arabic Writing System

Educational mobile application

Since the new writing system is still unknown to humans, there are no similar projects teaching this system. On the other hand, there are a large number of applications that teach the braille writing system.

Related work

Target users Visually impaired and auditory learners Interactive technology keyboard, sound card. Braille Easy (Find Reference): Braille Easy was developed for visually impaired users and supports two languages, Arabic and English.

Table 1.  Taptilo educational application Features
Table 1. Taptilo educational application Features

3 Methodology

  • Analysis
  • Design
  • Keyboard design
  • Implementation
  • Testing

The system architecture design describes the structure, behavior and provides multiple visualizations of the application from the perspective of these three users. The third user (Admin): Admin interacts with the system by deleting or editing one or more existing lesson(s) in the application.

Fig. 1.  Main Screen of Application
Fig. 1. Main Screen of Application

4 Result and Discussion

Data analysis

Finally, during the experiment, Talah rated the participants from one to ten on their communication skills, and from the statistics, she found that the new writing system was easier than the Arabic Braille writing system. Time required to read a three-word sentence in Arabic Braille and the new writing system.

Fig. 5.  Survey
Fig. 5. Survey

5 Result

As shown in Figure 2, most students reported that the 'practice practice' task had high learnability, efficiency, memorability, few errors, and they were satisfied. As shown in Figure 4, most students who did the 'feed test' task reported that it had high learnability, efficiency, memorability, few errors, and they were satisfied.

Fig. 10.  Result of Nielsen measurement – ‘Perform Exercise’ Task
Fig. 10. Result of Nielsen measurement – ‘Perform Exercise’ Task

6 Conclusion

Bashayer Abdulhakeem Hindi is a student at the College of Computer Science and Engineering, Department of Information System and Technology, University of Jeddah, Jeddah, Saudi Arabia (email: hindi.bashayer@gmail.com). Shaima Yassin Al-Jahdali is a student at the College of Computer Science and Engineering, Department of Information System and Technology, University of Jeddah, Jeddah, Saudi Arabia (e-mail: sheem_y5@hotmail.com).

Mobile Application Development of Managing Elderly Household Accounts Using Speech Recognition

Since older people in Thailand mostly live with their children and grandchildren as an extended family, they play an important role in taking care of the household. The principles and concepts of speech recognition will be used in the development of a mobile application for managing household accounts by integrating spoken voice and touch screen functionality on smartphones, which is presented in Chapter 3.

2 Speech Recognition

  • Probability theory of speech recognition
  • Speech recognition architecture
  • Automatic speech recognition techniques
  • Collection data
  • The design of the mobile application
  • Development of the mobile application
  • The mobile application training for elderly people
  • The evaluation of the mobile application’s effectiveness

The features in the mobile application were evaluated by five experts specialized in the field of information technology and accounting. The effectiveness of the mobile application was evaluated by thirty-three samples who were elderly.

Fig. 1.  Speech Recognition System Structure
Fig. 1. Speech Recognition System Structure

4 Results

The evaluation with respect to the learning outcomes

From the paired sample t-test table, the significance value was analyzed to determine whether the means of the two groups were different. Comparison test results before and after training according to the statistical hypothesis test.

The effectiveness evaluation of the mobile application from the comprehen sion and user experience aspects

The evaluation results of the mobile application are based on accessibility barriers that could be detected by older people while using them. The comparison between the arithmetic mean of the mobile application based on accessibility barriers.

Table 4.  The evaluation results of the mobile application based on accessibility barriers that  could be detected by elderly people while being used
Table 4. The evaluation results of the mobile application based on accessibility barriers that could be detected by elderly people while being used

5 Conclusion

The result of the evaluation for acceptance of the mobile application based on accessibility barriers that can be detected by the elderly during use has a high degree of consensus. Easy access to the menu and submenus” with the mean value of 4.52 and the standard deviation of 0.51.

6 Acknowledgement

Touch-based mobile phone interface guidelines and design recommendations for the elderly: A survey of the literature, International Conference on Neural Information Processing, Springer, 568-574. Proceedings of the 7th International Conference on Software Development and Technologies for Improving Accessibility and Combating Info-Exclusion, ACM, 331–338.

8 Author

The Use of Gamification in Gastronomic Questionnaires

When an existing gastronomic questionnaire is expanded with game elements, the engagement of the users increases

When an existing gastronomic questionnaire is expanded with game elements, customer satisfaction remains at least the same

2 Research Design

  • Development tools
  • Game design elements of the gamified questionnaire
  • Sequence of the gamified questionnaire
  • Measurement

The structure and sequence of the gamified questionnaire is slightly modified compared to the classic questionnaire. All responses as well as the corresponding date and time of access are stored in the database.

Fig. 2.  Start page – Gamified questionnaire. (You are one of the few chosen to fill out the gam- gam-ified questionnaire
Fig. 2. Start page – Gamified questionnaire. (You are one of the few chosen to fill out the gam- gam-ified questionnaire

3 Evaluation

  • Demographics – Gender and age
  • Processing time during the completion process of the questionnaire
  • Response rate
  • Median of number of characters in text responses
  • Dropout rate

Text response from the classic questionnaire Text response from the gamified questionnaire Put tofu back in your range A little cheaper. When analyzing the text responses from the classic questionnaire, very often only one letter was used.

Table 3 shows the median and the average of the number of characters in open-text  responses, the text reply rate, as well as the maximum and minimum number of  char-acters in a text response for the classical and the gamified questionnaire
Table 3 shows the median and the average of the number of characters in open-text responses, the text reply rate, as well as the maximum and minimum number of char-acters in a text response for the classical and the gamified questionnaire

4 Discussion

The processing time for the gamified questionnaire increases by 46 seconds on average compared to the classic questionnaire. In the comparison between the classic and the gamified questionnaire, customer satisfaction remained at least the same.

Motorsafe: An Android Application for Motorcyclists Using Decision Tree Algorithm

While the motorcyclist e.g. detected "on vehicle", the phone will automatically switch to silent mode and all incoming calls from unimportant or unknown persons will be rejected. When the cyclist stops the bike, the phone will also automatically return to normal mode.

2 Material and Method

Data collection and feature extraction

Rejecting all non-essential and unknown incoming calls and automatically sending a message to inform the caller of the user's "On Vehicle" status. Allows receiving incoming calls from important persons (VIP) regardless of whether the user is in the vehicle or not.

Data classification

In the case of highly dynamic activities (such as walking and running), the output was marked "Not on vehicle (1)". In the case of low dynamic activity, the system continued to compare the VeDBAs with threshold B to classify the data under two classes "On vehicle" and "Not on vehicle (2)".

Fig. 1.  The decision tree algorithm flowchart
Fig. 1. The decision tree algorithm flowchart

3 Results and Discussion

The findings indicated that the specificity and precision of the system were significantly high. From then on, the software automatically detects the behavior of the users to indicate whether they are driving or not.

Table 1.  Average Performance (mean±standard deviation) of our software
Table 1. Average Performance (mean±standard deviation) of our software

4 Conclusion

5 Acknowledgement

He received his B.Sc. in Electronics and Telecommunications at Hanoi University of Transport and Communications, Hanoi, Vietnam, in 2002 and M.Sc. She received her master of engineering (ME) in telecommunications engineering from the University of Engineering and Technology, Hanoi, Vietnam, in 2005.

Mobile-Heutagogical Practices among Student Teachers

Its Pedagogical Affordances and Challenges

As such, the teacher can remain in front of the classroom and still be able to interact with the technology. The teacher's responsibility is not only to learn and become familiar with the hardware and software of such a learning tool, but also to understand how it can be used to contribute to the achievement of the learning objectives in a meaningful way.

Fig. 1.  The Principle of Mobile-Heutagogy (M-Heutagogy) in this study
Fig. 1. The Principle of Mobile-Heutagogy (M-Heutagogy) in this study

2 The Study

Most of the studies conducted in the West have shown that the use of the heutagogic practices has brought about significant pedagogical change in teaching and learning. As such, teachers should learn and explore the functionalities of the mobile to ensure that it can be used as a learning tool as well as a learning tool.

3 The Context of the Study and Methodology

Since the validity of the instrument is an essential process in the initial stage of the research, the content validity, criterion and construct validity of this study had necessarily been carried out by the researchers. In the process of testing the validity of the instrument, subject experts had been given a set of instruments and linked to the objectives of this study on the effectiveness of m-heutagogy.

4 Findings and Discussion

M-Heutagogical practice in cultivating self-directed learning paradigm The analysis of the interview data helped the researchers to determine several themes

The advantages of the M-Heutagogical practices

Also, easy navigation enabled them to return to any part of a teaching presentation to reinforce their students' understanding of learning concepts that students had difficulty grasping. With such a learning tool, students' works can be easily accessed for reference in learning activities.

Pedagogical challenges

In the interviews, the teachers indicated that using such a novel M-Heutagogy had led them to make such a switch. The results obtained from this study confirm some of the above benefits identified in the previous literature.

Design and Implementation of Voice Time, Time Indicator Application for Diabetic Retinopathy Patients

  • Diabetic retinopathy
  • Similar applications
  • Related works
  • Sounds
  • Speech recognition
  • Google speech API

Using the speech recognition, patients with diabetic retinopathy can give commands to mobile devices using voice [4] [5]. Reflecting on this, this study aims to develop an application to show time to diabetic retinopathy patients with the help of Google Speech API and volume buttons on Android devices.

Table  1  shows  a  comparison  of  several  applications  for  time  indicator  that  can  be  downloaded from Play Store [13]
Table 1 shows a comparison of several applications for time indicator that can be downloaded from Play Store [13]

3 System design

  • System block diagram
  • Data flow diagram system level 0
  • Data flow diagram system level 1
  • Application pages

The design of the Voice Time application for diabetic retinopathy patient in the form of level 0 and level 1 data flow diagrams is shown in Figure 2. Emergency contact Locate the position of user 1 (diabetic retinopathy patient), receive calls and automatic messages in the form of longitude and latitude, and set phone numbers and alarms.

Figure 1 shows the overall system planning block diagram of the time indicator ap- ap-plication for patients with diabetic retinopathy, described as follows:
Figure 1 shows the overall system planning block diagram of the time indicator ap- ap-plication for patients with diabetic retinopathy, described as follows:

4 Application Implementation

  • Voice time and emergency call features
  • Settings page
  • Time picker page
  • Pop up alarm for medication

There are two simple ways to know the time, by double-pressing the volume up button or by saying the words "What time is it?" The application will announce the time, for example "It is 30 minutes past 22:00" The phone number displayed on the emergency call is the phone number previously set in the settings menu.

Fig. 5.  Displays of The Main Page and Emergency Call Page
Fig. 5. Displays of The Main Page and Emergency Call Page

5 Results and Discussion

Testing methods

Voice Time application test, which checks the function of volume up and down, speech recognition, voice time and emergency call buttons, settings menus which include phone numbers and alarm list, as well as pop-up alarm messages. Voice timing test, which aims to measure the timing accuracy of voice timing activated by speech recognition or volume up button.

Results and discussion on the success of the application

Speech Recognition Tests, testing the application's accuracy in reading and recognizing speech by using the volume up button for speech time and the volume down button for emergency calls. The greater the distance between the user and the application, the greater the amplitude and speech recognition delay.

Figure 7b shows the displays when the system can recognize the voice from the pa- pa-tient  and  can  execute  the  commands  so  that  the  application  can  provide  time   infor-mation or make an emergency call, and then send an automatic message in the
Figure 7b shows the displays when the system can recognize the voice from the pa- pa-tient and can execute the commands so that the application can provide time infor-mation or make an emergency call, and then send an automatic message in the

To use the voice recognition function and connect to the Google API, the mobile phone must be connected to the internet network. 15] Iizuka S, Tsujino K, Oguri S, and Furukawa H, "Speech Recognition Technology and Applications for Improving Terminal Functionality and Service Usability", NTT DOCOMO Technical Journal, vol. 2010) 3D sound for virtual reality and multimedia.

Lens Application

Mobile Application Using Augmented Reality

  • Vision 2030
  • Technology in teaching and the classroom
  • History Augmented Reality-based learning
  • Theoretical framework
  • Related Work
  • Comparison between applications
  • Implementation
  • Testing

This way called "The Magic-Book" which is about enabling people's fantasies to become a part of the story a reality through the use of both original books and AR handheld device. Second, we are interested in investigating whether the application improved the outcome of the learning process.

Fig. 1.  Bloom
Fig. 1. Bloom's Taxonomy of Cognitive Goals[4], [16]

4 Results and Discussions

Distribution of the participants (teachers)

This confirms that although the difference in grades is statistically significant, it is actually relatively small. You need to consider whether this difference in grades is practically important, not just statistically significant.

6 Conclusion and Future Work

Rahaf Al-Amri is a student at the College of Computer Science and Engineering, Department of Information Systems, University of Jeddah, Jeddah, Saudi Arabia (Email: .rah14234@gmail.com). Maram Al-khaldi is a student at the College of Computer Science and Engineering, Department of Information Systems, University of Jeddah, Jeddah, Saudi Arabia (Email: .maram00za@gmail.com).

Development of a Smartphone Application for Safe Car Driving Using Google API and Built-in Sensor

As can be seen in Figure 1, although the car is usually considered a safer means of road participation than walking or two- and three-wheeled vehicles, the percentage of car occupants. There are a number of main reasons that often lead to traffic accidents: bad weather, excessive speed, drunk driving, fatigue, mobile phone distraction, etc.

Fig. 1.  Percentage of different road user type worldwide
Fig. 1. Percentage of different road user type worldwide

2 Related Work

Although it shows a promising result of crash detection, the whole system setup requires both IMU and smartphone, which already has its own built-in sensors. After recognizing the shortcomings of other apps, we developed Car Safe, which is compatible with every genre of Android smartphone and uses GAR_API (Google Activity Recognition Application Programming Interfaces) along with built-in sensors.

3 Proposed Application

  • Proposed algorithm
  • Message readout
  • Vietnamese text speak replacement database
  • Drive time warning
  • VIP list and call reception decision
  • Crash detection and post-crash aid

In that case, Car Safe is set to continue until it reconfirms 2 minutes later whether the user is still driving or not. The default threshold for driving time is set to 3 hours, which can be manually adjusted in the application to suit the user's needs.

Fig. 2.  Flowchart of Car Safe’s enhanced driving recognition based on GAR_API  In order to improve the performance, we process activity recognition by assenting  to the  majority of every 3 consecutive samples as each refers to the most likely  cur-rent s
Fig. 2. Flowchart of Car Safe’s enhanced driving recognition based on GAR_API In order to improve the performance, we process activity recognition by assenting to the majority of every 3 consecutive samples as each refers to the most likely cur-rent s

4 Result and Analysis

Crash detection and notification

Upon the arrival of the message as in Figure 10, contact from the other end can locate the accident site and send help. Since sending SMS via the application is now prohibited, the function will be lost from the application and sending email will be chosen as a replacement in the next update.

Fig. 9.  Crash data from 3-axes accelerometer
Fig. 9. Crash data from 3-axes accelerometer

Feature comparison

Driving state recognition test

15] Google Inc., Text-to-speech API, web resource: https://cloud.google.com/text-to-speech/. 18] Google Inc., Activity Recognition API, web resource: https://developers.google.com/lo cation-context/activity-recognition/.

Ant Colony Optimization for Real Time Traffic Lights Control on a Single Intersection

Then, in Sections 4 and 5, we present related works and Ant System Colony optimization metaheuristics. Then, in Section 6, we implement the ACO dynamic semaphore system for phase scheduling.

2 Traffic Lights Control Problem Control in an ITS Context

The paper is organized as follows: after the introduction, we present the context of the traffic light control problem in Section 2, then we show the analogy of the traffic light control problem with the scheduling problem in Section 3. Finally, in Section 7, we evaluate our method via the SUMO simulator and demonstrate its effectiveness by comparing the results with others methods.

3 Analogy of Traffic Light Control Problem With Scheduling

4 Related Works

Hình ảnh

Fig. 11.  Result of rate when GPA=2.95 and average correct answers=18.4 i.e. 60%
Table 2.  Cronbach’s Alpha values for the pilot study (Cronbach’s Alpha  0.70).
Table 8.  Results of structural Model - Research Hypotheses Significant at p**=<0.01 , p*
Fig. 1.  Design of Proposed System
+7

Tài liệu tham khảo

Tài liệu liên quan

- Play the recording all the way through for student to listen while they are reading the chant in their books. - Have student circle all the words containing the focused sounds