{"title":"Orientation and Scale Based Weights Initialization Scheme for Deep Convolutional Neural Networks","authors":"A. Abdullah, Wong En Ting","doi":"10.17576/apjitm-2020-0902-08","DOIUrl":"https://doi.org/10.17576/apjitm-2020-0902-08","url":null,"abstract":"Image classification is generally about the understanding of information in the images concerned. The more the system able to understand the image contains, the more effective it will be in classifying desired images. Recent work has shown that the convolutional neural network (CNN) paradigm is useful for obtaining more accurate image classification results. A crucial component in the CNN is the convolution filters which consist of a series of predefined filter weight initialization values. The filter weights are then automatically learned by the neural network throughout the back-propagation training algorithm. However, most initialization schemes used in the deep convolutional neural networks are mainly to deal with vanishing gradient problems. Thus, selecting optimal weights are crucial to improve convergence and minimize the complexity which can enhance the generalization performance. One possible solution is to replace the standard weights with parameterized filters that proven to be efficient in extracting useful features such as Gabor filter bank. The Gabor filter bank is popular due to its ability in dealing with spatial transformation, especially on edges and texture information of different scales and directions. Thus, in this paper, we investigate the effect of utilizing Gabor and convolutional filters on small size kernels of deep VGG-16 architecture. The standard VGG-16 filter is replaced with the Gabor filter bank to obtain uniform distribution at all layers of the network. The result shows that the orientation and scale weights initialization scheme outperforms the standard filter weights on an image classification problem.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114217885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Towards The Engagement of Children with ADHD Using Sifteo Cube Technology","authors":"I. Ahmad, S. M. Aliyu, Hafsa Kabir Ahmad","doi":"10.17576/APJITM-2019-0802-02","DOIUrl":"https://doi.org/10.17576/APJITM-2019-0802-02","url":null,"abstract":"This paper examines the impact of Sifteo Cube Technology in engaging children with attention deficit hyperactivity disorder (ADHD). ADHD is an early childhood neurodevelopmental disorder which starts as early as five years of age. The core symptoms are inattentiveness, impulsiveness, and hyperactivity. By identifying the history of games development and ADHD, the researchers explored the viability of using the kinesthetic technology of Sifteo Cubes to engage these children. Engaging children with ADHD can lead to better management of the children, administering of learning materials, or aid other therapeutic methods. To carry out this research, an adventure game playable on the Sifteo Cubes using open-source games development kit called Wildflower was developed and evaluated with children with ADHD for qualitative analysis. Results obtained from video capture and ethnography proved favourable. Sifteo Cubes can effectively engage the children for an average of 20 minutes. The results show that Sifteo Cubes is effective is in engaging children with ADHD.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130611175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MMORPG Game Framework Based on Learning Style for Learning Computer Netwoking","authors":"Mercy Trinovianti Mulyadi, N. Zin","doi":"10.17576/APJITM-2019-0801-06","DOIUrl":"https://doi.org/10.17576/APJITM-2019-0801-06","url":null,"abstract":"The widespread use of computer networks and high demand for computer networking skills in business and industry led to computer networking courses becoming popular in higher education institutions. However, conventional learning has not succeeded in developing the understanding and relevant skills at the expected level. Students’ performance in computer networking courses has shown a significant drop. Preliminary survey found that majority of students feel that the teachings do not match their learning styles, so boredom seems to be the main cause of decreasing performances. Therefore, this study aims to examine the effectiveness of using a Massive Multiplayer Online Role Playing Game (MMORPG) designed based on learning styles in motivating and helping the learning of Computer Network courses. The objectives of the study are to develop a Computer Network course learning framework using online games that take into account student’s learning style, verifying and validating the framework through implementation in game prototype and assessing student acceptance of the game. The IPGame prototype designed based on constructivism, adult learning, flow and engagement theories and scaffolding techniques was developed, while the learning styles used are sequential and global. The results showed that the game has a high motivational value to students and thus the framework can be used to guide development of educational games with similar content.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127214197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tarik Abu-Ain, S. N. H. S. Abdullah, K. Omar, Siti Zaharah Abd. Rahman
{"title":"Advanced Stroke Labeling Technique Based on Directions Features for Arabic Character Segmentation","authors":"Tarik Abu-Ain, S. N. H. S. Abdullah, K. Omar, Siti Zaharah Abd. Rahman","doi":"10.17576/APJITM-2019-0801-08","DOIUrl":"https://doi.org/10.17576/APJITM-2019-0801-08","url":null,"abstract":"Offline Character segmentation of text images is an important step in many document image analysis and recognition (DIAR) applications. However, the character segmentation of both writing styles (printed and handwritten) remains an open problem. Moreover, the manual segmentation is time-consuming and impractical for large numbers of documents. Based on the unconstraint-cursive handwritten perspective, the auto character segmentation is more challenging and complex. The Arabic script writing style suffers from many common problems, such as sub-words overlapping, characters overlapping, and missed characters. These challenging issues have attracted the attention of researchers in the field of DIAR for Arabic character segmentation. The proposed method combines a new advanced Stroke Labelling based on Direction Features (SLDF2) technique and a modified vertical projection histogram (MVPH) technique. This technique extracts the relationship between each text stroke pixel and its 8 neighboring foreground pixels and labels it with the proper value before identify the possible segmentation points. The text preparation for the segmentation process was achieved using multiple preprocessing steps and developing an advanced stroke labelling technique based on direction features. Several Arabic language structural-rules were made to detect the candidate segmentation points (CSP), detect many character overlapping cases, solve the missed characters problem that appears as a result of using the text skeleton in VPH, and validate the CSP. All techniques and methods are tested on the ACDAR benchmark database. The validation method used to measure segmentation accuracy was a quantitative analysis that includes Recall, Precision, and F-measurement tests. The average accuracy of the proposed segmentation method was 92.44%, which outperforms the state-of-the-art method.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"273 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124852560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Aspect-Based Sentiment Analysis Methods in Recent Years","authors":"Zohre Madhoushi, A. Hamdan, S. Zainudin","doi":"10.17576/APJITM-2019-0801-07","DOIUrl":"https://doi.org/10.17576/APJITM-2019-0801-07","url":null,"abstract":"Sentiment Analysis (SA) is the computational treatment of opinions, sentiments and subjectivity of text. Aspect-based Sentiment Analysis (ABSA) is a specific SA that aims to extract most important aspects of an entity and predict the polarity of each aspect from the text. A review of the recent state-of-the-art in ABSA, shows the remarkable growing in finding both aspect, and the corresponding sentiment. Current methods are categorized based on their proposed algorithms and models. For each discussed study, aspect extraction method and sentiment prediction method, the dataset, domain and the reported performance is included. The main goal of this work is to review ABSA techniques with brief details. The main contributions of this paper consist of the refined categorizations of a great number of recent articles, comparing them and the illustration of the recent trend of research in the ABSA.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130895729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Use of Addie Model for Designing Blended Learning Application at Vocational Colleges in Malaysia","authors":"Muhamad Azhar Stapa, Nazeri Mohammad","doi":"10.17576/APJITM-2019-0801-05","DOIUrl":"https://doi.org/10.17576/APJITM-2019-0801-05","url":null,"abstract":"Teaching is a highly complex occupation, which needs to adapt to a great deal of variety in context, subject matter and learners. It does not lend itself to broad generalization. However, academic knowledge is not the only kind of knowledge that is important in today's society, and as teachers we have to be aware of other forms of knowledge and their potential importance to our students, and make sure that we are providing the full range of contents and skills needed for students in a digital age. E-learning strategies are still not explored extensively in the system of vocational education for the learning process in Malaysia. Nevertheless it i possible to provide guidelines or principles based on best practices, theory and research, which must then be adapted or modified to local conditions. This study discusses the instructional design and development of e-Iearning prototype called Vocational Learning (Voc-Learning) by using ADDIE model and implemented via blended learning method. ADDIE model is one of the instructional design models used by many researchers to develop software or applications related to the field of education.The design of application development based on the ADDIE is explained as Analysis, Design, Development, Implementation and Evaluation. The strength of concerned is according to the variables have been devided into several items such as; teaching design, content, user controls and technical. Implementation phase involves formative evaluation of a prototype developed and make adjustments and improvements where necessary. The percentage of expert approval percentage becomes a benchmark in comparison. This study highlights the development of blended Voc-Learning model based on the relevant theories of teaching and learning.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117102652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Malay Named Entity Recognition Using Rule Based Approach","authors":"Ulfa Nadia, N. Omar","doi":"10.17576/APJITM-2019-0801-04","DOIUrl":"https://doi.org/10.17576/APJITM-2019-0801-04","url":null,"abstract":"Named Entity Recognition (NER) research based on rule is widely investigated and is used in various languages mainly English. However, the English NER rules are different with Malay language due to different morphology. Some of challenging issue in Malay is cross reference between named entities, and entity repetition. This paper proposes to solve the issues in Malay NER. This study starts by providing Malay online news corpus, gazeteer development, rules development and evaluation. This study focus on nine name entities i.e person, organization, position, date, time, currency, measurement and percentage. Overall the experimental result shows 90.23% precision, 92.13% recall and 91.05% f-measure. The outcome from this research is expected to help other researchers in implementing the Malay NER using rule based approach through the addition of new rules to achieve higher accuracy.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132746860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Thanatchai Sirivichayakul, Kristian Spoerer, H. Iida
{"title":"Homogeneous Group Performance and Stability in Checkers","authors":"Thanatchai Sirivichayakul, Kristian Spoerer, H. Iida","doi":"10.17576/APJITM-2019-0801-02","DOIUrl":"https://doi.org/10.17576/APJITM-2019-0801-02","url":null,"abstract":"Experiments on groups of Checkers programs, playing by majority voting, were performed to investigate performance and stability. Homogeneous groups, copies of the same program, was used to perform these experiments instead of heterogeneous group that was more complicated by factors of different programs. Experiments were performed based on a search-depth of 5, 10 and 12 using the Samuel checkers program. Games of checkers were played between groups of size ranging from 1 up to 10 for each side. Experiment results suggest that group performance increases as a kind of logarithm function as the group size gradually increases for stronger player, and the performance slowly decreases in the case of a weaker player, stability seems to increase as the group size increases.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129866555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Soft Skills Assessment Based on Undergraduate Student Perception","authors":"Hazura Mohamed, H. M. Judi, Ruzzakiah Jenal","doi":"10.17576/APJITM-2019-0801-03","DOIUrl":"https://doi.org/10.17576/APJITM-2019-0801-03","url":null,"abstract":"Soft skills are generally interpreted as a person's skill in building good relationships with oneself and others, i.e. what is being said as intrapersonal skills and interpersonal skills. The element of soft skills should be available to an individual to meet the skills of every graduate. However recent statistics from the Ministry of Higher Education in its official website indicate that the number of graduates still unemployed is high. Therefore, this study aims to examine the level of soft skills among students of the Faculty of Technology and Information Science (FTSM) through activities conducted by each special interest group (SIG). There are 11 SIGs with various computing activities. Kirkpatrick's Assessment Model which contains four categories (reactions, learning, behavior and outcomes) is used to measure the achievement level of the soft skills of FTSM students. The results show that the four categories are in good level, with the overall level of FTSM student's soft skills in good category. The Kirkpatrick Assessment Model can be applied in evaluating the performance of a training or its equivalent.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"84 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115754397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Perceived Ease of Use Towards Acceptance on Focused Educational Video Sharing Site","authors":"Sazanah Md Ali, A. Ali","doi":"10.17576/APJITM-2019-0801-01","DOIUrl":"https://doi.org/10.17576/APJITM-2019-0801-01","url":null,"abstract":"This study aimed to analyse psychological, social, technological and institutional factors in influencing perceived ease of use towards focused educational video sharing site. The acceptance factors were studied based on the technology acceptance model (TAM) constructs, namely perceived usefulness, perceived ease of use, attitude towards the use and behavioural intention. A series of learning software video tutorial in the form of screencast has been developed and uploaded to two forms of video sharing sites which were the focused educational video sharing site (LearnSoftware) and social media based video sharing site (YouTube) to be used in this study. A questionnaire has been used as an instrument to compare and analyse the level of students' acceptance towards both forms of video sharing site based on the original construct TAM developed. Quantitative research method was used and data were collected from 294 students of Multimedia studies (major and minor) from 5 Public Higher Learning Institutions. significant difference found in terms of the attitude towards the use. From the multiple regression analysis conducted, it was found that psychological, and technological factors have a significant connection with the students' perceived ease of use towards focused educational video sharing sites, while social and institutional factors were not significant. In conclusion, the findings of this study can benefit the educational institutions, students and instructors as well as video sharing site developers in understanding students' behaviour on accepting and using the new technology introduced.","PeriodicalId":130300,"journal":{"name":"Asia-Pacific Journal of Information Technology & Multimedia","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133415573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}