JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
Predicting Factors that Affect East Asian Students’ Reading Proficiency in PISA
Get PDFTeachers, schools, and parents contribute to equipping students with essential knowledge and skills during their education years. When students are approaching the end of their education, they are randomly selected to participate in Program for International Student Assessment (PISA) to assess their reading proficiency. Existing work on analyzing PISA achievement results concentrates solely on identifying factors related to Parent or in combination with Student. Limited work has been proposed on how factors related to Teacher and School affect the students’ reading proficiency in PISA. This study focuses on identifying the factors related to Teacher and/or School that affect East Asian students’ reading proficiency in PISA. The PISA achievement results from East Asian students are chosen as the domain study because they are consistently the top performers in PISA in the past decade. Decision Tree (DT), Naïve Bayes (NB), K-Nearest Neighbors (KNN) and Random Forest (RF) are compared. Hamming score is used as the evaluation metric. The results indicate that RF produces the best predictive models with highest Hamming score of 0.8427. Based on the findings, School-related factors such as the number of school’s disciplinary cases, size of the school, the availability of computers with Internet facilities, the quality and educational qualifications of teachers have higher impact on the PISA achievement results. The identified factors can be used as a reference in assessing the current school’s teaching, learning environment, and organizing extra activities as part of intervention programs to cultivate reading habits and enhance reading abilities among students
Predicting the Welfare Cost of Premature Deaths Based on Unsafe Sanitation Risk using SutteARIMA and Comparison with Neural Network Time Series and Holt-Winters
Get PDFUnhealthy and unsafe sanitation will make it easier for various diseases to attack the body. In addition, unsafe sanitation will also affect a country's economy, including declining welfare, tourism losses, and environmental losses due to the loss of productive land. The research aimed to estimate the welfare cost of premature deaths based on unsafe sanitation risks using the SutteARIMA, Neural Network Time Series, and Holt-Winters. The study analyzed estimates and projections of the welfare cost of premature deaths based on the risks of unsafe sanitation of BRICS countries (Brazil, Russia, Indonesia, China, and South Africa). The data in this research used secondary data. Secondary time series data was taken from the Environment Database of the OECD. Stat. (Mortality and welfare cost from exposure to environmental risks). The data on the study was based on variables: welfare cost of premature deaths, % GDP equivalent, risk: unsafe sanitation, age: all, sex: both, unit: percentage, and data from 2005 to 2019. The three forecasting methods (SutteARIMA, Neural Network Time Series, and Holt-Winters) were juxtaposed in fitting data to see the forecasting methods' reliability and accuracy. The accuracy of forecasting results was compared based on MAPE and MSE values. The results of the research showed that the SutteARIMA and NNAR(1,1) methods were best used to predict the welfare cost of premature deaths in view of unsafe sanitation risks for BRICS countries
History Students’ Readiness in Using QR Code Based E-Job Sheet
Get PDFThe research objective is to identify primary history students' readiness to use QR code-based e-job sheets in terms of knowledge, experience, and supporting facilities. The research material consists of digital technology devices, smartphones, internet networks, electronic worksheets, QR Code applications, and an assessment of historical learning. This research applied a quantitative approach. Research respondents included significant history students at the Faculty of Social Sciences Universitas Negeri Padang from 2018 to 2022, including 140 students. Data were collected through a Google Form application questionnaire and shared with the students via WhatsApp. The data were analyzed quantitatively by using percentages and averages. General findings showed that many students were ready to use QR code-based e-job sheets, but others still needed them. The particular findings included: 1) more than half of respondents knew what the e-job sheet was, but two-thirds of them had no experience using the e-job sheet, 2) related to QR codes, it was found that half of the respondents knew what QR code was, but a part of them had no experience using QR codes, and 3) two-thirds of the respondents stated that supporting facilities such campus internet and their smartphone were unable to support the use of QR codes-based e-job sheets. QR code-based e-job sheets have become essential in optimizing digital technology in learning activities. Further research is needed to measure the effectiveness of using QR code-based e-job sheets as an alternative strategy and instrument for assessing learning outcomes in the digital era
Curriculum Management Systems for Blended Learning Support
Get PDFThe ongoing COVID-19 has left some serious impacts on education, bringing academic activities to a halt, and restrictions have been in place to hamper the proliferation of the virus. The utilization of technology these days plays a vital role in assisting students in attending education online or blended learning and keeping academic activities running. However, limited learning management systems present a new problem in online learning, especially in higher education. Thus, a new information system is required to resolve this issue. This study aims to develop the Bauran information system to assist lecturers in higher education with curriculum design and semester lesson plans and to evaluate the effectiveness of Bauran's implementation using the ISO 25010 model. The material used during the research process included the Bauran application, Guidelines for Developing Higher Education Curriculum, and some data from relevant users to test the application. Meanwhile, during the development stage of the research, the prototype method was used to adjust the development to the feedback given by stakeholders. This application received positive feedback from relevant users regarding the curriculum development flow in line with the Guidelines of Curriculum Drafting for Higher Education. Using the ISO 25010 model during the testing process, the results of user evaluations demonstrated its effectiveness with an average score of 4.84 out of 5. Future research is expected to evaluate the long-term effectiveness of Bauran using a larger sample size and a different software evaluation model
Node.js Performance Benchmarking and Analysis at Virtualbox, Docker, and Podman Environment Using Node-Bench Method
Get PDFAs an asynchronous runtime environment (interpreter) for the development of scalable JavaScript-based network applications, it is necessary to know the performance of the web framework on Node.js in a virtualization-oriented development environment and a container-oriented development environment. This research aims to compare the performance of Node.js in several frameworks in VirtualBox, Docker, and Podman environments. The testing was carried out using some materials like a bench utility at Node Package Manager (NPM) involving the Adonis, Connect, Express, Fastify, Foxify, Hapi, Koa, Molecular, Plumier, Restify, and Sails frameworks, using Object Relational Mapping (ORM) and Raw Query Bookshelf, Knex, MySQL, MySQL2, and Sequelize at Ubuntu Linux operating system. The method research used in this research is the Node-Bench method with requests, latency, and throughput parameters. The testing results show that the best performance score is the Fastify framework with the Sequelize library (ORM) in a container-oriented development environment (Docker and Podman), and the worst performance score is the Express framework with the Mysql2 library (Raw Query) in a virtualization-oriented development environment (VirtualBox). Based on the testing results, developers who use Node.js are more advised to use the Fastify framework with the Sequelize library (ORM) in a container-oriented development environment (Docker or Podman) to obtain better performance. For further research, the implementation and testing at container-oriented development can use cloud-based service (IaaS cloud or PaaS Cloud) for the read-only immutable environment, scalability, and security reasons.Keywords— Docker, Node-Bench method, Node.js, Podman, VirtualBox
Improved Image Classification Task Using Enhanced Visual Geometry Group of Convolution Neural Networks
Get PDFConvolutional Neural Networks (CNNs) have become essential to solving image classification tasks. One of the most frequent models of CNNs for image classification is the Visual Geometry Group (VGG). The VGG architecture is made up of multiple layers of convolution and pooling processes followed by fully connected layers. Among the various VGG models, the VGG16 architecture has gained great attention due to its remarkable performance and simplicity. However, the VGG16 architecture is still prone to have many parameters contributing to its complexity. Moreover, the complexity of VGG16 may cause a longer execution time. The complexity of VGG16 architecture is also more highly prone to overfitting and may affect the classification accuracy. This study proposes an enhancement of VGG16 architecture to overcome such drawbacks. The enhancement involved the reduction of the convolution blocks, implementing batch normalization (B.N.) layers, and integrating global average pooling (GAP) layers with the addition of dense and dropout layers in the architecture. The experiment was carried out with six benchmark datasets for image classification tasks. The results from the experiment show that the network parameters are 79% less complex than the standard VGG16. The proposed model also yields better classification accuracy and shorter execution time. Reducing the parameters in the proposed improved VGG architecture allows for more efficient computation and memory usage. Overall, the proposed improved VGG architecture offers a promising solution to the challenges of long execution times and excessive memory usage in VGG16 architecture.
Hybrid Deep Learning Approach For Stress Detection Model Through Speech Signal
Get PDFStress is a psychological condition that requires proper treatment due to its potential long-term effects on health and cognitive faculties. This is particularly pertinent when considering pre- and early-school-age children, where stress can yield a range of adverse effects. Furthermore, detection in children requires a particular approach different from adults because of their physical and cognitive limitations. Traditional approaches, such as psychological assessments or the measurement of biosignal parameters prove ineffective in this context. Speech is also one of the approaches used to detect stress without causing discomfort to the subject and does not require prerequisites for a certain level of cognitive ability. Therefore, this study introduced a hybrid deep learning approach using supervised and unsupervised learning in a stress detection model. The model predicted the stress state of the subject and provided positional data point analysis in the form of a cluster map to obtain information on the degree using CNN and GSOM algorithms. The results showed an average accuracy and F1 score of 94.7% and 95%, using the children's voice dataset. To compare with the state-of-the-art, model were tested with the open-source DAIC Woz dataset and obtained average accuracy and F1 scores of 89% and 88%. The cluster map generated by GSOM further underscored the discerning capability in identifying stress and quantifying the degree experienced by the subjects, based on their speech pattern
Indonesian Hate Speech Detection Using IndoBERTweet and BiLSTM on Twitter
Get PDFHate speech is an act of speech to spread hate to other people. In this digital era where everyone connects with social media, hate speech is growing rapidly and uncontrollably. Many people do not realize they are giving hate speech when critics something on social media due to a lack of awareness of the difference between hate speech and free speech. The results make victims feel alienated from society, and the people who spread it would often face the law. Detection in the sentences to identify whether it contains hate speech is essential to counter people's ignorance. For detecting such sentences, a machine learning algorithm is widely used to help identify each sentence. In this paper, we used a subset from machine learning named deep learning with the latest IndoBERT model named IndoBERTweet and combined it with RNN layer named BiLSTM. The appearance of IndoBERTweet opened more chances to further improve text classification performance with the addition of BiLSTM layer. The model first made a token representative from the sentence, then calculated it to analyze and made the classification based on the calculation. For this model to be effective, we trained our model with the labeled public dataset retrieved from Twitter. These datasets are classified into hate speech and non-hate speech, and these labels are applied to the models. We evaluated our model and achieved an accuracy of 93.7%, an improvement for classifying hate speech sentences from previous research
The study on Malaysia Agricultural E-Commerce (AE): Customer Purchase Intention
Get PDFElectronic commerce (E-Commerce) became an essential trading platform after the Covid-19 pandemic. From essential products to luxury brands, consumers can find almost everything on the normal E-Commerce platforms with the exception of fresh agricultural products. Agricultural E-Commerce (AE) is introduced to overcome the market needs. Technology Acceptance Model (TAM) is studied and integrated with additional variables to determine the needs of AE in Malaysia. In this study, five variables (product quality, logistic service quality, perceived price & value, platform design quality, and platform security) were studied to determine the Malaysian consumers’ purchase intention towards the AE. Five hypotheses were developed to identify the relationship between the variables. A total of 300 AE users have contributed their perception as respondents in this study through a survey questionnaire. The collected data were processed before the data analysis via Statistical Package for The Social Science (SPSS) version 25.0. Descriptive analysis, and inferential analysis were conducted. The result shows that all five variables are significantly related to the purchase intention towards AE. The product quality has the highest significant value (0.805) towards the purchase intention on AE, followed by logistic service quality, platform security, platform design quality and perceived price and value. Implication, limitation, and recommendation were also being discussed to assist the AE stakeholders in improving their AE
The Evaluation of Entropy-based Algorithm towards the Production of Closed-Loop Edge
Get PDFThis research concerns the common problem of edge detection that produces a disjointed and incomplete edge, leading to the misdetection of visual objects. The entropy-based algorithm can potentially solve this problem by classifying the pixel belonging to which objects in an image. Hence, the paper aims to evaluate the performance of entropy-based algorithm to produce the closed-loop edge representing the formation of object boundary. The research utilizes the concept of Entropy to sense the uncertainty of pixel membership to the existing objects to classify pixels as the edge or object. Six entropy-based algorithms are evaluated, i.e., the optimum Entropy based on Shannon formula, the optimum of relative-entropy based on Kullback-Leibler divergence, the maximum of optimum entropy neighbor, the minimum of optimum relative-entropy neighbor, the thinning of optimum entropy neighbor, and the thinning of optimum relative-entropy neighbor. The experiment is held to compare the developed algorithms against Canny as a benchmark by employing five performance parameters, i.e., the average number of detected objects, the average number of detected edge pixels, the average size of detected objects, the ratio of the number of edge pixel per object, and the average of ten biggest sizes. The experiment shows that the entropy-based algorithms significantly improve the production of closed-loop edges, and the optimum of relative-entropy neighbor based on Kullback-Leibler divergence becomes the most desired approach among others due to the production of more considerable closed-loop edge in the average. This finding suggests that the entropy-based algorithm is the best choice for edge-based segmentation. The effectiveness of Entropy in the segmentation task is addressed for further research.