IJITEE (International Journal of Information Technology and Electrical Engineering)
Not a member yet
95 research outputs found
Sort by
Product Recommendation Based on Eye Tracking Data Using Fixation Duration
Full text linkE-commerce can be used to increase companies or sellers’ profits. For consumers, e-commerce can help them shop faster. The weakness of e-commerce is that there is too much product information presented in the catalog which in turn makes consumers confused. The solution is by providing product recommendations. As the development of sensor technology, eye tracker can capture user attention when shopping. The user attention was used as data of consumer interest in the product in the form of fixation duration following the Bojko taxonomy. The fixation duration data was processed into product purchase prediction data to know consumers’ desire to buy the products by using Chandon method. Both data could be used as variables to make product recommendations based on eye tracking data. The implementation of the product recommendations based on eye tracking data was an eye tracking experiment at selvahouse.com which sells hijab and women modest wear. The result was a list of products that have similarities to other products. The product recommendation method used was item-to-item collaborative filtering. The novelty of this research is the use of eye tracking data, namely the fixation duration and product purchase prediction data as variables for product recommendations. Product recommendation that produced by eye tracking data can be solution of product recommendation’s problems, namely sparsity and cold start
Optimal Capacity and Location Wind Turbine to Minimize Power Losses Using NSGA-II
Full text linkVoltage deviations and power losses in the distribution network can be handled in various ways, such as adding diesel power plants and wind turbines. Adaut Village, Tanimbar Islands Regency, Maluku Province has installed a diesel power plant with a capacity of 1,200 kW, while the average hourly electricity load is 374.9 kW. Adaut Village has high wind potential that can be used for distributed generations namely wind turbine (WT). WT can be used to improve power quality in terms of power losses and voltage deviations. In adding WT, the capacity and location must be determined to get good power quality in terms of power loss and voltage deviation. The research applied an optimization technique for determining the capacity and location of WT using non-dominated sorting genetic algorithm II (NSGAII) with an objective function of power losses and voltage deviation. In addition, the economic aspects of the power plant were calculated using the levelized cost of energy (LCOE). The research used scenarios based on the number of WT installed. The best results were obtained in scenario IV or 4 WT with 1.38 kW on Bus 2, 422.43 kW on Bus 15, 834.33 kW on Bus 30, and 380.81 kW on Bus 31 which could reduce power losses by 80% with an LCOE value of Rp7,113.15/kWh. The addition of the WT could also increase the voltage profile to close to 1 pu, which means it can minimize the voltage deviation in the distribution network
Image Analysis for MRI-Based Brain Tumor Classification Using Deep Learning
Full text linkTumors are cells that grow abnormally and uncontrollably, whereas brain tumors are abnormally growing cells growing in or near the brain. It is estimated that 23,890 adults (13,590 males and 10,300 females) in the United States and 3,540 children under the age of 15 would be diagnosed with a brain tumor. Meanwhile, there are over 250 cases in Indonesia of patients afflicted with brain tumors, both adults and infants. The doctor or medical personnel usually conducted a radiological test that commonly performed using magnetic resonance image (MRI) to identify the brain tumor. From several studies, each researcher claims that the results of their proposed method can detect brain tumors with high accuracy; however, there are still flaws in their methods. This paper will discuss the classification of MRI-based brain tumors using deep learning and transfer learning. Transfer learning allows for various domains, functions, and distributions used in training and research. This research used a public dataset. The dataset comprises 253 images, divided into 98 tumor-free brain images and 155 tumor images. Residual Network (ResNet), Neural Architecture Search Network (NASNet), Xception, DenseNet, and Visual Geometry Group (VGG) are the techniques that will use in this paper. The results got to show that the ResNet50 model gets 96% for the accuracy, and VGG16 gets 96% for the accuracy. The results obtained indicate that transfer learning can handle medical images
Topic Modeling in the News Document on Sustainable Development Goals
Full text linkIndonesia is a developing country and supports the program of the Sustainable Development Goals (SDGs) which consist of 17 goals. SDGs is not only the government’s duty, but a shared duty from any elements. Online media has a crucial role in implementing goals of Indonesia’s SDG. Information published in online news related to the SDGs is an important consideration for the government, society, and all elements. Categorizing news manually to find out news topics is very time-consuming and done by the ability of news editors. News presented by online media on the news site can be used as topic modeling, where hidden topics can be found in the news on online media. Topic modeling will classify data based on a particular topic and determine the relationship between text. Latent Dirichlet allocation (LDA) is one of the methods on topic modeling to find out the trend of topics of SDGs news. Based on the result of this research, the implementation of LDA is the right choice for finding topics in a document. The result of topic modeling with k = 17 obtained the highest coherence score of 0.5405 on topic 8. Topic 8 discussed news related to the eighth SDGs goals, namely decent work and economic growth. This categorization was based on words formed after the LDA process. Then, topic 5 discussed the news on the 17th SDGs goals, namely partnerships for the goals. Topic 6 discussed the news of the first SDGs, namely no poverty
A Review on Face Anti-Spoofing
Full text linkThe biometric system is a security technology that uses information based on a living person's characteristics to verify or recognize the identity, such as facial recognition. Face recognition has numerous applications in the real world, such as access control and surveillance. But face recognition has a security issue of spoofing. A face anti-spoofing, a task to prevent fake authorization by breaching the face recognition systems using a photo, video, mask, or a different substitute for an authorized person's face, is used to overcome this challenge. There is also increasing research of new datasets by providing new types of attack or diversity to reach a better generalization. This paper review of the recent development includes a general understanding of face spoofing, anti-spoofing methods, and the latest development to solve the problem against various spoof types
Factors Affecting Collaboration Portal Effectiveness of the Audit Board of Indonesia
Full text linkThe Audit Board of the Republic of Indonesia is known as Badan Pemeriksa Keuangan (BPK). In carrying out its duties and functions, it empowers and relies on information technology (IT) infrastructure that covers all aspects, including planning, procurement, service provision, information asset security, service continuity, and evaluation. BPK implements a collaboration portal to meet service needs and teamwork during the audit process, ad-hoc committees, and leader instructions to follow BPK’s strategic plan. BPK needs to assess the effect of the collaboration portal in supporting employee performance and improving IT services. As a result, this study aims to investigate the factors that influence the effectiveness of the BPK collaboration portal. This study used Delone and McLean model of information system success by looking at the relationship of system quality, information quality, service quality, facilitating conditions, and collaboration quality to user satisfaction and individual job performance. The research method used a quantitative approach with partial least squares-structural equation modeling (PLS-SEM). The sample data was collected from 60 respondents at BPK. The data obtained from the respondents were processed using the SmartPLS application. The study results show that information quality, facilitating conditions, and collaboration quality positively and significantly affect user satisfaction. There is a positive and significant influence of user satisfaction on individual job performance. In addition, system quality and service quality do not significantly influence user satisfaction with collaboration portal services
Modified Usability Test Scenario: User Story Approach to Evaluate Data Visualization Dashboard
Full text linkThe data processing results are commonly displayed in a dashboard with various graphic visualization forms to deliver new knowledge easier to understand by users. However, many data analysis dashboards cannot communicate the knowledge effectively and efficiently given the unsuitable design implementation. Therefore, research to measure the interface display's effectiveness in the data analysis system is deemed necessary. This research proposed a scenario modification in the usability test with a user story approach to measuring the system interface display in delivering the information to users. The approach of a usability test with the user story is expected to be capable of helping the researcher in understanding the user habits indirectly. There were 20 participants to validate the proposed method. Participants were asked to use the system and answer several questions to develop their user experience. After developing user experience for each user, the System Usability Scale (SUS) was conducted. SUS score results obtained from this research was 75.25. Besides, the researcher also measured the understanding level among the users using questionnaires. The questionnaire results were converted into numbers and resulted in a mean value of 91.8. Those two values indicate the users' ability to use the system well and obtain the new knowledge displayed in the data analysis dashboard
Applying Machine Learning for Improving Performance Classification on Driving Behavior
Full text linkTraffic accident is a very difficult problem to handle on a large scale in a country. Indonesia is one of the most populated, developing countries that use vehicles for daily activities as its main transportation. It is also the country with the largest number of car users in Southeast Asia, so driving safety needs to be considered. Using machine learning classification method to determine whether a driver is driving safely or not can help reduce the risk of driving accidents. We created a detection system to classify whether the driver is driving safely or unsafely using trip sensor data, which include Gyroscope, Acceleration, and GPS. The classification methods used in this study are Random Forest (RF) classification algorithm, Support Vector Machine (SVM), and Multilayer Perceptron (MLP) by improving data preprocessing using feature extraction and oversampling methods. This study shows that RF has the best performance with 98% accuracy, 98% precision, and 97% sensitivity using the proposed preprocessing stages compared to SVM or MLP
A Review of Feature Selection and Classification Approaches for Heart Disease Prediction
Full text linkCardiovascular disease has been the number one illness to cause death in the world for years. As information technology develops, many researchers have conducted studies on a computer-assisted diagnosis for heart disease. Predicting heart disease using a computer-assisted system can reduce time and costs. Feature selection can be used to choose the most relevant variables for heart disease. It includes filter, wrapper, embedded, and hybrid. The filter method excels in computation speed. The wrapper and embedded methods consider feature dependencies and interact with classifiers. The hybrid method takes advantage of several methods. Classification is a data mining technique to predict heart disease. It includes traditional machine learning, ensemble learning, hybrid, and deep learning. Traditional machine learning uses a specific algorithm. The ensemble learning combines the predictions of multiple classifiers to improve the performance of a single classifier. The hybrid approach combines some techniques and takes advantage of each method. Deep learning does not require a predetermined feature engineering. This research provides an overview of feature selection and classification methods for the prediction of heart disease in the last ten years. Thus, it can be used as a reference in choosing a method for heart disease prediction for future research
Serendipity Identification Using Distance-Based Approach
Full text linkThe recommendation system is a method for helping consumers to find products that fit their preferences. However, recommendations that are merely based on user preference are no longer satisfactory. Consumers expect recommendations that are novel, unexpected, and relevant. It requires the development of a serendipity recommendation system that matches the serendipity data character. However, there are still debates among researchers about the available common definition of serendipity. Therefore, our study proposes a work to identify serendipity data's character by directly using serendipity data ground truth from the famous Movielens dataset. The serendipity data identification is based on a distance-based approach using collaborative filtering and k-means clustering algorithms. Collaborative filtering is used to calculate the similarity value between data, while k-means is used to cluster the collaborative filtering data. The resulting clusters are used to determine the position of the serendipity cluster. The result of this study shows that the average distance between the recommended movie cluster and the serendipity movie cluster is 0.85 units, which is neither the closest cluster nor the farthest cluster from the recommended movie cluster