CogITo Smart Journal

Hybridization Model for Air Pollution Prediction Using Time Series Data

Roni Yunis — 2024-06-30

In recent years, data science analysis, particularly time series predictions, has been widely employed across various industrial sectors. However, time series data presents high complexity, especially in seasonal patterns such as monthly, daily, or hourly fluctuations. Irregular fluctuations and external factors increasingly challenge accurate predictions. Therefore, this research proposes a hybrid approach combining SVR-SARIMA, SVR-Prophet, LSTM-SARIMA, and LSTM-Prophet to enhance time series prediction accuracy. This study followed the OSEMN methodology approach: gathering data, cleaning data, exploring data, developing models, and interpreting crucial aspects of problem-solving. Seasonal effect predictions indicated a rise in SO₂ and NO₂ during dry and rainy seasons until the next two years (average daily increments of 0.0831 μg/m3 for SO₂ and 0.0516 μg/m3 for NO₂). Estimates suggest a decrease in the order of three particles. The evaluation showed that the SVR model performed better compared to the other three models (RMSE 7.765, MAE 5.477, and MAPE 0.261). The best-performing hybrid model was LSTM-Prophet (99.74% accuracy) with RMSE 12.319, MAE 12.057, and MAPE 0.259 values.

QR Code-Based Attendance System for Contact Tracking Post-Pandemic

Imam Husni Al Amin — 2024-06-30

The COVID-19 pandemic has brought about profound changes in daily life and introduced new challenges to public health maintenance. Despite ongoing uncertainties, with certain regions easing or completely lifting community activity restrictions, persistent concerns about the virus's continued threat prompt the need for robust health monitoring measures. In this context, the use of contact tracing apps becomes pivotal for organizing individuals' movements, monitoring social distancing, and ensuring adherence to health protocols. This study introduces a QR code-based attendance system, a meticulously designed web and Android application aimed at efficiently and accurately tracking individuals' whereabouts. The system leverages QR code scanning technology, and to enhance security, employs the Advanced Encryption Standard (AES) method for data encryption. This ensures the safe encryption of sensitive data, preserving its confidentiality and integrity during transmission and storage. The research outcome is a versatile application facilitating seamless access across diverse locations, allowing real-time tracking of individuals' presence. This capability proves crucial for contact tracing efforts in the event of positive cases, contributing to the implementation of post-pandemic security and surveillance policies. The system's design and features align with the evolving landscape of the pandemic, emphasizing adaptability and comprehensive support for public health initiatives.

Web-Based Application of Indonesia-Manado Translation Forum Using Extreme Programming Methodology

Vivi Peggie Rantung — 2024-06-30

Manado language (Manadonese) is one of the languages that is registered in the ISO 639-3 standard system with the code of xmm and used by 3.320.000 users. In daily life, Manadonese is commonly used verbally. In its oral use, Manadonese becomes a low-resource language, meaning it lacks text-based resources, which makes it difficult to develop various linguistic-based technologies to preserve Manadonese. This research aimed to provide a data source to develop advanced linguistic-based technology. The methodology used for this research is extreme programming (XP). The result of this research is a Web-Based Application Of Indonesia-Manado Translation Forum with various functions, such as uploading Indonesian articles that will be translated into Manadonese, from this diverse amount of translation the best of it will be chosen to be processed every word and sentence that will be saved in the database. The application is tested with Acceptance Testing as an indicator and the result shows that the forum managed to accomplish the goal set up before.

Structural Equation Modeling in E-Commerce Application Users: Case Study of Shopee

Ronny H. Walean — 2024-06-30

In line with current developments, especially advances in technology that are increasingly advancing, it facilitates all community activities in buying and selling goods, with the existence of e-commerce now people no longer need to go directly to the store to make these transactions. One of the e-commerce applications that are widely used today is a platform for shopping on the internet called Shopee which is easy to use. This study aims to see what factors are included in the form of acceptance by users of e-commerce applications, especially at Shopee, using Davis' (1989) Technology Acceptance Model (TAM) methodology. In this study, the analysis was conducted on 220 respondents who often or have used the Shopee application using the SEM PLS data analysis tool and a quantitative approach with the SmartPLS application. The results demonstrate the pathway through which users' attitudes toward usage are shaped by their perceptions of usefulness and ease of use, subsequently influencing their behavioral intentions, and ultimately impacting their actual usage behavior on the e-commerce application, namely Shopee. This study comprehensively elucidates the interrelationship among each Technology Acceptance Model (TAM) variable examined. Overall, the application of TAM in investigating the use of Shopee is validated through the findings of this study

Enhancing Machine Learning Model Performance in Addressing Class Imbalance

Lucky Lhaura Van FC — 2024-06-30

This research aims to investigate methods for handling class imbalance in machine learning models, with a focus on the Support Vector Machine (SVM) algorithm. We apply oversampling (SMOTE) and undersampling techniques to a dataset with class imbalance and evaluate the performance of SVM using these methods. Experiments are conducted using data from Twitter social media regarding the 2024 general electionsThe findings indicate that incorporating SMOTE effectively enhances the performance of SVM models, particularly within the SVM Polynomial variant. However, the use of undersampling shows limited impact on improving SVM model performance. This study provides valuable insights for researchers and practitioners in choosing the appropriate strategy for handling class imbalance in machine learning models.

Leveraging Machine Learning and Long-Short Term Memory Algorithm for Early Prediction of Diabetes

Yuri Pamungkas — 2024-06-30

Diabetes, a chronic condition, affects numerous populations. Poor insulin production from the pancreas combined with high blood sugar levels can result in the onset of diabetes. Diabetes can be caused by numerous factors. Observe and prevent these factors to reduce the high prevalence of diabetes. This study concentrates on medical record data for determining diabetes risk factors via statistical correlation analysis. These factors will be utilized as machine learning and LSTM input parameters for diabetes prediction. The factors analyzed include blood glucose levels, HbA1c levels, age, BMI, hypertension, heart disease, smoking habits, and gender. Based on the research results, we found that glucose levels (>137 mg/dL) and HbA1c levels (>6.5%) are the main benchmarks in diagnosing diabetes. It is also supported by the correlation value, which is relatively high (0.42 and 0.40, respectively) compared to other factors. Increasing age and BMI also increase the risk of developing diabetes. Comorbidities (such as hypertension or heart disease) and smoking habits can worsen the condition of people with diabetes. Meanwhile (based on gender), women are more at risk of developing diabetes than men because their body mass index increases during the monthly cycle. Apart from that, there is a tendency for blood sugar levels in women to increase in the last two weeks before menstruation. Based on the prediction results, the highest levels of accuracy, sensitivity, and F1 score were obtained (96.97%, 99.97%, and 98.37%) using the LSTM method. This performance shows that LSTM is relatively good for the diabetes prediction process based on existing factors/parameters.

Does Audit Software Adoption Matter? Evidence from Local CPA Firms in Indonesia

Judith Sinaga — 2024-06-30

The integration of technology in the audit practice is widely used nowadays. IT-based audits are applied since most of the accounting transactions are done computerized. This paper aims to assess the adoption of audit software by local CPA Firms in Jakarta and Medan, Indonesia. This research used the descriptive method with the quantitative approach. The research was conducted at five local CPA firms in Jakarta and Medan, with a research sample of 63 auditors. Data collections were done through questionnaires. Descriptive statistics, correlation, and regression were used to analyze data. The results of this study showed that perceived benefit and company readiness have positive and significant effects on the adoption of audit software. Adoption risk has a negative and significant effect on the adoption of audit software, and external pressure has no significant effect on the adoption of audit software. This research provides added value to all local CPA firms and makes audits more efficient and effective. It encourages all local firms to conduct the audit in a more advanced method through the use of audit software. This research corroborates the previous research in a different context (types of business and place). It focused more on a partnership type of business.

Effectiveness of SunPlus as an Accounting Information System in SDAC East Indonesia Union Conference Using DeLone & Mclean Information System Success Model

Roy Mandagi — 2024-06-30

Faith-based organizations play a pivotal role in society, necessitating robust information management systems for efficient functioning. This study examines the effectiveness of SunPlus, an accounting information system, within the context of the Seventh-day Adventist Church (SDAC), utilizing the Delone & McLean information system success model. The SDAC is a global faith-based organization overseeing numerous institutions. Data for this study was gathered through a questionnaire distributed among all SunPlus users within the SDAC East Indonesian Union Conference, which yielded responses from 80 participants. The findings highlight the significant impact of information and system quality on user usage and satisfaction, which in turn affect the overall net benefit to the organization. However, the study also reveals that service quality variables do not significantly influence usage and user satisfaction. Consequently, while SunPlus serves as an essential accounting information system, it may require additional enhancements to achieve optimal effectiveness in meeting the organization's needs. The study underscores the importance of continuous evaluation and improvement of information systems in faith-based organizations to ensure they adequately support their complex administrative and operational functions. These findings are crucial for the SDAC and similar organizations striving to enhance their information management systems for better performance and user satisfaction.

IT Management Shapes Marketing Using React Native at Gold Konveksi

Yesri Elva — 2024-06-30

Gold Konveksi is a small and medium-sized enterprise (SME) engaged in the garment industry that has not yet fully utilized technology in its marketing and product promotion. As a result, Gold Konveksi's market reach has been limited. This study aims to analyze the responses from questionnaires completed by respondents, with a specific focus on respondent profiles to generate brief demographic information. The objective of this study is to assess the readiness of both employees and customers of Gold Konveksi towards the adoption of new technology. The methods used in this research include data collection through questionnaires filled out by 247 respondents. The validity and reliability of the questionnaire instruments were tested using SPSS data processing. The validity test involved applying the r-value formula, compared to the r-table value, to determine validity. The reliability test was conducted using Cronbach's Alpha value compared to the reliability threshold. Additionally, the Technology Readiness Index (TRI) was calculated to measure user readiness in adopting new technology. The results of the study indicated a high level of readiness among users. The program interface was evaluated, and system testing was conducted using black box testing to ensure its functionality. Overall, the findings of the research show a high level of readiness among users in adopting new technology, which is expected to enhance transactions and sales data recording at Gold Konveksi.

Implementation of The Multi-Attribute Utility Theory Method in Determining the Best Work on The Yuwana Wikimedia Project

Muhammad Ikhlas — 2024-06-30

Reading activities are a form of literacy that can foster societal development. We can encounter various short forms of literacy besides reading and writing books, such as novel reviews, communicating and cross-talking. “However, there is still limited access to platforms that support literacy activities, particularly those that encourage community storytelling”. The Yuwana Project is one of the competitions held by Wikimedia Indonesia to provide space for people to work on writing children's short stories and traditional game stories. This competition is held online via Wikibuku. Where participants who take part in this competition will be assessed to determine the best work. The assessment process needs to be thorough so that those assessed comply with the assessment criteria that have been determined. For this reason, there is a need for a method that can produce the best decisions. The Multi-Attribute Utility Theory (MAUT) method is a method for making decisions by identifying and analyzing several variables quantitatively, In this study, 10 alternative data were tested, where the results were A6 with a preference value of 0.65 with the best first rank, then A7 with a preference value of 0.62 ranked second, and A2 with a preference value of 0.60 ranked third. So that the MAUT method can provide recommendations for selecting the best work for the Yuwana Wikimedia project.

The Effect of Brand Awareness on Decisive Customer Intention and Purchase Behavior of Shopee Gen Z Customers

Francis Hutabarat — 2024-06-30

The pervasive influence and evolution of social media continue to reshape societal dynamics. Accordingly, the current study endeavors to scrutinize whether brand awareness (BA), brand knowledge (BK), and brand preference (BP) serve as independent variables influencing customer intention (CI), with Purchase Decision (PD) serving as the dependent variable with CI as mediating factor in the relationship between BA, BK, BP, and PD. Against the backdrop of the Shopee marketplace, the study was conducted through a survey targeting Shopee customers specifically generation Z or millennials who had a history of purchasing or frequent platform usage in West Java, Indonesia. The quantitative dataset was compiled from responses provided by 91 participants, employing purposive sampling technique, the collected data were subjected to Structural Equation Modeling (SEM) using SmartPLS software for analysis. The outcomes indicated that BA and BK had insignificant effects on CI and PD. Conversely, BP demonstrated a significant and positive influence on customer intention and purchase decision. Moreover, the analysis revealed that CI acts as a significant mediator between BP and purchase decision. Thus, leveraging social media can augment brand preference, with an associated increase in customer intention leading to heightened purchase decisions. These findings furnish valuable insights to businesses, aiding them in making informed decisions regarding the selection of the most suitable social media strategy.

Analysis of Factors Affecting Intention in Using Google Classroom in Post-Pandemic Era with UTAUT2 Approach

Enrico Samuel Djimesha — 2024-06-30

A pandemic that happened a few years ago has forced universities around the world to adopt online learning. This was driven by government regulations that forced society to adopt health protocols and social distancing. The adoption of Google Classroom as a learning management system (LMS) has potential for universities because of its relatively lower cost than other LMSs, its ability to integrate with Google Meet, an online video conference application, and its ability to help manage learning files. XYZ University provides learning management services through Google Classroom. However, the usage of this LMS post-pandemic decreases after the social distancing regulation is lifted. This has become attention for the researcher to analyze and give recommendations to XYZ University on improving the usage of Google Classroom in the post-pandemic era to digitalize and centralize the learning process in a system. The researcher has designed the research stages, starting with problem formulation, using the UTAUT2 approach, analysis with PLS-SEM, and providing recommendations for the university. This model resulted in two factors affecting the acceptance of Google Classroom: performance expectancy and habit. Also, this model explains 56.5% of behavioral intention on using Google Classroom and 59.9% of use behavior of Google Classroom. This study recommends the institution to enforce the use of Google Classroom for every learning activity so that both faculty members and students are used to using it. This study also recommends the institution to socialize about the features and advantages of Google Classroom to help users aware of the positive impact of using Google Classroom on learning activities.

Comparative Analysis Clustering Algorithm for Government’s Budget Performance Data

Isnen Hadi Al Ghozali — 2024-06-30

The government's budget performance is a benchmark for the government's success in optimizing people's money to achieve national goals. Even though performance measurement has reached the Work Unit level, the data formed still do not have a specific grouping, in the sense of unstructured data. The purpose of this research is to find the best clustering algorithm for classifying budget performance data. The data used is budget performance data for 19,460 Indonesian Government Work Units. The data is sourced from the SMART application and the OM SPAN application. This research uses a comparative study approach for the K-Means algorithm, DBSCAN, and agglomerative hierarchical clustering (AHC). Evaluation of the clustering results formed using the Davies-Bouldin Index (DBI) method. The AHC algorithm with k = 6 achieved the lowest DBI value of 0.3583472. The DBI value for the DBSCAN algorithm with MinPts = 10 is 0.5398259. However, the AHC algorithm is not good in terms of ease of implementation. Therefore, the K-means algorithm with parameters k = 10 is the best alternative. The K-Means algorithm gets a DBI value of 1.052678. The K-Means algorithm produces 10 clusters. Based on knowledge extraction, it is determined that cluster 2 and cluster 5 are ideal clusters in terms of budget performance. While the clusters that require attention are cluster 1, cluster 3, cluster 4, and cluster 8.

Development of a Location-Based Augmented Reality Application for Navigation

Edson Yahuda Putra, M.Kom — 2024-06-30

Universitas Klabat (UNKLAB) is one of the private higher education institutions directly affiliated with the Seventh-day Adventist Church (SDA), located in North Minahasa, North Sulawesi. UNKLAB has approximately 3,500 students and boasts many buildings and facilities, including lecture halls, dormitories, sports fields, and more. Given the vast campus and numerous buildings, navigation is essential to help individuals find their way to specific buildings or locations. With the advancement of technology, the author identified an opportunity to implement Augmented Reality (AR) technology as a navigation aid at Universitas Klabat, utilizing iOS as the chosen platform. In this application, users can search for various locations, such as buildings, facilities, or faculty residences. The Research and Design (R&D) method was employed for this study, wherein the researcher conducted investigations and subsequently developed this application. During the application's development, one of the models within the Software Development Life Cycle (SDLC), namely the Prototyping model, was utilized. The researcher successfully created a location-based Augmented Reality application for navigating UNKLAB's campus, and it functions effectively on iOS mobile devices.

Deep Learning for Peak Load Duration Curve Forecasting

George Morris William Tangka — 2024-06-30

As the energy landscape changes towards renewable energy sources and smart grid technologies, accurate prediction of peak load duration curve (PLDC) becomes crucial to ensure power system stability. The background to this research is the urgent need for more effective prediction methods to manage increasingly complex energy loads. This research presents a leading-edge approach to PLDC prediction, leveraging Deep Learning, a subsection of artificial intelligence. Focusing on data from the Taiwan State Electric Company, this study uses a Long Short-Term Memory (LSTM) network to capture complex load patterns. The LSTM model, consisting of two layers and trained on 2019-2020 data, demonstrated excellent accuracy with a Mean Absolute Percentage Error (MAPE) as low as 0.03%. These results confirm the potential of Deep Learning to revolutionize PLDC predictions in complex energy systems. These research recommendations involve exploring diverse datasets, integrating real-time data streams, and conducting comparative analyses for more reliable prediction methodologies. The benefits of this research include providing relevant insights for sustainable energy resource management amidst a dynamic energy landscape.

Designing User Interface (UI) And User Experience (UX) of a Sport Space Rental Application using Design Thinking Method

Raissa Maringka — 2024-06-30

This study aims to enhance the design and streamline the process of renting sports facilities through the development of a user interface (UI) and user experience (UX) for a sport space rental application. Utilizing the Design Thinking method, the research addresses inefficiencies in the current manual booking process and proposes innovative solutions, including search features, user reviews, availability notifications, and direct booking options. The state of the art in this study is represented by the application of user-centric design principles and iterative prototyping to meet the evolving needs of sports enthusiasts. Usability testing, conducted through detailed task scenarios on the MAZE platform, yielded positive results, with an average completion rate of 80% and insights into areas for improvement. The findings suggest that the proposed UI/UX design significantly enhances the efficiency and user experience of renting sports facilities, providing a more convenient and engaging platform for users.

Implementation of CNN of Mobile-based COVID-19 Chest X-Ray Images

Indo Intan — 2024-06-30

The COVID-19 pandemic outbreak is the most significant event from 2019 until 2021. A medical examination of radiological images is carried out to check the condition of the patient's lungs. The limitations of this examination need alternative computer-assisted applications for patient CXR. This research aims to implement a back-end and front-end-based Convolutional Neural Network (CNN) model. Its advantage is that it can detect CXR images in real-time and non-real-time using multi-classification, namely normal, pneumonia, and COVID-19. The CNN model carries out the process of convolutional feature extraction and multi-layer perceptron classification at the back-end stage. In contrast, it uses an Android mobile-based application at the front-end stage. The research results show that the non-real-time condition has an accuracy of 98%, while the real-time is 95% lower. This research produces model and application performance that is flexible for user needs. The results can be recommended for developing applications for more comprehensive users.

Implementing QR code and Geolocation Technologies for the Student Attendance System

Semmy Wellem Taju — 2024-06-30

Attendance is one of the important factors in supporting lecture activities that can be used to see how well the performance of student attendance in class. Traditional attendance systems used in various educational institutions often cause problems. This research aims to develop an innovative and efficient student attendance system to help the process of taking attendance by utilizing QR-Code and geo-location technologies at Klabat University. The research method employed for this development is the Prototyping Model, which involves iterative development and refinement processes. The system is designed as a web-based application and a mobile application, developed using PHP as the programming language, MySQL as the database management system, Bootstrap 5 as the CSS and JavaScript framework for creating responsive websites, Apache as the web server and Ubuntu 22.04 as the operating system for the server. QR-Code technology is proposed as a medium for recording and verifying student attendance, while Geo-Location technology is used to verify the presence of students in the right lecture venue. The results of this research are expected to make a positive contribution to Klabat University in terms of recording student attendance.

Research Project Topic Recommender System Using Generative Language Model

Debby Erce Sondakh, S.Kom, M.T, Ph.D — 2024-06-30

Education has become a driver of a person's continuous innovation to improve their quality. Currently, the use of artificial intelligence determines progress in education. In this research, artificial intelligence technology was applied to develop a web-based recommendation system to help students at the Faculty of Computer Science, Klabat University, choose appropriate research topics for their final assignments. To provide personalized and contextually relevant suggestions, the recommendation system leverages deep learning and generative language models, specifically GPT-3. The Rapid Application Development process model is employed to develop the system. Its key components include semantic search, rapid engineering, and an advanced vector database for effective data management and retrieval. The functions provided by the system include user account registration, login, input of major subject grades and research preferences, and personalized recommendation results. Some additional features such as profile management, previous recommendation history, and password reset options are also provided. All these functions have been tested using the black box method.

Enhancing TikTok Account Performance with Data Pattern Identification

Wilem Musu — 2024-06-30

TikTok is a social media platform widely used to share information through short videos to achieve goals and interests in business, education, politics, government, and personal existence. Every activity on this platform is recorded and presented privately to each account owner. However, this data has not been utilized optimally to improve account performance. This research aims to offer a data analysis concept that integrates statistical and machine learning approaches to identify data patterns in each user's data collection, enabling the improvement of account performance. The approach utilizes Linear Regression, k-means, and Decision Tree methods. The results obtained show that the concept of identifying data patterns in TikTok account data has successfully developed a predictive model for video posts that can potentially increase total viewership, video plays, and audience engagement. This is achieved through optimizing video components such as captions, text, hashtags, sound genre, and video type. The outcome yielded a classification model that can predict capable component content to enhance account performance.

Comparative Analysis of Lung Cancer Classification Models Using EfficientNet and ResNet on CT-Scan Lung Images

Green Arther Sandag — 2024-06-30

This study investigates the classification of lung cancer, a major global cause of mortality. The accurate diagnosis and classification of lung cancer through CT-Scan images demand significant expertise, precision, and time to ensure appropriate treatment for patients. Transfer learning has emerged as a beneficial technology to aid in this process by effectively classifying lung cancer-related patterns in CT-Scan images. In this research, a dataset of 1,000 lung CT-Scan images, divided into four categories—Adenocarcinoma, Large Cell, Squamous, and Normal—was employed. The study evaluated several transfer learning models, including ResNet50, ResNet101, EfficientNetB1, EfficientNetB3, EfficientNetB5, and EfficientNetB7. The findings revealed that the EfficientNetB3 model outperformed the others, achieving an accuracy of 97.78%, a precision of 97.34%, a recall of 98.33%, and an F1-Score of 97.78%. These results demonstrate that the EfficientNetB3 model enhances the accuracy of lung cancer classification in CT-Scan images more effectively than other transfer learning models. This research underscores the significant potential of EfficientNetB3 in facilitating early diagnosis, advancing the integration of machine learning in medical practices, and providing critical insights for the selection of transfer learning models in clinical applications. The implications of these findings suggest a substantial impact on improving diagnostic processes and outcomes in lung cancer management.

IoT-based Environmental Monitoring with Data Analysis of Temperature, Humidity, and Air Quality

Jacquline Waworundeng — 2024-06-30

Environment monitoring has been linked to the use of the IoT. To raise awareness for the environment, the IoT system is built as an instrument tool based on a Prototyping model with an experimental approach. The hardware consists of sensors, microcontrollers, a Wi-Fi modem, powered with solar cells, and electricity integrated with IoT platforms Blynk and ThingSpeak. The prototype detectors were installed in two different locations at the Universitas Klabat. The IoT systems can store data, display information, and send push notifications as alerts to the user’s smartphone when critical conditions emerge. In the two locations for a specified time of May 2023, the data analysis shows average temperatures are 28,39˚C and 28,44˚C, where 28˚C is the optimal value. The average humidity shows 90,18%RH and 85,28%RH. These humidity values are critical because the humidity outside 40-60%RH can significantly impact health. The average air quality shows 59,62 AQI as “moderate” and 3.7 AQI as “good”. While “good” air quality is the best, “moderate” is safe because only when a value higher than 100 is unhealthy. The IoT system can help to monitor and provide real-time information about the environmental parameters.

Development of Web-Based Uteach Tutoring Application

Rolly Lontaan — 2024-06-30

In the rapidly evolving digital era, challenges in the field of education have become increasingly complex. This research aims to develop the UTeach learning guidance application, designed to assist students of Universitas Klabat in addressing academic issues. The application enables students to book mentors and meet face-to-face for guidance sessions. By implementing and utilizing the prototype model development method using the Software Development Life Cycle (SDLC), this study designs a prototype application aimed at facilitating student access to learning guidance by reducing time and distance barriers. Prototype testing is conducted through trials to evaluate the performance and usability of the application. This application is anticipated to serve as a potential tool in supporting Universitas Klabat students in improving academic performance and addressing financial issues. Development recommendations for this application may include adding conversation features, incorporating notification features, and developing a mobile application to enhance user efficiency. This research contributes to the advancement of educational technology by offering innovative solutions to enhance student learning experiences.