Digital Zone: Jurnal Teknologi Informasi dan Komunikasi

Decision Support System For Training Provider Selection Using Profile Matching Method

2024-06-08T09:10:28+00:00

The process of selecting training providers at PCU (Pertamina Corporate University) is currently not very effective and efficient, still relying on conventional methods that take a long time to choose a training provider, requiring one month for each training session. Conventional document collection by applicants can lead to the loss of documents, and there is no method in the selection of training providers, resulting in frequent occurrences of sole providers and difficulties in choosing providers for specific training needs. The research has led to the development of a web-based system using the Profile Matching method. The Profile Matching method was chosen because it involves determining competency values (standard assessment criteria) required for specific types of training, serving as a reference to evaluate selected provider candidates. This method selects the best alternative from various options by comparing the individual competencies of providers with the desired training profile values, resulting in competency differences (Gains Across Product). The smaller the GAP, the higher the weight of the score generated. Providers with the highest score have the highest ranking and a greater chance of being selected as training instructors at PCU. Data collection techniques used include observation and interviews.

Implementation of the Linear Regression Method to Determine Predictions of the Influence of Religion on General Election Participation

2024-06-08T08:57:16+00:00

This research aims to predict election participation in places of worship through statistical data analysis methods and predictive algorithms. Election participation, as a complex phenomenon, is influenced by various factors, with religion often being a crucial element that motivates or inhibits voter turnout. This study uses variables from Central Statistics Agency (BPS) data and recapitulation of previous general elections, based on historical patterns. Using a statistical approach, the relationship between religious variables and the level of voter participation in places of worship is identified. The linear regression method is used to predict the influence of religion on election participation. In this research, a series of scenarios were carried out, and the research results showed different variations in R-squared (R-Square) and Mean Squared Error (MSE) results. The best scenario, namely the R-squared scenario with a value of around 0.00012 and an MSE of 0.09934, highlights the potential relationship between religion and voter participation. These findings suggest the need for further considerations in this context, as well as demonstrating the need for model adjustments to improve the accuracy of future election predictions.

Public-Private Collaboration to Overcome the Digital Divide in Digital Transformation of Government

2024-06-08T08:59:05+00:00

The objective of this article is to explore the issue of the digital divide and how we can bridge it to overcome the challenge of digital transformation. We will start by examining the key factors that contribute to the issue of the digital divide, which include economic factors, accessibility of infrastructure and technology, and also digital literacy. We will explore the strategies and initiatives that need to be implemented to address these challenges and promote digital inclusion. Based on our research, we have argued that bridging the digital divide is not only limited to social justice and equity but is also a key driver for achieving economic growth and innovation. We will focus on how important it is to ensure that every citizen can access digital services equally. Also, they should be trained with the skills to use it effectively. Public-private collaboration is essential for bridging the digital divide in government digital transformation. This study identifies key strategies and outcomes of such collaborations, emphasizing their role in enhancing digital access and service delivery. Findings underscore the importance of partnership models in fostering inclusive and effective digital governance. So, overall, this article will provide a comprehensive overview of the digital divide, its challenges, and how we can solve these problems to create opportunities that will add value to the country's progress.

Implementation of a CNN-trained model for coffee type detection in an Android app with photo input of beans, fruits, and leaves

2024-06-08T09:00:13+00:00

Coffee is the most consumed type of drink in the world. Each type of coffee has different physical characteristics from leaves, fruits to seeds. Now technology is needed in the world of agriculture in making decisions. To determine the type of coffee with fission characteristics, there are still many people who do not understand in distinguishing the physical characteristics of coffee plants. In this case, an application was developed using the RAD method by utilizing the flutter framework and the Convolutional Neural Network model that has been trained. The pre-train model used is NasNet Mobile with a dataset of 900 photos and 100 epochs with early-stopping utilization and heti at epoch 55 with an accuracy of 90.67%. In this study, implementing existing models into Android applications using the Flutter framework. With the implementation process carried out by the application can help the detection process using an android device. The implementation results get good test results with a score of 0.97. This application can help the process of identifying the type of coffee and minimize errors in identifying directly.

Application of the Naïve Bayes Algorithm in Sentiment Analysis of Using the Shopee Application on the Play Store

2024-06-08T09:03:07+00:00

This research aims to find out the opinions of users of the Shopee application on the Play Store using the Naive Bayes Naive Algorithm and to find out the suitability of the correct application of the Naive Bayes algorithm in carrying out sentiment analysis with the classification of three sentiment classes. The dataset used in this study consisted of 2000 customer reviews obtained from the Play Store in 2024 collected by the scraping process using the Python library. The dataset has 1,198 examples of negative attitudes, 583 examples of good sentiment, and 219 examples of neutral sentiment. The results of this study are expected to be used as evaluation material for Shopee Apilkation to improve the performance of Shopee applications. Research findings show that the Bayes naive approach reaches accuracy determined by various aspects, such as the quantity of data collections and positive and negative data distribution. This study shows that the Bayes naive algorithm can function properly as a technique to evaluate user sentiment for applications in the Play Store. However, with the classification of three classes, another algorithm is needed to produce higher accuracy.

Recommendation System to Determine Achievement Students Using Naïve Bayes and Simple Additive Weighting (SAW) Methods

2024-06-08T09:04:24+00:00

Giving appreciation to outstanding students can motivate students to compete with each other in learning. MA Tanwirul Qulub Tanggungan often experiences difficulties in determining outstanding students due to There is no application that can assist school management in identifying outstanding students, the implementation is considered less than optimal. besides that, the determination of outstanding students is still based on report cards that are only ranked, and there are no criteria that refer to the K-13 curriculum. The purpose of this research is to offer a solution to create a recommendation system for selecting outstanding students using the parameters of midterm exams, final exams, assignments, attendance, attitude, extracurricular activities, organizations, and award certificates using decision support system techniques. Extracurricular grades are taken from Scouting activities only because students are generally required to participate in them. Naïve Bayes and Simple Additive Weighting methods are used in this research, where the Naïve Bayes method classifies the categories of outstanding students and not, while the SAW method is used for ranking. The contribution of this research has the potential to increase school efficiency in student assessment and support efforts to improve the quality of education by rewarding students appropriately. The validation test results of Naïve Bayes and SAW techniques get an accuracy value of 100%, which shows that the SAW method can produce the best alternative recommendations

Comparative Study of the Effect of Datasets and Machine Learning Algorithms for PDF Malware Detection

2024-06-08T09:05:32+00:00

This research presents an innovative approach to detecting malicious PDFs through machine learning algorithms, focusing on the expansion of the Evasive-PDFMal2022 dataset. The objective is to enhance the accuracy of detecting malicious PDFs by enriching the dataset, augmenting its representation and diversity, and developing a practical tool—a website—for extracting and detecting malicious PDFs. The methodology involves updating and enlarging the dataset with additional malicious PDFs sourced from CVE and Exploit-db, along with non-malicious PDFs from diverse origins. Features are then extracted using the PDFID tool, and these 20 features serve as the foundation for implementing K-Nearest Neighbor (KNN), Random Forest, and Random Committee algorithms. The outcomes demonstrate that the model trained with the expanded dataset achieves a remarkable 99% accuracy, surpassing the performance of models relying solely on the Evasive-PDFMal2022 dataset. Additionally, this research significantly enhances the representation and diversity of the dataset while delivering a practical solution in the form of a website tailored for the extraction and detection of malicious PDFs.

Enhancing Dental Image Segmentation Techniques: Edge Detection and Color Thresholding

2024-06-08T09:06:40+00:00

Rapid advancements in medical technology, particularly in the field of dentistry, have led to significant progress in the application of medical imaging techniques to generate valuable image data. The resulting images often exhibit heterogeneous intensity distributions, with boundaries not always distinctly clear between the tooth roots and bone, along with variations in shape and pose. This study specifically aimed to identify the optimal image for segmenting specific parts of the dental structures. Image segmentation is crucial for ensuring effective diagnosis in the context of dental medicine. To achieve optimal dental image segmentation, this research combines edge detection methods with the determination of color thresholds, specifically grayscale and Hue, Saturation, Value (HSV). The research findings revealed that edge detection using the Sobel gradient operator yielded a relevant count of 17,099 pixels. Using RGB=3 and HSV=0.3 the color thresholds show an enhancement in the brightness of the resulting HSV-segmented image, while in the RGB-segmented image, the selected object appears more prominent. The findings of this study contribute significantly to the evolution of dental image segmentation techniques, potentially enhancing the accuracy and effectiveness of diagnoses within the realm of modern dental practice

Optimizing Arowana Fish Breeding with IoT Aquaculture

2024-06-08T08:55:57+00:00

Monitoring and controlling water temperature and pH levels are crucial aspects in maintaining a healthy environment for breeding Arowana fish. Arowana fish are sensitive to fluctuations in water temperature and pH levels, which can lead to stress, diseases, and even death. Therefore, it is essential to regularly monitor and maintain the temperature and pH levels within suitable ranges for the fish. This study aims to develop Internet of Things (IoT) technology that is expected to assist Arowana fish farmers in monitoring and controlling more effectively and practically. The methodology employed in this study is a case study approach, with Arowana fish farmers as respondents. In monitoring the water quality for Arowana fish, many farmers still rely on traditional farming models that heavily depend on experience, lacking the ability to assess water quality and environmental changes scientifically. By utilizing LoRa and cellular technologies, this study provides intelligent solutions for water quality monitoring to create controlled and sustainable growth conditions. The ultimate outcome of this research is the development of an IoT-based application designed to enhance the efficiency of Arowana fish farming. This application involves automatic control of water pH and temperature in three different treatments. The methodology employed in the application design involves the development of an IoT-based system integrated with temperature and pH sensors. The functionality of the application includes real-time monitoring and automatic control of the aquarium environment. Testing was conducted through a series of field trials to ensure system performance and reliability. With a pH range of 6.5 - 7.5 and temperature range of 26 - 30°C, this application has proven to provide optimal responses for Arowana fish farming, enhancing growth and reducing feeding time.