Inspiration: Jurnal Teknologi Informasi dan Komunikasi

Software Defect Prediction For Quality Evaluation Using Learning Techniques Ensemble Stacking

Muhammad Romadhona Kusuma — 2023-11-24

This research aims to improve the software quality and effectiveness of zakat management by the National Amil Zakat Agency (BAZNAS) through the development of a software defect prediction model (SDPM). We used machine learning techniques and ensemble stacking approach on the "Masjid Tower" dataset containing 228 records and 34 attributes. The preprocessing process involved label encoding, feature selection with Pearson correlation, standard normalization, and the use of SMOTE to handle data imbalance. We performed hyperparameter tuning with grid search CV on Machine Learning algorithms such as Ada Boost and Gradient Boosting. The results showed that the ensemble stacking approach with a combination of Gradient Boosting, Ada Boost, Decision Tree, Bayesian Ridge, and LightGBM meta learner algorithms provided high accuracy with R2 score reaching 0.97, MAE of 0.037, and MSE of 0.006. This finding proves that the ensemble stacking approach is able to overcome the problem of software defects with accurate prediction results, provide useful guidance in the management of zakat and other software applications, and has the potential to improve software quality and the effectiveness of BAZNAS in managing zakat.

Handover Analysis Of 4G LTE (Long Term Evolution) At A Frequency Of 2400 Mhz

Al Habib Maulana Akhyar — 2023-12-12

Information technology has now become a primary need for many individuals, facilitating access to various needs, including work, learning, and other activities. Mobile phones allow users to stay connected to the internet without interruption, even when traveling out of town, thanks to their ability to switch between cells or through a process known as handover. The focus of this article is on the impact of handover on 4G LTE networks. The data collection approach in this research uses the drive test method by utilizing the tems pocket application to retrieve internet network data. The research results highlight the importance of understanding how handover can affect 4G LTE network performance. With the role of information technology increasingly dominating everyday life, a deep understanding of technical aspects such as handover has become essential to maintaining the quality and efficient availability of cellular communications services.

Darunnajah Vote System Application Design Using PHP Programming Language

Supriadi Panggabean — 2023-12-11

Voting is the most important part of choosing leaders in an organization or institution, especially for those of us who use a democratic system. The election of organizational leaders in Darunnajah is still carried out conventionally, elections still use paper to select organizational leaders which is carried out by recording and counting the name or picture of one of the candidates. Creating the Darunnajah Vote System in the form of a web application for the election of organizational leaders in the Darunnajah environment can speed up the voting process. The web application is built using PHP and MySQL with features of user management, class management, candidate management, and E-Voting. This study aims to build an e-voting system that is expected to provide voting results quickly, and accurately and can be monitored in real-time during the implementation of the leader election. This system development method uses a web application-based SDLC Waterfall model. Testing using the black box method, every feature contained in the Darunnajah Vote System application, namely the Admin Login feature, User Login, User Voting, and User Data Processing features runs normally and functions properly.

Time Effort Prediction Of Agile Software Development Using Machine Learning Techniques

Muchamad Bachram Shidiq — 2023-12-08

To run a software development project, an effective and efficient project management mechanism is needed to coordinate the activities carried out. The agile method was developed because there are several weaknesses in the classic method that can interfere with the course of the software development process according to user desires. However, in applying agile methods, time effort estimation cannot be done properly. This can cause project managers to have difficulty preparing resources in software development in scrum projects. For this reason, this research aims to predict the time effort of agile software development using Machine Learning techniques, namely the Decision Tree, Random Forest, Gradient Boosting, and AdaBoost algorithms, as well as the use of feature selection in the form of RRelieff and Principal Component Analysis (PCA) to improve prediction accuracy. The best-performing algorithm uses Gradient Boosting k-fold validation with PCA with an MSE value of 2.895, RMSE 1.701, MAE 0.898, and R2 0.951.

Sentiment Analysis Of Indonesian Civil Servan Candidates 2023 Twitter Network With Naive Bayes Algorithm Method

Harman Akbar Tullah — 2023-12-29

The main objective of this research is to uncover the important role played by the social media platform Twitter in shaping public opinion regarding the 2023 Civil Servant Candidate (CPNS) selection process in Indonesia. Using advanced techniques such as social network analysis and Python language processing, as well as the application of the Naive Bayes algorithm, this research carefully examines the conversation patterns and topic trends prevalent on Twitter during the CPNS selection phase. The findings of this research unequivocally highlight the enormous influence of Twitter on public sentiment related to CPNS selection, as demonstrated by the classification model's impressive accuracy rate of approximately 95.19%. In addition, this research successfully identifies the influential roles played by key actors, prominent accounts, and narratives in shaping public perceptions. These groundbreaking insights foster a comprehensive understanding of the dynamic nature of public opinion in the context of CPNS selection, providing an invaluable basis for designing more effective communication strategies for the government and prospective civil servants.

Prototype Of DPO Search Information System (People Search List) On CCTV Cameras Using Face Recognition

Tri Reski Anugraha — 2023-12-31

The efficiency aspect of the housing security sector is the main consideration in creating information technology in a CCTV security development, because so far CCTV has not guaranteed maximum housing security, because CCTV can only record not analyze. This makes CCTV only a recording device for the point of occurrence, so this activity is less effective considering CCTV cannot analyze the face of a person who has committed a DPO action. So on that basis, researchers are developing existing technologies with facial recognition systems using the face recognition method for housing security. This method works by detecting a person's facial features. The face recognition apps provide information to the authorities by notifying the notification on the user's smartphone (security guard). So face recognition apps have been applied to the Green Cakra Housing, to help security guards monitor the entrance and exit of guests in the housing. This system can recognize the face of DPOs by obtaining a percentage of the assessment as much as agreeing that the application is effective enough.

Design of An Agricultural Extension Schedule Management System

Teguh Soedarto — 2023-11-24

Based on the strategic plan of the Ministry of Agriculture for 2015-2019, development in the agricultural sector will refer to the Agriculture for Development Paradigm which positions the agricultural sector as a driver of balanced and comprehensive development transformation including demographic, economic, intersectoral, spatial, institutional and development governance. With such great potential, the Pasuruan Regency Food and Agriculture Security Service has problems in the availability of human resources in quantity, especially agricultural instructors. For this reason, there is a need for a system that can optimize existing human resources. The system development method used is the waterfall method, the waterfall method is a method that works sequentially, the development of the agricultural extension schedule management system has been going well. So that it can help the work management process of agricultural instructors in distributing agricultural extension at the village level. This agricultural extension schedule management system is implemented using a MySQL database and the PHP programming language. This system is easy to use so it helps related parties in schedule management and recording extension activities.

IoT-Based Propane and Butane Pressure Measurement

Frabowo Prasetia — 2023-12-15

Liquefied Potreleum Gas is a hydrocarbon containing two main gas components, propane, and butane, produced from oil and gas refineries Liquefied Potreleum Gas is a hydrocarbon containing two main gas components, propane, and butane, produced from oil and gas refineries. In this study, researchers will do the same thing in the IoT field but not in health monitoring but refer to Butane and Propane Gas Pressure Monitoring in LPG. Errors often occur when using an analog manometer (needle panel) when taking pressure measurements due to inaccurate measurements. There is a clear necessity for using digital manometers to ensure precise gas methane pressure measurement. The sensor receives data then the Arduino processes the data for conversion, the final results will be sent to the cloud using the esp8266 module and then forwarded to the smartphone as a monitoring user to see and also check gas conditions.

Implementation Model Prototyping In Application Design of Halal Food Product Detection For Overseas Muslim Students

Fandisya Rahman — 2023-11-24

In the age of globalization, the production and trading of food have become more widespread, and consumers, particularly those who follow the Islamic faith, require access to information about the halal status of the products they consume. It is crucial to provide accurate and relevant information to them regarding the halal nature of the products they buy. To cater to this need, many people are using barcode scanners via mobile platforms to obtain product information. These barcode scanners use optical scanners called code readers, and they are popular as they provide a quick and efficient way of obtaining information. Creating a barcode application using the prototyping method is an effective solution that involves several steps, such as gathering and analyzing requirements, rapid design, building a prototype, user evaluation, and refining the prototype. The programming language Kotlin is used to create these applications, which support building Android applications on the Java Virtual Machine Platform (JVM). The use of Kotlin, which is statically expressed and executed, makes the process of developing these applications efficient and straightforward. In summary, developing a barcode application using the prototyping method and Kotlin is an excellent solution to provide consumers with accurate and accessible information about the halal status of food products they consume.

User Segmentation Based on Purchasing Habits and Preferences on the Amazon Platform Using K-Means Clustering

Al Isra Denk Rimakka — 2023-12-08

As a large company, Amazon operates an online marketplace with a diverse user base exhibiting varied purchasing habits. This diversity challenges Amazon to provide tailored services and marketing strategies for each user with distinct characteristics. Therefore, this research aims to assist Amazon in segmenting its users based on their characteristics, enabling the implementation of targeted marketing strategies and service provision for each user. The study employs the K-Means Clustering method to segment Amazon platform users based on their purchasing behavior, site feature interactions, and preferences. The research process involves Knowledge Data Discovery (KDD) stages, including data processing, attribute selection, and applying the K-Means Clustering algorithm. The analysis results reveal five distinct user clusters, each with unique characteristics reflecting user behavior and preferences. These clusters depict variations in purchasing frequency, interactions with site features, and responses to product recommendations. This user segmentation provides valuable insights for Amazon to develop more focused marketing strategies, enhance personalized services, and improve overall customer satisfaction.

Controlling System of Automatic Microcontroller for Passion Fruit Juice Extractor

Sitti Wetenriajeng Sidehabi — 2023-12-11

The fruits are squeezed to extract their concentrate in fruit processing factories or industries, especially for the purple passion fruit variety. However, separating seeds from the fruit pulp uses a blender, resulting in a mixture of seeds and pulp. In this industry, seeds and fruit pulp are separated using a spinner machine and operated manually by operators. So, adding an automatic mechanism has the potential for optimization and improvement. This research aims to develop a passion fruit squeezing machine with maintenance and automation, upgrading the passion fruit filtering and squeezing spinner machine. The purpose is to control the speed of the passion fruit filtering motor using an AC Dimmer module and create an efficient automated tool for the passion fruit mixer and extractor machine. A squeezing machine is designed by utilizing a counter module to count the incoming passion fruits into the cylinder, and an Arduino Uno is used as the controller to adjust the motor speed using an AC dimmer. The passion fruit filtering machine is operated at a minimum triggering angle of 130 degrees and a maximum triggering angle of 80 degrees, or voltages ranging from 69.9 V to 102 V, with a minimum speed of 780 RPM and a total rate of 1462 RPM, and the squeezing time varies from 2 to 4 minutes.