CCIT (Creative Communication and Innovative Technology) Journal

Conceptual Design of an Integrated Smart Home System with PV Solar Power for Traditional Minahasa Wooden House

2025-02-11T07:57:10+00:00

The traditional Minahasa wooden house is an integral part of Indonesia's cultural heritage. However, in this modern era, the challenge of preserving cultural authenticity while introducing it to the technological era is becoming increasingly urgent. This research aims to design a Smart Home System concept integrated with Photovoltaic (PV) Solar Power Plant for traditional Minahasa wooden houses. The objective of this study is to identify the potential for integrating smart home technology and PV Solar Power Plant in Minahasa wooden houses and to develop a concept that combines traditional elements with modern technology. The research methodology will involve a literature review to understand the concepts of smart homes, PV Solar Power Plant, and the characteristics of traditional Minahasa wooden houses. Additionally, descriptive research through interviews will be conducted in collaboration with industry partners to obtain data and examples of traditional Minahasa wooden houses to be used as benchmarks in the concept design. This research can contribute to integrating modern technology into Indonesia's cultural traditions while enhancing the competitiveness of Minahasa wooden house products in the market. The result of this research is a conceptual design for the implementation of a Smart Home System integrated with a PV rooftop solar power plant system in Minahasa wooden houses. The utilization of solar energy as electrical energy is predicted to achieve an annual energy yield of 16,775 kWh.

Comparative Analysis of Time Series Methods LSTM and ARIMA for Predicting Inventory Availability (Case Study: PT XYZ)

2025-02-11T07:56:11+00:00

Product availability plays a crucial role in supply chain management, directly impacting all aspects of business operations, from production to distribution. This study analyzes the optimization of product availability at PT. XYZ, a frozen and chilled food trading company in Indonesia, focusing on four main commodities: beef, buffalo meat, chicken, and potatoes. Utilizing historical transaction data from 2020 to July 27, 2024, this research compares the performance of two forecasting models: ARIMA (AutoRegressive Integrated Moving Average) and Long Short-Term Memory (LSTM), in predicting product availability The traditional ARIMA model has proven effective in time series data analysis but has limitations in capturing complex patterns and non-linear fluctuations. LSTM, as a machine learning technique, demonstrates superiority in capturing long-term temporal relationships. This study finds that the LSTM model consistently outperforms ARIMA for beef, buffalo meat, and chicken categories, although there is a slight increase in error for the potatoes category. Model performance evaluation is conducted using metrics such as Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Error (RMSE). The results indicate that the LSTM model exhibits lower errors compared to ARIMA, proving its effectiveness in predicting dynamic demand patterns. With a better understanding of product availability, the company is expected to reduce operational costs, avoid losses, and enhance customer satisfaction through more efficient supply chain management. This research provides significant insights for PT. XYZ and similar industries in implementing more accurate forecasting methodologies

Interface Analysis of Bullying Monitoring Systems for Students in Avicena Rajeg School

2025-02-17T07:59:41+00:00

The Emergency Panic Button tool has been developed to provide quick response and accessibility in emergency situations. In this research, we designed and developed an Emergency Panic Button tool using the Arduino ESP32 Devkit V1. This tool allows users to easily trigger emergency signals, send help messages to Telegram, and includes user location information and monitoring of the user's body temperature. The development method includes the integration of electronic components such as buttons, communication modules such as GSM or Wi-Fi, and body temperature sensors. We use Arduino ESP32 Devkit V1 as the main platform and utilize the Telegram API software to send help messages to specified contacts. In this research, we study the theoretical foundations related to emergency systems, Arduino technology, integration with the Telegram API, and user body temperature training. We design and implement tools by developing Arduino programs that allow training panic buttons, sending emergency messages to Telegram, acquiring locations using GPS modules or other methods, as well as training the user's body temperature using temperature sensors.

Sentiment Analysis of Twitter Data on the 2024 Indonesian Presidential Election Using BERT

2025-02-17T08:00:29+00:00

Social media platforms, particularly Twitter, are frequently employed by individuals to articulate their opinions on various subjects in textual form. The proliferation of viewpoints from diverse sources can influence public perceptions on these topics. The greater the popularity of a topic, the more abundant the opinions generated. Currently, the most widely discussed topic is the 2024 Indonesian presidential election. Sentiment analysis, or opinion mining, is an academic discipline that examines sentiments towards a given entity, while text mining involves the extraction of information through processing, classifying, and analyzing extensive datasets. This study will utilize data crawling techniques to gather data from Twitter which will subsequently undergo preprocessing and cleaning. Following this, the cleaned data will be classified by sentiment (positive, negative, or neutral) using a pre-trained language model (BERT) and Natural Language Toolkit (NLTK). The classified data will then be visualized with tools such as Matplotlib and Wordcloud to elucidate the data distribution.

Analysis of CSR Program Against Regional Inequality in Bogor Regency Using K-Means and Random Forest Algorithms

2025-02-17T08:01:27+00:00

Bogor Regency is vast and has significant economic and social potential. Collaboration between businesses and local governments is essential to achieve regional development goals. Corporate Social Responsibility (CSR) plays a role in sustainable economic, enhancing the quality of life for the community. CSR can be implemented independently by companies or supported by the CSR Support Group (TF-TJSL). The Bogor Regency is divided into three development areas, the Western, Central and Eastern, with regional inequality reflected in a Williamson index of 0.731. CSR has the potential to reduce these inequalities through positive contributions. This study analyzes CSR programs on regional inequality in Bogor Regency using data mining technology with K-Means and Random Forest algorithms. The K-Means algorithm shows the optimal result with the best silhouette score at K=2 with a score of 0.76268, reflecting a clear separation between clusters representing regional inequality. The Random Forest algorithm shows excellent classification ability with an accuracy of 0.985 and other evaluations of precision, recall, and f1-score are almost perfect, which indicates its effectiveness in classifying data into three clusters according to development areas. The regression model evaluation results are also good, with a very low MSE (0.003961), indicating minimal prediction error.

Comparison of Data Mining for Classifying Student Graduation Levels Using Naive Bayes, Decision Tree, and Random Forest Methods (Case Study of The Undergraduate Program at Mitra Indonesia University)

2025-02-17T08:09:13+00:00

This study aims to apply data mining techniques to classify student graduation rates in the Undergraduate Program at Mitra Indonesia University. The methods used in this study include Naive Bayes, Decision Tree, and Random Forest. The data used includes student academic data, such as grades, attendance, and other demographic information. The research steps include data collection, data cleaning, data analysis, and the application of data mining algorithms. The results of the study show that the Random Forest method provides the highest accuracy compared to Naive Bayes and Decision Tree in predicting student graduation rates. The Random Forest method achieved an accuracy of 85%, while the Decision Tree achieved 80%, and Naive Bayes achieved 75%. These findings are expected to help Mitra Indonesia University identify students at risk of not graduating on time, so appropriate interventions can be provided to improve graduation rates

Automating Internet Distribution with Script-Driven Provisioning and Load Balancing Methods

2025-02-17T08:09:31+00:00

The utilization of software-based automation technology in the internet network distribution process is currently relatively expensive, while conventional configuration methods cause inefficient use of time, cost, and energy. The time spent is about 5 minutes for each configuration process. The waiting time for a queue of 5 customers with 1 technician is 20 minutes. This problem can be solved by applying the concept of network automation using the Zero Touch Provisioning method, which can increase time efficiency to 5 seconds for each configuration process. Additionally, the use of Priority and Round-Robin algorithms is very helpful in overcoming queue management problems, allowing the server to work according to the desired process logic. The results showed an average wait time of 7.6 seconds with a quantum value of 10. This value was obtained in the process of 5 customer queues with 1 server.

Usability Analysis of The Student Service Information System at The Faculty of Engineering Tadulako University Using Heuristic Evolution and The System Usability Scale (SUS)

2025-02-17T08:09:47+00:00

The Student Service Information System is defined as a system designed to assist students, faculty, and administration at Tadulako University's Faculty of Engineering in managing various academic aspects. This research identifies issues or obstacles users face while utilizing the website. The usability evaluation employs the Heuristic Evaluation method and the System Usability Scale (SUS). Based on the research conducted with 100 respondents, all active students at Tadulako University, the usability measurements revealed significant findings. According to the Heuristic Evaluation method, which utilizes 10 principles, areas requiring improvement were identified in qualifications B1.2, B3.3, B8.2, B10.2, and B10.3. Recommendations for enhancements include adding a notification feature, ensuring the search function is easily discoverable, selecting appropriate color combinations, and improving the placement of the user guide. The System Usability Scale yielded a score of 50, categorizing the website as "OK" on the adjective scale, "D" on the grade scale, and "Marginal" on the acceptability scale, with a net promoter score indicating a "Passive" reception.

Implementation of Data Mining for Classifying Student Graduation Levels Using Naive Bayes, Decision Tree, Random Forest, Support Vector Machines and Neural Networks Methods (Case Study of The Undergraduate Program at Mitra Indonesia University)

2025-02-17T08:10:54+00:00

This study aims to classify student graduation levels using five data mining methods: Naive Bayes, Decision Tree, Random Forest, Support Vector Machines, and Neural Networks. Conducted as a case study at Mitra Indonesia University, the research utilizes academic data, including GPA, course completion rates, and attendance records, to predict graduation success. The results reveal that Random Forest and Neural Networks exhibit the highest accuracy, making them the most suitable methods for predicting student outcomes. These findings contribute to the development of early intervention programs for students at risk of delayed graduation, providing valuable insights for higher education institutions.

Application of Webqual 4.0 and Importance Performance Analysis Methods in Analyzing The Quality of Information Technology SIPENDEKAR Services

2025-02-17T08:11:06+00:00

Information technology plays a very important role, especially in the field of education, one of which is through the use of websites. The Department of Information Engineering at Tadulako University is one of the universities that utilizes websites, one of which is the information system for administrative services and final assignments (SIPENDEKAR). Sipendekara is designed to facilitate the submission of titles, guidance, and proposal exams, final exams, and thesis exams. But so far, there has been no research that measures the quality of the sipendekar website based on perceptions of usability, information quality, and service interaction quality using the IPA method. This study aims to determine the quality of Sipendekar services using the webqual 4.0 method as the basis for determining the questionnaire. Then the Importance Performance Analysis method to analyze questionnaire data to identify attributes that have met and have not met user expectations. The results showed an average level of conformity of 92.63%. The average gap analysis result is -0.33. The results of the Cartesian quadrant there are 4 attributes in the first quadrant that are prioritized for improvement and there are 9 attributes that achieve a high level of satisfaction and only need to maintain quality.

The Effectiveness of Using WordPress-Based Digital Invitations in Social Event Marketing

2025-02-17T09:07:07+00:00

Digital marketing plays an important role in enhancing the promotion of social events in the digital era. In an effort to reach a wider audience, WordPress-based digital invitations are one of the potential tools to support marketing effectiveness. This study aims to analyze the extent to which the use of WordPress-based digital invitations can help social event organizers increase audience participation and engagement. This research uses a quantitative descriptive method with data collection through a survey of social event organizers and analysis of traffic and engagement data from the WordPress platform. The data collection process was conducted to understand the impact of WordPress features, such as flexible design, SEO optimization, and social media integration, on social event marketing success. The results showed that WordPress-based digital invitations significantly increased the number of event participants, the level of audience engagement, as well as the perceived professionalism of the event. These findings indicate that WordPress can be an effective strategic tool in digital marketing for social events. In conclusion, WordPress is a platform that can support social event organizers in designing more effective marketing strategies, especially by leveraging its features to optimize the appeal of digital invitations. This research provides practical insights for event organizers and opens up opportunities for further research in similar areas.