Journal of Applied Computer Science and Technology

Deteksi Helm Keselamatan Menggunakan Jetson Nano dan YOLOv7

Hadi Supriyanto — 2024-02-03

Increasing awareness of the importance of head personal protective equipment in industrial and construction environments has become a major concern in efforts to improve occupational safety. This research developed an early detection system for the use of computer vision-based head protective equipment using the YOLOv7 model and the Jetson Nano controller. The YOLOv7 algorithm was chosen for its ability for fast and accurate object detection. The YOLOv7 model was trained with a total dataset of 2799 images and iterations of 100 epochs to detect head personal protective equipment with a high degree of accuracy. The system captures imagery, activates a warning alarm, and sends a notification to Telegram when a violation occurs on an object that is not wearing a safety helmet. The test results using the confusion matrix method showed that the developed system was able to detect head personal protective equipment with an accuracy rate of 97.23%, which shows the system's ability to recognize personal protective equipment with very high accuracy. In addition, the system also showed a precision value of 98.71% indicating that all detections performed were correct, and a recall of 95.63% which describes the system's ability to recognize most of the head personal protective equipment available. The average FPS result using GPU with CUDA on Jetson Nano reached 5,723 FPS.

Desktop Application for Traceability System on The Printed Circuit Board (PCB) Storage Process

Alvin — 2024-02-03

This paper discusses the development of desktop applications for traceability systems. The application was developed to facilitate data recording and tracking in an electronics manufacturing company's storage process of Printed Circuit Board (PCB) products. The application is developed using the Visual Basic language and Microsoft Excel databases. Additionally, the application is integrated with a barcode scanner to simplify the data entry process from PCBs and employee ID cards. Through the trial process conducted on the developed application, it has generally functioned in accordance with the development goals. Program control validation has been tested through several application access attempts from users registered as operators and administrators. The application has successfully recorded data from inbound and outbound processes, demonstrating storage and tracking functionality. Furthermore, the application has displayed the actual status data of the PCBs present in the warehouse. In terms of user satisfaction, seven users stated that this application was effective and efficient compared to the manual data recording process previously used by the company. This result was obtained from a questionnaire after the application was implemented in the company warehouse.

Analisis Sentimen: Pengaruh Jam Kerja Terhadap Kesehatan Mental Generasi Z

Muhammad Daffa Al Fahreza — 2024-02-03

Mental health is a significant concern in society today, particularly for Generation Z, who are vulnerable to experiencing mental health problems that can disrupt daily productivity. The influence of working hours also contributes to the mental health of this generation. To assess public opinion on this issue, sentiment analysis is needed on social media, especially twitter. This research uses the Gaussian Naïve Bayes algorithm and Support Vector Machine with various stemming algorithms such as Nazief-Adriani, Arifin Setiono, and Sastrawi. The sentiment analysis method is used to assess positive, negative, and neutral sentiment in related tweets. The research results show that the Sastrawi stemming algorithm on the Gaussian Naïve Bayes model achieves 84% precision, 84% recall, and 84% f1-score, with 84% accuracy. Meanwhile, Support Vector Machine achieved 91% precision, 90% recall, 90% f1-score, and 91% accuracy. The Nazief-Adriani stemming algorithm on the Gaussian Naïve Bayes model has 80% precision, 80% recall, and 80% f1-score, with 80% accuracy. Meanwhile, on the Support Vector Machine, precision is 87%, recall is 85%, f1-score is 86%, and accuracy is 85%. Arifin Setiono's stemming algorithm on the Gaussian Naïve Bayes model achieved 81% precision, 81% recall, 81% f1-score, with 82% accuracy, while on Support Vector Machine, 88% precision, 86% recall, 86% f1-score, with 86% accuracy. Public opinion was recorded as 33% positive, 9% neutral, and 58% negative. This research aims to increase public awareness of the importance of mental health, especially regarding the influence of working hours, to create a healthy work environment for Generation Z and society in general, as well as improving the quality of mental health.

Aktivitas Dinamis pada Appreciative Game “Warik the Adventurer” berbasis Finite State Machine

Muhammad Rakha' Naufal — 2024-02-04

Serious games have become potential tools for education due to their advantage of giving a fun experience to the learner. Therefore, game experience is a fundamental element in serious game design. The game experience is mainly produced by the game activity, such as a quest or mission. However, in many serious games, the game activities do not have a clear design and concept, resulting in a poor playing experience which produce poor understanding of the material. Appreciative Game is a game that is based on Appreciative Learning concept. Appreciative Learning concepts could be used to design game activities. Appreciative Learning consists of four main stages. The stages are discovery, dream, design, and destiny. These four stages lay down the foundation of serious game activity. This study uses the Finite State Machine to produce intelligent agents in order to develop more dynamic game activity to enhance the game experience. We developed a 3D game called Warik the Adventurer as the testbed for this research. The game is about the cultural diversity in Indonesia. The game Experience Questionnaire (GEQ) is used to evaluate the player experience. The GEQ resulted in an acceptable score of 3 out of 5.

Chatbot Informasi Penerimaan Mahasiswa Baru Menggunakan Metode FastText dan LSTM

Fahmi Yusron Fiddin — 2024-02-04

New Student Admission (PMB) is an important stage in the continuity of education in an educational institution. The Faculty of Science and Informatics (FSI) at Jenderal Achmad Yani University (UNJANI) provides information services about PMB to prospective students and parents/guardians of prospective students but is still inefficient, so it is necessary to improve PMB information services by using Chatbots as a solution that is able to serve questions effectively and consistent. This study aims to develop a PMB information Chatbot system for FSI using the FastText and Long Short-Term Memory (LSTM) methods. Several methods have been used in Chatbot development research, such as Term Frequency–Inverse Document Frequency (TF-IDF), Bag of Words (BoW), and Convolutional Neural Networks (CNN). However, these studies still have certain limitations, such as the inability to grasp the meaning of words and difficulties in handling certain inputs. In this study, the text classification model uses the FastText method as the stage for representing words in vector form, then combined with several pre-processing methods (Tokenization & Casefolding) and LSTM for the classification stage. Then put it into the Chatbot component according to the architecture that was made. In testing, the Black Box Testing method is used to ensure the functionality of the Chatbot system. The test results show that the Chatbot system is able to understand the topic of questions asked by users properly. The interaction between users and Chatbots also runs smoothly, resulting in appropriate and informative responses. The results of this study are expected to be an effective and consistent solution for providing information about PMB to prospective students and parents/guardians of prospective students at FSI.

Prototipe Deteksi Letak Kebocoran Pipa dengan Optimalisasi Kinerja Penerimaan Paket LoRa menggunakan Pengkodean Parameter Fisik

Dedy Wahyu Herdiyanto — 2024-03-24

The purpose of this research is to determine the effect of the physical coding of LoRa communications on monitoring water pipelines. Optimizing the performance of packet receivers in the LoRa communication system using coding on the physical parameters SF (spreading factor), BW (bandwidth), and CR (coding rate). The detection system consists of 3 sensor nodes, 3 intermediate nodes, and 1 receiver node. Data from these sensors is sent to a cloud database. The SX1278 LoRa communication module works using a 433 MHz frequency. During the transmission process on the LoRa communication system, optimization is carried out for receiving data packets using the parameter coding method of physical spread factors, bandwidth, and coding rate. As a result of the research, it is shown that the greater the value of the third parameter (SF, BW, and CR), such as improvement in packet reception performance, improvement in bit security, and increasing packet resistance to various disturbances in transmission, but the time required for sending data be longer. The optimal parameters for detecting pipe leak locations include SF 10, BW 500 KHz, and CR 4/8. The LoRa SX1278 scenario is optimal with a distance of 400 meters, where packet and byte reception are obtained 100%.

Penerapan Algoritma K-Means Untuk Mengelompokkan Kepadatan Penduduk Di Provinsi DKI Jakarta

Frisma Handayanna — 2024-03-24

DKI Jakarta Province is an attraction for immigrants. If the population increases, if it cannot be resolved and managed well, it will result in bad things such as increasing the number of unemployed and affecting economic growth. Population data is used to help group regions based on population density in DKI Jakarta Province in 2019-2022 using the K-Means clustering method. From the results of the research, it provides a solution for the government to pay attention to population groups with the aim of preventing population density because it causes bad effects, so that community welfare is more guaranteed, so grouping (clustering) of provinces in DKI Jakarta is needed to provide information for people who wish to live in the Province DKI Jakarta. The research proves that the test results carried out clustering iterations of population density data were obtained in three iterations. For the results obtained by calculations using the K-Means method and using the rapidminer application, the results obtained were of the same value, namely the cluster with the highest population density of three districts/cities, namely South Jakarta, East Jakarta and West Jakarta whose population density continues to increase.

Deteksi Clickbait pada Judul Berita Online Berbahasa Indonesia Menggunakan FastText

Muhaza Liebenlito — 2024-03-24

The rise of people accessing news portals has created intense competition between online media to get readers or visitors to maximize their revenue. This is what triggers the development of clickbait. Clickbait can reduce the quality of the news itself, and it also has the potential to be misinformation regarding to news contents as known as fake news. Therefore, it is necessary to detect news titles that contain clickbait. This study aims to obtain an optimal clickbait news title classification model using FastText. To get the optimal model can be done by cleaning the data and optimizing the model's hyperparameters. The model was trained using 9600 training data collected from Indonesian online news. The best model obtained in this study has performance with an accuracy of 77% and an F1-Score of 69%.