Jurnal Informatika: Jurnal Pengembangan IT
Not a member yet
437 research outputs found
Sort by
Implementasi Smart Helmet Cabinet pada Penyimpanan Helm Berbasis Mobile QR Code
No full textThe use of Smart Helmet Cabinet in helmet storage based on Mobile QR Code has been implemented as an innovative solution to overcome the problem of safe and efficient helmet storage. By utilizing QR Code technology, authentication on the system facilitates users in the process of helmet storage and retrieval, as well as ensuring storage security. In addition, several challenges such as the need for reliable access authentication and reduction of access delay are the main focus to improve the effectiveness and reliability of the system. This research discusses the implementation of the Smart Helmet Cabinet by highlighting the benefits as well as potential future developments in improving user experience and security of stored helmets. The ESP32-CAM is used to scan the QR Code to authenticate user access, while the ESP32 NodeMCU controls the relay to open the door of the locker. The test results show that the average delay time for adding locker access is about 4.73 seconds, while access authentication using QR Code takes about 5.99 seconds. The implemented Smart Helmet Cabinet system is able to determine which lockers are given access and identify users by using QR Code as access authentication on the locker
Identifikasi Pola Kepuasan Mahasiswa Terhadap Proses Pembelajaran Menggunakan Algoritma K-Means Clustering.
No full textStudent satisfaction levels with the learning experience at higher education institutions often exhibit variability. This study aims to comprehend the varying degrees of student satisfaction at Institut Agama Islam Negeri (IAIN) Syekh Nurjati Cirebon. Employing the K-Means clustering method, this research categorizes students based on their satisfaction levels. The survey data analyzed includes 20 dimensions of Service Quality criteria evaluated by students, with these 20 dimensions grouped into five key aspects of Service Quality assessment: tangible, reliability, responsiveness, assurance, and empathy. The analysis reveals three distinct groups of students with differing satisfaction levels: neutral/fair (class 1), agree/good (class 2), and strongly agree/excellent (class 3). Comparisons among these groups highlight the diversity of student perceptions. Furthermore, an examination of the distribution of evaluations within each class uncovers differing priorities in assessment criteria. These research findings offer insights into the spectrum of student satisfaction levels and pinpoint areas warranting further attention in each class. Such insights can inform the development of policies and strategies aimed at enhancing the quality of learning experiences at IAIN Syekh Nurjati Cirebon
Aplikasi Prediksi IHSG Berbasis Web Dengan Integrasi Multi-Algoritma
No full textThe four regression algorithms used in predicting the Composite Stock Price Index (IHSG) have contributed significantly, as the test results show that the Decision Tree algorithm outperforms k-Nearest Neighbor, Linear Regression, and Random Forest, especially in terms of Mean Squared Error (MSE) and R2 score. The stages of data collection, pre-processing, and modeling, followed by model performance measurement, have provided valuable insights into the effectiveness of each algorithm. The success of the Decision Tree in this testing has further propelled its development into a web-based application. This conversion process, following the outlined flowchart, integrates various essential aspects of the model, including user interface and back-end integration, ensuring that the application can be accessed and used efficiently and effectively. Furthermore, the black box testing and User Acceptance Testing (UAT) results, using the Mean Opinion Score (MOS), enhance the validity and reliability of the application. Black box testing involving 2 features with 37 steps demonstrates the system's effectiveness in producing valid outputs, from the initial menu display to the prediction results. Additionally, UAT involving students and entrepreneurs as respondents provides in-depth insights into user acceptance. With a focus on functionality at 97.08%, reliability at 96.09%, and usability at 98.09%, UAT yields high scores in all three aspects, with usability achieving the highest score. These results not only confirm the efficiency of the system in performing its functions but also indicate a high level of user satisfaction, strongly suggesting the potential for widespread adoption of this application in the future
Perbandingan Random Forest dan SVM dalam Analisis Sentimen Quick Count Pemilu 2024
No full textThe implementation of the 2024 elections is regulated in the General Election Commission Regulation (PKPU) Number 3 of 2022, which also stipulates the election schedule and stages.After the simultaneous general elections that took place on February 14, 2024, problems arose among the public regarding the Quick Count results, especially for the Presidential election.The Quick Count results themselves generated various opinions, both positive and negative.In the post-election Twitter page, there are many conversations in cyberspace related to the Quick Count results on Twitter. Thus, sentiment analysis can be used to classify tweets and comments about the 2024 election quick count results into three categories, namely positive, negative, and neutral.Thus, this analysis is expected to provide some significant benefits related to the quick count results in the 2024 election. Random Forest and Support Vector Machine are two machine learning techniques used to measure how accurate the resulting sentiment analysis is. From the results of the research that has been carried out, there are 2000 data collected during February 2024. After preprocessing and labeling, there are 1,116 positive class data, 730 negative class data and 154 neutral class data.From the results of the comparison of the algorithms evaluated, the accuracy value of the two algorithms was obtained.The Random Forest algorithm produces an accuracy of 78%, while the SVM algorithm produces an accuracy of 80%.This shows that in sentiment analysis on the 2024 election quick count, the SVM method obtained a greater accuracy value compared to Random Forest
Analisis Sentimen Inses di Social Media menggunakan Algoritma Naïve Bayes
No full textSexual violence, especially against women and children, is a serious problem in Indonesia. Cases are increasing every year, including incest, which involves sexual relations between close family members. Girls, who are often considered weak and vulnerable, are the main victims. The latest data from the National Commission on Violence Against Women records a decrease in incest cases from 1,210 in 2017 to 215 in 2020. However, attention is still needed, especially because biological fathers are the largest perpetrators. This research uses the Naïve Bayes algorithm for sentiment analysis. This algorithm is an effective classification method based on Bayes' theorem with simple assumptions but is quite effective. Assuming that each feature in the data is independent, Naïve Bayes can work well in text analysis. The research results showed an accuracy rate of 94%. Continued attention to sexual violence, especially incest, is needed to protect vulnerable girls. Protection efforts must continue to be improved, including the application of sentiment analysis methods such as Naïve Bayes for monitoring and early detection. Public awareness and cross-sector cooperation are also key in overcoming this phenomenon
Implementasi Sistem Monitoring Lingkungan Pada Budidaya Tanaman Hidroponik Berbasis IoT
No full textThe increase in population and the reduction of agricultural land are major concerns in Indonesia. The country's population rose from 244,016,173 in 2010 to 277,534,122 in 2023, raising food needs. Population growth promotes the use of pesticides to protect agriculture;ntegration of hydroponic automation technology in households with limited land, such as for salad and sawmills, is expected to meet increasing food needs, reduce environmental impact, and improve well-being, in line with the SDGs. however,excessive use can lead to environmental damage, water pollution, and health risks for humans. In addressing this problem, hydroponic planting media became a potential solution. Hydroponics is the cultivation of plants without soil, using a nutrient solution. This technology supports the Sustainable Development Goals (SDGs) with clean and sustainable crop growth. Integration of hydroponic automation technology for households with limited land, such as for salad and sawmills, is expected to meet increasing food needs, reduce environmental impact, and improve well-being, in line with the SDGs. Thus, hydroponics can be an effective solution in addressing the agricultural challenges facing Indonesi
Komparasi dan Implementasi Algoritma Regresi Machine Learning untuk Prediksi Indeks Harga Saham Gabungan
No full textIndeks Harga Saham Gabungan (IHSG) or Indonesia Composite Index (ICI) is part of the macro indicators of a country that describes the economic condition of a country. ICI is an interesting study to research since its existence will be able to show market sentiment regarding an event that occurred in a country. This research tries to predict the ICI in the future based on historical data. The dataset used in this research is publicly available in Yahoo Finance. The experiment is conducted by implementing some regression machine learning algorithms, such as Decision Tree, Random Forest, k-Nearest Neighbor (kNN), and Linear Regression. As a result, Decision Tree has the lowest MSE value compared to other methods: 1268.242. In this research, a website-based application prototype was also developed that can be used to view IHSG graphs and make future predictions, using the 4 (four) tested algorithms
Segmentasi Pembelian Produk Menggunakan Algoritma K-Means Berdasarkan Clusterisasi pada pemilihan menu yang ada diUMKM Kuliner
No full textMarketing strategy can be seen as one of the bases used in preparing comprehensive SME planning. One of the SMEs that will be highlighted in this research is restaurants. Customer loyalty is an important thing that must be maintained by companies for the sustainability of the company and can improve good relationships between service provider companies and their customers. K-Means Cluster Analysis is a non-hierarchical cluster analysis method that attempts to partition existing objects into one or more clusters or groups of objects based on their characteristics, so that objects that have the same characteristics are grouped in the same cluster and objects that have similar characteristics. different groups are grouped into other clusters. The purpose of this research is to find out how to group menus that have high selling power and also the relationship between one menu variable and another menu when a transaction or purchase occurs by a customer. The results obtained in this research were to create a segmentation of products purchased by customers in the period May-November 2023 in SMEs operating in the culinary sector in the Central Java area. The results showed that the types of products most frequently purchased were Chicken Rice, Tea, Chicken, White Rice which is at the highest purchase order. Where Chicken Rice was purchased 5409 times, Tea 1867 times, White Rice 1452 times, Chicken 1110 times. In the K-Means Algorithm to determine which products sell frequently and require more inventory and which do not
Analisis Sentimen Twitter Terhadap Pemindahan Ibu Kota Negara Menggunakan Support Vector Machine
No full textThe Indonesian government announced plans to move the capital from Jakarta to East Kalimantan due to the high population burden and economic contribution on the island of Java. Statistical data shows that the island of Java has a large population, reaching 151.59 million people or around 56.10% of the total population of Indonesia, and will provide a large participation in national GDP in 2021. Moving the capital city is seen as a step. . for the sake of equal distribution of population and economy throughout Indonesia. Rapid urbanization on the island of Java, especially in the buffer areas of the capital city of Jakarta, is one of the main reasons behind this decision. This research uses data from the social media platform Twitter to analyze sentiment using 2 categories, namely positive and negative sentiment regarding the relocation of the National Capital, analyzed using the Support Vector Machine method. In this study, the SVM kernel type was used, namely a linear kernel with an accuracy of 92.70%, then improved with Stratified k-Fold Cross Validation, getting 100% accuracy in iterations 1 and 5. The classification results using the Support Vector Machine method are statedthat the linear kernel has better accuracy. This sentiment analysis provides insight into the public's views on the proposed measure. This research can be used as material for consideration of future government policy regarding relocating the capital city
E-learning Academy Untuk Meningkatkan Kapasitas SDM Di Lingkungan Perusahaan Transportasi X
No full text Services in the field of land transportation services are still a sector needed by the community for mobility and economic growth. The main problem faced by Transportation Company X in developing human resources (HR) is the uneven skills and knowledge between generations in the organizational structure. Gen X dominates with 57.36%, Gen Y (38.34%) and Gen Z (4.29%). This has an impact on the ability to adapt to the demands of the modern transportation industry. This research aims to develop and implement an e-Learning Academy, to increase the capacity of X Transportation Company's human resources. This research methodology uses SCRUM framework in learning system development, with agile approach that allows adaptation to changes quickly and efficiently. E-Learning Academy features video-based learning and interactive elements that allow employees to learn independently, thus maximizing knowledge transfer and improving skills in various fields. Survey results after testing by users through user acceptance test activities show that on the Ease of Navigation aspect, 55% of respondents stated “strongly agree” the application is easy to use”. The aspect of Confidence in Application Capabilities, the results are 55% of respondents “strongly agree” this application believes it can improve HR skills and abilities. For the Quality of Main Features, 36% of respondents stated “strongly agree” the main features in this application are easy to use and the remaining 64% stated “agree”. On the aspect of Impact on HR Improvement, 46% of respondents “strongly agree” this application has a positive impact and the remaining 54% of respondents stated “agree”. Finally, on the aspect of Benefit for the Company, 36% of respondents “strongly agree” that this application is useful and the remaining 64% stated “agree”. This platform can be accessed across all business sectors so that it becomes a strategic tool that helps Transportation Company X achieve its goals and improve its public transportation services