ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
ANALISIS SENTIMEN PENGGUNA TWITTER TERHADAP SKINCARE DENGAN METODE SUPPORT VECTOR MACHINE (SVM)
Get PDFThe Originote Hyalucera Moisturizer skincare product has attracted public attention because it offers superior quality at an affordable price. Social media, especially Twitter, is used by consumers to express opinions regarding this product, whether positive, negative, or neutral. However, the large number of reviews with various sentiments can confuse potential consumers in assessing product quality. Therefore, this study aims to understand user perception through sentiment analysis and evaluate the effectiveness of the Support Vector Machine (SVM) algorithm in sentiment classification. A total of 1,820 tweets were collected using the crawling technique with Python. The data undergoes preprocessing, including text cleaning, tokenization, stopword removal, and stemming, reducing it to 902 tweets. Key text features are extracted using Term Frequency-Inverse Document Frequency (TF-IDF). For sentiment classification, this study used the SVM algorithm, which is known as an effective method in text processing. Model evaluation showed good results with an accuracy of 87%, precision of 89%, and recall of 87%. This study provides insight into public perception of The Originote Hyalucera Moisturizer and measures the effectiveness of SVM in social media-based sentiment analysis. The results of the study can be utilized by manufacturers for more targeted marketing strategies, product quality improvement, and more effective communication in responding to opinions on social media. In addition, this study contributes to the development of machine learning-based sentiment analysis methods in the context of skincare products
DEVELOPMENT OF CNN-LSTM-BASED IMAGE CAPTIONING DATASET TO ENHANCE VISUAL ACCESSIBILITY FOR DISABILITIES
Get PDFVisual accessibility in public spaces remains limited for individuals with visual impairments in Indonesia, despite technological advancements such as image captioning. This study aims to develop a custom dataset and a baseline CNN-LSTM image captioning model capable of describing sidewalk accessibility conditions in Indonesian language. The methodology includes collecting 748 annotated images from various Indonesian cities, with captions manually crafted to reflect accessibility features. The model employs DenseNet201 as the CNN encoder and LSTM as the decoder, with 70% of the data used for training and 30% for validation. Evaluation was conducted using BLEU and CIDEr metrics. Results show a BLEU-4 score of 0.27 and a CIDEr score of 0.56, indicating moderate alignment between model-generated and reference captions. While the absence of an attention mechanism and the limited dataset size constrain overall performance, the model demonstrates the ability to identify key elements such as tactile paving, signage, and pedestrian barriers. This study contributes to assistive technology development in a low-resource language context, providing foundational work for future research. Enhancements through data expansion, incorporation of attention mechanisms, and transformer-based models are recommended to improve descriptive richness and accurac
PELATIHAN LITERASI DIGITAL BAGI GURU SD N 1 TOYAREKA GUNA MENDUKUNG PEMBELAJARAN KURIKULUM MERDEKA
Get PDFThis community service project aims to enhance the digital literacy of teachers at SD Negeri 1 Toyareka in supporting the implementation of the Merdeka Curriculum. One of the challenges teachers face is their limited ability to utilize digital technology and artificial intelligence (AI) to create interactive and relevant learning experiences for students. The program was conducted through socialization, digital literacy training, AI technology introduction, and continuous mentoring and evaluation. During the training, teachers were provided with insights into digital platforms that can be used in the teaching and learning process, as well as AI applications to assist in student data analysis and the creation of adaptive learning materials. The training results show a significant improvement in teachers' skills in using digital technology and AI, particularly in creating more personalized and compelling learning experiences. Teachers could utilize digital tools to manage their classrooms more efficiently and use AI to personalize learning based on students' needs. The program evaluation revealed that teachers felt more confident using technology to support teaching and learning. The sustainability of this program is ensured through regular mentoring and assessment, as well as plans for further training to keep teachers updated with rapidly evolving technologies. This initiative is expected to be a model for developing digital literacy in other schools
PENGEMBANGAN UMKM MELALUI PLATFORM E-COMMERCE BERBASIS AI UNTUK MENINGKATKAN PENJUALAN PRODUK LOKAL
Get PDFThe development of Micro, Small, and Medium Enterprises (MSMEs) in Indonesia is a top priority in efforts to strengthen the national economy. The UMKM Natar Community serves as a platform for MSME actors in Natar District, South Lampung Regency, consisting of 113 members engaged in sectors such as culinary, crafts, fashion, agriculture, and health. Despite its great potential, this community still faces several challenges, including the suboptimal use of digital media for marketing, conventional business management practices, and limited human resource skills. To address these issues, digital transformation is believed to be an effective solution to support MSME growth. This community service activity aims to provide outreach, training, and mentoring to UMKM Natar members regarding digital transformation and skills enhancement in product marketing management. Through methods involving education, technology application, and training in digital marketing, business management, and human resource development, this activity successfully improved participants' understanding and ability to use technology, including Artificial Intelligence (AI), to support the online management and marketing of their businesses
PENGARUH KUALITAS LAYANAN TERHADAP LOYALITAS PELANGGAN PADA PENGGUNA GRABBIKE DI MASYARAKAT
Get PDFOne of the most rapidly expanding industries in the modern digital age is online transportation services. The purpose of this research is to find out how much of an impact service quality has on GrabBike customer loyalty. Dependability, responsiveness, assurance, empathy, and concrete proof are the five main criteria used to evaluate service quality. Data was gathered using a quantitative research technique, with 100 respondents being polled using questionnaires. All responses were evaluated using a Likert scale ranging from 1 to 5. The findings demonstrate that customer loyalty is positively and significantly impacted by service quality. A simple linear regression test confirmed this, with a t-value of 8.292 surpassing the t-table value of 1.987 and a R Squared value of 41.2%. This indicates that service quality influences customer loyalty to a lesser extent than other criteria (58.8% vs. 41.2%). These results stress the need of enhancing service quality as a means of attracting and retaining customers, and they call for ongoing innovation to make online transportation services more user-friendly.Layanan transportasi online menjadi salah satu sektor yang berkembang pesat di era digital. Penelitian ini bertujuan untuk menganalisis pengaruh kualitas layanan terhadap loyalitas pelanggan pada pengguna GrabBike di masyarakat. Kualitas layanan didefinisikan melalui lima dimensi utama: keandalan, responsivitas, jaminan, empati, dan bukti fisik. Penelitian menggunakan metode kuantitatif dengan data yang dikumpulkan melalui penyebaran kuesioner kepada 100 responden. Skala Likert 1-5 digunakan untuk mengukur tanggapan responden. Hasil analisis menunjukkan bahwa kualitas layanan memiliki pengaruh positif dan signifikan terhadap loyalitas pelanggan, sebagaimana dibuktikan oleh hasil uji regresi linear sederhana dengan nilai T hitung sebesar 8,292 (lebih besar dari T tabel 1,987) dan koefisien determinasi (R Square) sebesar 41,2%. Hal ini menunjukkan bahwa 41,2% loyalitas pelanggan dipengaruhi oleh kualitas layanan, sedangkan sisanya 58,8% dipengaruhi oleh faktor lain. Penelitian ini menegaskan pentingnya peningkatan kualitas layanan dalam membangun loyalitas pelanggan, sekaligus menjadi dasar bagi penyedia layanan transportasi online untuk terus berinovasi dalam menciptakan pengalaman pengguna yang optimal.
 
PERFORMANCE COMPARISON OF RANDOM FOREST REGRESSION, SVR MODELS IN STOCK PRICE PREDICTION
Get PDFThe stock market is characterized by high volatility and complexity, making it an intriguing and challenging subject for researchers and practitioners. This study aims to predict stock prices by comparing the performance of two machine learning models: Random Forest Regression and Support Vector Regression (SVR). These models were selected for their ability to handle complex data and high volatility. The dataset used in this study consists of BNI stock data over the last five years (2019–2024), comprising a total of 1,211 data points. Testing was conducted using a cross-validation approach, and model performance was evaluated based on several metrics, including MSE, R², RMSE, MAPE, MAE, and Score. The results indicate that Random Forest Regression outperforms SVR. The model achieved an MAE of 17.766, an RMSE of 22.376, and an R² of 0.997. These findings suggest that Random Forest Regression is more effective in predicting stock prices, particularly in unstable market conditions. This study recommends Random Forest Regression as a reliable model for stock price prediction, with potential applications in other stock markets with similar characteristics
MAPPING OF DOMESTIC AND FOREIGN TOURIST VISITS IN EAST JAVA USING THE DBSCAN METHOD
Get PDFTourism is important in economic growth and regional development, especially in East Java Province with diverse tourist attractions. However, the mapping of domestic and foreign tourist visit patterns in this province is still limited. For this reason, this study uses the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method which can group density-based data without determining the number of clusters from the beginning and handle noise. The study aims to map districts/cities in East Java based on the number of tourist visits from 2018 to 2022, using visit data from the East Java Provincial Culture and Tourism Office. The analysis results show that in domestic tourist data, with parameters MinPts = 3 and ε = 1.00, one main cluster is formed consisting of 31 tourist locations and 7 noisy locations. In foreign tourist data, with ε = 0.6 and MinPts = 3, there is one cluster with 30 tourist locations and 8 other locations are categorized as noisy. Noisy locations tend to have higher visits but do not fit into the main cluster. These findings provide important insights for more targeted tourism promotion strategies and efficient resource allocation in East Java
PROJECT MANAGEMENT OF STEEL PLATE WAREHOUSE INVENTORY INFORMATION SYSTEM
Get PDFInformation system project management is an activity of available resources from an information system solution development project so that a system solution can be produced that meets predetermined objectives. From the findings in the field that the process of applying the inventory information system project management is still constrained because the previous business process lacks support and some still use ms. office excel in recording the process of entering and exiting goods becomes an obstacle if many transactions occur in a day, and inventory data tends to have differences from the warehouse and head office, so this study aims to apply the inventory information system project management that has been developed using the waterfall development method can function optimally and effectively by implementing the Project Management Body of Knowledge (PMBOK) method where the focus of discussion is work breakdown structure analysis, activity of arrow analysis, and project cost estimate analysis. The results of this study obtained the results of stage-based WBS analysis, activity of arrow analysis with 58 days, while project cost estimate analysis with 14% for the communication stage, 20% for the planning stage, 57% for the modeling stage, 4% for the construction stage, 5% deployment stage
DETERMINATION OF POTENTIAL BUSINESS LOCATIONS USING DATA MINING CLUSTERING
Get PDFPotential locations for businesses are highly sought after by business people to set up, expand their business, or establish a new business. Limited information on potential business locations is still a problem faced by many business people in making business decisions. The purpose of this research is to overcome the limitations of potential business location information. The approach used is the K-Means data mining clustering method which is compared to the Gaussian Mixture Model. The dataset used is residential, road access data and business points that already exist around the location. Both clustering methods are compared to the model evaluation method to determine the model with the best performance. The results show that the clustering method with the K-Means algorithm is the clustering model with the best performance. The results of the clustering resulted in 2 clusters, one of which is a cluster of potential business locations of 1041 locations. The conclusion of this study is that data mining clustering can be used to determine the optimal business location cluster. The results of this study can be recommended for business people to look for potential business locations, and for local governments to publicize potential business locations in order to attract investors from outside
DESIGNING A WEB-BASED RESTAURANT RESERVATION INFORMATION SYSTEM WITH REQUIREMENT PROTOTYPING METHOD
Get PDFThe development of information technology is proliferating, along with the increasing human need for fast, precise, and accurate information. The role of information technology in supporting the business world will make it easier for business people to run their business. One of the business fields that can implement information technology is restaurants. Restaurant management is gradually changing from using conventional methods with manual recording to being more systematic through digital devices. With digital devices, restaurant managers can more efficiently record table reservations and food menu orders. On the consumer side, it is also easier because they can make reservations and food menus from anywhere via a computer or smartphone device connected to the internet. In this research, a web-based application will be created that is used as a means to record table reservations and order food menus with the case studies at Wisata Kampung Kemiri Jember. The design and creation of the website at Wisata Kampung Kemiri Jember uses the requirement prototyping software development method. For the testing process, the Black Box Testing method is used to test all features on the website that have been running according to their functions. To test the user experience, the User Acceptance Testing (UAT) method was used by distributing questionnaires. Through the implementation of this website-based table reservation and food ordering system, it is hoped that work efficiency can be improved to optimize customer satisfactio