ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
IMPLEMENTASI METODE CLUSTERING UNTUK PEMETAAN WILAYAH PRODUKSI DAN EKSPOR KOPI DI INDONESIA
Full text linkCoffee is one of the main agricultural commodities in Indonesia, but the distribution of production and export contribution is still uneven. This study aims to map the patterns of coffee production and export in Indonesia using clustering methods, namely K-Means and Hierarchical Agglomerative Clustering (AHC). The data used includes coffee production by province and regency (2015–2022), as well as coffee export data by destination country (2016–2023), obtained from BDSP and BPS. The system is developed in the form of an interactive website that allows users to upload datasets, select clustering methods, and view analysis results in the form of tables, graphs, and interactive maps. Clustering quality is evaluated using the Silhouette Score and Davies-Bouldin Index (DBI). The testing results show that the optimal number of clusters is two for all datasets, with the highest Silhouette score reaching 0.85 and the lowest DBI of 0.21, indicating good clustering quality. AHC is more effective in analyzing export and provincial-level production data, while K-Means performs better for regency-level data. This system is expected to provide insights into the distribution patterns of coffee production and exports and support decision-making in the agricultural sector, particularly for coffee commodities
DETERMINAN PENGUNGKAPAN ISLAMIC CORPORATE SOCIAL RESPONBILITY BANK UMUM SYARIAH DI INDONESIA
No full textIslamic Corporate Social Responsibility (ICSR) is a form of reporting that refers to the principles of Maqashid Syariah. The purpose of the research is to examine the factors of investment account holders, profitability, company size, and company age as determinants of ICSR in Sharia Commercial Banks registered with the Financial Services Authority (OJK) for the period 2019–2023. The purposive sampling method was used to obtain a sample of 42 companies. Data analysis used the panel data regression method with E-Views 12. The research findings indicate that ICSR is not significantly influenced by investment account holders, profitability, company size, or company age. These results indicate that there are still other internal factors that play a role as determinants of ICSR and emphasise the importance of ICSR reporting in the annual report as a basis for consideration by investors in investing in Islamic banks.Pengungkapan Islamic Corporate Social Responbility adalah pelaporan tanggung jawab sosial perusahaan dengan prinsip syariah berdasarkan nilai-nilai konsep Maqashid Syariah dalam laporan tahunan perusahaan. Penelitian ini bertujuan untuk menguji pengaruh investment account holder, ,profitabilitas, ukuran perusahaan dan umur perusahaan terhadap pengungkapan Islamic Corporate Social Responsibility pada perusahaan perbankan Syariah yang terdaftar di Otoritas Jasa Keuangan (OJK) periode 2018-2023.. Pengambilan sampel menggunakan teknik purposive sampling dengan jumlah 42 sampel. Metode analisis yang digunakan adalah analisis regresi data panel dengan aplikasi E-views 12. Hasil dalam penelitian ini menunjukkan bahwa investment account holder, profitabilitas, ukuran perusahaan dan umur perusahan tidak berpengaruh terhadap pengungkapan Islamic Corporate Social Responsibility.
 
DEVELOPMENT OF VT-UNUJA APPLICATION AS A WEBVR-BASED CAMPUS ENVIRONMENT INTRODUCTION MEDIA
Full text linkConventional campus introductions are often limited in providing an immersive experience to prospective students, especially for those who cannot attend in person. This encourages the need for technology-based solutions that can overcome these limitations. This research develops a WebVR-based VT-UNUJA application as a campus introduction media that offers an interactive experience with 360-degree panoramic image features, hotspot descriptions, navigation, and voice-over. The purpose of this research is to create an application that can increase user understanding of campus locations and facilities more efficiently and easily accessible. The test results show that this application is effective in improving user understanding, with a high level of satisfaction with the ease of use and interactivity of the application. The benefits of this research are to contribute in improving campus professionalism in presenting information digitally, as well as providing innovative alternatives for other educational institutions in supporting the orientation process for prospective students
COMPARISON OF ACTIVATION AND OPTIMIZER PERFORMANCE IN LSTM MODEL FOR PURE BEEF PRICE PREDICTION
Full text linkOne of the primary factors impacting the economy is the ability to forecast the prices of commodities such as beef. This paper aims to evaluate the effectiveness of various activation functions and optimization strategies when integrated into the LSTM (Long Short-Term Memory) architecture model in predicting the price of lean beef in Aceh. The data sample utilized was obtained from the Indonesian National Food Agency panel, which shows daily prices for beef within the time frame of July 14th, 2022, to July 31st, 2024. As for the conducted research, the process of preparation data preprocessing, partitioning data into training, validation and test sets and the actual execution of the LSTM model which was trained using four different types of activation functions: tanh, ReLU, sigmoid and PReLU together with three different optimizers: Adam, Nadam and RMSprop for 50, 70, 100 and 200 training iterations. The evaluation metrics employed were Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R-squared). The best performance was recorded at 200 epochs with the combination of PReLU activation function and Nadam optimizer, which had the best performance with RMSE = 2.56, MAPE = 0.65% and R² = 0.104. This combination was more effective than others since it depicted better overall performance in identifying complex non-linear relationships that existed in the price data. Further on, Nadam seems to have benefits in terms of allowing the model to converge faster and making the training more stable. This work stresses the selection of activation functions and optimization methods when building LSTM models aimed at forecasting prices of commodities with large volatility. It will be very helpful in developing better predictive models and decision-making processes in the agro-business. Another way to enhance predictive performance could be changing the model architecture or using different techniques, such as attention mechanisms
PENERAPAN DECISION TREE DENGAN PENYEIMBANGAN DATA IMBALANCE MENGGUNAKAN UPSAMPLING DALAM PREDIKSI PENYAKIT LIVER
Full text linkAcute liver disease has a significant impact on liver function and is often only detected at an advanced stage due to the lack of patient awareness for early examination. One of the challenges in treating liver disease is the delay in diagnosis, where many patients do not notice the early symptoms until their condition has worsened. Therefore, a predictive system is needed that can identify liver disease patients early on, allowing for regular check-ups and timely treatment. In this study, a classification model was developed using a machine learning approach, specifically the Decision Tree algorithm, by balancing the data in the minority class through upsampling. The research results show that this model is capable of predicting liver disease status with an accuracy rate of 89.22%, a recall of 88.45%, a precision of 83.21%, and an f1-score of 85.78%. In addition, the ROC-AUC value of 0.89 is categorized as a good classification. This model achieved a higher accuracy score than other studies with similar datasets. This system is expected to help improve early detection and expedite the treatment of liver disease patients
OPTIMASI HYBRID INTELLIGENT SYSTEM UNTUK IDENTIFIKASI BUAH: STUDI KASUS PISANG DAN APEL
Full text linkImage processing-based fruit classification is one of the rapidly developing technology applications in the field of digital agriculture. This study aims to develop a fruit identification system, especially yellow bananas, green bananas, and apples, by utilizing the K-Nearest Neighbors (KNN) and Principal Component Analysis (PCA) methods. The background of this study is the need for an accurate automatic system to distinguish fruit types based on visual characteristics, such as color, texture, and shape, to support the distribution and management of agricultural products. The method used in this study involves four main stages: image loading, segmentation, feature extraction, and classification. PCA is used to reduce data dimensions by maintaining relevant main features, while KNN functions for classification based on the closest distance between test data and training data. The dataset used consists of 130 images, with 120 images as training data and 10 images as test data. The results of the study show that the developed system is able to classify all test data with 90% accuracy. This success proves that the combination of PCA and KNN methods is effective in identifying fruit types based on extracted visual characteristics. This system is expected to be the basis for further development in the field of automatic fruit classification
IMPROVING THE IMAGE OF A BANANA USING THE OPENING AND CLOSING METHOD
Full text linkOne significant technique in image processing is morphological image operations, which include methods such as opening and closing. This research explores the application of the opening and closing methods in improving the quality of banana images. The Opening process effectively reduces noise and eliminates small, unwanted details, improving the clarity of the image. However, the Closing process presents some challenges, particularly in altering the natural texture of the banana and blurring fine lines. Careful adjustments are necessary to avoid reducing the visual quality of the image. The study begins with pre-processing steps such as image cleaning and contrast adjustment to enhance the image clarity. The Opening operation, using mathematical morphology and a structural element, removes unwanted small elements from the image, making fine lines and textures more visible for further analysis. The Closing operation, applied after Opening, fills small gaps and connects separated parts of the banana image, restoring the original structure and maintaining image continuity. The combined application of opening and closing methods significantly enhances the quality of banana images by improving clarity, preserving structural integrity, and optimizing overall visual appearance
OPTIMIZED FACEBOOK PROPHET FOR MPOX FORECASTING: ENHANCING PREDICTIVE ACCURACY WITH HYPERPARAMETER TUNING
Full text linkMPOX (Monkeypox) has become a significant global health concern, requiring accurate forecasting for effective outbreak management. This study improves MPOX case prediction using Facebook Prophet with hyperparameter optimization. The dataset consists of global MPOX case records collected over time. Data preprocessing includes missing value imputation, normalization, and aggregation. Facebook Prophet is applied to forecast case trends, with model performance evaluated using Mean Squared Error (MSE) and Root Mean Squared Error (RMSE). A baseline Prophet model is first trained using default parameters. The model is then optimized by fine-tuning seasonality mode, changepoint prior scale, and growth model. The results show that hyperparameter tuning significantly enhances forecasting accuracy. The optimized model reduces MSE from 541,844.77 to 320,953.34 and RMSE from 736.10 to 566.53, demonstrating improved precision. The model also captures trend shifts and seasonal fluctuations more effectively. In conclusion, this study confirms that tuning Facebook Prophet improves epidemic forecasting, making it a reliable tool for MPOX monitoring. Future research should integrate external factors, such as vaccination rates and mobility data, to further refine predictions
DEEP BELIEF NETWORK (DBN) IMPLEMENTATION FOR MULTIMODAL CLASSIFICATION OF SENTIMENT ANALYSIS
Full text linkIn sentiment analysis, the use of multimodal data, consisting of a combination of images and text, is becoming increasingly important for understanding digital context. However, the main challenge lies in effectively integrating these two types of data into a single learning model. Deep Belief Network (DBN), with its capability to learn hierarchical data representations, is utilized to explore optimal strategies for multimodal sentiment analysis. The dataset includes 34,034 images from the FERPlus dataset to train the model in classifying emotions based on facial expressions, as well as 999 text and image samples obtained through crawling X. Experiments were conducted by comparing the performance of DBN with 2, 3, and 4 hidden layers across different test data sizes (10%-50%). The results indicate that the 3-hidden-layer configuration achieved the best performance, with a highest accuracy of 76% at a 20% test data size. Additionally, testing different learning rates (10⁻⁴ to 10⁻⁷) produced consistent results, but the fastest computation time was achieved with a learning rate of 10⁻⁴. Based on these findings, DBN with a 3-hidden-layer configuration and a learning rate of 10⁻⁴ is considered a more efficient alternative for multimodal sentiment analysis based on text and images
LAND COVER CHANGE PREDICTION USING CELLULAR AUTOMATA AND MARKOV CHAIN MODELS
Full text linkThis research examines the impact of land use change on mobility. Spatial problems arise due to increased activity, population, and transportation in the same space, necessitating the development of modeling strategies. This aligns with SDG 11 on cities and settlements, as well as the PRN's focus on transportation innovation. The urgency of this research lies in its adaptive and sustainable spatial prediction efforts aimed at controlling future land use. This study aims to analyze land use change patterns using the Cellular Automata Markov Chain (CA-Markov) model in Kupang City until 2043. CA-Markov simulations efficiently evaluate land cover changes and movement. The quantitative research method was conducted based on spatial predictions and spatial configuration. Quantum GIS (QGIS) and GeoSOS-FLUS were used to obtain results from each stage. There are three research stages. First, identification of land cover (land use in 2018 and 2023), driving factors (distance to settlements, airports, highways, elevation, slope, slope orientation, rainfall, population density), and conservation areas. Second, standardisation of spatial data. Third, land cover prediction using GeoSOS software (five-year prediction) to identify patterns of land use change. These findings emphasize the importance of using CA-Markov-based spatial predictions as a foundation for adaptive spatial planning to control land-use conversion and maintain sustainable spatial connectivity in Kupang City until 2043