Jurnal Inotera

Implementation of the Forward Chaining Method in Identifying Study Programs Based on Students Interests and Talents

2025-09-13T01:24:19+00:00

This study aims to develop a decision support system (DSS) based on the Forward Chaining method to assist prospective students in selecting a study program that aligns with their interests, talents, and abilities. The system is designed to analyze 34 facts related to the respondents' interests and talents using predefined Rules, generating program recommendations in the form of rankings based on suitability weights. Testing was conducted with 100 respondents, one of whom, named Najmil Ula, was recommended to choose the Chemical Engineering program with a suitability weight of 2,3 or 26.44%, based on fulfilled facts such as an interest in understand in physics and love doing an experiment. Additionally, the system provided alternative recommendations, such as Informatics Engineering and Arcitecture, with lower suitability levels. These results demonstrate that the system can provide relevant and objective recommendation, making it an effective tool to support prospective students in selecting study programs that match their potential.

Determining the Main Sizes of Gears to Drive Rubber Sheet Roll Grinding Machines on Speed Roll Rotation on the Roll Machine Unit Sheeter

2025-09-13T01:25:28+00:00

This research aims to determine the main dimensions of the roll drive gear on the roll rotation speed in the roll sheeter machine. The roll rotation speed influences the quality and efficiency of the milling process to produce Ribbed Smoke Sheet. The results of the research show that the main sizes of gears on the roll sheeter machine are the gear module used is 8.34 mm, the diameter of the stitch is (150.12 mm), the inside diameter is (129.27 mm), the outside diameter is (166.80 mm), tooth height (18.76 mm), circle distance (26.18 mm), tooth width (125.10 mm), and tooth thickness (14.40 mm) and roll rotation speed on the roll sheeter machine (roll-1 =0.45 m/s), (roll-2 =0.49 m/s), (roll-3 =0.53 m/s), (roll-4 =0.57 m/s), (roll-5 =0.68 m/s), and (roll-6 =0.56 m/s).

Structure Analysis of Warren Truss Bridge Using 3D CAD Software

2025-09-13T01:26:13+00:00

The Warren truss consists of longitudinal members joined only by angled cross-members, forming alternately inverted equilateral triangle-shaped spaces along its length, ensuring that no individual strut, beam, or tie subjected to bending or torsion straining forces, but only to tension or compression. Tension and compression resulting from the reaction force from the load received. Every bridge has a load limit that can be received. These limits can be seen from the bridge safety factor. The purpose of the analysis of safety factor that occurs on a Warren truss bridge, i.e. to know the load limit that can be received for a bridge structure design, Warren truss types. On the bridge with a length of 57.38 m, 9.25 m wide bridge, with a thickness of 27.5 m of concrete, and asphalt thickness of 4.5 m, will be given a load containing 28 Toyota avanza 4 adults with 75 kg per person, which to determine load limits and safety factors of this bridge design. Before the static analysis, safety of factor and stress calculations performed with the determination of area of road A = 530.765 m2, the determination of the height of asphalt t = 0.045 m, and the determination of the height of concrete t = 0.275 m, this calculation aims to facilitate the determination of volume of asphalt and volume of concrete, and the results of maximum load obtained from the determination of volume, and the determination of gravitation to gain maximum load. From maximum load, it can be determined of reaction force that to be used for analysis. Stress analysis and safety factors analysis were performed using solidworks software.

Application of Triple Exponential Smoothing Method for Predicting the Number of Patients at RSUD dr.Fauziah Bireuen

2025-09-13T01:27:08+00:00

RSUD dr. Fauziah Bireuen is the main referral hospital in Bireuen Regency which has an important role in public health services. Fluctuations in the number of patients per polyclinic are a challenge in managing resources such as medical personnel, medicines, and other supporting facilities. This study aims to apply the triple exponential smoothing method in predicting the number of patients per polyclinic. The results showed that the triple exponential smoothing method has a high level of accuracy with a MAPE value of 1.456% (98.544% accuracy). Predictions using triple exponential smoothing predict 211,460 patients in January 2025, 211,454 in February 2025, and 211,455 for March 2025 to December 2026. Based on these results, triple exponential smoothing is recommended as it provides accurate results and supports the hospital's operational efficiency.

Evaluating the Impact of Data Balancing Techniques on the k-Nearest Neighbors Algorithm for Microarray Data Classification

2025-09-13T01:27:47+00:00

Microarray data classification poses significant challenges in bioinformatics due to the nature of the data, which has a very high number of features but a limited number of samples, and an unbalanced class distribution. This condition can cause a decrease in the performance of classification models, including k-Nearest Neighbor (kNN). This study aims to evaluate the performance of the kNN algorithm in classifying unbalanced and balanced data. The balancing techniques used are Random Undersampling (RUS), Random Oversampling (ROS), and Synthetic Minority Over-sampling Technique (SMOTE). The datasets used in this study are three leukemia datasets with different class structures, namely two, three, and four classes. The experimental results show that the ROS and SMOTE techniques consistently improve the performance of kNN, with the best accuracy reaching more than 97%. In the two-class dataset, ROS gave the best performance (99.4%), while in the three-class dataset, SMOTE showed the most optimal results (98.5%). In the four-class dataset, the performance improvement due to balancing was very significant; SMOTE and ROS were able to improve the accuracy from 89.7% (without balancing) to 99.0% and 98.8%, respectively. Although RUS recorded perfect accuracy of 100%, the results were anomalous and inconsistent. RUS showed less stable performance and was often lower than the condition without balancing, especially on datasets with four classes. Overall, the SMOTE technique proved to be the most stable and effective for various class structures. This study shows the importance of balancing strategies in the classification of complex and imbalanced microarray data.

Deep Learning Based Classification of TB and Normal Chest X-rays Using a Custom CNN with Minimal Epoch Training

2025-09-13T01:28:34+00:00

Tuberculosis (TB) is a major global health concern and remains one of the deadliest infectious diseases, particularly in developing countries. Early and accurate diagnosis is crucial to initiate timely treatment, prevent complications, and reduce transmission rates. Conventional diagnostic methods, such as sputum tests and laboratory cultures, are often time-consuming and require specialized resources. Therefore, there is a growing need for automated, efficient, and accurate computer-aided diagnosis (CAD) systems. This study proposes a lightweight Convolutional Neural Network (CNN) architecture to classify chest X-ray images into TB and normal categories. The model is trained using the publicly available Shenzhen chest X-ray dataset, with three training durations: 10, 25, and 50 epochs. Although the model trained for 25 epochs achieved a slightly higher accuracy (86.36%) compared to the 10 epochs model (85.61%), the latter is considered more optimal due to its better balance between performance and efficiency. Specifically, the 10 epochs model produced high precision (92.86%) and a competitive F1-score (84.27%) while requiring significantly less training time and computational resources. Moreover, it maintained stable validation performance without signs of overfitting. In contrast, models trained for longer durations showed diminishing returns or performance degradation, particularly at 50 epochs. These results indicate that a shorter training cycle, when coupled with appropriate architectural design and regularization, can yield a robust and efficient classification model. This approach is particularly beneficial for deployment in resource-constrained environments, where rapid and reliable TB screening using chest X-ray images is critically needed.

Identification of Slum Distribution Patterns Based on GWR (Case Study: Panjang District, Bandar Lampung City)

2025-09-13T01:29:15+00:00

Slums are densely populated settlements that are not habitable, the building density is very high in a very limited area, causing various problems such as being prone to social diseases and diseases. The distribution of slums in an area can be analyzed using geographic information systems as an innovative strategy to visualize geospatial information accurately, allowing for more in-depth and data-based analysis to support decision making. This study uses the Geographically Weighted Regression (GWR) method. Geographically Weighted Regression (GWR) is a statistical analysis that allows researchers to evaluate spatial variations in the relationship between dependent and independent variables, using the Fixed Gaussian kernel function to provide constant weighting across research locations, so that they can understand complex and different spatial relationships in each location. Based on data processing on seven indicators and 16 slum parameters stipulated in PUPR Regulation No. 14 of 2018, Panjang District, Bandar Lampung City, there are 5 sub-districts that are categorized as light slums with slum distribution points spread across various locations without clear concentration. The results of the Geographically Weighted Regression (GWR) model show that the independent variables (X) and dependent variables (Y) reflect a complex relationship with variable X 11 (non-standard wastewater management system) having the highest coefficient of 0.213830. The results of the GWR model in the ANOVA table show that the GWR model does not provide significant improvement.

Comparison of Convmixer Method and Resnet Method in Classification and Detection of Gastrointestinal Diseases Using Kvasir Dataset

2025-09-13T01:29:58+00:00

This research discusses the comparison of ConvMixer and ResNet methods in the classification and detection of gastrointestinal diseases using the Kvasir dataset. Gastrointestinal diseases are often difficult to detect early due to the similarity of visual patterns in endoscopy images, requiring an efficient deep learning-based solution. The purpose of this research is to compare and evaluate the models used. The research used a quantitative approach with an experimental method. Endoscopy image data was processed through augmentation, normalization, and division of the dataset into train, validation, and test. ConvMixer and ResNet were trained with customized hyperparameters, and evaluated using accuracy, precision, recall, and F1-score metrics.

The results showed that ResNet excelled with 86% accuracy, slightly higher than ConvMixer which recorded 84% accuracy. ResNet's residual structure overcomes the problem of vanishing gradients, while ConvMixer offers better training speed. Both models showed high performance, although the challenge of similar patterns between classes was still an obstacle. As a result, ResNet provides better results in detecting gastrointestinal diseases, but ConvMixer is also a promising alternative. Further development with more diverse datasets is needed to improve model performance.

Apriori Algorithm in Electrical Equipment Sales for Inventory Control Optimization

2025-09-13T01:31:13+00:00

XYZ Electrical Store is one of the small and medium enterprises that sells various types of electrical equipment for household needs. The management of sales data in the store is still done by recording sales transactions in a book, making the sales report generation process take a long time. With such a sales data management system, control and planning of stock items become less than optimal. Customers often find that the items they want to buy are out of stock. Moreover, the accumulation of less popular items also poses a challenge to the store's cash flow, resulting in subopti mal business processes. This research was conducted to address the issues of controlling and planning stock of goods using data mining techniques with the Apriori algorithm on sales transactions of electrical tools. Through a series of threshold tests, a minsup of 10% and minconf of 60% were obtained. This study results in information on the types of electrical tools that need to be monitored as they can lead to stock shortages when buyers need them, namely, the categories of LED lights, electrical cables, plugs, electrical insulation, and out bow. By knowing this information, it can provide solutions to Sinar Mulya Electric Store in stocking the most frequen tly sold items in the store.

WebGIS-Based Mapping of Blood Donor Communities in Metro City

2025-09-13T01:31:53+00:00

The availability of sufficient blood supplies is essential for fulfilling medical requirements, particularly in emergency scenarios. In Indonesia, the Indonesian Red Cross (Palang Merah Indonesia, PMI) is tasked with managing blood supplies across various regions, including Metro City. However, the current donor data management system at PMI Metro City is not yet fully optimized, potentially undermining efforts to meet local blood demands. Inconsistent donor data management poses significant challenges to blood transfusion processes, especially during emergencies. To address these inefficiencies, this study aims to develop a database system integrated with a Web-based Geographic Information System (WebGIS). The proposed WebGIS platform provides an interactive and informative visualization of blood donor distribution across Metro City. The system development follows a structured methodology comprising several phases: planning, data identification, WebGIS development using PHP, HTML, CSS, JavaScript, and Leaflet, and web hosting. The key outcomes of this research include a well-structured database and an interactive web-based map for identifying donor locations. The WebGIS system enhances PMI’s capacity to optimize blood supply strategies, particularly for urgent medical needs, by improving real-time visibility and management of donor data.

Multiple Linear Regression Model to Measure the Influence of Gold Price Fluctuations and Promotions on Customer Interest in Gold Installment Products

2025-09-13T01:21:59+00:00

This study aims to determine the effect of gold price fluctuations and promotions on customer interest in using gold installment products at PT. Pegadaian UPS Johan Pahlawan. The population in this study were customers of PT Pegadaian UPS Johan Pahlawan. The sample in this study amounted to 61 respondents. The technique used in this test is Multiple Linear Regression Analysis. The model used in this research is descriptive quantitative. data analysis was carried out using the help of SPSS version 25. With a sig value of 0.000 <0.05, the Fhitung value is 25.766> Ftabel 3.16. So gold price fluctuations and promotions, simultaneously, have a positive and significant influence on customer interest. in the first regression equation obtained a Rsquare value of 0.470 or 47.0%. So it can be concluded that at PT Pegadaian UPS Johan Pahlawan, gold price fluctuations and promotions simultaneously have a positive effect on customer interest in using gold installment products.

Analysis of the Decision Support System for the Selection of the Best Teaching Staff Using The AHP and Topsis Methods

2025-09-13T01:32:42+00:00

The selection of the best teaching staff is very important to improve the quality of education at SMK Al - Amanah. However, the selection process carried out by SMK Al – Amanah is still subjective and less structured, so this can cause difficulties in determining the best teaching staff because of the many criteria that must be considered. In addition, the existing selection methods are not systematic and measurable, so they have the potential to cause bias and inconsistency in decision-making. This research aims to analyze and develop a decision support system that can help in the selection of the best teaching staff objectively and efficiently. The proposed solution is the development of a system that integrates the Analytical Hierarchy Process (AHP) method to determine the weight of the assessment criteria, as well as the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method to rank teaching staff based on this weight. The method used for collecting data on assessment criteria for the selection of the best teachers is through interviews and applying the AHP method in determining the weight of the criteria, as well as the application of the TOPSIS method for ranking in the selection of the best teaching staff. From the results of the research, it was obtained that the creation of a Decision Support System can simplify and accelerate the assessment process carried out by the leadership of each teaching staff and also the assessment of each teaching staff to be more accurate and minimize errors in making decisions.

Optimizing Acoustic Materials through Surface Geometry: A Review of Engineering Strategies and Design Insights

2025-09-13T01:33:29+00:00

Optimizing the acoustic performance of materials is a crucial objective in architectural and industrial engineering, particularly for controlling sound absorption in enclosed environments. While traditional design approaches emphasize intrinsic material properties such as porosity, thickness, and density, recent advancements in material engineering highlight the significant role of surface geometry in enhancing sound absorption behaviour. This literature review synthesizes recent studies from 2009 to present. This article review explores how engineered surface shapes such as sinusoidal, pyramidal, corrugated, and conical forms can improve acoustic efficiency by promoting scattering, diffraction, and micro-resonance effects. The review examines various testing methods, including impedance tube and in-situ measurements, and discusses how geometric features interact with frequency, air gaps, and mounting configurations. It also identifies limitations in current modelling practices, where surface texture is often simplified or ignored. The insights gathered underscore the potential of geometry-driven design as a cost-effective and scalable strategy for developing high-performance acoustic panels. This review serves as a foundation for future experimental work and simulation-based optimizations aimed at integrating advanced surface design into sustainable and application-specific acoustic materials.

Classification of Creditworthy Customer Using Support Vector Machine Algorithm

2025-09-13T02:49:58+00:00

The increase in the number of credit applications in the banking and financial institutions sector requires an efficient and accurate creditworthiness assessment system. Manually conducted assessments tend to be time-consuming and prone to subjectivity, so they can have an impact on errors in credit decision-making. The main problem faced is how to classify customers appropriately into creditworthy or non-creditworthy categories based on historical data. To overcome this, this study proposes the use of the Support Vector Machine (SVM) algorithm as an artificial intelligence-based solution that is able to handle classification problems with a high level of accuracy. The purpose of this study is to develop a model for classifying customer creditworthiness using the SVM algorithm and optimizing parameters to improve model performance. The methods used include the data preprocessing stage (handling missing values, categorical data encoding, and normalization), data division into training and test data, SVM model training, performance evaluation with accuracy, precision, recall, F1-score metrics, and parameter tuning using Grid Search and visualization through heatmaps. Kernel comparisons are also done to obtain the best configuration of the model. The results of the study show that the SVM model with the RBF kernel provides the best test performance reaching 87%, which means that the model is very good at recognizing potential customers who are not creditworthy. These results show that the SVM algorithm is effective in classifying customers' creditworthiness, so that it can be used as a decision-making tool in a more objective and efficient credit selection process.

Determination of Zenith Tropospheric Delay (ZTD) Using CORS GNSS Data, 2016 – 2020 In Lampung

2025-09-13T02:49:56+00:00

GNSS satellites transmit signals in the form of electromagnetic waves to ground-based observation stations (receivers). As these signals pass through the atmosphere - particularly the troposphere - they undergo delays and bending due to differences in atmospheric properties. This results in deviations in signal path length, known as Zenith Tropospheric Delay (ZTD). In positioning applications, ZTD is considered an error that must be minimized. However, in meteorological studies, ZTD serves as valuable information representing atmospheric water vapor content. This study aims to estimate ZTD values using GNSS observation data from CORS stations in the Lampung region. Data was processed using the Precise Point Positioning (PPP) method via an online platform. The results show that the highest ZTD value in 2016 was recorded at the CSBK station on DOY 182 with 2682.8 mm. In 2017, the highest value occurred at the CTCN station on DOY 274 with 2650.2 mm. From 2018 to 2020, the highest ZTD values were recorded at the CKRI station, with 2655.8 mm (DOY 001.18), 2676.4 mm (DOY 001.19), and 2691.0 mm (DOY 091.20), respectively. These findings indicate that ZTD data derived from GNSS observations hold significant potential for supporting local atmospheric studies.