Publication Search

Rainfall plays a crucial role in determining flood risk, particularly in regions with high precipitation intensity and limited drainage capacity. Langkat Regency in North Sumatra is one of the areas frequently affected by seasonal flooding. This study aims to model the spatial distribution of rainfall and estimate the rainwater volume using the double integral approach as a basis for flood mitigation planning. Monthly rainfall data from various observation stations in 2024 were processed to obtain the average rainfall intensity, which was then converted into meters and multiplied by the total area of Langkat Regency to compute the rainwater volume. The results indicate that the total estimated rainwater volume throughout 2024 reached 16,409,819,800 m³, with peak precipitation occurring from September to November, contributing significantly to the increasing flood risk in low‐lying zones and riverine areas. These findings demonstrate that the use of double integrals is an effective quantitative method for predicting potential flood volume based on rainfall distribution. The outcomes of this study are expected to serve as a scientific reference for local governments in developing data-driven flood mitigation strategies, such as improving drainage capacity, constructing retention basins, and strengthening watershed management.

Work volume calculations are essential for project cost estimation. Many projects, such as the Laboratory Building of the Faculty Engineering at Tanjungpura University, calculate work volumes conventionally. Conventional calculation considered less efficient and prone to errors. Building Information Modeling (BIM) provides a solution that produces more accurate and efficient calculations than conventional methods. This research aims to compare structural work volume results produced by BIM using Autodesk Revit against conventional methods and project’s BOQ. This research also describes the benefits and challenges of BIM implementation based on the researcher’s experience applying BIM with Autodesk Revit in work volume calculation. The comparison between BIM and conventional method shows a maximum difference of 2% across all work items. Meanwhile, the comparison between BIM and the BOQ shows significant differences: 81% in column formwork area, 24% in grade beam/beam concrete volume, 25% in column reinforcement weight, 25% in steel beam weight, and 10% in the steel plate weight. This research proves that BIM implementation produces more accurate and efficient calculations and serves as an effective BOQ cross-check tool. Based on the researcher’s experience in implementing BIM with Autodesk Revit, challenges found in procurement aspects, modeling aspects, and model dependency on reference drawings.    

This study aims to analyze the process of processing fruit peel waste from juice traders into eco-enzymes as an effort to reduce environmental pollution. The research uses qualitative descriptive methods through direct observation, documentation, and literature studies. Fruit peel waste is fermented at a ratio of 1:3:10 (molasses : fruit waste : water) for three months under anaerobic conditions. The fermentation results show good eco-enzyme characteristics, characterized by a pH of 3, a fresh sour aroma, and a brownish color as an indicator of fermentation success. These findings show that the process of processing eco-enzymes from fruit peel waste can be done simply, cheaply, and environmentally friendly. In addition, the use of eco-enzymes has the potential to reduce the volume of organic waste disposed of in landfills and reduce water and soil pollution. The resulting eco-enzyme also has potential applications as natural cleaners, liquid fertilizers, and odor controllers. Thus, the treatment of fruit peel waste not only supports sustainable environmental management practices, but also encourages the implementation of the circular economy as well as community empowerment ecologically and economically.

Traditional arts in Indonesia face a growing threat not from physical displacement, but from algorithmic distortion. This study examines how social media algorithms shape and distort public perception of Indonesian traditional arts — specifically jaranan and barongan — through the lens of Van Dijck's (2013) popularity principle: the principle that content distribution is determined by interaction volume rather than cultural value. Employing qualitative thematic content analysis, this study analyzes comments on five viral social media videos sourced from YouTube and TikTok, each depicting riots or tension at traditional art performances. Findings demonstrate that the popularity principle operates consistently and cumulatively across all five samples: algorithmically provocative titles, emotional polarization in comment sections, and micro-behavioral signals such as watch duration and replay collectively function as interaction signals that drive the platform to distribute riot content far more widely than culturally substantive footage. The consequences extend beyond perception: event organizers suffer long-term reputational and economic damage, while collective stereotypes — associating jaranan with violence and disorder — become sufficiently entrenched to surface spontaneously in unrelated contexts. A comparative analysis of a Kangen Band concert video reveals that these stereotypes have already achieved the status of cultural reference points. This study argues that strategic resistance is possible: the same algorithmic logic that amplifies negative content can be deployed to circulate culturally rich content, provided that artists, communities, and government commit to producing content designed to generate high-quality interaction. The challenge is to transform social media from a distorting mirror into an instrument of cultural preservation.

Traffic performance on urban road segments is strongly affected by vehicle volume and travel time, particularly during peak periods. This study analyzes the relationship between travel duration and the total number of vehicles passing along Otto Iskandar Road as an illustration of urban traffic conditions. Data were collected through field surveys, focusing on two main variables: average vehicle travel time and total traffic volume. Statistical analysis was performed using IBM SPSS Statistics, including normality testing and the Wilcoxon Signed Rank Test to identify potential differences between the observed variables. The results show a difference in average values between travel duration and vehicle volume; however, this difference is not statistically significant at the 95% confidence level (p = 0.180). These findings indicate that increases in traffic volume do not always lead to proportional increases in travel time, although they can still influence the stability and efficiency of traffic flow. The results are consistent with previous studies, such as Halim (2021), who reported that U-turn movements affect speed and traffic performance, and Handayani et al. (2024), who found that parking activities and vehicle maneuvers reduce road capacity. Other studies also highlight the impact of side friction and traffic flow variations on speed and saturation levels. Overall, this study emphasizes the importance of managing vehicle flow and monitoring travel time in urban transportation planning and traffic management.

This study focuses on the analysis of traffic density in Jember City, particularly at the Wirolegi Intersection, which is known to have a high density level. This condition often triggers congestion that hinders public mobility, so that appropriate and data-based handling efforts are needed. The purpose of this study is to identify and analyze the level of density at critical congestion points through a statistical approach using the One Way ANOVA method. The research method used is quantitative descriptive with a descriptive observational approach. Primary data was collected directly through a field survey in 2025 at the Wirolegi Intersection as one of 3 intersections in Jember City. The data obtained were then processed using normality tests, homogeneity tests, and One Way ANOVA with the help of SPSS software. The results of the analysis show that the traffic flow density on the three routes studied, namely Jalan Gunung Haryono, Jalan Brigjen Katamso, Jalan Yos Sudarso, does not show a significant difference. The significance value of the ANOVA test is greater than 0.05 which indicates the similarity of density levels between routes. Further testing (post hoc testing) also strengthens this finding. The conclusion of this study shows that handling congestion at the Wirolegi Intersection needs to be done comprehensively through traffic control and evaluation of the transportation system to improve smoothness and mobility in Jember City.

This study examines the application of double integrals in calculating the volume of cylindrical concrete piles as a basis for estimating material requirements in building foundation structures. The volume calculation was carried out using a double-integral approach in polar coordinates for three pile segments with lengths of 4 m, 3.9 m, and 4 m, each having a diameter of 60 cm. The results were then validated using the standard geometric formula to ensure consistency and mathematical reliability. The obtained concrete volume was subsequently used to estimate material needs based on a 1:1.5:3 mix proportion consisting of cement, sand, and gravel. The findings indicate that double integrals can be effectively applied to generate accurate estimations of both volume and material requirements, supporting logistical planning in construction. This approach also highlights the strong connection between mathematical concepts—particularly multivariable calculus—and practical applications in civil engineering. Furthermore, the study emphasizes that double integrals may serve as a relevant alternative when structural modeling requires deeper analytical exploration or validation beyond conventional geometry. Therefore, the implementation of double integrals not only reinforces theoretical understanding but also enhances precision in evaluating structural components within building foundation planning.

Flower disease detection is a common challenge in modern agriculture. Various factors, such as changes in leaf color, shape, petal structure, and environmental conditions, make it difficult to achieve high accuracy with conventional models. Transfer learning is an effective solution to improve model performance in image detection, especially when available data is limited. This study used several pre-trained models, namely VGG16, ResNet50, and EfficientNet-B0, to detect three types of flower diseases: black spot on roses, white powdery mildew, and leaf rust. The process included data processing, increasing the data volume, model training, and result verification. The results showed that the EfficientNet-B0 model provided the highest accuracy of 97.2%, significantly better than the CNN model created from scratch with an accuracy of 85.1%. This study proves that the transfer learning method is very effective in improving the accuracy of flower disease detection. These results confirm that transfer learning is effective for detecting plant diseases with higher accuracy, especially when the dataset is limited.  

Increasing traffic activity at unsignalized intersections often results in congestion and delays. The intersection of Jl. Imam Bonjol and Jl. Daya Nasional experiences these conditions, making performance evaluation necessary. This research tends to scrutinize the intersection performance under existing conditions and five-year projected conditions and to identify appropriate improvement measures. The analysis was carried out using the 2023 Indonesian Road Capacity Guidelines (PKJI 2023) and PTV VISSIM microsimulation software. Data on intersection geometry, vehicle speed, and traffic volume were collected through CCTV observations on weekdays and weekends. The results show that under existing conditions, the degree of saturation reached 1.170 with an average delay of 33.75 seconds (LOS D). In the five-year projection, the degree of saturation increased to 1.239 with an average delay of 53.69 seconds (LOS E). These findings indicate a decline in intersection performance, highlighting the need for alternative traffic management measures to improve operational performance and service levels.    

The increasing volume of online hotel reviews provides valuable insights into customer perceptions but poses challenges for manual analysis due to its unstructured nature. This study aims to compare the performance of Recurrent Neural Network (RNN) and Bidirectional Encoder Representations from Transformers (BERT) in hotel review sentiment analysis. A total of 20,491 TripAdvisor hotel reviews were classified into three sentiment categories: negative, neutral, and positive. The research methodology includes text preprocessing, stratified data splitting, class imbalance handling using Random Over-Sampling, tokenization, and supervised model training. Model performance was evaluated using a confusion matrix and classification metrics. The results indicate that BERT outperforms RNN, achieving an accuracy of 80.54%, while RNN reached 62.21%. BERT demonstrated superior capability in capturing contextual and semantic information in hotel reviews. These findings suggest that transformer-based models are more effective for sentiment analysis of complex textual data in the hospitality domain and can support data-driven service improvement strategies.    

The rapid growth of e-commerce platforms in Indonesia, particularly Tokopedia, has resulted in a large volume of consumer reviews containing valuable information regarding customer perceptions and satisfaction. However, manual analysis of such reviews is inefficient and prone to subjectivity, necessitating an automated approach based on machine learning. This study aims to classify the sentiment of sports product reviews on Tokopedia into positive, negative, and neutral categories by applying Logistic Regression, Support Vector Machine (SVM), and Random Forest using the Term Frequency–Inverse Document Frequency (TF-IDF) approach. The data were collected through web scraping of Indonesian-language sports product reviews and processed through several preprocessing stages, including data cleaning, case folding, tokenization, stopword removal, and stemming. Feature representation was performed using TF-IDF to transform textual data into numerical vectors, after which the dataset was divided into training and testing sets with an 80:20 ratio. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The results indicate that the application of TF-IDF significantly improves the performance of all models, with SVM consistently achieving the most optimal performance compared to Logistic Regression and Random Forest. These findings demonstrate that classical machine learning algorithms combined with TF-IDF remain highly effective for sentiment analysis of Indonesian-language text. The implications of this study are expected to assist sellers in understanding customer opinions, support consumers in making informed purchasing decisions, and serve as a foundation for the development of sentiment analysis and recommendation systems on e-commerce platforms.

This study aims to classify customer payment methods at 17 Coffee & Eatery using machine learning algorithms, namely Naïve Bayes and Support Vector Machine (SVM). The increasing use of digital and non-cash payments has generated large volumes of transaction data that are rarely analyzed optimally, even though such data contain valuable information for business decision making. This research used secondary transaction data collected from January to March 2025, consisting of 10,147 transaction records. The dataset included several attributes such as order time, payment time, transaction type, total sales, number of items, and payment method. Data preprocessing was performed through data cleaning, feature engineering, normalization, and label encoding before being divided into training and testing sets with an 80:20 ratio. The Naïve Bayes and SVM models were then trained and evaluated using accuracy, precision, recall, F1-score, and ROC–AUC metrics. The results show that both algorithms were able to classify payment methods effectively, but SVM achieved higher accuracy and more stable performance than Naïve Bayes. These findings indicate that SVM is more suitable for handling complex and heterogeneous transaction patterns. The implementation of machine learning for transaction classification can support more efficient financial management and data-driven decision making for small and medium enterprises in the culinary sector.

Waste from used Polypropylene (PP) and High Impact Polystyrene (HIPS) plastic is problematic in its management. The purpose of this research is to obtain the fatigue life of a mixture of used PP and HIPS plastics in its pure plastic. The research method is through the stages of mixing pure PP and 50% volume of used PP, pure HIPS and 50% volume of used HIPS, injection molding of R.R. Moore standard fatigue test specimens for pure PP, pure HIPS, pure PP + used PP, and pure HIPS + used HIPS, checking the straightness and smoothness of the molded specimen surface, fatigue testing with increasing serial loads, analysis of the bending stress curve (S) against fatigue life (N). The results showed that mixing used PP and used HIPS in pure plastic affected the fatigue life at the test speed (n)=2100 rpm for recycled PP was 9.84% shorter than pure PP, and at n=1600 rpm for recycled PP it was 9.32% shorter than pure PP, while at n=2100 rpm for recycled HIPS it was 4.45% shorter than pure HIPS, and at n=1600 rpm for recycled HIPS is 4.77% shorter than pure HIPS, while the fatigue life of pure PP is 1627704 cycles and the fatigue life of pure HIPS is 1291636 cycles or the fatigue life of pure HIPS is 20.65% shorter than pure PP, the implication of which is that the addition of used PP and used HIPS reduces the fatigue life to 9.84% for PP and 4.45% for HIPS.

The rapid development of digital streaming platforms such as Netflix has generated a large volume of content data with diverse characteristics, thereby requiring effective analytical methods to understand emerging patterns and trends. This study aims to classify Netflix content into two main categories, namely movies and television shows, and to analyze genre trends and content characteristics using a data mining approach with the Naive Bayes algorithm. The dataset used in this study is the Netflix Shows dataset, consisting of 8,809 content entries, with the primary features analyzed including genre, rating, and country of production. The research process begins with data exploration and preprocessing stages, including data cleaning, handling missing values, and transforming categorical features to enable effective model construction. Subsequently, the dataset is divided into training and testing sets to objectively and systematically build and evaluate the Naive Bayes classification model. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics to assess the model’s ability to accurately distinguish between Netflix content types. The experimental results demonstrate that the Naive Bayes algorithm is able to classify Netflix content into Movie and TV Show categories with accuracy, precision, recall, and F1-score values of 100%, respectively. The confusion matrix indicates that no misclassification occurred, suggesting that genre, rating, and country of production features provide a very clear separation between content classes. These findings indicate that the Naive Bayes algorithm can achieve exceptionally high classification performance with optimal evaluation results. The results further reveal distinct differences in characteristics between movies and television shows based on genre and production attributes. Therefore, this study is expected to contribute to the development of content recommendation systems and strategic content management within the streaming industry.

The rapid development of the sea transportation industry produces a massive and complex volume of transaction data, requiring strategic management to support managerial decision-making. This research aims to implement the Executive Information System on SeaPass in order to evaluate the performance of ship ticket sales. The research method uses data visualization with a two-level drill-down mechanism, which allows the presentation of information hierarchically from general summaries to specific details. The methodological stages include needs analysis, user interface (UI) design using Figma, front-end implementation with HTML, CSS, and JavaScript, database integration, and system testing through Black Box Testing. The results showed that the SIE implementation successfully integrated operational data, including schedules, ships, and manifests, into an interactive dashboard. The two-level drill-down feature provides the ability for executives to identify operational anomalies and market fluctuations in real-time. In conclusion, the system significantly enhances executive data analysis capabilities, transforming complex transaction data into accurate strategic information, thereby supporting more precise business decision-making and adaptive to the dynamics of the marine transportation market.

Flower disease detection is a significant challenge in modern agriculture, particularly with factors such as changes in leaf color, petal shape and structure, and environmental conditions affecting the accuracy of conventional models. These factors make it difficult to achieve optimal results using traditional methods. Transfer learning is an effective solution to improve image detection performance, especially when data is limited. This study used several pre-trained models, namely VGG16, ResNet50, and EfficientNet-B0, to detect three types of flower diseases: black spot on roses, white powdery mildew, and leaf rust. The research process included data processing, increasing the data volume using augmentation techniques, model training, and evaluation of the results. Experimental results showed that the EfficientNet-B0 model produced the highest accuracy of 97.2%, significantly better than the CNN model built from scratch with an accuracy of 85.1%. This study demonstrates that transfer learning is highly effective in improving the accuracy of flower disease detection, making it a more reliable alternative to methods that do not utilize pre-trained models, especially for agricultural applications that require high levels of accuracy in disease detection.

This study aims to determine the ideal stocking density of catfish using the triple integral method. This mathematical method is applied to accurately calculate the volume of the cultivation pond and analyze the stocking amount and biomass projection at three different density levels, namely 50, 75, and 100 fish/m³. The calculation of the volume of the pond measuring 27 m x 11 m x 1.5 m produces a value of 445.5 m³. Based on the integral calculation, the optimal stocking amount is 22,275 fish, 33,413 fish, and 44,550 fish for each density, with the final biomass projection reaching 300.7 kg, 451.1 kg, and 600.4 kg, respectively. The analysis shows that the density of 100 fish/m³ produces the highest biomass, but its application must consider technical factors such as water quality, oxygen availability, and food competition. This method provides a solid and practical mathematical foundation for more efficient, scalable, and sustainable aquaculture planning.

Laskar Buah is a modern retail chain specializing in the sale of fresh fruit. At present, the company operates one hundred branches across ten regencies. One of its outlets, Laskar Buah Ngumpakdalem, ranks among the top three branches in terms of transaction volume; however, it has received a considerable number of customer complaints regarding the quality of service provided. This situation has prompted management to conduct a thorough evaluation of the store’s service quality.This study was conducted with the aim of analyzing and evaluating service quality using the Importance–Performance Analysis (IPA) method based on the Retail Service Quality Scale (RSQS). The results of the IPA analysis were subsequently used as a foundation for determining priority areas for service improvement.The findings reveal that four service attributes fall within Quadrant B, indicating that they should be prioritized for immediate improvement. These attributes include the cleanliness of the shopping area, store layout, employee product knowledge, and product quality. Additionally, twelve attributes fall under Quadrant C, where performance should be maintained due to their already strong results. On the other hand, eleven attributes fall into Quadrant A, meaning they are considered lower  priority, while one attribute is located in Quadrant D, suggesting that Laskar Buah Ngumpakdalem is providing excessive performance in that particular aspect.

Waste has become a serious environmental problem in Indonesia, which continues to increase along with population growth. The issue of waste management poses serious challenges for the environment, especially in the process of separating organic and inorganic waste. In the field of computer vision, recognising the type and shape of waste through camera images remains a challenge due to variations in shape, colour, and complex lighting conditions. Therefore, this problem utilises Deep Learning technology, which is expected to be widely applied in Indonesia, especially in large cities with high waste volumes. This study aims to distinguish between organic and inorganic waste using the Convolutional Neural Network (CNN) method based on digital images. The developed CNN model was trained to recognise the visual patterns of each type of waste and tested to measure its accuracy. The test results show that the CNN-based classification system is capable of achieving an accuracy rate of 95%, thus proving the effectiveness of this method in supporting artificial intelligence-based automatic waste sorting systems.

This study aims to analyze the quality control of white crystal sugar production at ABC Sugar Factory using the Statistical Quality Control (SQC) method. The research employed a descriptive quantitative approach with a case study design. The primary data consisted of production volume and defective product data during the 2024 production period, while supporting data were obtained through observation and interviews with the Quality Control department. The analytical tools applied included check sheets, histograms, Pareto diagrams, p control charts, and fishbone diagrams. The results show that from a total production of 190,745.89 tons, defective products amounted to 66.70 tons, representing 0.33 percent of total output. The identified defects consisted of wet sugar at 45 percent, brownish sugar color at 30 percent, and oversized sugar crystals at 25 percent. Defective products occurred only during the first to third production periods, while no defects were observed from the fourth to seventh periods. The p chart analysis indicates that the production process was statistically out of control in the early periods but became stable and controlled in the subsequent periods. From a managerial perspective, these findings provide practical guidance for improving manufacturing quality through enhanced process control, equipment maintenance, and workforce capability development.