Publication Search

Freshwater fish diseases significantly affect aquaculture productivity and economic sustainability, while accurate visual classification remains challenging due to interclass similarity and image variability. This study presents a comparative evaluation of three deep learning architectures—DenseNet201, ResNet50, and EfficientNetV2-S—using a stepwise optimization strategy combined with Gradient-weighted Class Activation Mapping (Grad-CAM) for freshwater fish disease classification. Models were trained through three phases: baseline, optimized, and fine-tuned. Performance was evaluated using accuracy, precision, recall, F1 score, Matthews correlation coefficient (MCC), Cohen’s kappa, and per-class ROC–AUC. Results show consistent performance improvement across all architectures, with EfficientNetV2-S achieving the highest accuracy (97.14%), followed by ResNet50 (96.11%) and DenseNet201 (94.40%). High ROC–AUC values (>0.98) indicate strong discriminative capability. Grad-CAM analysis confirms that all optimized models focus on biologically relevant lesion regions, enhancing model transparency and reliability.

Traditional association rule analysis is effective at uncovering co-purchase patterns but fails to provide a global structural view of the market, which often results in fragmented and isolated insights. This study proposes a hybrid framework that integrates the Apriori algorithm with a Minimum Spanning Tree (MST) in order to validate and contextualize association rules within a single structural backbone. Transaction data from a retail store are transformed into a weighted, undirected product graph using an inverse-support function, and an MST is then extracted to represent the market backbone, while frequent itemsets and strong rules are obtained using Apriori. Experimental results on 236 multi-item transactions show that the MST backbone comprises 10 products and 9 fundamental links, with 66.67% of these links being confirmed by strong association rules, indicating a substantial coherence between statistical and structural evidence. The proposed model identifies 41 Apriori patterns that can be embedded in the MST and ranks them using a new metric, Structural Distance, which enables the categorization of Core Patterns, Bridge Patterns, and Complex Patterns according to their structural tightness. This hybrid perspective distinguishes dense, strategically meaningful bundles from anomalous but frequent combinations that are structurally peripheral, thereby offering a more holistic and actionable alternative to conventional Market Basket Analysis. The validated framework can support various applications, including store layout optimization, cross-selling strategies, and the design of path-based recommender systems, and it opens avenues for future extensions based on dynamic graphs and Graph Neural Networks.

This study compares the effectiveness of MAUT (Multi-Attribute Utility Theory), SMART (Simple Multi-Attribute Rating Technique), and WASPAS (Weighted Aggregated Sum Product Assessment) methods in a decision support system for determining the best employees at Sisilia Boutique. The quality of human resources is crucial in the retail business, but performance evaluation is often influenced by subjectivity. To address this, a multi-criteria-based decision support system is needed. MAUT translates preferences into a numerical scale, SMART calculates the average value of attributes based on weights, while WASPAS combines weighted summation (WSM) and weighted multiplication (WPM) for more balanced results. Employee performance data from Sisilia Boutique in June 2025, including attendance, store layout, customer service, and discipline, were used as the research object. The comparison results show consistency in the highest (K3) and lowest (K7) ratings across the three methods, with differences in the middle ratings. WASPAS offers a more balanced distribution of final scores, making it a comprehensive alternative for performance evaluation.

Production quantity planning is a crucial component in the bottled water industry (AMDK) to ensure that consumer demand is met efficiently. Inaccuracies in determining the amount of production can lead to overproduction and supply shortages, which ultimately leads to increased operational costs and decreased customer satisfaction. This study applies the Sugeno fuzzy logic method to predict the amount of production based on two main variables, namely weekly demand and raw material stock. The analysis stages include the fuzzification process, the preparation of the rule base, inference using the zero-order Sugeno method, and defuzzification using the Weighted Average (WA) method. The data used is synthetic data that represents the operational conditions of the medium-scale bottled water industry. The results show that the Sugeno fuzzy system is able to produce production predictions that are adaptive and responsive to fluctuations in demand and stock availability. This model provides consistent and stable output, so it can help companies in determining the optimal production amount. These findings confirm that Sugino's fuzzy approach can be an effective decision support tool in bottled water production management, especially in the face of uncertainty and variability in market demand.

Advances in information and communication technology (ICT) have revolutionized various aspects of life, including the education sector. The application of technology in education enables more flexible, interactive, and personalized learning, as well as expanding access for students in various regions, including remote areas. SMK Negeri 2 Binjai is one of the vocational education institutions in Binjai City that is currently facing challenges in the process of determining recipients of educational assistance, particularly the Indonesia Pintar (PIP) Program, which is intended for underprivileged students. Until now, the selection mechanism for PIP recipients has been carried out manually, making it prone to subjectivity, lack of transparency, and limited integrated data. To overcome this problem, a decision support system is needed to help schools determine the recipients of educational assistance objectively and structurally using the Weighted Aggregated Sum Product Assessment (WASPAS) method, which is an effective multi-criteria decision-making technique for processing various assessment criteria to produce the best alternative ranking. The results of the calculation using the WASPAS method produced different preference values (Qi) for each student alternative. The highest score was obtained by Ilyas Ramadhanu with a Qi of 0.6899, followed by Binar Sembiring with a Qi of 0.5963, and Dimas Dwi Andika with a Qi of 0.5790. The lowest value was obtained by Adit Rahmazi with a Qi of 0.3852.

The development of information technology has accelerated digitization in various sectors, including in the decision-making process. In the DayTrans Shuttle service, the selection of the best route is still done manually using Microsoft Excel. This process is time-consuming, inefficient, and has the potential to cause errors and subjectivity. The purpose of this study is to design and develop a web-based decision support system by applying the Weighted Product (WP) method to determine the most optimal shuttle route objectively and efficiently. The research data was obtained through interviews, observations, and literature studies, then analyzed according to system requirements. The development was carried out through the stages of requirements analysis, database and interface design, implementation, and testing. The developed system is equipped with features for managing criteria data, alternative routes, weight calculations, and real-time presentation of recommendation results. The research results show that the system functions well, is able to speed up the route selection process, and produces accurate and transparent recommendations. Thus, this system is expected to improve DayTrans' operational efficiency while supporting the quality of inter-city transportation services.

The rapid development of information technology has had a significant impact on various aspects of life, including the decision-making process that requires precision and objectivity. One of the problems often faced is product selection with various complex criteria, for example in selecting a quality drum. Drums as a percussion instrument have many variations in terms of sound quality, material, design, price, and durability, so a system is needed that can assist users in making a more rational choice. This study aims to develop a website-based Decision Support System (DSS) using the Weighted Product (WP) method to provide recommendations for drum selection. The WP method was chosen because it is able to perform calculations by considering the weight of each criterion so that the recommendation results are more objective. The system implementation is carried out through the design of a user-friendly web-based interface, making it easier for users to access, compare alternatives, and obtain recommendations without having to perform manual assessments that are time-consuming and potentially subjective. System testing was carried out by comparing the results of the system's recommendations with expert assessments, which obtained an accuracy level of 95%. These results indicate that the developed system has a high level of reliability and is suitable for use as an aid in decision-making in selecting quality drums. With this system, it is hoped that users, both beginners and professionals, will find it easier to choose drums that suit their needs and preferences.

Groundnut plants must be well maintained so that they can be food crops that have economic value and high fat and protein content. Many farmers still plant with the old pattern so that peanut plants are less fertile because they are affected by pests and other diseases. So with an expert system to diagnose peanut plants can help farmers or the general public in knowing the solution if experiencing problems or symptoms of this peanut plant. The application of the WP (weighted product) method can help the application become structured. From the results of the study, the expert system for diagnosing peanut plants can help many people for use as fundamental insights.

This study aims to analyze the business development strategy of Depot Kusen Rahmat by reviewing four main aspects, namely production, human resources (HR), finance, and marketing. The analytical approach used in this study is SWOT (Strengths, Weaknesses, Opportunities, Threats) and QSPM (Quantitative Strategic Planning Matrix). Primary data was obtained through a survey of 16 respondents who are active consumers of Depot Kusen Rahmat. The results of the SWOT analysis identified that the company has four strengths, four weaknesses, four opportunities, and four threats. The most dominant internal strength is efficient and neat products, with the highest weighted score of 0.509, which indicates that the quality of production results is the main competitive advantage. On the other hand, the main weakness found is the absence of a product catalog, with a score of 0.158, which indicates a lack of visual information media as a means of product promotion and communication to consumers. From external factors, the biggest opportunity is the increasing consumer interest in custom products, with a score of 0.479, which indicates a positive trend towards product personalization. The most significant threat is the rapidly changing design trends, with a score of 0.186, which requires the company to be more adaptive to changing market tastes. Based on the results of the SWOT matrix analysis, the company's position is in Quadrant I with an IFAS value of 1.368 and EFAS of 1.206, which indicates that the company is in a position to support an aggressive growth strategy. The QSPM results recommend prioritizing strategies in the form of emphasizing quality and balanced prices, followed by improving customer service and developing high-quality custom products as strategic steps to win market competition and increase business competitiveness sustainably.

This study aims to determine the SWOT analysis in increasing competitiveness at PT. Matahari Department Store Kediri. The problem in this study is "does SWOT Analysis play a role in increasing competitiveness at PT. Matahari Department Store Kediri. The research method used is the descriptive analysis research method, SWOT Matrix, External Factor Evaluation Matrix (EFE Matrix), Internal Factor Evaluation Matrix (IFE Matrix). The results of the study indicate that when PT. Matahari Department Store Kediri The competitive strategy implemented by PT. Matahari Department Store Kediri only provides quality products at affordable prices but also considers maximum product sales through social media, and maintains the company's image in the eyes of consumers so as to increase customer loyalty and the weighted value of the Internal Factor Evaluation Matrix (IFE Matrix) is 2.85 which indicates that the position of PT. Matahari Department Store Kediri has a very strong internal position. While the weighted value of the External Factor Evaluation Matrix (EFE Matrix) is 3.02 which indicates that PT. Matahari Departement Store Kediri in facing the dynamics of the external environment the company's position is relatively strong.

Toko Liv Beauty is one of the business players in the beauty sector that is developing in North Sumatra, specifically in the West Binjai sub-district, Binjai City. As a store that provides various beauty products, this research aims to assist Toko Liv Beauty in determining a strategic location for opening a new branch using the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. The TOPSIS method was chosen for its ability to analyze alternatives based on positive and negative ideal solutions objectively. A case study was conducted at three potential locations in Binjai: Binjai City, Binjai South, and Binjai North, considering five main criteria: population density, ease of transportation access, number of competitors, rental costs, and building area. The analysis process involves normalizing the decision matrix, calculating weighted values, identifying ideal solutions, and determining alternative preferences. The analysis results show that the location with the highest preference is Binjai North (1), followed by Binjai South (0.5885) and Binjai City (0). Thus, Binjai North is recommended as a strategic location for opening a new branch of Toko Liv Beauty. The implementation of the TOPSIS method in this research is expected to contribute to more effective data-driven decision-making for the business development of Toko Liv Beauty.

Teachers provide dedication to students to convey knowledge. In addition, teachers also play a role in educating, guiding, and training students so that they can understand the material being taught. Teachers have a very significant role in creating a superior and quality generation. The Principal at SDN Weetame does not utilize the application in the process of selecting qualified and competent teachers or instructors. Researchers observed and designed A selection support system for determining the best instructors implementing multi-attribute-based decision-making method, namely the WP (Weighted Product) method. The outcomes of this study reveal that SPK application can be used easily and produce decisions quickly so that the Principal can make the right choice.

Students who excel academically as well as non-academically in the classroom and at school. High achieving students are very difficult to find because there is no system that can assess student talent in the classroom. Thus, there is a need for a computer-based system that can facilitate teachers in identifying outstanding students. . The system is an application that is made, SPK using the WP method. With the application of the following method, the best option can be determined from various choices and their features through the weighing process. Thus, the results of this research can help teachers and principals at SDN Daha Walu in obtaining the highest score ranking based on the system that can be used as a reference for decision making.

Decision Support System for Selecting Contraceptives for Women Using the Weighted Product (WP) Method to determine the best alternative results. In this method, there are 5 (five) criteria and 5 alternative contraceptives for women. To test the results, a comparison is made of the results given by the midwife with the results from the system. After that, ranking is carried out according to the highest value from the calculation results for selecting contraceptives for women.

PT XYZ is a private company in Palembang that supplies medical devices and equipment. This company conducts performance assessments every year to provide appropriate rewards in the form of gifts, bonuses or incentives to employees. In carrying out the performance assessment process for providing employee rewards, it is still done manually. This process is inefficient because it takes a lot of time, is prone to errors in calculation and it is not clear which aspects of the criteria are important. By using the Weighted Product methodology, this study tries to create a decision support system (DSS) that will simplify this evaluation procedure. This application is made website-based, using the laravel framework with the Iterative system development method. The results obtained indicate that the system can help companies improve efficiency by conducting automatic assessments, providing measurable weights, transparently and using the Weighted Product method for more accurate assessments. Overall, the system developed meets the research objectives.

A cooperative is a business entity based on the principle of kinship. Cooperatives have the aim of improving the welfare of their members through the activities they carry out. The Binjai City Cooperatives and UMKM Service is a regional apparatus within the Binjai City Government for government affairs in the field of Cooperatives, Small and Medium Enterprises. The Binjai City Cooperatives and UMKM Department always carries out assessments of every cooperative in the city of Binjai in the form of an assessment of the best cooperatives which aims to increase the motivation of cooperative institutions and as an evaluation material for the performance of cooperatives recorded in the City of Binjai. In carrying out the assessment of the best cooperatives carried out by the Binjai City Cooperatives and UMKM Service, it took quite a long time. This is because the data collection and processing process is conventional and simple. To overcome existing problems, a decision support system was created to facilitate the management and calculations of each cooperative. In this research, the method used in the calculation process is WASPAS (Weighted Aggregated Sum Product Assessment). The Weighted Aggregated Sum Product Assessment (WASPAS) method is a method that is able to minimize errors or maximize the assessment to determine the highest and lowest values. The final result of this research is a decision support system that is able to produce decision recommendations in determining the best cooperative at the Binjai City Cooperative and UMKM Department.  

Members of the KPPS (Voting Organizing Group) are responsible for organizing voting in a polling station (TPS) during general elections in Indonesia. They are the spearhead in carrying out the democratization process by supervising and ensuring the continuity of elections honestly, fairly, and transparently. The duties of KPPS members include preparing TPS before voting begins, receiving and examining voters, supervising the election process to ensure compliance with applicable regulations, counting votes after voting is complete, reporting election results, and maintaining security and order around TPS. Decision support system is a Decision support system or Decision Support System (DSS) is an interactive system that supports decisions in the decision-making process through alternatives obtained from data processing results. The purpose of this study is to facilitate the recruitment of members of the Voting Organizing Group (KPPS). The research method is Weighted Aggregated Sum Product Assessment (WASPAS). WASPAS is to find the most appropriate priority location choices using weighting. The results of this study are that the development of this support system can help the KPU in selecting or selecting KPPS members and this decision support system as a tool in developing KPPS members by viewing or using criteria according to the criteria needed using the WASPAS method.      

In the modern era, laundry services have become a practical solution for busy people. Sukmajaya Laundry, located in a strategic area in Depok, offers various services such as kilo laundry, bed cover washing, and express washing. However, despite having a wide range of ironing fragrance options, the laundry owner faces difficulties in determining which fragrance is most preferred by customers. This study aims to assist the owner of Sukmajaya Laundry in recommending the most popular ironing fragrance to customers. With this recommendation, it is hoped that new customers will no longer struggle to choose a fragrance that suits their preferences. The research employs the Weighted Product (WP) method, which combines several attributes with weighted criteria to calculate the total value. The alternative with the highest total value will be considered the best solution. This study results in a decision support system that can recommend the most popular ironing fragrance based on previous customer preferences, thereby enhancing customer satisfaction and operational efficiency at Sukmajaya Laundry.

In the modern era, laundry services have become a practical solution for busy people. Sukmajaya Laundry, located in a strategic area in Depok, offers various services such as kilo laundry, bed cover washing, and express washing. However, despite having a wide range of ironing fragrance options, the laundry owner faces difficulties in determining which fragrance is most preferred by customers. This study aims to assist the owner of Sukmajaya Laundry in recommending the most popular ironing fragrance to customers. With this recommendation, it is hoped that new customers will no longer struggle to choose a fragrance that suits their preferences. The research employs the Weighted Product (WP) method, which combines several attributes with weighted criteria to calculate the total value. The alternative with the highest total value will be considered the best solution. This study results in a decision support system that can recommend the most popular ironing fragrance based on previous customer preferences, thereby enhancing customer satisfaction and operational efficiency at Sukmajaya Laundry.

Forecasting demand for screen-printed clothing products at the UMKM "D'mitz Screen Printing" in Sobrah Village, Wungu District, Madiun Regency helps with production control planning to maximize supply chain management for screen-printed clothing products. To predict future product demand, it is very important for UMKM to forecast market demand. Forecasting future demand is very important to avoid sales prediction errors that can cause waste, such as increased production costs due to sales predictions being too large, or stock outs due to sales predictions being too small, which results in customers having to wait longer to get the goods they want. Based on this problem, the UMKM "D'mitz Screen Printing" carried out a demand forecasting analysis for screen printed clothing with the aim of reducing waste and maximizing value. Forecasting demand for screen printed clothing for the next five months using time series analysis and moving average methods. Forecasting results for the period March 2022 to February 2023 show sequential forecasting values of 3266.67; 3300; 3250; 3283.33; 3233.33; 3316.67; 3333.33; 3372.22; 3305.56; and 3272.22. From the Mean Absolute Error (MAE) and Mean Square Error (MSE) calculations that have been carried out, the MAE value is 94.44 and the MSE value is 16018.593.