Bulletin of Applied Mathematics and Mathematics Education

Comparison of Continuous Review System and Min-Max Method in Soybean Inventory Control

Ellysa Syafitri, Riri Syafitri Lubis — Tue, 15 Oct 2024 00:00:00 +0000

This study aims to compare the effectiveness of two inventory control methods, namely continuous review system and min-max in controlling soybean raw material inventory in tofu production. The continuous review system method is an inventory control system where raw material inventory is checked continuously while the min-max method is a method that maintains raw materials between the minimum and maximum limits. The data used are data on soybean raw material inventory and needs at the Ali Musa tofu factory in Serdang Bedagai Regency. Based on the results of the analysis of total inventory costs using the continuous review system method, it is IDR 418,978,693/year 2021 and IDR 430,271,76/year 2022. While the total inventory cost using the min-max method is IDR 366,272,031/year 2021 and IDR 367,964,100/year 2022. While the company uses IDR 429,321,708/year 2021 and IDR 445,381,200/year 2022. From the calculations above, the min-max method is more effective in reducing total inventory costs with infrequent ordering frequencies. Since orders are not made regularly, this strategy reduces the number of soybean orders and reduces the cost of ordering. When the reorder limit is reached, the company will place the order. The choice of inventory control method must be adjusted to the needs and operational characteristics of the company. The continuous review system method is better for companies with high and fluctuating raw material needs, while min-max can be used for companies with more stable raw material needs.

Optimization of Feature Selection on Semi Supervised Data

Dian Eka Wijayanti, Sugiyarto Surono; Deshinta AD; Sintia Afriyani — Tue, 15 Oct 2024 00:00:00 +0000

This research explores feature selection optimization in semi-supervised text data by utilizing the technique of dividing data into training and testing sets and implementing pseudo labeling. Proportions of data division variations, namely 70:30, 80:20, and 90:10, were used as experiments, employing TF-IDF weighting and PSO feature selection. Pseudo labeling was applied by assigning positive, negative, and neutral labels to the training data to enrich information in the classification model during the testing phase. The research results indicate that the Linear SVM model achieved the highest accuracy at a 90:10 data division proportion with a value of 0.9051, followed by Random Forest with an accuracy of 0.9254. Although RBF SVM and Poly SVM yielded good results, KNN showed lower performance. These findings emphasize the importance of feature selection strategies and the use of pseudo labeling to enhance the performance of classification models in semi-supervised text data, offering potential applications across various domains that rely on semi-supervised text analysis.

The Tahani Fuzzy Logic Method for Detecting Violence against Women in North Sumatera

KHAIRUN NISA, Rina Filia Sari — Tue, 15 Oct 2024 00:00:00 +0000

Violence against women is a pervasive issue in society. Violence often encompasses various forms, such as physical, psychological, economic, and sexual violence. This research employs the Tahini fuzzy logic method to predict cases of violence against women. The results of the analysis in query fuzzification indicate that there are 16 districts experiencing high values in cases of violence against women, namely: Asahan, Batu Bara, Dairi, Deli Serdang, Karo, Binjai City, Gunung Sitoli City, Pematang Siantar City, Tanjung Balai City, Labuhan Batu Utara, Labuhan Batu, Langkat, Padang Lawas Utara, and Simalungun. This research also provides recommendations based on detection results, utilizing the fire strength value as the highest level ranking. Looking at the total 33 districts in North Sumatera, the highest level of violence against women is in Medan City, which occurred from July to December 2022, where all four criteria for typical cases of violence against women are significantly high.