Rice is a strategic commodity in supporting national food security. However, its productivity remains hindered by manual growth monitoring processes, climate change challenges, and limited human resources. This final project develops a seedling detection and counting system using the YOLO (You Only Look Once) algorithm, with aerial imagery input acquired from UAV (Unmanned Aerial Vehicle), presented through an interactive web-based dashboard. The dataset is enhanced with MIRV (mirror vertical) and MIRH (mirror horizontal) augmentation techniques to improve training data diversity. All experiments were conducted on three models: YOLO11n, YOLOv10n, and YO-LOv8n. Evaluation shows that the YOLO11n configuration using AdamW and a learning rate of 0.01 achieves mAP@50 of 0.592 and precision of 0.852. The system supports data-driven agronomic decision-making to anticipate crop failure risks, thus assisting large-scale rice field owners in monitoring seedling effectively and efficiently.

The government ensures educational quality in universities through a quality assurance (QA) system implemented via accreditation, which evaluates both study programs and institutions. A key concern in accreditation is the decline in new student enrollment, making accurate predictions of enrollment numbers essential for quality assessment. This study proposes a linear regression (LR) model to forecast future university student enrollments based on enrollment figures from the previous year as input feature. Using a dataset from one of Indonesia’s leading university spanning 2013 to 2023, the experimental results demonstrate that the LR model outperforms other regression techniques, including multi-layer perceptron (MLP), K-nearest neighbors (KNN), decision tree (DT), and random forest (RF). The LR model achieves R² values between 0.87 and 0.95, reflecting a strong linear relationship between current and future student numbers. It also delivers high accuracy, with root mean square error (RMSE) values ranging from 11.72 to 41.21 per year. The trained LR model has been integrated into a web-based system, offering data visualization and enrollment predictions to support university management in monitoring quality, addressing enrollment challenges, and facilitating informed decision-making.

Bike sharing is increasingly gaining popularity as an affordable and environmentally friendly mode of transportation in urban areas. However, the nature of bike sharing, where users can pick up and return bikes at different stations, often results in an uneven distribution of bikes across stations. Consequently, accurately predicting the future number of rented bikes at each station becomes crucial for bike-sharing operators to optimize the bike inventory at each location. This study introduces a multi-step-ahead forecasting model that employs machine learning methods to predict the hourly demand for rented bikes. We utilize information on rented bikes from the preceding day to forecast the forthcoming counts of rented bikes for the next 1, 3, 6, 12, and 24 h. Additional features extracted from timestamps are incorporated to enhance the accuracy of the model. We compare the proposed model, based on multilayer perceptron (MLP), with various machine learning prediction algorithms, including Support Vector Regression (SVR), K-Nearest Neighbor (KNN), Decision Tree (DT), Adaptive Boosting (AdaBoost), Random Forest (RF), and Linear Regression (LR). Applying the proposed MLP model to the Seoul bike-sharing dataset demonstrates a positive outcome, indicating a reduction in prediction error compared to other forecasting models. The proposed model achieves the highest R2 (coefficient of determination) values when compared to other models, with values of 0.973, 0.882, 0.82, 0.807, and 0.79 for prediction horizons of 1, 3, 6, 12, and 24 h, respectively. By obtaining future values for predicted rented bikes, the trained model is anticipated to assist in optimizing the number of available bikes for bike-sharing companies.

This paper examines the integration of digital twin (DT) and simulation technologies in warehouse management to enhance efficiency and competitiveness in the logistics industry, specifically for third-party logistics (3PL) providers. It uses a case study to benchmark current practices and identify areas for improvement. The research also analyses industry trends and competitor strategies, revealing a growing adoption of DT and simulation for warehouse optimization. The findings highlight significant benefits of DT and simulation integration, including improved operational efficiency, enhanced decision-making, optimized inventory management, and increased supply chain visibility. The paper proposes a practical framework for implementing these technologies, emphasizing a phased approach to ensure smooth integration and maximize impact for 3PL providers.

Online health communities generate vast knowledge on various topics, making it challenging to track latent themes and correlations among key variables. Identifying these hidden variables and their relationships can enhance user engagement and content curation. This paper introduces a novel approach using fuzzy cognitive maps to uncover these variables and causal relationships in online health communities, providing users with valuable insights for disease management and treatment. The study employed Latent Dirichlet Allocation (LDA) to generate topics from an online health forum, using this as evidence to construct fuzzy cognitive maps. The proposed system reflects disease development and offers significant insights for managing health conditions. The findings have theoretical and practical implications for developing online recommendation systems in the healthcare domain. This study contributes to the literature by proposing a method for identifying key variables and relationships, aiding health professionals and patients in understanding and managing health conditions. Future research will explore the system’s effectiveness in real-world settings and the role of user-generated content in enhancing recommendation systems.

Data is increasingly recognized as a valuable asset for generating new insights and information. Given the importance of data, businesses must always look for ways to get more value from data generated from sales transactions. In data mining, association rule mining is a good standard technique and is widely used to find interesting relationships in databases. Association rule is closely related to market basket analysis to find items that often appear together in one transaction. This study proposes the frequent pattern growth (FP-Growth) algorithm in finding association rules on sales transaction data. Our methodology includes dataset preparation for modeling, evaluation of model performance, and subsequent integration into a web-based platform. We conducted a comparative analysis of the FP-Growth algorithm against the Apriori algorithm, finding that FP-Growth outperformed Apriori in efficiency. Using the same dataset and constraint level, both algorithms produce the same number of frequent itemsets. However, in terms of computation time, FP-Growth excels by taking 2.89 seconds while Apriori takes 5.29 seconds. We integrated trained FP-Growth algorithm into a web-based dashboard application using the streamlit framework. This system is anticipated to simplify the process for businesses to identify customer purchasing patterns and improve sales.

Recent advancements in biosensors have empowered individuals with diabetes to autonomously monitor their blood glucose levels through continuous glucose monitoring (CGM) sensors. Nevertheless, the data collected from these sensors may occasionally include outliers due to the inherent imperfections of the sensor devices. Consequently, the identification of these outliers is critical to determine whether blood glucose levels deviate significantly from the norm, necessitating further action. This study employs an outlier detection approach based on the 3-sigma method and the interquartile range (IQR), along with the application of the Winsorizing technique to correct the identified outliers. Additionally, a web-based system for visualizing blood glucose levels is developed, utilizing both outlier detection methods. In order to assess the system's performance, two types of testing are conducted: black box testing and load testing. The results of black box testing indicate that all test scenarios operate as anticipated. As for the load testing response times, it is observed that the 3-sigma visualization page loads an average of 606.75 milliseconds faster compared to the IQR visualization page. This study's outcomes are expected to enhance data quality, enhance the precision of analyses, and facilitate more informed decision-making by identifying and addressing extreme data points.

Analyzing customer shopping habits in physical stores is crucial for enhancing the retailer–customer relationship and increasing business revenue. However, it can be challenging to gather data on customer browsing activities in physical stores as compared to online stores. This study suggests using RFID technology on store shelves and machine learning models to analyze customer browsing activity in retail stores. The study uses RFID tags to track product movement and collects data on customer behavior using receive signal strength (RSS) of the tags. The time-domain features were then extracted from RSS data and machine learning models were utilized to classify different customer shopping activities. We proposed integration of iForest Outlier Detection, ADASYN data balancing and Multilayer Perceptron (MLP). The results indicate that the proposed model performed better than other supervised learning models, with improvements of up to 97.778% in accuracy, 98.008% in precision, 98.333% in specificity, 98.333% in recall, and 97.750% in the f1-score. Finally, we showcased the integration of this trained model into a web-based application. This result can assist managers in understanding customer preferences and aid in product placement, promotions, and customer recommendations.

Social media's tendency for instant reactions can be harnessed by companies and organizations to gather feedback. Nevertheless, effectively analyzing vast amounts of social media data poses a challenge. This issue can be addressed through the use of sentiment analysis technology. In this study, a sentiment analysis model is developed, employing Support Vector Machine (SVM) and Term Frequency-Inverse Document Frequency (TF-IDF) algorithms. The study aims to investigate the impact of feature engineering on TF-IDF, by incorporating statistical features into the SVM model's sentiment analysis performance. The experimental results reveal that the prediction model utilizing the conventional TFIDF approach achieves an SVM model with an F-measure score of 84.55%. Through the implementation of feature engineering, by adding max, min, and sum features, the model's performance shows a noticeable improvement, with an increase of 0.65% in the F-measure score difference. Consequently, the proposed feature engineering method positively enhances the capability of the SVM-based sentiment analysis model. To facilitate the acquisition of sentiment analysis results through user interfaces, the trained SVM model is integrated into a web-based sentiment analysis application. By doing so, the findings of this study contribute to streamlining the process of obtaining sentiment analysis results from social media data.

Radio Frequency Identification (RFID) technology has significantly improved in the past few years and is presently sought for implementation in the identification and traceability of perishable food in the food sector to safeguard food safety and quality. It is currently considered a worthy successor to the barcode system and has significant advantages for monitoring products in the perishable food supply chain (PFSC). The present study proposes a traceability system that utilizes RFID and Internet of Things (IoT) sensors. RFID technology can be used to track and trace perishable food while IoT sensors can be used to measure temperature and humidity during storage and transportation. Furthermore, it is important that RFID gates can identify the direction of tags and whether products are being received or shipped through the gate. In this study, machine-learning models are utilized to detect the direction of passive RFID tags. The input features are derived from receive signal strength (RSS) and the timestamp of tags. The proposed system has been tested in the perishable food supply chain and has revealed significant benefits to managers and customers by providing real-time product information and complete temperature and humidity history. In addition, by integrating a machine-learning model into the RFID gate, tagged products that move in or out through a gate can be correctly identified and thus improve the efficiency of the traceability system.

Due to the growing customer health awareness, food quality and safety has gained considerable attention. Therefore, consumer demand for complete visibility of food quality and history along the supply chain has significantly increased. This study proposes an e-pedigree food traceability system, utilizing radio frequency identification technology to track and trace product location and wireless sensor network to collect temperature and humidity during storage and transportation. Missing sensor data may occur in real cases, as sensor data are lost or corrupted due to many reasons. The proposed system utilizes data mining techniques to predict missing sensor data. The proposed system was tested for kimchi supply chain in Korea, and showed significant benefit to managers as well as customers by providing real-time location as well as complete temperature and humidity history. The multilayer perceptron model provided the best prediction accuracy for missing sensor data compared to other models. The proposed e-pedigree food traceability system will help managers optimize food distribution while also increasing customer satisfaction, as it can monitor product freshness.

Sustainability relies on the environmental, social and economical systems: the three pillars of sustainability. The social sustainability mostly advocates the people’s welfare, health, safety, and quality of life. In the agricultural food industry, the aspects of social sustainability, such as consumer health and safety have gained substantial attention due to the frequent cases of food-borne diseases. The food-borne diseases due to the food degradation, chemical contamination and adulteration of food products pose a serious threat to the consumer’s health, safety, and quality of life. To ensure the consumer’s health and safety, it is essential to develop an efficient system which can address these critical social issues in the food distribution networks. This research proposes an ePedigree (electronic pedigree) traceability system based on the integration of RFID and sensor technology for real-time monitoring of the agricultural food to prevent the distribution of hazardous and adulterated food products. The different aspects regarding implementation of the proposed system in food chains are analyzed and a feasible integrated solution is proposed. The performance of the proposed system is evaluated and finally, a comprehensive analysis of the proposed ePedigree system’s impact on the social sustainability in terms of consumer health and safety is presented.

Food quality and safety has attained the considerable attention, because of the consumers increasing health awareness, improved economic standards and lifestyle of modern societies. Thus, it is important for distributors, retailers and consumers to purchase agriculture food products and track that they have come through the legal and safe distribution channels. In this paper we proposed a Centralized EPCIS and Sensor Data Repositories based e-pedigree system for agriculture food products to guarantee the quality, safety and reliability of agriculture food products for final consumers. This system not only assure the authenticity of the agriculture food products but also assure the food quality through environmental information such as temperature and humidity during storage, distribution and transportation for food quality.