In the context of increasingly uncertain maritime logistics environments, container Demurrage and Detention (D&D) charges pose a significant challenge to both carriers and shippers. Traditional policies typically impose separate cost structures for container pickup (demurrage) and container return (detention), yet such separate impositions often fail to capture the interconnected nature of operational delays and the pervasive uncertainty present in hinterland container flows. This study addresses the problem of D&D decision-making under uncertainty by proposing a merged free time policy that integrates both D&D charges into a unified framework. By merging the free time allocated for both pickup and return processes, the proposed policy aims to enhance operational flexibility, reduce overall logistics costs, and provide a more predictable cost structure for carriers while improving service quality for shippers. To achieve these objectives, we develop a mathematical optimization model that incorporates stochastic pickup and return scenarios, thereby reflecting the uncertainties in container availability and transportation delays. The model embeds a strategic decision-making process between carriers and shippers through a hierarchical framework to jointly optimize free time allocations and penalty structures. Numerical experiments based on simulated data demonstrate that the merged free time policy outperforms traditional separate policies by improving container turnover efficiency and mitigating the negative impact of uncertainty on operational performance. Our findings offer valuable insights into cost management and risk reduction in maritime logistics and contribute to the literature by providing a comprehensive strategy for D&D management that supports more collaborative hinterland container operations and enhances overall supply chain resilience.
Virtual Reality Head Mounted Display (VR HMD)-based flight simulators have recently emerged as promising tools for enhancing pilot training effectiveness. This study aims to establish a set of evaluation criteria for the development of VR HMD-based flight simulators and to determine their relative importance and priority using the Analytic Hierarchy Process (AHP). Through an extensive review of the literature, a hierarchical evaluation model was constructed, consisting of three primary criteria and ten sub-criteria. A structured questionnaire was administered to experienced pilots, and the collected data were analyzed using the AHP methodology to assess the relative weights of each criterion. The analysis revealed that the fidelity of system performance is the most influential factor in evaluating VR HMD-based flight simulators. These findings present a structured evaluation framework and offer practical insights for guiding the strategic development and optimization of VR HMD-based flight training systems.
The casting manufacturing process of aluminum automotive wheels often involves processing various wheel models during stages such as flow forming, machining, packaging, and delivery. Traditionally, separate equipment or production lines were required for each model, which led to higher facility investment costs and increased labor costs for classification. However, the implementation of machine learning-based model classification technology has made it possible to automatically and accurately distinguish between different wheel models, resulting in significant cost savings and enhanced production efficiency. Additionally, this approach helps prevent product mix-ups during the final inspection process and allows for the quick and precise identification of wheel models during packaging and delivery, reducing shipping errors and improving customer satisfaction. Despite these benefits, the high cost of machine learning equipment presents a challenge for small and medium-sized enterprises(SMEs) to adopt such technologies. Therefore, this paper analyzes the characteristics of existing machine learning architectures applicable to the automotive wheel manufacturing process and proposes a custom CNN(Convolutional Neural Network) that can be used efficiently and cost-effectively.
Recently, as informatization of transactions and digitization of product itself progress, the influence of network externalities is increasing. The reason why network externalities receive so much attention is that they fundamentally lead to fierce price competition between products. Following this trend, in this paper, we study the effect of quality and compatibility on the price competition between products under network externalities. To do this, we first present a new market model incorporating quality, network externalities and compatibility. Based on the presented model, the Nash and Stackelberg equilibrium solutions are derived and analyzed numerically. The results can be summarized as follows: First, when the quality difference between products is small, the Nash method of pricing is optimal, whereas when the quality difference is large to some extent, the Stackelberg method of pricing is optimal. Second, in the case of the low quality product, it was shown that there are situations where it is necessary to intentionally lower its own quality for more profit. Third, it was also shown that compatibility mitigates the effects of network externalities.
The COVID-19 pandemic has caused significant disruptions in global air travel demand, presenting new challenges for accurately forecasting passenger volumes. This study analyzes the monthly air passenger demand data from 2010 to 2022 to identify key external factors that influence passenger demand. Our analysis shows that the number of international visitors to Singapore is a critical determinant of passenger demand. Consequently, we propose a SARIMAX (Seasonal AutoRegressive Integrated Moving Average with eXogenous variables) model to forecast monthly air passenger demand at Singapore's Changi Airport, integrating international visitor numbers as an exogenous variable. Through comprehensive model identification and parameter estimation, we select the best SARIMAX configuration. To validate the performance of the model, traditional time series methods such as SARIMA, various exponential smoothing methods, and advanced machine learning methods like LSTM (Long Short-Term Memory) and Prophet were compared for forecasting monthly air passenger demand at Changi Airport in 2023. The results show that the SARIMAX model significantly outperforms all other tested models, achieving the best performance across multiple forecasting metrics, including the Mean Absolute Percentage Error.
Unlike civilian logistics systems, which primarily focus on efficiency, military logistics emphasizes operational stability. To achieve this, the establishment of a dedicated support system and balanced inventory management are essential. However, the current Army logistics system requires improvements in the support rate through the dedicated support framework. Although long-term improvement is possible through procurement process optimization, short-term enhancement is difficult due to the military’s annual procurement cycle. As a short-term improvement, inventory adjustment between supply points could be effective, but this strategy has not been fully utilized. This is due to the lack of recognition that, while inventory adjustment may increase costs in the short term, it contributes to improved logistics efficiency and stability in the long term. This study proposes a cost-minimizing plan that includes inventory adjustment between supply points in military logistics and aims to verify the effectiveness of inventory adjustment. To this end, a mathematical model for optimizing transportation planning was developed. Additionally, the effectiveness of inventory adjustment was demonstrated through a case study reflecting actual Army logistics conditions. The results of the study confirmed the positive effects of inventory adjustment. Inventory adjustment is expected to enhance the dedicated support rate and promote procurement process optimization, contributing to the advancement of the Army logistics system.
The number of significant issues on many welding processes are often connected to high productivity and manufacturability at low costs. The research on welding processes in the literature has reported several research activities, but there is still scope for improvement in most industrial settings. The primary goal of this research is to determine the best super-TIG welding settings to use for groove welding. First, in order to determine the quality characteristics and risks associated with them, concepts and frameworks of quality by design (QbD) which is a new standard in pharmaceutical area in order to improve drug qualities were integrated into this process optimization. Second, stepwise experimental design approaches including a factorial design as well as a response surface methodology (RSM) were customized and performed for this specific automated super-TIG welding process. Third, based on experimental design results, the optimal operating conditions with both design space (i.e., acceptable range of operating conditions) and safe operating space (i.e., safe range of operating conditions) were obtained. Finally, a case study including QbD steps, stepwise experimental design approaches, design and operating spaces, the optimal factor settings, and their association validation results was conducted for verification purposes.
Business model(BM) innovation is widely known as a differentiated strategy and strategic framework for companies to secure a sustainable competitive advantage in an uncertain environment. While prior research has studied new business models in accordance with changes in manufacturing trends such as digitalization and servitization, empirical understanding of the dynamic processes of BM innovation is still lacking. This study addresses this gap by proposing an analytical framework of the BM innovation matrix that classifies companies' BM innovation cases into four types according to the degree of BM change and the influential level of the industry/market outcome through a critical literature review on business models and dynamics. Drawing on this framework, we conduct longitudinal case studies of leading global 3D printing firms to examine the dynamic processes and external environmental factors that shape the evolution of BM innovation. Our findings reveal previously underexplored patterns of co-evolution between firms’ business models and their broader industrial and market environments. This study has the significance of constructing a framework for dynamically analyzing BM innovation based on longitudinal case studies of emerging 3D printing companies. We presented implications for companies seeking successful commercialization of emerging technologies, such as the strategic usefulness of the BM innovation framework and the importance of co-evolution with industrial structure and environmental factors in the process of change.
Small and medium-sized manufacturing enterprises(SMEs) have traditionally relied on skilled labor to support multi-variety, small-batch production. However, demographic changes such as low birth rates and aging populations have led to severe labor shortages, prompting increased interest in collaborative robots(cobots) as a viable alternative. Despite this necessity, many SMEs continue to face significant challenges in implementing such technologies due to technical, organizational, and environmental(TOE) constraints. While prior research has mainly focused on technology adoption from the perspective of user organizations, this study adopts a differentiated approach by analyzing adoption factors from the perspective of smart factory experts—specifically, evaluators/mentors and solution providers—who play a critical role in Korea’s policy-driven smart manufacturing environment. Using the Analytic Hierarchy Process(AHP), the study evaluates the relative importance and prioritization of adoption factors across three dimensions: technology, organization, and environment. Survey data collected from 20 smart factory experts indicate that top management support, relative advantage, and safety are key determinants in cobot adoption. Furthermore, the findings reveal that organizational readiness and technical effectiveness have greater influence on implementation decisions than external pressures such as partner pressure. This study provides new insights by incorporating expert perspectives into the adoption framework and offers practical policy and managerial implications to support cobots implementation in the SMEs.
Fault detection in electromechanical systems plays a significant role in product quality and manufacturing efficiency during the transition to smart manufacturing. Because collecting a sufficient number of datasets under faulty conditions of the system is challenging in practical industrial sites, unsupervised fault detection methods are mainly used. Although fault datasets accumulate during machine operation, it is not straightforward to utilize the information it contains for fault detection after the deep learning model has been trained in an unsupervised manner. However, the information in fault datasets is expected to significantly contribute to fault detection. In this regard, this study aims to validate the effectiveness of the transition from unsupervised to supervised learning as fault datasets gradually accumulate through continuous machine operation. We also focus on experimentally analyzing how changes in the learning paradigm of the deep learning model and the output representation affect fault detection performance. The results demonstrate that, with a small number of fault datasets, a supervised model with continuous outputs as a regression problem showed better fault detection performance than the original model with one-hot encoded outputs (as a classification problem).
Republic of Korea is building a multi-layered missile defense system against North Korea’s growing ballistic missile threat. To maximize the intercept performance of a multi-layered missile defense system, it is important to develop an efficient engagement plan that considers the interceptable time/space of each interceptor system for ballistic missiles. To do so, it is necessary to predict the flight trajectory of the ballistic missile, which must be done within a short time considering the short battlefield environment and the speed of the ballistic missile. This study presents a model for rapid trajectory prediction of ballistic missiles using the kinetic characteristics of each flight phase(thrust phase, midcourse phase, and re-entry phase) of ballistic missiles, a method for estimating kinetic information from ballistic missile observation data(time and position), and a mathematical analysis of the equations of motion of ballistic missiles.
Nitrogen fertilizers are generally known to be of great help in improving crop yields, but excessive nitrogen fertilizer usage can not only destroy the environment but also negatively affect crop growth. This study aims to develop a decision-making system for optimal nitrogen fertilizer use for efficient production of Chinese cabbage (Brassica rapa), one of the major vegetables. The proposed system has the functions of detecting farmland based on satellite images, predicting cabbage yields and greenhouse gas (e.g., nitrous oxide) emissions according to nitrogen fertilizer use, and making decisions using the prediction results. To develop the proposed system, a generalized prediction model is developed using experimental data collected from South Korea, Egypt, India, Canada, Lithuania, and China, and the effectiveness of the proposed system is validated through experiments. As a result, the proposed system will enable farmers to conduct eco-friendly agricultural activities through appropriate nitrogen fertilizer use while stably maximizing productivity of Chinese cabbages.
This study proposes a weighted ensemble deep learning framework for accurately predicting the State of Health (SOH) of lithium-ion batteries. Three distinct model architectures—CNN-LSTM, Transformer-LSTM, and CEEMDAN-BiGRU—are combined using a normalized inverse RMSE-based weighting scheme to enhance predictive performance. Unlike conventional approaches using fixed hyperparameter settings, this study employs Bayesian Optimization via Optuna to automatically tune key hyperparameters such as time steps (range: 10-35) and hidden units (range: 32-128). To ensure robustness and reproducibility, ten independent runs were conducted with different random seeds. Experimental evaluations were performed using the NASA Ames B0047 cell discharge dataset. The ensemble model achieved an average RMSE of 0.01381 with a standard deviation of ±0.00190, outperforming the best single model (CEEMDAN-BiGRU, average RMSE: 0.01487) in both accuracy and stability. Additionally, the ensemble's average inference time of 3.83 seconds demonstrates its practical feasibility for real-time Battery Management System (BMS) integration. The proposed framework effectively leverages complementary model characteristics and automated optimization strategies to provide accurate and stable SOH predictions for lithium-ion batteries.
This study investigates the impact of perpetual swaps on structural complexity and market efficiency within cryptocurrency markets. Utilizing 15-minute interval price data from 35 cryptocurrencies, we employ multifractal detrended fluctuation analysis (MF-DFA), Multifractal-based measure of the degree of market efficiency (MED), and Market deficiency measure (MDM) to comparatively evaluate market characteristics before and after the introduction of perpetual swaps. Our empirical analysis reveals a substantial decrease in multifractality and structural complexity across most cryptocurrencies post-introduction, particularly pronounced over longer horizons (4–6 months). This reduction indicates enhanced information dissemination and more efficient price formation mechanisms. Notably, Bitcoin (BTC), benefiting from superior liquidity and efficient information flow, exhibited relatively stable multifractal characteristics, although significant volatility driven by fat-tail distributions remained persistent. Statistically significant improvements in market efficiency were consistently demonstrated via paired t-tests, one-sided t-tests, and Wilcoxon non-parametric tests. These improvements were particularly salient during extended observation periods, providing robust empirical evidence that perpetual swaps markedly enhance market efficiency. Consequently, our findings highlight that the introduction of perpetual swaps contributes meaningfully to cryptocurrency market efficiency beyond mere liquidity enhancement, promoting more accurate price discovery and reducing informational asymmetries.
Anomaly detection technique for the Unmanned Aerial Vehicles (UAVs) is one of the important techniques for ensuring airframe stability. There have been many researches on anomaly detection techniques using deep learning. However, most of research on the anomaly detection techniques are not consider the limited computational processing power and available energy of UAVs. Deep learning model convert to the model compression has significant advantages in terms of computational and energy efficiency for machine learning and deep learning. Therefore, this paper suggests a real-time anomaly detection model for the UAVs, achieved through model compression. The suggested anomaly detection model has three main layers which are a convolutional neural network (CNN) layer, a long short-term memory model (LSTM) layer, and an autoencoder (AE) layer. The suggested anomaly detection model undergoes model compression to increase computational efficiency. The model compression has same level of accuracy to that of the original model while reducing computational processing time of the UAVs. The proposed model can increase the stability of UAVs from a software perspective and is expected to contribute to improving UAVs efficiency through increased available computational capacity from a hardware perspective.
Ensuring operational safety and reliability in Unmanned Aerial Vehicles (UAVs) necessitates advanced onboard fault detection. This paper presents a novel, mobility-aware multi-sensor health monitoring framework, uniquely fusing visual (camera) and vibration (IMU) data for enhanced near real-time inference of rotor and structural faults. Our approach is tailored for resource-constrained flight controllers (e.g., Pixhawk) without auxiliary hardware, utilizing standard flight logs. Validated on a 40 kg-class UAV with induced rotor damage (10% blade loss) over 100+ minutes of flight, the system demonstrated strong performance: a Multi-Layer Perceptron (MLP) achieved an RMSE of 0.1414 and R² of 0.92 for rotor imbalance, while a Convolutional Neural Network (CNN) detected visual anomalies. Significantly, incorporating UAV mobility context reduced false positives by over 30%. This work demonstrates a practical pathway to deploying sophisticated, lightweight diagnostic models on standard UAV hardware, supporting real-time onboard fault inference and paving the way for more autonomous and resilient health-aware aerial systems.
Vertical takeoff and landing (VTOL) drones are increasingly recognized as an important solution for last-mile delivery in the food and beverage sector, owing to their rapid deployment capabilities and high operational flexibility. In particular, growing interest in drone delivery services has been observed among fast food and coffee franchises, where rapid delivery is essential due to the time-sensitive nature of food and beverage items intended for immediate consumption. Despite this trend, there remains a lack of research on the structural modeling of flight routes for VTOL drones operating under automatic flight conditions, and on the implementation of first-come-first-served (FCFS) delivery services utilizing predefined flight routes. Accordingly, this study comprehensively describes the operations for food and beverage delivery services using VTOL drones. In particular, it addressed the use of multiple drones to conduct FCFS-type multi-point delivery services along fixed routes suitable for automatic flight.
The expansion of online retail markets has driven the development of personalized product recommendation services leveraging platform-based product and customer data. Large retailers have implemented seller-oriented recommendation systems, where AI analyzes POS sales data to identify similar stores and recommend products not yet introduced but successful elsewhere. However, small and medium-sized retailers face challenges in adapting to rapidly evolving online market trends due to limited resources. This study proposes a recommendation algorithm tailored for small-scale retailers using sales data from an online shopping mall. We analyzed 600,000 transaction records from 13,607 sellers and 95,938 products, focusing on Beauty Supplies, Kitchenware, and Cleaning Supplies categories. Three algorithms—Attentional Factorization Machines (AFM), Deep Factorization Machines (DeepFM), and Neural Collaborative Filtering (NCF)—were applied to recommend top 10% weekly sales items, with an ensemble model integrating their strengths. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was employed, and performance was evaluated using AUC, Accuracy, Precision, and Recall metrics on separate training and test datasets. The ensemble model outperformed individual models across all metrics, while DeepFM excelled in Precision. These findings demonstrate that ensemble-based recommendation algorithms enhance recommendation accuracy for suppliers in large-scale online retail environments, offering practical implications for small-scale retailers.
In this paper, a water rescue mission system was developed for water safety management areas by utilizing unmanned mobility( drone systems) and AI-based visual recognition technology to enable automatic detection and localization of drowning persons, allowing timely response within the golden time. First, we detected suspected human subjects in daytime and nighttime videos, then estimated human skeleton-based poses to extract human features and patterns using LSTM models. After detecting the drowning person, we proposed an algorithm to obtain accurate GPS location information of the drowning person for rescue activities. In our experimental results, the accuracy of the Drown detection rate is 80.1% as F1-Score, and the average error of position estimation is about 0.29 meters.
This study investigates a vision-based autonomous landing algorithm using a VTOL-type UAV. VTOL (Vertical Take-Off and Landing) UAVs are hybrid systems that combine the forward flight capability of fixed-wing aircraft with the vertical take-off and landing functionality of multirotors, making them increasingly popular in drone-based industrial applications. Due to the complexity of control during the transition from multirotor mode to fixed-wing mode, many companies rely on commercial software such as ArduPilot. However, when using ArduPilot as-is, the software does not support the velocity-based GUIDED commands commonly used in multirotor systems for vision-based landing. Additionally, the GUIDED mode in VTOL software is designed primarily for fixed-wing operations, meaning its control logic must be modified to enable position-based control in multirotor mode. In this study, we modified the control software to support vision-based landing using a VTOL UAV and validated the proposed algorithm in simulation using GAZEBO. The approach was further verified through real-world experiments using actual hardware.