Jurnal Optimasi Sistem Industri

Physiological Signals as Predictors of Mental Workload: Evaluating Single Classifier and Ensemble Learning Models

2024-01-02T10:27:56+07:00

With a growing emphasis on cognitive processing in occupational tasks and the prevalence of wearable sensing devices, understanding and managing mental workload has broad implications for safety, efficiency, and well-being. This study aims to develop machine learning (ML) models for predicting mental workload using Heart Rate Variability (HRV) as a representation of the Autonomic Nervous System (ANS) physiological signals. A laboratory experiment, involving 34 participants, was conducted to collect datasets. All participants were measured during baseline, two cognitive tests, and recovery, which were further separated into binary classes (rest vs workload). A comprehensive evaluation was conducted on several ML algorithms, including both single (Support Vector Machine/SVM and Naïve Bayes) and ensemble learning (Gradient Boost and AdaBoost) classifiers and incorporating selected features and validation approaches. The findings indicate that most HRV features differ significantly during periods of mental workload compared to rest phases. The SVM classifier with knowledge domain selection and leave-one-out cross-validation technique is the best model (68.385). These findings highlight the potential to predict mental workload through interpretable features and individualized approaches even with a relatively simple model. The study contributes not only to the creation of a new dataset for specific populations (such as Indonesia) but also to the potential implications for maintaining human cognitive capabilities. It represents a further step toward the development of a mental workload recognition system, with the potential to improve decision-making where cognitive readiness is limited and human error is increased.

Optimizing Surface Finish and Dimensional Accuracy in 3D Printed Free-Form Objects

2024-01-02T10:27:47+07:00

3D printing of free-form objects presents inherent complexity due to their organic and intricate shapes. Designers engage with such objects, considering a range of factors including aesthetics, engineering viability, and ergonomic comfort. This research is focused on achieving the most effective printing parameters for a free-form object utilizing the Digital Light Processing (DLP) technique within a 3D printer. Within this study, a squeezed hexagonal tube-shaped CAD model was employed as an experimental subject, following the principles of the Response Surface Method (RSM). The research delved into the optimization of printing parameters, particularly layer thickness and exposure time, to enhance the dimensional accuracy and surface quality of the free-form model. Two levels were established for each factor: layer thickness was set at 0.06 mm (low) and 0.08 mm (high), while exposure time was tested at 6 s (low) and 8 s (high). The assessment of surface quality involved a qualitative evaluation employing a digital microscope to identify potential defects and imperfections in the print outcomes. The investigation culminated in the identification of the optimal printing parameters: a layer thickness of 0.0753 mm and an exposure time of 7.2143 seconds. This achievement not only enhances the understanding of 3D printing variables in the context of intricate free-form models but also contributes to the broader field of additive manufacturing parameter optimization.

Dynamic Scoring and Costing in the Orienteering Problem: A Model Based on Length of Stay

2024-01-02T10:28:05+07:00

In today's travel and tourism landscape, the role of travel agents has become increasingly complex as they are challenged to explore a variety of potential destinations. More specifically, the complicated task of planning itineraries that truly satisfy travellers puts travel agents in a crucial role, increasing the complexity of itinerary planning. This complexity is compounded not only by the multitude of possible destinations, but also by non-negotiable constraints such as cost and time. To address these challenges, the orienteering problem represents a fundamental mathematical model that provides a theoretical basis for understanding the nuanced difficulties faced by travel agents.This study ventures into a novel iteration of the orienteering problem, with a particular focus on optimizing travel satisfaction based on length of stay. A notable aspect of this variant is the inclusion of time and cost constraints in the route determination process. Using an integer programming model, the satisfaction scores for each location are described by a diminishing returns function linked to length of stay, while the costs associated with each location follow a linear function influenced by the same parameter. The application of this model is in a hypothetical scenario with 32 nodes, with the calculations facilitated by the FilMINT solver. A sensitivity analysis examines time and cost constraints and shows their decisive influence on the optimization of travel routes. The results of this research contribute significantly to a strategic framework and provide travel agencies with the opportunity to create itineraries that not only meet practical limits but, more importantly, increase traveller satisfaction.

AVOA and ALO Algorithm for Energy-Efficient No-Idle Permutation Flow Shop Scheduling Problem: A Comparison Study

2024-01-02T10:28:13+07:00

Global energy consumption is a pressing issue and is predicted to continue increasing between 2010 and 2040. Among the various sectors, the industrial sector, particularly manufacturing, is the main driver of this increase. To effectively address this growing problem and support energy conservation efforts, reducing idle time on production-related machines is critical. The No-Idle Permutation Flow Shop Problem (NIPFSP) and, indirectly, the need to reduce energy consumption in manufacturing processes are the driving forces behind this study. The African Vultures Optimization Algorithm (AVOA) and the Ant Lion Optimizer (ALO) are two novel meta-heuristic algorithms designed to achieve this goal. The effectiveness of both AVOA and ALO was rigorously evaluated across three distinct scenarios: small, medium, and large. Statistical analysis, in the form of independent sample t-tests, was employed to compare the performance of these algorithms. We found that, while both algorithms yielded similar results in the small case, AVOA demonstrated a superior capability in optimizing the NIPFSP in the medium and large cases and, consequently, in curbing energy consumption. This implies that AVOA offers a more promising approach to addressing energy consumption concerns in the manufacturing sector, particularly in scenarios involving medium- to large-scale production processes. The implementation of such innovative meta-heuristic algorithms holds the potential to significantly contribute to global energy conservation efforts while enhancing the efficiency of industrial operations.

An integrated Optimization Model of Product Mix, Assortment Packing, and Distribution in A Fashion Footwear Company

2024-01-02T10:28:00+07:00

Recognizing the paramount importance of operational effectiveness and resource management in supply chain management (SCM) of the fashion industry, this study addresses a specific challenge faced by a prominent Indonesian fashion footwear company. The inefficiency is due to repetitive sorting and packaging processes during product distribution, which significantly impact optimal production mixes and product distribution from the distribution center to the point of sale. A crucial aspect is also the optimization of the delivery route. To address these challenges and minimize the total cost of ownership, the study proposes an integrated optimization model. This model simultaneously determines the optimal production quantity, assortment packaging, and distribution channels, taking into account decision variables related to distribution in configuration boxes, overload and underload products, as well as production numbers that respond to store-specific demand fluctuations. A notable contribution of this research is the integration of product mix decisions into the assortment packaging and distribution model, which represents a novel approach. The optimal solution determined using the LINGO 18.0 software highlights the significant influence of product penalty costs and product demand parameters on the objective function, while shipping costs have no noticeable influence. By emphasizing the integration of product mix decisions into the optimization framework, this research contributes significantly to improving the understanding and practical application of efficient supply chain management in the fashion industry.

Eye Tracking-based Analysis of Customer Interest on The Effectiveness of Eco-friendly Product Advertising Content

2024-01-02T10:27:51+07:00

Amid the escalating environmental crisis that has prompted consumers to adopt eco-friendly lifestyles, the popularity of eco-friendly personal care products is increasing significantly. Nevertheless, marketing these products presents challenges that include inadequate product information, perceived unaffordable prices, and relatively low consumer trust. These challenges present an opportunity for the marketing field to increase consumer interest, particularly through advertising, an important medium for disseminating product information. Recognizing the importance of advertising components in influencing consumer preferences, this study uses eye-tracking to identify critical elements in promoting eco-friendly personal care products. The components examined include information on environmental and personal benefits, the presence or absence of price information, and the presentation of an environmental label (logo and text) in advertising. Each of the 43 participants is confronted with eight carefully crafted advertising stimuli. The results of the study highlight the significant influence of clear benefits and price information on consumer preferences, while indicating that eco-label display does not have a significant impact on consumer preference. This research is intended to serve as a source of actionable marketing strategies and is intended to help promote eco-friendly products and increase consumer interest through targeted and effective advertising.

Synergizing IFTOPSIS and DEA for Enhanced Efficiency Analysis in Inpatient Units

2024-01-02T10:27:44+07:00

The pursuit of efficiency in the business sector is a multifaceted endeavor, extending beyond mere cost reduction to encompass a strategic optimization of operational performance. The enhancement of efficiency is not solely for the benefit of investors or proprietors but is also a concerted effort to maximize resource utilization and minimize waste. This study introduces an integrative approach combining IFTOPSIS and DEA methodologies to deliver a robust efficiency evaluation framework.The fusion of IFTOPSIS's qualitative analysis with DEA's quantitative assessments addresses the complexity of operational performance, providing a balanced evaluation that transcends subjective bias with data-driven insights. IFTOPSIS articulates decision-makers' preferences in uncertain scenarios, assigning weights to criteria, while DEA discriminates between efficient and inefficient operational units. This confluence of methods is applied to the assessment of inpatient healthcare units—a sector that has traditionally relied on patient-centric evaluations, neglecting the comprehensive review of resource deployment. The results of this amalgamated approach reveal dimensions of operational efficiency previously unexplored, offering stakeholders a data-enriched foundation for strategic decision-making. The study's findings have significant implications for the healthcare industry, providing a template for resource evaluation that could inform policy and drive improvements in patient care services.

Innovative Multi-Criteria Decision-Making Approach for Supplier Evaluation: Combining TLF, Fuzzy BWM, and VIKOR

2024-01-02T10:27:14+07:00

When confronted with underperforming suppliers, the need to evaluate and improve supplier performance becomes apparent. However, the inherent inaccuracies in information introduce complexity, especially when subjective human judgment is involved in the supplier evaluation process. Associated with such problem, this study presents a novel methodology for supplier performance evaluation in the crumb rubber industry, integrating the Taguchi Loss Function (TLF), fuzzy Best-Worst Method (BWM), and VIKOR technique in group decision-making environment. Aimed at addressing the challenges in industries with variable supplier quality and performance, such as the crumb rubber industry in Indonesia, the methodology was empirically tested to demonstrate its practical utility. The process involved identifying evaluation criteria through literature review tailored to the needs of decision makers (DMs), applying TLF to quantify losses from supplier performance deviations, using fuzzy BWM to determine criteria weights based on the DMs judgment, and employing the VIKOR technique for comprehensive supplier ranking. The findings underscore the methodology's effectiveness in enhancing decision-making, offering a unified metric that accommodates diverse criteria and balances precise data with subjective assessments. This approach simplifies the evaluation process, particularly in situations with conflicting interests among decision-makers. Demonstrating its practical application in the crumb rubber industry, the study highlights the methodology's potential for broader industrial applicability. Future research could explore comparative analyses with other analytical methods, further establishing the methodology's robustness and adaptability in different management contexts.

Enhancing Quality Control of Packaging Product: A Six Sigma and Data Mining Approach

2024-01-02T10:28:09+07:00

Six Sigma is of paramount importance to organizations as it provides a structured and data-driven approach, fostering continuous improvement, minimizing defects, and optimizing processes to meet and exceed customer expectations. In response to the increasing defects of packaging product in a cosmetics industry in Indonesia, surpassing the speciﬁed 3% tolerance limit, this research conducts a thorough investigation into the root causes, corrective measures, and improvement proposals to elevate product quality. By leveraging the Six Sigma method and data mining techniques, the study systematically addresses the complexities associated with defect reduction in packaging for cosmetics product. The research methodology encompasses deﬁning the problem through SIPOC and Critical to Quality (CTQ) diagrams, measuring via control charts and sigma level calculations, and analyzing using tools like pareto diagrams, Apriori algorithms, ﬁshbone diagrams, and Fault Mode and Eﬀect Analysis (FMEA). Key ﬁndings reveal a notable correlation between spot defects and varying colors, leading to pearl defects as identiﬁed by the Apriori algorithm. FMEA identiﬁes critical failures, including suboptimal printing plate conditions, clumpy ink usage, and insuﬃcient operator attention to ink ﬁlling. The improvement stage proposes practical solutions, such as implementing alarms and buzzers, color-indicator-adjusted ink storage labels, and a structured form for cleaning and monitoring printing plates. These ﬁndings carry signiﬁcant implications, providing a tailored roadmap for enhancing the quality of cosmetic packaging. The anticipated implementation of proposed improvements aims to elevate customer satisfaction by addressing speciﬁc pain points in the production process. Furthermore, the research contributes valuable insights to the broader cosmetics industry, oﬀering eﬀective methodologies for defect reduction and quality enhancement in packaging processes.

Technical Evaluation and Financial Analysis of a Retrofitting Investment Project for Production Machinery in a Cement Plant

2024-01-02T10:28:17+07:00

In today's rapidly evolving industrial landscape, businesses are increasingly challenged to strike a balance between enhancing productivity and maintaining product quality. Company X, a renowned cement manufacturer in Indonesia, relies heavily on four key raw materials, among which clay is particularly crucial for the raw mix. Recent trends have shown a decrease in the Al2O3 composition of clay, necessitating adjustments in clay capacity to uphold quality standards. A thorough technical evaluation of the plant highlighted that a significant number of critical machines, totaling 17, were operating with mechanical availability below the desired threshold. Additionally, a utility analysis pinpointed a shortfall in meeting the required clay tonnage, leading to the identification of machines that would benefit from retrofitting. The financial implications of this initiative were substantial, with the initial investment for the upgrades and subsequent operational costs in the first year being considerable. Yet, this expenditure was offset by a notable profit in the first year post-retrofitting. Key financial metrics further underscored the project's viability: a highly favorable Net Present Value (NPV), an impressive Internal Rate of Return (IRR), a rapid Payback Period (PP), and a significant Profitability Index (PI). These parameters, derived from an exhaustive analysis, clearly support the strategic decision to invest in retrofitting the production machinery at Company X's cement plant, illustrating the project's feasibility and the prospective benefits of this investment.