Penelitian ini bertujuan untuk mengevaluasi faktor yang memengaruhi kualitas shoe last (cetakan sepatu) di Industri Kecil dan Menengah (IKM) persepatuan dilihat dari ukuran (penomoran) dan bentuk shoe last tersebut. Produk sepatu dituntut memiliki kenyamanan sebagai salah satu aspek penting dalam perancangannya. Aspek kenyaman ditentukan oleh ukuran dan bentuk shoe last yang dipengaruhi oleh kualitas ketepatan ukuran dan bentuk master shoe last-nya. Kualitas ukuran dan bentuk shoe last belum dilihat sebagai salah satu aspek penting oleh pengrajin di IKM persepatuan. Umumnya mereka lebih mengutamakan aspek modelnya saja yang lebih diprioritaskan. Oleh karena itu, terdapat ketidakseragaman ukuran dalam penomoran sepatu dan ketidaksesuaian ukuran sepatu dengan standar ukuran pada sistem mondopoint maupun Eropa yang dibuat oleh para produsen. Selain itu, terjadi juga kesalahan proses pembentukan pada tahapan perancangan master shoe last. Perubahan bentuk kaki (punggung kaki/ lengkung kaki/ dan tumit) pada saat menggunakan sepatu/sandal dan high heel, kurang diperhatikan oleh para pembuat master shoe last sehingga bentuk yang dihasilkan tidak sesuai dengan karakter kaki pengguna, khususnya orang Indonesia. Hal penting lainnya yang harus diperhatikan dalam pembuatan master shoe last, terdapat pada bentuk bagian toe-box dan back counter. Hasil penelitian ini adalah dihasilkannya sebuah prototype master shoe last untuk jenis sepatu high heel, yang telah disesuaikan dengan antropometri kaki dan karakteristik kaki orang Indonesia.

Previous research has elucidated the prediction of human errors through the integration of eye tracking and machine learning methods.  However, work-related stress can directly influence human errors due to the environment and job demands. In addition, the methods applied in previous studies were limited to computer-based tasks only. This research utilizes direct measurements of the human body and the environment, thereby not being limited to specific types of work only. The aim of this study is to develop a predictive model for human error occurrence due to stress based on the work environment and job demands, using a classification algorithm approach in machine learning. Machine learning algorithms such as Random Forests and Decision Trees are applied to classify the occurrence of human errors. The research process begins with collecting a dataset, data preprocessing, modeling, and evaluation. The results show that both algorithms achieve a model accuracy of > 90%. However, the Random Forest algorithm exhibits the highest accuracy and recall compared to the Decision Tree algorithm. Therefore, this research recommends the use of the Random Forest algorithm for modeling human error prediction.   Keywords: Stress, Work Environment, Job Demand, Human Error, Machine Learning

A shift in lifestyle during COVID-19 pandemic affects daily conditions, including sleep condition. During pandemic, humans have plenty of time to rest by the virtue of eliminating commuting time for daily activities, therefore changing the sleeping pattern in society, including for students. Students from academic year 2020 are the first to experience online classes, but since Semester 1 of 2022/2023 academic year ITENAS are going back to normal, on-site class activities. This condition reverted the lifestyle shaped over the past two years, affecting cognitive function because one of the supporting factors of cognitive function is sleep quality. Data from ITENAS Academic Bureau showed 48% of students from 2020 suffered decline in GPA index during the first semester of 2022/2023 academic period. In this research the sleep quality of students will be studied using Pittsburgh Sleep Quality Index (PSQI), while cognitive capabilities will be observed through Cognitive Failure Questionnaire (CFQ) with special attention for student’s GPA index. From 97 students sampled for this research, there is an increase of students having bad sleeping quality at the start, during, and at the end of semester, with average percentage during all 3 periods at 89.69% of students with bad sleep quality. The number of students with high cognitive capabilities is increasing from the start, during, and after the end of semester, therefore there is no correlation between sleep quality and cognitive capabilities (p>0.05), as well as between sleep quality and academic achievement and between cognitive capabilities and academic achievement. Despite differences in sleep quality between students from Faculty of Industrial Engineering, Faculty of Civil Engineering and Planning, and Faculty of Architecture and Design, no apparent differences in cognitive capabilities and academic achievements to be observed.

A shift in lifestyle during COVID-19 pandemic affects daily conditions, including sleep condition. During pandemic, humans have plenty of time to rest by the virtue of eliminating commuting time for daily activities, therefore changing the sleeping pattern in society, including for students. Students from academic year 2020 are the first to experience online classes, but since Semester 1 of 2022/2023 academic year ITENAS are going back to normal, on-site class activities. This condition reverted the lifestyle shaped over the past two years, affecting cognitive function because one of the supporting factors of cognitive function is sleep quality. Data from ITENAS Academic Bureau showed 48% of students from 2020 suffered decline in GPA index during the first semester of 2022/2023 academic period. In this research the sleep quality of students will be studied using Pittsburgh Sleep Quality Index (PSQI), while cognitive capabilities will be observed through Cognitive Failure Questionnaire (CFQ) with special attention for student’s GPA index. From 97 students sampled for this research, there is an increase of students having bad sleeping quality at the start, during, and at the end of semester, with average percentage during all 3 periods at 89.69% of students with bad sleep quality. The number of students with high cognitive capabilities is increasing from the start, during, and after the end of semester, therefore there is no correlation between sleep quality and cognitive capabilities (p>0.05), as well as between sleep quality and academic achievement and between cognitive capabilities and academic achievement. Despite differences in sleep quality between students from Faculty of Industrial Engineering, Faculty of Civil Engineering and Planning, and Faculty of Architecture and Design, no apparent differences in cognitive capabilities and academic achievements to be observed.

When a person is exposed to a prolonged workload, he/she enters a fatigue phase, the indication is the decline of cognitive performance that leading to human error. As an integral part of a system, human contributes to system reliability; therefore, it plays an important role in potential failure. Those, it is necessary to investigate how human reliability relates to physical workload rate, in order to predict maximum work duration to eliminate potential failure. A physical experiment involving 20 participants was conducted to generate medium workload, followed by Stroop test to observe selective attention and cognitive control as a form of cognitive performance. The physical workload was observed through energy expenditure and oxygen consumption during physical activity, and cognitive performance through response error time on the Stroop test. The usage of Weibull distribution was aimed to obtain reliabilities for each participant. There was a decline in reliability for all participants from one test to the other. Based on scale and form parameters, the prediction of resting time was based on mean time to human error (MTTHE), and from this experiment, varied MTTHE from each participant were obtained. The variation was created by differences in physical performance, cognitive capabilities, and other contributing factors such as environment and time of the implementation of the experiment. From this research, it was evident that human reliability can be utilized to predict potential failure in humans, which then implies a preventive action is necessitated to prevent failure from manifesting in the shape of taking a break/rest or reducing work rhythm. The application of human reliability in human resource management can be directed towards fatigue management and operator-related operational management.

Purpose: This research aims to design a model of quality prediction system using data mining methods in the software-as-a-service (Saas) environment in order to facilitate manufacturers to be able to analyse process and product quality without software investment. Methodology/Approach: To develop the quality prediction model, this study utilized a data mining methodology to extract knowledge from historical data collected from the offset printing industry, focusing on manufacturing parameters. Four classification algorithms (Decision Tree, k-NN, Naive Bayes, Random Tree) were employed and compared to identify the most precise model specifically tailored for offset printing. Subsequently, the prediction model was integrated into a web-based system to enable quality prediction. Findings: This study demonstrates practicality of integrating quality prediction into the SaaS framework, specifically for offset printing. This integration is designed to predict how manufacturing control parameters, such as printing slope angle, engine temperature, paper size, ink density, and roller speed, relate to the occurrence of product defects such as crumpled paper and imprecise printing. Research Limitation/implication: Generalizability is constrained by its focus on the offset printing industry, and prediction accuracy relies on historical data, which can vary across manufacturing sectors, affecting model performance. Originality/Value of paper: This article presents the concept and practical implementation of utilizing data mining in a SaaS environment to enhance the quality of manufacturing, with a particular emphasis on the offset printing sector.

Since the issue of productivity is increased, Industry 4.0 also promotes the issue of quality of product, processes, and services. However, studies show that recent quality initiatives are still facing the old problem and companies cannot get benefit from industry 4.0 environment to establish better quality. This paper proposes a framework of Cloud-based Quality Analyzer (CQA) which is designed specifically to perform quality analysis by reducing the dependency to the human quality engineer with respect to faster and more accurate information. Equipped by the standard quality analysis tools and some data mining algorithms, CQA can perform a wide-range quality-related activity from simple analysis to fully automated feedback loop quality control. Moreover, by adopting Cyber Physical System (CPS) technology, CQA is also expected to be able to realize real-time online quality control. However, since this is a conceptual framework, many technical details related to the data flow, configurability, security, the quality of service, connectivity and network aspect are still required for further investigation. From a quality engineering point of view, quality analysis techniques, data modeling, formal procedure of quality analysis, and more advanced data mining algorithms for extracting quality-related information are open for further research.

Assessing the production process primarily revolves around quality. When dealing with a basic manufacturing process, quality can be easily anticipated. However, as manufacturing processes grow in complexity, it has been discovered through prior studies that directly predicting the quality of an intricate production system becomes challenging. This is due to the interdependency between each stage of manufacturing, where the outcomes of preceding stages impact subsequent processes. To address this issue, the Cascade Quality Prediction Method (CQPM) was developed. However, as this method employed a classification algorithm, CQPM cannot be directly applied when dealing with datasets that lack target variables for prediction or when the distribution of classes is imbalanced. This study aimed to improve the effectiveness of the CQPM in the context of multistage manufacturing. To achieve this, Hotelling’s T2 and the Synthetic Minority Over-sampling Technique (SMOTE) algorithm were incorporated during the data preparation phase, especially when dealing with imbalanced class distributions and missing target variables. The results demonstrated that the inclusion of Hotelling’s T2 allowed for the application of classification algorithms. By combining the CQPM approach with a random forest classifier and the SMOTE algorithm, notable improvements were observed in the model’s performance. The enhanced data pre-processing techniques led to impressive metric values, including 99.95% accuracy, 93.75% G-Mean, and 96.76% F-Measure. These findings indicate the potential of the proposed model framework to accurately predict quality in multistage manufacturing systems.

The heterogeneous fixed fleet vehicle routing problem (HFFVRP) is investigated using the variable neighborhood search (VNS). The initial solution is generated using the Sweep algorithm and the 2-opt procedure and then the customers are allocated to the smallest vehicle first by considering vehicle occupancy level. The proposed VNS algorithm uses several neighborhoods and a number of local search methods which are adapted for this problem. The local searches are implemented within a multi-level framework. The performance of the proposed algorithm is then tested using data set taken from literature and the experiments show competitive results with less computing time. Future research directions are also highlighted.  

The heterogeneous fleet vehicle routing problem is investigated using some adaptations of the variable neighborhood search (VNS). The initial solution is obtained by Dijkstra’s algorithm based on a cost network constructed by the sweep algorithm and the 2-opt. Our VNS algorithm uses several neighborhoods which are adapted for this problem. In addition, a number of local search methods together with a diversification procedure are used. Two VNS variants, which differ in the order the diversification and Dijkstra’s algorithm are used, are implemented. Both variants appear to be competitive and produce new best results when tested on the data sets from the literature. We also constructed larger data sets for which benchmarking results are provided for future comparison.

The multi-depot fleet size and mix vehicle routing problem, also known as the multi-depot routing with heterogeneous vehicles, is investigated. A mathematical formulation is given and lower as well as upper bounds are produced using a three hour execution time of CPLEX. An efficient implementation of variable neighborhood search that incorporates new features in addition to the adaptation of several existing neighborhoods and local search operators is proposed. These features include a preprocessing scheme for identifying borderline customers, a mechanism that aggregates and disaggregates routes between depots, and a neighborhood reduction test that saves nearly 80% of the CPU time, especially on the large instances. The proposed algorithm is highly competitive as it produces 23 new best results when tested on the 26 data instances published in the literature.