FoITIC

Electrical Properties Research of PA6 Low Warp Composite Material Using Selected Machine Learning Method

Lukáš Vacho — 2026-02-12

This paper focuses on the study of the electrical properties of PA6 Low Warp material using Artificial Neural Network model. The model classifies the material samples into a given class depending on the time of exposure of the material to increased temperature according to the input electrical properties and the mechanical properties of the material in tension. For the neural network models tested, the primary effectiveness of the ReLu and Tanh activation functions to classify a sample into a given class for a given time interval at an increased environment temperature of 180 °C was examined. The highest classification accuracy of 82.46% was obtained for the model using the Tanh activation function. The results show that in researching the physical properties of engineering materials used in 3D printing using artificial neural networks allows to predict the response of material properties under certain initial ambient conditions.

Assessment of CO₂ Purity and Recovery in Absorption from Natural Gas Wells

Vibianti Dwi Pratiwi — 2026-02-12

One potential technology to mitigate emissions is Carbon Capture and Storage (CCS) technology. Carbon capture and purification technology is one of the key requirements in the CCSU system, which necessitates a high level of CO2 purity as a raw material for production. In utilizing CO2, different CO2 capture technologies are required to achieve the required purity according to utility standards. Absorption technology is one of the most common and effective methods. In this study, absorption technology was used to capture carbon from gas wells with different concentrations of 10%, 20%, 30%, and 40%. Researchers analyzed the effectiveness of solvents in the CO2 gas absorption process from various CO2 concentrations simulated using Aspen Hysys V.15.0. The simulation results showed the highest purity obtained in the CO2 variation in the 40% feed at 86.58%. In comparison, the highest recovery was found in the CO2 variation of 30% at 99.85%. Although the recovery obtained was high, this study still requires review because the purity achieved was still below the CCUS requirement standard.

Indonesia's renewable energy transition opportunities

Nuha Desi Anggraeni — 2026-02-12

Indonesia, as the world’s largest archipelagic nation, holds vast renewable energy resources, including solar, wind, geothermal, hydro, and biomass. Despite an estimated potential exceeding 420 GW, deployment remains constrained by fossil fuel dependence, inadequate infrastructure, and uneven regional development. This paper develops a geospatial framework that integrates resource mapping with technical feasibility and region-specific strategies. Using data from national and international sources, thematic maps were created to identify renewable energy hotspots across Java-Bali, Sumatra, Kalimantan, Sulawesi, Nusa Tenggara, Papua, and Maluku. The analysis reveals that rooftop and floating PV are optimal for Java-Bali, hybrid microgrids for Nusa Tenggara and South Sulawesi, geothermal and hydropower expansion for Sumatra, biomass-to-energy for Kalimantan, and floating PV with community-based systems for Papua and Maluku. The novelty of this study lies in combining geospatial mapping with engineering feasibility considerations – such as storage integration, modular geothermal plants, and grid retrofitting – while also assessing risks and mitigation strategies. Furthermore, the discussion highlights the mechanical engineering implications of system design, including turbine optimization, thermal management, and advanced gasification technologies. This framework provides policymakers, engineers, and investors with a practical roadmap to accelerate Indonesia’s renewable energy transition toward energy security, sustainability, and socio-economic development

Deep Learning based Approach for Face Mask Detection

Divya Rani — 2026-02-12

The CRONA virus’s malady (COVID-19) which is an enormous family of distinctive infections have gotten to be exceptionally common, spreadable, infectious and perilous to the whole world of human kind. It transmits for the most part through nose and mouth if a tainted individual sniffle or hack which clears out beads of the infection on distinctive surface which is at that point breathed in by other individual, he too catches the disease as well. So, it has ended up exceptionally pivotal to secure ourselves and the individuals around us from this circumstance. We require to take safety measures such as keeping up social separating, washing hands each two hours, utilizing sanitizer, and the most vitally wearing a cover. To prevent the spread of virus, face mask is important and with face mask it is difficult to recognize face of human being with machine. The proposed method developed an approach of face mask detection based on deep learning approaches. Proposed approach encompasses with pre-trained models VGG16 and VGG19. The proposed model demonstrated on a real-world information set and tried with live video gushing. Higher the precision value of the demonstrated dataset with diverse hyper parameters and different individuals at distinctive has been performed. The results have been reported in the present manuscript.

Analysis of Playing Styles of NBA Players Using the K-Medoids Method

Kurnia Ramadhan Putra — 2026-02-12

The evolution of basketball in the NBA has shifted from traditional five-position roles to more flexible, skill-based playstyles. This study explores the classification of NBA players based on their individual performance metrics using the K-Medoids clustering method. Data from the 2015–2016 to 2024–2025 NBA seasons were collected and processed using the CRISP-DM framework. After data standardization and dimensionality reduction with PCA, the K-Medoids algorithm was applied to group players into distinct clusters. Evaluation using Davies-Bouldin Index (DBI) and Silhouette Score confirmed that a three-cluster configuration yielded the best cohesion and separation. The identified clusters reflect distinct roles such as elite scorers, defensive big men, and versatile contributors, providing valuable insights for team composition and strategy optimization.

Ergonomic Approach for Designing Water Therapy Handling Tool in a Veterinary Clinic

Maheiza Putra Sembadha — 2026-02-12

Praktek Dokter Hewan Bersama (PDHB) drh. Anton S.A.P has water therapy used for treating small animals up to 30 kg. Handling issues arose when paramedics treated larger animals, as the therapy activity triggered awkward postures that increased the risk of musculoskeletal disorders (MSDs) for the paramedics. This research aimed to design a handling aid for animals (patients) up to the size of a large dog. Based on direct observation and non-formal interviews with paramedics, the design process began with a Rapid Entire Body Assessment (REBA) to identify the ergonomic needs that would be used in the design process with Ergonomic Function Deployment. The selected design concept was the second concept (Ergonomic Semi-Electric Concept), where parts of the aid have an ergonomic shape and adjustable-sized equipment. Based on a simulation, the REBA evaluation of the design showed a decrease in the REBA score from 12 to 2.

Design of a personalized water intake monitoring system using rfid-enabled smart bottle station and mobile application with target intake estimation

Yusup Miftahuddin — 2026-02-12

Underhydration remains common, while existing digital and sensor-based tools still depend on manual entry, single-user wearables, or fixed profile-based targets, limiting practicality and adherence in shared or institutional settings. Recent smart-bottle systems automate volume capture, but they lack reliable multi-user identification and individualized targets, so scalable, low-burden monitoring remains unmet. This research address this by designing an RFID-enabled Smart Bottle Station that pairs a load cell with user identification, a Laravel backend, and an Android app, with two-way communication over REST and WebSocket for live status and control. Each interaction is logged with weight and timestamps, then filtered into valid drinking events using weight delta, temporal coherence, and scan pairing. In a four-month deployment with three participants, the system recorded 1,747 raw entries and retained 904 valid drinking events. Functional tests confirmed weight sensing, RFID identification, data synchronization, and remote commands. Results show that the platform accurately distinguishes real intake in a multi-user setting and supports personalized logging with minimal manual input. Across users, daily intake trends increased over time, indicating consistent engagement with the system and the practical feasibility of automated, shared-use hydration monitoring.

Visual Inspection and Hardness Test of Fatigue Damage in Shaft Latching of Slab Tong

Ringga Firmansyah — 2026-02-12

Visual inspection and hardness tests were conducted to investigate the fatigue failure of the shaft latching component on a slab tong used in a truck-mounted crane system. After nearly nine years of repetitive operation under dynamic loading, the shaft latching fractured during use. The fracture surface displayed typical signs of fatigue failure, such as smooth, shiny areas and semi-circular patterns, indicating progressive crack propagation over time. To complement the visual findings, a hardness test was performed using an Equotip 2 device. The purpose of this research is to know the type of damage that occurs in shaft latching. The result showed a surface hardness of 41 HRC, significantly below the recommended 60 HRC for components subjected to cyclic loads. Based on visual evidence and comparison with theoretical references, the failure was classified as unidirectional bending fatigue. The shaft material, AISI 4140 alloy steel, may have experienced decreased fatigue resistance due to insufficient hardness and prolonged exposure to cyclic stress. The fracture occurred at a high-stress bending region, and the absence of plastic deformation suggested a sudden break following gradual crack growth.

A Hybrid Jiang Conrath Product Recommendation System for E-commerce in The Case of Data Sparsity

Marisa Premitasari — 2026-02-12

Collaborative Filtering (CF) is commonly used in e-commerce recommendation systems, but it has limitations in cold-start conditions and data sparsity. This study implements the Hybrid Jiang-Conrath method to address these issues. This approach combines the semantic similarity of WordNet-based Jiang-Conrath Similarity (JCN) with the behavioral similarity of CF. JCN evaluates how conceptually similar the definitions of product categories were. Both approaches were combined using contribution values. The best contribution value across four datasets was α = 0.1 (10% CF, 90% JCN). The Hybrid model outperformed CF in the Industrial & Scientific dataset (MAE 0.64096, RMSE 0.88609). In contrast, the User-Based model achieved the lowest errors in Grocery & Gourmet (MAE 0.94661, RMSE 1.42904) and Video Games (MAE 0.04194, RMSE 0.04194). The Musical Instrument dataset showed comparable results between Item-Based (MAE 0.63247) and User-Based (RMSE = 1.05750) methods. Overall, the Hybrid model demonstrated better stability across diverse data sets. Compared to regular CF that offers only 31 products, hybrid Jiang-Conrath can generate more predictions for 65 product recommendations

Design of a Business Continuity Plan and Disaster Recovery Plan at UPT – TIK Based on the COBIT 2019 Assessment Result

Mira Musrini Barmawi — 2026-02-12

Information technology plays an important role in supporting academic and business operations in higher education institutions; however, its implementation also presents risks such as technical disruptions, natural disasters, and information security incidents that may affect finances, reputation, and business continuity. Therefore, it is necessary to evaluate IT governance to ensure alignment with organizational objectives. Data collection was carried out through literature review, interviews, direct observations, and questionnaires, which were analyzed using the COBIT 2019 Process Assessment Model (PAM) and Design Guide. The evaluation results show that the capability of domain DSS04 – Managed Continuity is at level 1 with an achievement of 51% (Largely Achieved) and a gap of two levels from the target, indicating the need for improvement in Managed Continuity. Based on these findings, a Business Continuity Plan (BCP) and Disaster Recovery Plan (DRP) were designed with reference to ISO 22301:2012, with risk identification conducted using the OCTAVE and FMEA methods. The analysis identified 17 risks with 37 business impact assessments, as well as the determination of MTD, RPO, and RTO along with strategies to mitigate the risks.

Influence of Evaporation Temperature on Palm Sugar Production via Atmospheric Evaporation Methods

Ronny Kurniawan — 2026-02-12

Palm sap (Arenga pinnata) represents an important raw material for Indonesia’s agro‑industrial sector, particularly for palm sugar production. However, conventional processing often relies on refined sugar and additives, resulting in inconsistent product quality. This study investigates direct palm‑sap crystallization under atmospheric evaporation to evaluate the influence of temperature (80, 90, 100, 110, and 120 °C) on product yield and physicochemical properties. The results show that increasing temperature enhances yield, reaching 16.11% at 120 °C, while moisture content decreases to 3.57%. Higher temperatures also lead to darker coloration and harder crystal texture. Ash content remains stable at approximately 1.5%. Reducing sugar levels increase with temperature, peaking at 13.91% at 110 °C, whereas sucrose content decreases significantly, with a minimum of 56.48% at 110 °C. Crystal size shows slight growth (1.28–1.33 mm), remaining within the SNI 3743:2021 limit. Overall, thermal conditions strongly influence sucrose inversion, sugar degradation pathways, and crystal formation behavior, highlighting the importance of temperature control in producing high‑quality palm sugar.

Bitcoin Price Volatility Prediction on Technical Indicators with GARCH and LSTM

Alzildan Abrar Rabbani — 2026-02-12

Bitcoin is one of the most volatile cryptocurrency assets, infl uenced by technical factors, market sentiment, and macroeconomic conditions. This high volatility poses both challenges in risk management and opportunities for market participants. This study aims to predict Bitcoin price volatility by developing a hybrid GARCH-LSTM model that combines the strengths of statistical approaches and deep learning. Historical Bitcoin data from June 2009 to June 2025 was collected through scraping from TradingView and enriched with seven technical indicators (SMA, EMA, RSI, Stochastic Oscillator, OBV, and MFI). Dimensionality reduction using PCA produced two principal components explaining 82.9% of the variance. Stationarity was confi rmed using the ADF test, while GARCH (1,2) was selected based on AIC and BIC criteria to capture short-term volatility patterns. GARCH outputs then integrated into LSTM to learn long-term non-linear patterns. Model performance was evaluated using MAE, RMSE, and MAPE. Results indicate that the hybrid GARCH (1,1)-LSTM model achieved the best performance, with MAE = 0.24981, RMSE = 0.39597, and MAPE = 7.8%, demonstrating high accuracy for highly volatile cryptocurrency data. Although long-term forecast accuracy declined, this model shows strong potential for applications in Value-at-Risk strategies, short-term trading decisions, and asset portfolio allocation. Future research is recommended to incorporate external variables such as market sentiment and macroeconomic factors to enhance adaptability to dynamic market conditions.

Raw Material Ordering Quantity for Wiring Harness Using Economic Order Quantity Method Considering Warehouse Capacity

Arie Desrianty — 2026-02-12

This research aims to determine the optimal ordering quantity of bus wiring harness raw materials by taking into account warehouse capacity constraints and procurement efficiency. The main challenges encountered by the company include stock shortages resulting from sudden demand increases and limited storage space, which consequently cause production delays and hinder the fulfilment of customer demand targets. The methodology applied involves the probabilistic Economic Order Quantity (EOQ) model to establish the optimal order quantity, in conjunction with the Lagrange Multiplier approach to facilitate the simultaneous ordering of various types of raw materials, thereby minimizing the total inventory cost. The data utilized in this study comprise historical demand, ordering cost, holding cost, warehouse capacity, and the targeted service level. The findings of this research are expected to reduce the risk of stock shortages, lower total inventory cost, and enhance the efficiency of production processes.

Overall Equipment Effectiveness and Autonomous Maintenance Methods in Manufacturing Industry

Lisye Fitria — 2026-02-12

The measurement of machine effectiveness using Overall Equipment Effectiveness (OEE) method can be used as a basis for evaluating the machine performance. The autonomous maintenance approach is used as the improvement framework to reduce breakdown and downtime through basic maintenance performed by operator to improve the effectiveness. Measuring machine effectiveness using OEE method can identify types of losses based on the six big losses and design improvement steps using Autonomous maintenance approach. The research results shows that the average OEE value of the 200TR press machine is 78.16%, indicating that it is still below the ideal standard. The largest loss contribution come from setup (8.75%) and adjustment losses (6.21%). The implementation of Autonomous Maintenance is proposed to increase the role of operator in basic machine maintenance, reducing breakdown frequency, and improve the machine effectiveness

Real-Time Plant Stem Segmentation on Smartphones Using YOLO for Precision Agriculture

Miroslav Holý — 2026-02-12

A crucial aspect of precision agriculture is plant phenotyping, as it provides insights into plant development, status and productivity. In this study, we present an approach for plant stem segmentation optimized for deployment on smartphones to support cost-effective precision agriculture practices. Using the YOLO (You Only Look Once) object detection framework, we trained a custom lightweight model capable of segmenting main stems under variable lighting and plant conditions. The model was evaluated on a dataset collected using a smartphone in a greenhouse, where it achieved 0.727 mAP50 and 20 FPS on Google Pixel 7a smartphone. Therefore, real-time stem segmentation can be effectively integrated into agricultural practices as a practical tool for data-driven crop management.

Raw Material Inventory System Using Multi-Item Single Supplier in a Furniture Company

Arie Desrianty — 2026-02-12

Inefficient management of raw material inventory can lead to high storage costs or stock shortages that hinder production. This study was conducted at Techno Art, a company that manufactures portable fitting rooms with raw materials supplied by a single supplier. The current ordering system is carried out separately for each item without a scheduled plan, resulting in a high frequency of orders and increased operational costs. This research designs a multi-item inventory system using the Joint Replenishment method with a model P approach to determine the basic ordering interval and the interval for each item in order to minimize inventory costs. The implementation of this method has proven to reduce costs, decrease ordering frequency, and maintain the availability of raw materials in accordance with production requirements.

Application of nearest neighbour search and 1-insertion local search to improve the distribution route of a textile company

Mochamad Syahrul Syam — 2026-02-12

This study aims to optimize the distribution system of a textile company that delivers products to 31 locations in Bandung and the surrounding areas. The company faces issues, including inefficient delivery routes. To address these challenges, three heuristic methods are applied: the Clarke and wright Savings Algorithm, the Nearest Neighbor Search, and 1-insertion intra-route. The Savings method is used to determine initial routes based on distance savings; Nearest Neighbor Search is applied to organize customer visits by proximity; and 1-insertion intra-route is used to improve the existing routes for greater efficiency. The distances used in this study are obtained using Google Maps. The results show that the combination of these three methods can reduce the total distance by 18,2% compared to the company's current distribution routes. The implementation of these methods led to a more efficient distribution process, resulting in cost reduction and improved service quality.

Information Technology Management Based From Technology Component Contribution Assessment On Academic Information System: A Case Study

Caecilia Sri Wahyuning — 2026-02-12

This study evaluates the academic information system at ITENAS using the Technology Contribution Coefficient (TCC) approach. The TCC values based on perceptions of lecturers, staff, and students were 0.718, 0.713, and 0.690, respectively. While staff and lecturers viewed the system as modern and effective, students perceived it as only moderately effective. This perception gap is primarily attributed to deficiencies in the Inforware component, especially in documentation quality and accessibility. Moreover, the low contribution intensities of Inforware (0.116) and Orgaware (0.081) reflect their underappreciated strategic role by the institution’s technical task unit. To address these issues, improvement strategies must begin with a comprehensive usability evaluation, focusing on learnability, efficiency, memorability, effectiveness, and satisfaction. Emphasis is placed on the development of better supporting documentation, such as SOPs and work instructions (WIs), using participatory design methods. Tools like storyboards—developed through Hierarchical Task Analysis—can enhance users’ understanding and engagement. These approaches strengthen the Humanware aspect by aligning user needs with system functionality.Improving Orgaware maturity through usability testing and refining system documentation is expected to indirectly enhance Humanware performance. This study recommends future research to assist the technical task unit in conducting usability assessments and redesigning the system through a human-centered, participatory design approach to ensure sustainable and user-driven improvements.

Optimization of Raw Material Order Quantity for Single Items Multiple Suppliers Using Linear Programming Methods: A Case Study at PT. TELPP

Dhimas Raditya Wj — 2026-02-12

PT. Tanjungenim Lestari Pulp and Paper (TLPP) is a world-class pulp manufacturer with high-quality products and environmentally friendly pulp mills. The company uses Eucalyptus Pellita trees as raw material, which will be processed into paper pulp. The problem currently faced by the company is a shortage of raw materials (under stock), which means that when the company experiences a shortage of raw materials, it will not be able to meet its monthly and daily production targets. This study aims to determine the optimal order quantity from two suppliers while minimizing total costs at TLPP using the Linear Programming approach. The results of the study indicate the optimal order quantities for both suppliers. Thus, this method can be applied by the company to avoid lost sales that could be detrimental to the company.
Keywords: Linear Programming, Inventory, Shortages and Surpluses of Raw Materials, Economic Order Quantity

Improving Printing Machine Effectiveness Using OEE and SMED: A Case Study at PT Kreasi Permata Sinergi

Erlangga Teguh Darmawan — 2026-02-12

This study aims to improve the effectiveness of a printing machine at PT Kreasi Permata Sinergi by applying the Overall Equipment Effectiveness (OEE) and Single Minute Exchange of Die (SMED) methods. OEE is used to evaluate machine performance based on availability, performance efficiency, and quality rate. When the OEE value falls below the world-class standard (≥85%), a Six Big Losses analysis is conducted to identify the dominant sources of inefficiency. The study utilizes historical operational data collected from December 2024 to March 2025 on the Atexco Model X Plus printing machine. The results indicate that the average OEE value is below the benchmark, with setup and adjustment identified as the largest contributors to performance losses. To address this issue, improvement strategies are proposed through the implementation of SMED by separating internal and external setup activities. The proposed approach is expected to reduce setup time, enhance machine effectiveness, and minimize production delays.

Metaheuristic and Classical Approaches in Production Scheduling: Campbell Dudek Smith, Dannenbring, and Variable Neighborhood Descent

Hendro Prassetiyo — 2026-02-12

The flow shop scheduling problem is well known to be NP-hard when involving m machines and n jobs. To address such combinatorial optimization problems, both classical heuristics and metaheuristic algorithms are often employed to generate near-optimal solutions within a reasonable computational time. This study investigates the performance of two classical heuristic methods—Campbell Dudek Smith (CDS) and Dannenbring—alongside a metaheuristic approach, Variable Neighborhood Descent (VND), in solving the flow shop scheduling problem. The objective is to determine an effective job sequence that minimizes the total completion time (makespan). A set of benchmark case studies is utilized to evaluate the methods, and the resulting makespan values are compared to assess their efficiency. The findings highlight the trade-offs between classical and metaheuristic approaches, providing insights into their applicability for practical production scheduling problems.

Optimization of Block Ice Distribution Route using Insertion and Swap-based Local Search Improvement method: A Case Study

Muhammad Refaldi — 2026-02-12

PT X is a company engaged in the production of block ice and tube (crystal) ice, which currently faces the problem of unplanned and non-systematic distribution routes. This problem falls within the category of the Vehicle Routing Problem (VRP), specifically the Multi-Trip Vehicle Routing Problem (MTVRP). This study aims to determine new distribution routes for 25 kg block ice at PT X that minimize total travel distance by applying the Saving Matrix and Nearest Neighbour methods, followed by route improvement using Local Search techniques, namely 1–Insertion Intra-Route and (1–1) Swap Intra-Route. The results indicate that the Local Search-based Insertion and Swap Intra-Route method yields the greatest improvement, achieving a distance reduction of 44.59% compared to the company’s existing route.

Green Practice in Cement Industry: Energy and Economic Analysis on The Substitution of Limestone by Cement Kiln Dust

Devani Khairunnisa — 2026-02-12

The cement industry is one type of industry that is highly consuming energy. Cement production generally involves several stages: mining, raw milling, burning, finishing mill, and packaging. The finish mill is the stage where the clinker (output of burning stage) is mixed with other materials such as gypsum, limestone, and additives (trass or fly ash). This study is aimed to examine the substitution of limestone in the finish mill by cement kiln dust (CKD) that is generated from raw mill. The approach of study was simulations to calculate the mass and energy balance and economic aspects (production cost and profit) based on the varied percent of CKD that substitute the limestone. Simulation results show that energy requirements are reduced by 469,730 kJ/ton for each addition of %CKD thanks to lower water content of CKD than limestone. Less energy requirements means less fuel requirements thus lowering production costs by IDR 66,500 /ton of raw meal /%CKD. In addition, CKD substitution to limestone can reduce waste and pollution from the cement industry so that it can increase profit by IDR 312,000 /ton of product /%CKD.

A Cost-Based Decision Framework for Multi-Item Single-Supplier Inventory Control

Sri Suci Yuniar — 2026-02-12

Inventory control in manufacturing systems frequently involves managing multiple raw materials from a single supplier. Independent ordering policies in these settings often lead to higher inventory costs. This study presents a cost-based decision framework for determining optimal ordering policies in multi-item, single-supplier inventory systems. The framework integrates the Economic Order Quantity (EOQ) and Economic Order Interval (EOI) models to evaluate both independent and coordinated ordering strategies under deterministic demand conditions. A numerical example, based on a representative consumer goods manufacturing scenario, illustrates the application of the framework. Results demonstrate that coordinated ordering under the EOI policy achieves lower total inventory costs than independent EOQ-based ordering. Sensitivity analysis shows that variations mainly affect the cost-benefit of coordinated ordering through ordering costs and remain relatively stable despite demand fluctuations. This framework provides practical guidance for decision-makers aiming to implement cost-effective inventory ordering policies