Critical Performance Measures Research Articles

The performance comparison of machine learning methods for solar PV power prediction

Purpose The energy generation process through photovoltaic (PV) panels is contingent upon uncontrollable variables such as wind patterns, cloud cover, temperatures, solar irradiance intensity and duration of exposure. Fluctuations in these variables can lead to interruptions in power generation and losses in output. This study aims to establish a measurement setup that enables monitoring, tracking and prediction of the generated energy in a PV energy system to ensure overall system security and stability. Toward this goal, data pertaining to the PV energy system is measured and recorded in real-time independently of location. Subsequently, the recorded data is used for power prediction. Design/methodology/approach Data obtained from the experimental setup include voltage and current values of the PV panel, battery and load; temperature readings of the solar panel surface, environment and the battery; and measurements of humidity, pressure and radiation values in the panel’s environment. These data were monitored and recorded in real-time through a computer interface and mobile interface enabling remote access. For prediction purposes, machine learning methods, including the gradient boosting regressor (GBR), support vector machine (SVM) and k-nearest neighbors (k-NN) algorithms, have been selected. The resulting outputs have been interpreted through graphical representations. For the numerical interpretation of the obtained predictive data, performance measurement criteria such as mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE) and R-squared (R2) have been used. Findings It has been determined that the most successful prediction model is k-NN, whereas the prediction model with the lowest performance is SVM. According to the accuracy performance comparison conducted on the test data, k-NN exhibits the highest accuracy rate of 82%, whereas the accuracy rate for the GBR algorithm is 80%, and the accuracy rate for the SVM algorithm is 72%. Originality/value The experimental setup used in this study, including the measurement and monitoring apparatus, has been specifically designed for this research. The system is capable of remote monitoring both through a computer interface and a custom-developed mobile application. Measurements were conducted on the Karabük University campus, thereby revealing the energy potential of the Karabük province. This system serves as an exemplary study and can be deployed to any desired location for remote monitoring. Numerous methods and techniques exist for power prediction. In this study, contemporary machine learning techniques, which are pertinent to power prediction, have been used, and their performances are presented comparatively.

Determination of riding comfort on cycleways using a smartphone application

Well maintained cycleways will encourage more people to cycle, as the condition of cycleways is important for the safety, accessibility and riding comfort of cyclists. Despite the surface condition and quality of cycleways having a significant impact on the cycling experience, only a few models used to describe the quality of service for cyclists take these into account. Objective measuring methods are needed to enable reliable and effective assessment of surface conditions, and measurable performance criteria related to the needs of cyclists should be developed. The purpose of this study has been to test the reliability and validity of using accelerometers in smartphones to assess the riding comfort on cycleways. A smartphone application converting three-dimensional accelerometer measurements into a single indicator for cycleways has been used to assess road surfaces in two field studies, in Sweden and Norway, respectively. Both studies assessed test sections of varying quality. To relate the measurements to subjective riding comfort assessments by cyclists, recruited cyclists collected quantitative data using the app, whilst also rating their perceived riding comfort by completing a survey. Measurements were also related to standard road surface condition indicators, generated from a road surface tester equipped with 19 laser sensors: international roughness index (IRI), mega- and macrotexture. The results show that it is possible to describe the unevenness of a cycleway using the technology present in smartphones. A software application can be used to collect and analyse data from the acceleration sensors in the phone, which can then be used to describe the riding comfort of cyclists. It is mainly the unevenness in the 50–1000 mm size-range that create the greatest discomfort for cyclists, and intermittent vibrations are perceived as more uncomfortable than more evenly distributed vibrations. Due to this and the fact that IRI is developed for cars, we have determined that IRI is not a relevant measurement for describing the riding comfort of cyclists.

Investigation of the performance of a newly designed solar chimney for enhancing natural ventilation and mitigation of summer overheating

The significant challenge encountered in utilizing Trombe walls for winter heating is summer overheating, which limits the overall feasibility of the system. In response to this issue, the present study introduces a novel model of a Trombe wall-solar chimney system designed to enhance natural ventilation and address the problem of summer overheating. To assess the performance of the proposed model, a full-scale experimental test rig is constructed in Kirkuk, Iraq. This rig comprises a test room integrated with a Trombe wall-solar chimney system. Additionally, a numerical simulation based on the CFD approach along with a computer code is developed to investigate the behavior of the system. System analysis is conducted for the period August 14th–15th. The parameters studied include chimney height (ranging from 0.0m to 2.0m in 0.5m increments), chimney width (0.2m, 0.3m, 0.4m, and 0.5m), room inlet vent height (ranging from 0.2m to 0.4m with 0.05m increments), and chimney inlet vent height (ranging from 0.2m to 0.4m with 0.05m increments). The results highlight the crucial role of the massive storage wall in sustaining nighttime ventilation in the absence of solar energy by utilizing stored heat to warm the air and maintain the ventilation process. The study establishes that chimney height and width significantly influence airflow rate, while other factors have marginal effects. An empirical equation is formulated to predict the 24-h averaged air changes per hour (ACH), which is a critical measure of system performance in ventilation. This equation is developed using artificial neural network (ANN) techniques. Finally, the findings indicate that the suggested model effectively reduces summertime overheating while generating a satisfactory ventilation rate. This enhances the overall versatility and year-round usability of Trombe wall systems, making them more adaptive and efficient in regions with diverse climatic conditions.

Effects of the March 2021 Allocation Policy Change on Key Deceased-donor Kidney Transplant Metrics.

A major change to deceased-donor kidney allocation in the United States, Kidney Allocation System 250 (KAS250), was implemented on March 15, 2021. Evaluating the consequences of this policy on critical system performance metrics is critical to determining its success. We performed a retrospective analysis of critical performance measures of the kidney transplant system by reviewing all organs procured during a 4-y period in the United States. To mitigate against possible effects of the COVID-19 pandemic, Scientific Registry of Transplant Recipients records were stratified into 2 pre- and 2 post-KAS250 eras: (1) 2019; (2) January 1, 2020-March14, 2021; (3) March 15, 2021-December 31, 2021; and (4) 2022. Between-era differences in rates of key metrics were analyzed using chi-square tests with pairwise z-tests. Multivariable logistic regression and analysis of variations methods were used to evaluate the effects of the policy on rural and urban centers. Over the period examined, among kidneys recovered for transplant, nonuse increased from 19.7% to 26.4% (all between-era P < 0.05) and among all Kidney Donor Profile Index strata. Cold ischemia times increased (P < 0.001); however, the distance between donor and recipient hospitals decreased (P < 0.05). Kidneys from small-metropolitan or nonmetropolitan hospitals were more likely to not be used over all times (P < 0.05). Implementation of KAS250 was associated with increased nonuse rates across all Kidney Donor Profile Index strata, increased cold ischemic times, and shorter distance traveled.

An acronym for Internet Movie Database is an online database of information related to films, television, series

Abstract: Movie recommender systems are meant to give suggestions to the users based on the features they love the most. A highly performing movie recommendation will suggest movies that match the similarities with the highest degree of performance. This study conducts a systematic literature review on movie recommender systems. It highlights the filtering criteria in the recommender systems, algorithms implemented in movie recommender systems, the performance measurement criteria, the challenges in implementation, and recommendations for future research. Some of the most popular machine learning algorithms used in movie recommender systems such as K-means clustering, principal component analysis, and self-organizing maps with principal component analysis are discussed in detail. Special emphasis is given to research works performed using metaheuristic-based recommendation systems. The research aims to bring to light the advances made in developing the movie recommender systems, and what needs to be performed to reduce the current challenges in implementing the feasible solutions. The article will be helpful to researchers in the broad area of recommender systems as well as practicing data scientists involved in the implementation of such systems. Index-terms : movie recommender, filtering techniques, performance metrics, K-means, metaheuristics

A cost-effective skip-lot sampling scheme using loss-based capability index for product acceptance determination

Acceptance sampling plans are essential for quality control and assurance, empowering businesses to make well-informed decisions regarding lot disposition. Among these plans, the skip-lot sampling plan (SkSP) stands out as a cost-effective strategy for suppliers with consistently excellent product quality. In this article, we present an enhanced version of the SkSP, termed Cpm-based SkSP-RGSP, which incorporates a repetitive group sampling plan (RGSP) using the Taguchi capability index Cpm as its reference plan. We develop an optimization model to ensure that the proposed plan meets a two-point condition in its operating characteristic function and effectively minimizes the average sample number (ASN). Through investigations of two critical performance measures, ASN and discriminatory power, we demonstrate the superiority of our plan over conventional sampling approaches. Detailed plan parameters, including required sample size and lot sentencing criteria, are provided to assist examiners in practical implementation. Additionally, we showcase the plan's applicability and practicality through a case study. This research contributes to the field of quality control by offering an efficient and cost-effective sampling scheme for lot disposition.

Garmin Fénix 7® Underestimates Performance at the Lactate Threshold in Comparison to Standardized Blood Lactate Field Test.

Lactate threshold (LT) is a critical performance measure traditionally obtained using costly laboratory-based tests. Wearables offer a practical and noninvasive alternative for LT assessment in recreational and professional athletes. However, the comparability of these estimates with the regular field tests requires further evaluation. In our sample of 26 participants (nf=7 and nm=19), we compared the estimated running pace and heart rate (HR) at LT with two subsequent tests. First, participants performed the Fenix 7® threshold running test after a calibration phase. Subsequently, they were tested in a standardized, graded blood lactate field test. Age was 25.97 (± 6.26) years, and body mass index (BMI) was 24.58 (± 2.8) kg/m2. Pace at LT calculated by Fenix 7® (M=11.87 km/h±1.26 km/h) was 11.96% lower compared to the field test (M=13.28 km/h±1.72 km/h), which was significant (p <0.001, d=-1.19). HR estimated by the Fenix 7® at LT was 1.71% lower (p>0.05). LT data obtained in the field test showed greater overall variance. Our results suggest sufficient accuracy of Fenix 7® LT estimates for recreational athletes. It can be assumed that for professional athletes, it would fail to provide the nuanced data needed for high-quality training management.

Forecasting of the Dental Workforce with Machine Learning Models

The aim of this study is to determine the factors affecting the dental workforce in Turkey to estimate the dentists employed with machine learning models. The predicted results were obtained by applying machine learning methods; namely, generalized linear model (GLM), deep learning (DL), decision tree (DT), random forest (RF), gradient boosted trees (GBT), and support vector machine (SVM) were compared. The RF model, which has a high correlation value (R2=0.998) with the lowest error rate (RMSE=656.6, AE=393.1, RE=0.025, SE=496115.7), provided the best estimation result. The SVM model provided the worst estimate data based on the values of the performance measurement criteria. This study is the most comprehensive in terms of the dental workforce, which is among the healthcare resources. Finally, we present an example of future applications for machine learning models that will significantly impact dental healthcare management.

Revolutionizing performance measures and criteria for the facilities management industry in the UAE

PurposeAmidst the complicated nature of the UAE’s facilities management (FM) industry, the need to recalibrate the existing performance measurement (PM) system measures and criteria has been resonating to ensure their ability to capture the FM industry trends and dynamics, thus enhancing organizational excellence. Therefore, this research aimed to propose a specific PM tool to the country’s FM industry to accurately assess performance and establish strategic enhancements.Design/methodology/approachThe study reviewed literature on the available PM systems to gather the available measures, which were presented to a focus group of seven participants, who were purposively selected based on their expertise in FM and PM implementation in the UAE to adjust them and add ones relevant to the UAE’s FM industry.FindingsThe focus group conducted various changes, from retaining certain measures and criteria, renaming them to simplify or make them more representative of the industry, ranking them based on their importance to limit their numbers, to finally categorizing them as enablers or results. Consequently, the final proposed tool was composed of nine dimensions with 51 measures as performance enablers and three dimensions with 11 measures as performance results. Seven measures were added by the experts, who highlighted their increasing popularity in the UAE’s FM industry.Originality/valueThrough addressing the critical void in literature, this paper develops a specific PM tool aligning with the intricacy of the UAE’s FM industry, thus providing proactive contribution to the industry’s effective and sustainable growth.

Cloud computing-based framework for heart disease classification using quantum machine learning approach

Abstract Accurate early identification and treatment of cardiovascular diseases can prevent heart failure problems and reduce mortality rates. This study aims to use quantum learning to predict heart problems to increase the accuracy of traditional prediction and classification methods. Machine learning (ML) and deep learning (DL) techniques need quantum learning to quickly and accurately analyze massive volumes of complex data. With quantum computing, the suggested DL and ML algorithms can change their predictions on the basis of changes in the dataset. This approach could help with the early and accurate detection of chronic diseases. The Cleveland heart disease dataset is undergoing preliminary processing to validate missing values to increase the precision rate and prevent incorrect forecasts. This study examined the feasibility of employing and deploying a quantum ML (QML) framework via cloud computing to categorize cardiac conditions. The research was divided into four sections. First, the principal component analysis was used to preprocess the Cleveland dataset, recursive feature elimination was used to select features, and min–max normalization was used to give the dataset a high-dimensional value. Second, we compared traditional classifiers, such as support vector machine (SVM) and artificial neural network, with the quantum approach to verify the quantum approach’s efficiency. Third, we examined two unique QML classification methods: quantum neural networks (QNNs) and quantum SVM (QSVM). Fourth, bagging-QSVM was developed and deployed as an ensemble learning model. Experimental results using the QNN show an accuracy of 77%, a precision of 76%, a recall of 73%, and an F1 score of 75%. With an accuracy of 85%, a precision of 79%, a recall of 90%, and an F1-score of 84%, the QSVM method demonstrated a much better performance than the QNN. Particularly, the Bagging_QSVM model exhibited an outstanding performance, with a flawless score of 100% across all critical performance measures. The study shows that the bagging method for ensemble learning is a solid way of increasing the accuracy of quantum method predictions.

Analisa Rekayasa Ulang Proses Bisnis Pada UD. Top Stiker

Re-engineering is used to identify, analyze, and redesign the core business processes of the company/organization aimed at achieving a dramatic increase in critical performance measurements such as cost, quality, service, and speed. The achievement of re-engineering is to support more a corporate mission and reduce costs. UD. Top Stiker is one of the companies engaged in the field of mobile phone accessories, stationery and offices and motorcycles are currently developing, so the need to improve the quality of service is getting better. But the business process in UD. Top Stiker has not been going well and has problems that can interfere with the running of operational activities UD. Top Stiker. Using the BPR method and SWOT analysis to generate alternative strategies and BPMN for business process modeling. The research used to obtain data was obtained through literature studies, observations, interviews and provided questionnaires to UD. Top Stiker owners. The final result of this study was a recommendation of a business process redesign by reducing several process stages from the 18 process stages to 13 process stages so that it become more fast and simple. While the value of the IFAS strength factor is 1.55 and the weakness factor is 1.75, while the value of the EFAS opportunity factor is 1.7 and the risk factor is 1.45.

Surface Roughness Analysis in AWJM for Enhanced Workpiece Quality

Abrasive Water Jet Machining is a distinctive manufacturing process that effectively removes material from a workpiece by employing a high-pressure stream of water combined with abrasive particles. The final quality of the machined surface is directly influenced by various process parameters, such as the traverse speed, hydraulic pressure, stand-off distance, abrasive flow rate, and the specific type of abrasive used. In recent times, extensive research has been undertaken to enhance the performance of AWJM, with a specific focus on critical performance measures like surface roughness. This paper presents the latest advancements in AWJM research, with particular attention given to enhancing performance measures, implementing process monitoring and control, and optimizing process variables for applications involving high-carbon steel.

Reducing Industrial Water Consumption: The Impact of Organizational Learning

Using factory-level data from a large multinational manufacturer, we examine the effects of both organizational experience and knowledge transfer on an increasingly critical environmental performance measure, the consumption of water required for manufacturing. We estimate the direct effects on water consumption from in-factory cumulative production experience and the vicarious learning from peer factories in the same product category. We consider vicarious learning from three potential sources: observation of peer factories’ cumulative production experience; and benchmarking of water consumption performance with the best and worst performing peer factories. For each learning channel, we test for the moderating effects of water scarcity and geographic proximity. We find that factories learn to reduce their water consumption from their own experience but at a greater rate in water-scarce locations. Although we find that factories learn significantly from observing the cumulative production experience of peer factories, this effect does not hold in water-scarce locations or across geographic regions. We document that learning effects from observing others’ experience are quite distinct from learning effects by benchmarking others’ performance. We find vicarious learning effects from benchmarking the best-performing peer factories result in significant reductions in water consumption, and this effect is greater when the factory is in a water-scarce location, and when benchmarking other regions rather than within the same region. Finally, we find less significant vicarious learning from observing the worst-performing factories.

A Multi-Stage Approach for External Trucks and Yard Cranes Scheduling with CO2 Emissions Considerations in Container Terminals

Background: In container terminals, optimizing the scheduling of external trucks and yard cranes is crucial as it directly impacts the truck turnaround time, which is one of the most critical performance measures. Furthermore, proper scheduling of external trucks contributes to reducing CO2 emissions. Methods: This paper proposes a new approach based on a mixed integer programming model to schedule external trucks and yard cranes with the objective of minimizing CO2 emissions and reducing truck turnaround time, the gap between trucking companies’ preferred arrival time and appointed time, and the energy consumption of yard cranes. The proposed approach combines data analysis and operations research techniques. Specifically, it employs a K-means clustering algorithm to reduce the number of necessary truck trips for container handling. Additionally, a two-stage mathematical model is applied. The first stage employs a bi-objective mathematical model to plan the arrival of external trucks at the terminal gates. The second stage involves a mathematical model that schedules yard cranes’ movements between different yard blocks. Results: The results show that implementing this methodology in a hypothetical case study may lead to a substantial daily reduction of approximately 31% in CO2 emissions. Additionally, the results provide valuable insights into the trade-off between satisfying the trucking companies’ preferred arrival time and the total turnaround time. Conclusions: The integration of data clustering with mathematical modeling demonstrates a notable reduction in emissions, underscoring the viability of this strategy in promoting sustainability in port-related activities.

LSTM-based framework with metaheuristic optimizer for manufacturing process monitoring

Quick process shift detection and lower out-of-control run length are essential for monitoring the production process, especially in modern smart manufacturing. Specifically, the out-of-control run length is one of the most critical performance measures to evaluate the manufacturing process monitoring (MPM) model. The sooner the out-of-control is detected, the better the model is. However, developing a monitoring model which can provide quick shift detection for various data dimensions and volumes is challenging. In this research, single (1_LSTM) and stacked (S_LSTM) long-short-term memory (LSTM) based models with metaheuristic optimizer were proposed to detect process shifts quickly in the manufacturing domain. Based on the literature, three metaheuristic methods: Clustering-based organism search (CSOS), Particle Swarm Optimization (PSO), and Simulated Annealing (SA) that are suitable for high-dimensional optimization were utilized in the proposed method to optimize weights in the LSTM-based network. The proposed models were evaluated based on average out-of-control run length (ARL1) against benchmark methods on various synthesized multivariate normal and real-world datasets. Also, the performances of CSOS, PSO, and SA were compared. The results show that CSOS_S_LSTM outperforms other methods with lower ARL1. The result also confirmed the effectiveness and applicability of the proposed models for real-world problems. The experimental results showed that the response time of detection can be improved by 33.19% and 38.77% on average using the proposed 1_LSTM and CSOS LSTM-based metaheuristics models, respectively.

Investigating Sustainability Indicators for Urban Road Network — A Methodical Review Literature

Transportation that is both socially and environmentally responsible is an important factor in climate change. However, urban sustainable mobility schemes have no universally accepted success criteria. Sustainability evaluation lacks a common language. This document groups sustainable mobility strategies to establish critical transport performance measures. Sustainable transportation trumps targets, criteria, and indicators. The following are the top priorities for urban multimodal sustainable transportation, in descending order: There are 13 social, 11 economic, and 9 environmental criteria. Each of the three basic criteria used most often in the study specifically addresses the environment. Since the literature’s attribution of criteria to sustainability elements is complex, it’s recommended to analyze their interrelationships. As previously demonstrated, small and medium-sized cities have a high sustainability value of in terms of population and urban area, but large cities can improve their sustainability by controlling urban sprawl and managing urban transportation demand with adequate public transportation. It is proposed that in the future, the interrelationships between the criteria be evaluated, as their allocation to the aspects of sustainability is ambiguous in the available literature. This article can assist mobility executives in making decisions about urban transportation concepts and project management. Making transportation more environmentally friendly is crucial to reducing climate change’s negative impacts.

Developmental Trajectory of Anticipation: Insights from Sequential Comparative Judgments.

Reaction time (RT) is a critical measure of performance, and studying its distribution at the group or individual level provides useful information on the cognitive processes or strategies used to perform a task. In a previous study measuring RT in children and adults asked to compare two successive stimuli (quantities or words), we discovered that the group RT distribution was bimodal, with some subjects responding with a mean RT of around 1100 ms and others with a mean RT of around 500 ms. This bimodal distribution suggested two distinct response strategies, one reactive, the other anticipatory. In the present study, we tested whether subjects' segregation into fast and slow responders (1) extended to other sequential comparative judgments (2) evolved from age 8 to adulthood, (3) could be linked to anticipation as assessed using computer modeling (4) stemmed from individual-specific strategies amenable to instruction. To test the first three predictions, we conducted a distributional and theoretical analysis of the RT of 158 subjects tested earlier using four different sequential comparative judgment tasks (numerosity, phonological, multiplication, subtraction). Group RT distributions were bimodal in all tasks, with the two strategies differing in speed and sometimes accuracy too. The fast strategy, which was rare or absent in 8- to 9-year-olds, steadily increased through childhood. Its frequency in adolescence remained, however, lower than in adulthood. A mixture model confirmed this developmental evolution, while a diffusion model corroborated the idea that the difference between the two strategies concerns anticipatory processes preceding decision processes. To test the fourth prediction, we conducted an online experiment where 236 participants made numerosity comparisons before and after an instruction favoring either reactive or anticipatory responses. The results provide out-of-the-lab evidence of the bimodal RT distribution associated with sequential comparisons and demonstrated that the proportions of fast vs. slow responders can be modulated simply by asking subjects to anticipate or not the future result of the comparison. Although anticipation of the future is as important for cognition as memory of the past, its evolution after the first year of life is much more poorly known. The present study is a step toward meeting this challenge. It also illustrates how analyzing individual RT distributions in addition to group RT distributions and using computational models can improve the assessment of decision making cognitive processes.

MpwR: an R package for comparing performance of mass spectrometry-based proteomic workflows

mpwR is an R package for a standardized comparison of mass spectrometry (MS)-based proteomic label-free workflows recorded by data-dependent or data-independent spectral acquisition. The user-friendly design allows easy access to compare the influence of sample preparation procedures, combinations of liquid chromatography (LC)-MS setups, as well as intra- and inter-software differences on critical performance measures across an unlimited number of analyses. mpwR supports outputs of commonly used software for bottom-up proteomics, such as ProteomeDiscoverer, Spectronaut, MaxQuant and DIA-NN. mpwR is available as an open-source R package. Release versions can be accessed on CRAN (https://CRAN.R-project.org/package=mpwR) for all major operating systems. The development version is maintained on GitHub (https://github.com/okdll/mpwR) and full documentation with examples and workflow templates is provided via the package website (https://okdll.github.io/mpwR/).

Pythagorean Fuzzy AHP Based Dynamic Subcontractor Management Framework

In construction projects, a significant part of construction work is done by subcontractors (SCs). Therefore, their management by main contractors (MCs) becomes an important issue as the density of SCs is created at the construction sites. In recent years, more focus on SC evaluation and selection in bidding process has been on the agenda whereas the subject of SC performance appraisal on-site during the project execution phase has been untended in the literature. Thus, this study aims to focus on the measurement and evaluation of the performance of SCs in the project execution phase, and to provide a tentative performance-based dynamic management framework that MCs will use in the management of SCs in order to take proactive measures. In line with the aim, a total number of 23 performance measurement criteria (PMC) under 7 main groups were determined as a result of a comprehensive literature review and expert evaluations. Knowing that not every criterion will have the same effect in performance measurement, pairwise comparisons of the criteria were made using the Pythagorean Fuzzy Analytic Hierarchy Process (PFAHP) method and their importance weights were determined. The PFAHP method was obtained by integrating the Pythagorean fuzzy set into the AHP method and chosen with the aim of improving the fuzzy AHP method and obtaining more consistent results by eliminating the uncertainty since Pythagorean fuzzy sets is more capable than fuzzy sets at expressing and handling uncertainty in uncertain environments. Lastly, a framework for SC performance measurement and evaluation on project execution phase is presented. It is believed that the presented framework will allow for a proactive management style that will enable effective decisions to be made while the project is ongoing, and a dynamic way of working instead of static and conventional work.

Safest-path planning approach for indoor fire evacuation

Many evacuation approaches have been proposed to assist people in escaping from fires. Traditional approaches focus on finding the nearest exit and planning the shortest path. However, they involve disadvantages as they are inflexible and time-consuming to adapt to the dynamic spread of fires. Advanced approaches exploit real-time data provided by a sensor network to dynamically determine evacuation exits and paths. Their disadvantages include local optimal solutions and excessive dependence on the sensor network, which may be destroyed in fires. In contrast to previous approaches, in this study, we adopt fire prediction to determine the safest path. In addition, a path planning algorithm is proposed to utilize the prediction data in parallel.In contrast to previous approaches, in this study, we adopt fire prediction to determine the safest path. In addition, a path planning algorithm is proposed to utilize the prediction data in parallel. In the simulations, we adopted the fire trends simulated by the fire dynamic simulation tool, PyroSim. Common safety procedures are flexibly applied to our approach by transforming and modeling. The effects of a crowded area are disregarded. The survival rate and computation time are considered critical performance measurements. The experimental results indicate that our approach is 10 times faster than other approaches and exhibits a survival rate more than 10% higher than prior methods.