K-means Method Research Articles

A Model-Driven Approach to Extract Multi-Source Fault Features of a Screw Pump

Screw pumps’ faulty working conditions affect the stability of oil production. At project sites, different sensors are used simultaneously to collect multi-dimensional signals; the data fault labels and location are not clear, and how to comprehensively use multi-source information in effective fault feature extraction has become an urgent issue. Existing diagnostic methods use a single signal or part of a signal and do not fully utilize the acquired signal, which makes it difficult to achieve the required accuracy of diagnostic results. This paper focuses on the model-driven approach to extract multi-source fault features of screw pumps. Firstly, it constructs a fault data model (FDM) by analyzing the fault mechanism of the screw pump. Secondly, it uses the FDM to select an effective data set. Thirdly, it constructs a multi-dimensional fault feature extraction model (MDFEM) to extract featured signal features and data features, for which we also comprehensively used multi-source signals in effective fault feature extraction, while other traditional methods only use one or two signals. Finally, after feature selection, unsupervised fault diagnosis was achieved by using the k-means method. After experimental verification, the method can comprehensively use multi-source information to construct an effective data set and extract multi-dimensional, effective fault features for screw pump fault diagnosis.

Distributed Passive Positioning and Sorting Method for Multi-Network Frequency-Hopping Time Division Multiple Access Signals

When there are time division multiple access (TDMA) signals with large bandwidth, waveform aliasing, and fast frequency-hopping in space, current methods have difficulty achieving the accurate localization of radiation sources and signal-sorting from multiple network stations. To solve the above problems, a distributed passive positioning and network stations sorting method for broadband frequency-hopping signals based on two-level parameter estimation and joint clustering is proposed in this paper. Firstly, a two-stage filtering structure is designed to achieve control filtering for each frequency point. After narrowing down the parameter estimation range through adaptive threshold detection, the time difference of arrival (TDOA) and the velocity difference of arrival (VDOA) can be obtained via coherent accumulating based on the cross ambiguity function (CAF). Then, a multi-station positioning method based on the TDOA/VDOA is used to estimate the position of the target. Finally, the distributed joint eigenvectors of the multi-stations are constructed, and the signals belonging to different network stations are effectively classified using the improved K-means method. Numerical simulations indicate that the proposed method has a better positioning and sorting effect in low signal-to-noise (SNR) and low snapshot conditions compared with current methods.

High frequency radar error classification and prediction based on K-means methods

This study aims to characterize the high frequency radar and numerically simulated low-frequency filtered currents in the south-eastern Bay of Biscay (study area) using a K-means classification algorithm based on an improved Euclidean Distance calculation method that does not take missing values. The errors between observations and simulations was estimated and predicted based on this classification method. Results indicate that predominantly eastward (northward) currents over the Spanish (French) continental shelf/slope in winter and more variable currents in the west and south-west in summer. The model classification results for circulation characteristics are in relatively good agreement with HF radar results, especially for currents on the Spanish (French) shelf/slope. In addition, the probabilistic relationship between observed and modeled currents was explored, obtaining the probability of occurrence of modeled current groups when each group of observed currents occurs. Finally, predictions of model and observed current errors were made based on the classification results, and it was found that the predictions based on the classification of all data had the smallest errors, with a 17% improvement over the unclassified control experiment. This study provides a foundation for subsequent model error testing, forecast product improvement and data assimilation.

Comparison of Machine Learning Models and Feature Importance Investigation of Intelligent Fault Diagnosis Methods for Robots Based on Datasets Across Various Distributions

Intelligent fault detection is an important component of the industrial and automation fields. However, conventional research on intelligent fault detection mainly focuses on industrial production equipment, while there is little research on intelligent fault detection scenarios for robots. Based on a hexapod robot joints dataset, this paper investigates intelligent fault diagnosis tasks in the field of robotics. Firstly, the dataset is clustered into two new datasets with different distributions through k-means method, which is used to simulate the practicality of imbalanced distribution between healthy and fault data. Afterwards, several multioutput machine learning classification models were established to predict robot joints with faults. In two datasets with different distributions, the larger one is used as the training set and the smaller one is used as the testing set. The article compares the performance of these models with prediction accuracy as the main indicator. And based on the results, the paper selects the model with the highest accuracy for further exploration of feature importance. Finally, the article explains the significance of the results and analyzes possible reasons. The experimental results show that the random forest model better overcomes the problem of data distribution differences and has the highest accuracy. In the random forest model, the importance of position data representing position error is higher than that of slope with respect to the axis data representing angle error. This result may be related to the distribution of feature values and the fact that position data contains more crucial information.

A fire risk pre-warning framework for high-rise buildings based on unascertained method

The growing global interest in preventing and controlling fires in high-rise buildings reflects the increasing significance of this issue today. This research aims to establish an early warning framework for fire risk in high-rise buildings. Firstly, considering the importance of a scientific indicator system for the application of the model, this study combines the event analysis method with the building design fire code to identify 11 key risk factors that have a far-reaching impact on the prevention of fires in high-rise buildings. Based on identifying the risk factors, a high-rise building fire risk warning tree is also established, which scientifically solves the problem of the indicator system of the warning object. Subsequently, in response to the various complex issues arising from the uncertainty of fire occurrence in high-rise buildings, this study adopts the unascertained method to model the fire risk of high-rise buildings for early warning. In addition, the developed methodology was empirically validated through case studies and analyses of empirical data on fire risks in nine representative high-rise buildings. The results of the unascertained method were also compared with the results of the K-means method, from which it was concluded that the unascertained method can predict building fires more accurately. The research results provide a reliable decision support system for fire disaster prevention and control in high-rise buildings.

An interactive clustering method via metric learning for analyzing energy consumption patterns

Accurate analysis of energy consumption patterns is the key to achieving the goal of sustainable building energy efficiency, and clustering analysis in data mining techniques has shown efficacy in this regard. However, traditional clustering methods suffer from several issues including lack of users’ participation and low quality of results. To address these challenges, this paper proposes an interactive clustering method based on metric learning. It allows users to interact with clustering models by manipulating initial clusters and inject their domain knowledge for quality improvement. Meanwhile, a metric learning technique is applied to learn a distance metric based on the initial clustering results to improve the quality and flexibility of clustering. Accordingly, a latent graph that imitates the proximity of consumers can be constructed to propagate the clustering intent of users to larger unseen data. In collaboration with five experts in the field of building energy consumption, case studies demonstrate that our method can effectively recognize four types of daily consumption patterns. Compared with the classical k-means method, the mean variance of data features, the Davies-Bouldin Index (DBI) has decreased by 11.19 % and 21.54 %, respectively, and the Calinski-Harabasz (CH) has improved by 10.72 %.

Analysis of the Physiological Parameters of Cold Resistance in Core Winter and Spring Wheat Cultivars

We selected 46 core winter–spring wheat cultivars from China’s main wheat-producing areas as experimental materials to clarify the differences in the physiological parameters of their cold resistance and provide a theoretical basis and high-quality germplasm for cold resistance breeding. We investigated differences in their cold resistance under field conditions for two consecutive years, and determined the physiological parameters of the cold resistance, yield, and quality indicators of different winter–spring wheat cultivars. Our results showed that the cold resistance of winter wheat cultivars was higher than that of spring wheat cultivars. The chlorophyll (Chl), soluble sugar (SS), soluble protein (SP), and free proline (Pro) contents of different winter–spring wheat cultivars were positively correlated with cold resistance, and malondialdehyde (MDA) content was negatively correlated with cold resistance. The five physiological parameters can be used as physiological indicators for the breeding of cold-resistant cultivars. The cold resistance, yield, and quality indicators of different spring and winter wheat cultivars were comprehensively evaluated by using the average membership value and comprehensive score. It was found that the average membership value and comprehensive score of winter wheat cultivars were higher than those of spring wheat cultivars. Through classification using the K-means method, the cold-resistant, high-yield, and high-quality cultivars were screened out, namely, Jimai23 (JM23), Jimai44 (JM44), Shannong57 (SN57), and Jinmai 919 (JM919).

Decision-Making Process for Tourism Potential Segmentation: A Case Study Analysis

The tourism industry is one of the critical sectors driving regional economic development, creatingjobs, and preserving cultural and natural heritage. The Rembang Regency Government is trying todesign a strategy to increase various tourism potentials that support the tourism industry. Stakeholderscannot optimally manage various tourism potentials in Rembang Regency because the support systemfacilities still need to be improved. Potential tourism segmentation based on facility support systems(SSF) can assist the government in carrying out strategies to increase the potential of the tourismindustry. The main objective of this research is to assist stakeholders in the decision-making processand generate policy advice through tourist mapping results, reducing large-scale tourism industryproblems to a scale that can be understood and acted upon in successful tourism industry marketing.Methods in data collection using literature study and observation with accidental sampling todetermine as many as 20 tours. The K-Means method was chosen to classify tourism potential inRembang Regency, Central Java, Indonesia. The results showed three potential tourism clusters inRembang Regency based on Support System and Facilities (SSF) covering telecommunication, powersource, transportation, waste management, location, clean water source, supporting industry, spatial,hospitality, safety, and security. The results of this study can be used in designing decision-makingstrategies by stakeholders to improve the tourism industry. Increasing the potential of each touristcluster by stakeholders has its advantages and disadvantages.

Geographic information system for reporting damage and road grouping based on website using waterfall method and k-means method

Roads are a vital land transportation infrastructure and transportation route. One of the functions of roads is as a driving factor in the development process and equitable distribution of development in a region. Road damage that occurs disrupts the activities and routines of residents. Lhokseumawe City as the center of economic and social development in its region requires an efficient system for the management and maintenance of road infrastructure. The reason is that many road damages occur in Lhokseumawe City that have not been repaired due to limited damage information so reports are needed from residents to find out the location of the road damage so that it is easier for the Lhokseumawe City government to follow up on the report. With these problems, a geographic information system for reporting road damage is created. It is hoped that the government can follow up on the report and prioritize damage with the highest group, which groups road damage using the clustering method. This web-based information system is designed using the UML (Unified Modeling Language) model with the PHP programming language and uses MySQL as its database. With this system, the government can receive reports of existing damage and group the damage into three levels to determine the priority of road repairs to be carried out.

IMPLEMENTATION OF K-MEANS AND FUZZY C-MEANS CLUSTERING FOR MAPPING TODDLER STUNTING CASES IN GUNUNGKIDUL DISTRICT

Gunungkidul Regency has the highest prevalence of stunted toddlers in the Special Region of Yogyakarta. This study aims to describe the optimal clustering results of toddler stunting cases using the k-means and fuzzy c-means methods and to describe the characteristic of the mapping results of stunting-prone areas for toddlers in Gunungkidul Regency for the years 2020 – 2022. This study maps stunting-prone areas for toddlers across 30 community health centers in Gunungkidul Regency from 2020 to 2022, with variables including the percentage of babies with low birth weight, babies born stunted, babies receiving health services, stunted toddlers, toddlers receiving health services, babies given exclusive breastfeeding, poor couples of reproductive ages, and families with adequate drinking water. The k-means clustering method determines cluster membership using the distance between objects and centroids, while the fuzzy c-means method uses the degree of membership. Cluster evaluation uses the silhouette coefficient, Calinski-Harabasz index, Davies-Bouldin index, and Dunn index to obtain optimal clustering results. The mapping results are presented as a stunting vulnerability map. The findings indicate that the optimal number of clusters is two, with the fuzzy c-means method proving more optimal than the k-means method based on evaluation scores. In 2020, there were 23 community health centers in cluster 0 and 7 in cluster 1. In 2021, there were 21 community health centers in cluster 0 and 9 in cluster 1. In 2022, there were 18 community health centers in cluster 0 and 12 in cluster 1. Generally, community health centers in cluster 0 are less optimal in specific nutrition interventions, such as for infants and toddlers. In contrast, those in cluster 1 are less optimal in sensitive nutrition interventions, such as poverty and water adequacy.

Sistem Pendukung Keputusan Berbasis K-Means untuk Evaluasi Keberhasilan Bisnis dan Nilai Perusahaan

Business development is in line with the development of increasingly sophisticated technology. This requires every company to compete and be motivated to increase its value as an indicator of success in managing the company so that investors are interested in investing. This study aims to design a K-means-based Decision Support System with a clustering approach to classify the growth rate of company value. Investment Opportunity Set (IOS) and profitability variables are the leading indicators of increasing company value. The problem formulation is how the design of this K-means-based decision support system can assist in classifying the growth rate of the company's value based on the IOS and profitability variables. This research aims to produce a decision support system that can organize the growth rate of company value using the K-means method. System testing is conducted to evaluate the effectiveness of the applied clustering method, focusing on the accuracy of the results. The weighting of IOS and profitability variables is based on the percentage of positive relationship to firm value, and the ultimate goal is to group companies with different growth rates. As a result, the K-means-based Decision Support System, or "Business Growth Prediction Decision Support System," successfully clustered the growth rate of firm value. With reasonable accuracy, measured using the silhouette coefficient, the calculation results show an overall mean silhouette coefficient of 0.684, close to the maximum value of 1. This result confirms that this decision support system can group companies in the L (Low), M (Medium), and H (High) categories based on the level of value growth, using the IOS and profitability variables as the leading indicators. Thus, this research supports decisions related to company growth strategies using K-means-based decision support systems.

Application of Machine Learning Methods to Analyze the Dependence of Vibration Acceleration Signals on the Tightening Forces of Bolted Connections

The article is devoted to the application of machine learning methods for the analysis of vibration acceleration signals in bolted joints that occur under impact. The relevance of the work is due to the need to ensure the reliability and operability of bolted joints under loads. One of the promising areas of non-destructive testing is the analysis of the characteristics of vibration acceleration signals that change with changes in the state of structures, for example, with an increase in the tightening torque. This allows for the timely detection of possible defects and the prevention of emergency situations, ensuring the safety and durability of structures. The vibration acceleration signals under impact action on a bolted joint were analyzed. After calculating the signal characteristics, data sets were formed, including the values of tightening torques and the corresponding calculated signal characteristics, a search for a correlation between the tightening torque of bolted joints and the obtained set of vibration signal parameters was carried out. The frequency spectrum of signals, the Higuchi fractal dimension, detrended fluctuations, spectral power density and position of signal peaks were calculated. Machine learning models such as decision trees, the nearest neighbor method, the k-means method and neural networks were used for the analysis. For these methods, an optimal set of parameters correlating with the tightening torque was searched for. The main results show that machine learning methods are effective in classifying signals and finding correlations with stress state parameters. They allow us to detect the relationship between a set of signal characteristics and tightening torque, which opens up opportunities for more accurate and reliable monitoring of the condition of bolted connections. This should help to increase their operational reliability and durability, as well as reduce the likelihood of failures and accidents. The use of such methods can improve the quality of monitoring and diagnostics of bolted connections.

An observational study of female body shape characteristics in multiracial Malaysia

Abstract The current study aims to explore the representative and typical female body shapes through in-depth observation and analysis of the diversity in Malaysian female body shape characteristics across different ethnic and age groups, which assists in facilitating the establishment of accurate apparel size standards. This study was conducted in Selangor, which is the most populous and developed Malaysian state. The data were collected via a highly systematic approach. The K-mean clustering method was applied to synthesise and analyse the collected data, which classified the body types into five major clusters. The results not only revealed significant differences in the distribution of body shapes across ethnic and age groups but also highlighted the limitations of the various sizing systems currently employed by the Malaysian apparel industry to fulfil the requirements of the diverse Malaysian market. The findings provided practical implications for apparel manufacturers and retailers with concrete evidence to support improved product design and enhance customer satisfaction. A deeper understanding and categorisation of Malaysian females’ body types could also assist the apparel industry in developing more tailored sizing systems. Resultantly, an improved system minimises return rates, optimises inventory management, and supports environmental and sustainability goals by reducing overproduction.

Implementation of K-Means and Single Linkage on Types of Disabilities in East Java Province

The high number of people with disabilities is one of the problems faced by the Indonesian government, especially in Java Province. After West Java Province, East Java Province is in second place as the province with the highest rate of people with disabilities in Indonesia. Disabled people are people with physical disabilities such as not being able to walk, not being able to talk, not being able to see, and so on. The aim of this research is to group districts in East Java Province based on types of disabilities with the hope of facilitating activities in fulfilling the rights of people with disabilities in East Java Province. The grouping was carried out in order to determine the characteristics of each cluster using so that the optimal k-means method was used for clustering using the Euclidean distance method with cluster 1 in 29 districts and cluster 2 in 9 districts. The most optimal single linkage uses the Euclidean distance method with cluster 1 having 8 districts and cluster 2 having 30 districts. From the results of the validity index values, it was found that the single linkage method had the smallest validity value of the icdrate method compared to the k-means method.

8737 Primary Hyperparathyroidism (PHPT) “Phenotypes” and the Results of Parathyroid [99mTc]Tc-Sestamibi SPECT/CT Scintigraphy: Minimizing the Risk of Negative Imaging Results

Abstract Disclosure: K. Kucharczyk: None. A. Drynda: None. J. Podlewski: None. M. Trofimiuk-Muldner: None. A. Hubalewska-Dydejczyk: None. Introduction. Primary hyperparathyroidism (PHPT) is a prevalent endocrinopathy typically identified through biochemical testing. PHPT is characterized by hypercalcemia accompanied by increased or inappropriately normal plasma parathyroid hormone (PTH) concentrations. Preoperative imaging is conducted when surgery is indicated to pinpoint parathyroid adenomas. [99mTc]Tc-Sestamibi scintigraphy is highly specific and sensitive in diagnosing PHPT, with a higher adenoma detection rate demonstrated for patients with larger lesions or higher blood calcium concentrations. The study aimed to investigate the relationship between the results of biochemical tests and clinical manifestations (PHPT “phenotype”) and the rate of positive results of parathyroid [99mTc]Tc-Sestamibi scintigraphy. Materials and methods. This was a retrospective study of patients suspected of PHPT who underwent parathyroid [99mTc]Tc-Sestamibi SPECT/CT scintigraphy between 2010 and 2022. Patients’ cluster analysis was conducted based on PTH, serum calcium (Ca), and phosphate (Pi) concentrations to find distinct patterns in these parameters. Furthermore, we compared the distributions of additional patients’ attributes, including gender, lesion size, serum vitamin D, ALP concentrations, urinary calcium, urolithiasis prevalence, as well as parathyroid scintigraphy results. Results. 513 patients were divided into 5 clusters using different algorithms. Finally, clusters from K-means methods were selected based on statistical metrics and expert interpretation. Those were organized in ascending order of positive scintigraphy results, with Cluster 5 reaching a 79.5% positivity rate and median values of PTH - 315.5 pmol/L, Ca - 2.96 mmol/L, and Pi - 0.7 mmol/L. As the proportion of positive imaging outcomes declined, median PTH and calcium concentrations decreased while phosphate concentrations increased. In Cluster 1, with 30% of positive imaging results, medians were as follows: PTH - 79.06 pmol/L, Ca - 2.55 mmol/L and Pi - 1.1 mmol/L. A comparative analysis of various clinical and biochemical parameters revealed statistically significant differences between clusters. Patients from Clusters with a higher frequency of positive scintigraphy were significantly more likely to be males, vitamin D deficient, with higher ALP concentrations, diagnosed with urolithiasis, and harbouring larger lesions. Conclusions. PHPT “phenotypes” correlated with disease severity are evidently linked to parathyroid scintigraphy detection rate. Therefore, it is crucial to know that false-negative imaging is more likely in PHPT patients with minor deviations in laboratory tests. Judicious assessment of biochemical and clinical features may limit the number of redundant parathyroid scintigraphies and, in consequence, reduce healthcare costs and unnecessary radiation exposure. Presentation: 6/2/2024

Latent personality profiles of analog astronauts: An unsupervised clustering method analysis

The selection of astronauts for space missions is an important process that involves the assessment of multiple factors, including personality traits. Previous studies have corroborated that these traits exert a significant influence on the performance and adaptation of the crew during the execution of space missions. In this study, International Personality Item Pool - NEO – 120 (IPIP-120) was used to assess the personality of participants in a sample of 43 analog astronauts who took part in 9 different analog missions between 2022 and 2023. The objective was to identify specific personality profiles among the analog astronauts using the unsupervised k-means clustering method. The centroids of each cluster were analyzed to describe distinctive personality profiles. The results revealed the existence of two distinct personality clusters among the analog astronauts. The first cluster showed a greater propensity toward adventure, intellect, goal striving, extroversion, and cooperation. In contrast, the second cluster exhibited lower scores on these traits. The identification of these two differentiated personality profiles reinforces the importance of personality assessment as a valuable tool in the astronaut selection process. Furthermore, the application of the k-means method demonstrates its utility as an effective technique for identifying underlying patterns in complex datasets. These findings may inform future astronaut selection strategies, contributing to the formation of more effective and cohesive teams for space missions.

CLUSTER ANALYSIS OF OBESITY RISK LEVELS USING K-MEANS AND DBSCAN METHODS

Obesity is defined as excessive fat accumulation and abnormal accumulation of adipose tissue in the human body that poses health risks. The causes of obesity are multifactorial and include environmental and individual factors. Several factors that cause obesity include genetic, behavioral and environmental factors. Obesity causes various problems in various fields, including health, employment, demographics, economics and family. The problem of obesity has a significant impact on public health. Therefore, understanding and predicting the level of obesity risk is important in efforts to prevent and treat obesity risk. Data on eating habits, physical activity, and other factors associated with obesity levels in certain populations can provide an important basis for understanding obesity risk. This research clusters the risk of obesity to find hidden patterns in the data. The stages in this research consist of pre-processing, clustering, and analysis. The clustering methods used are K-means and DBSCAN. In clustering using the K-means method with a parameter value of k , results are obtained with the same pattern as clustering using the DBSCAN method with a parameter value of epsilon and a minimum sample . In clustering using the K-means method with a parameter value of k , Four clusters were formed which had different patterns. The clustering results obtained in this research can be used as an effort to prevent and treat the risk of obesity.

PEMETAAN KOMPONEN PENGELUARAN WISATAWAN DI KAWASAN WISATA TORAJA

Toraja is a tourist area located in South Sulawesi province. Toraja is divided into two districts, Tana Toraja and North Toraja. Toraja has the charm of natural, traditional and cultural tourism that attracts foreign tourists and domestic tourists. In making a visit, these tourists certainly spend certain costs so that they can enjoy the tourism in Toraja. Tana Toraja and North Toraja district governments have not yet mapped the components of tourist expenditure on tourist expenditure while visiting Toraja. Data processing using the K-Means method. K-Means is a data maining method that provides a group description of an item. Tools used in data processing is RapidMiner application. The purpose of this study is to map or group the components of tourist expenditure in the Toraja tourism area. The results of this mapping there are 2 clusters formed, namely, cluster 0 which amounts to 79 and cluster 1 which amounts to 21, so that the results of this study can be used as a reference and benchmark for the Tana Toraja and North Toraja Regency governments and decision making for interested parties so as to improve the regional economy.

Extensive Exploration of The Preference Correlations Between Architectural Features and Musical Attributes

This study investigates the correlations between empirically-based preferences for architectural features and self-reported preferences for musical attributes. Altogether, 16 architectural attributes related to architectural complexity, indentation, symmetry, rhythm, pattern, and stress and 36 musical attributes of genres, perceived psychological attributes, Five Factors of Music, and 3-Factors are considered in the study, and their correlations are examined across 61 different demographic classes. In short, after gathering the data, Pearson’s correlation coefficient analysis examined the existence of correlation, and Bonferroni correction screened the most reliable ones. Then, categorization and K-mean clustering methods summarized the outcomes to provide a holistic understanding of the discovered correlations. The former reflected a higher number of correlations within genre and FFM in music, and indentation, complexity, and symmetry in architecture. The latter presented interesting correlation trends, including between complicated music and complicated architecture, rap music and the existence of pattern in architecture, and mellow music and simple architectural forms.

The Impact of Chinese New Year on Air Quality in North China Based on Machine Learning

The reduced economic and social activities during the Chinese New Year offer a unique opportunity to assess declines in anthropogenic emissions. However, limited research quantifies changes in PM2.5, NO2, and O3 concentrations during this period while accounting for meteorological conditions. This study utilized machine learning and the Time Warping-based K-Means method to evaluate the effectiveness of firework bans, the impact of emission reductions on pollutants during the Chinese New Year holiday, and the influence of meteorological conditions on pollutant concentrations during this period. Our findings reveal a significant reduction in emissions, with PM2.5 and NO2 concentrations decreasing by up to 24.76% and 33.39%, respectively, while O3 concentrations increased by up to 45%. Regions without firework bans saw peak PM2.5 levels on New Year’s Eve. The ban has been effective, though signs of relaxation appeared in 2023. It is worth noting that pollution during the 2018 Chinese New Year holiday was more severe than before the holiday because the meteorological conditions before the holiday were favorable for pollutant dispersion, while unfavorable meteorological conditions during the holiday masked the emission reductions that occurred due to the holiday period. These results emphasize the significant role of meteorological conditions and the need for stricter emission controls beyond traffic restrictions or factory shutdowns to mitigate haze pollution during adverse weather.