K-means Research Articles

Autonomous particle-shape-based classification and identification of calcareous soils through machine learning

Recent geotechnical and geological applications have highlighted numerous challenges associated with conventional particle-size based soil classification, particularly for special calcareous soils widely used in marine and offshore constructions. Calcareous soils are always characterized by complex microstructures in terms of loose fabric, irregular particle shapes and abundant intra-particle pores. Therefore, this study aims to establish an autonomous particle-shape categorization criteria for calcareous soils, and further facilitate their intelligent particle identification and classification using image-based machine learning (ML) techniques. First, an extensive collection of images of individual calcareous sand particles were acquired through microscopic photography to establish the datasets for ML training. Four key shape parameters including circularity, roundness, aspect ratio and convexity were measured based on image processing and analysis. Subsequently, an unsupervised ML algorithm, K-means clustering, was applied to these shape parameters to autonomously determine optimal particle-shape categories for calcareous soils. Finally, based on the obtained particle shape classes, two supervised CNN algorithms, AlexNet and YOLO-v3, were trained and applied to automatically identify and classify individual particles or particle assemblies of calcareous soils from various raw image types. The predictive results demonstrate the high accuracy and efficiency of ML models in identifying and classifying the particle shapes of calcareous soils.

Comprehensive analysis of the prognostic and immunological role of cavins in non-small cell lung cancer

Caveolae, specialized and dynamic subdomains of the plasma membrane, have a crucial role in diverse cellular functions encompassing endocytosis, signal transduction, mechanosensation, lipid storage, and metabolism. Cavin family proteins are indispensable for caveolar formation and function. An increasing number of studies have found that cavins are involved in tumor growth, invasion, metastasis, and angiogenesis and may have dual roles in the regulation of cancer. However, the expression and prognostic value of cavins in non-small cell lung cancer (NSCLC) remain unexplored. In this study, the expression, survival data, immune infiltration, and functional enrichment of cavins in patients with NSCLC were investigated using multiple databases. Furthermore, different subtypes of cavin-binding proteins were identified through protein-protein interaction networks and k-means clustering. The results showed that the expression of Cavin-1–3 in NSCLC tissues was significantly lower than that in normal tissues, and that Cavin-2 is the major subtype of cavin that inhibits NSCLC progression. It regulates downstream signaling pathways, modulates the infiltration of immune cells and influences the prognosis of NSCLC. Related experiments also confirmed that Cavin-2 promotes the proliferation and metastasis of NSCLC cells. These findings suggest that cavins and their binding proteins may be novel biomarkers for NSCLC prognosis and immunotherapy, providing new treatment options for NSCLC.

Transformer model-based multi-scale fine-grained identification and classification of regional traffic states

To address the limitations in precision of conventional traffic state estimation methods, this article introduces a novel approach based on the Transformer model for traffic state identification and classification. Traditional methods commonly categorize traffic states into four or six classes; however, they often fail to accurately capture the nuanced transitions in traffic states before and after the implementation of traffic congestion reduction strategies. Many traffic congestion reduction strategies can alleviate congestion, but they often fail to effectively transition the traffic state from a congested condition to a free-flowing one. To address this issue, we propose a classification framework that divides traffic states into sixteen distinct categories. We design a Transformer model to extract features from traffic data. The k-means algorithm is then applied to these features to group similar traffic states. The resulting clusters are ranked by congestion level using non-dominated sorting, thereby dividing the data into 16 levels, from Level 1 (free-flowing) to Level 16 (congested). Extensive experiments are conducted using a large-scale simulated traffic dataset. The results demonstrate significant advancements in traffic state estimation achieved by our Transformer-based approach. Compared to baseline methods, our model exhibits marked improvements in both clustering quality and generalization capabilities.

Decoding Consumer Minds in the Age of Online Accommodation Reviews: A Client Profiling Approach

In the era of online accommodation reviews, understanding the consumer mind is essential for the hospitality industry. This study seeks to profile consumers based on their reservation decisions made after reviewing online feedback and to explore the complex relationship between consumer perceptions and their decision-making processes. To lay a solid foundation for this research, a thorough bibliometric analysis was conducted to map the existing literature and identify key trends in the field. Data were collected using a non-probability convenience sampling method through an online survey targeting Romanian residents. Performing a hierarchical cluster analysis, followed by a K-means cluster analysis, distinct consumer segments with varying levels of trust and responsiveness were identified. The four primary clusters are Young Risk-Averse Planners, Trust-Oriented Quality Seekers, Skeptical Detail Seekers and Independent Value Seekers. Each segment displayed unique preferences regarding the types of reviews they value and their influence on booking decisions. These findings highlight the need for hotel managers and marketers to develop tailored strategies that cater to the diverse needs of consumers, enhancing service delivery and promoting sustainable tourism practices. This research provides valuable insights into the dynamics of online reviews and stresses the importance of understanding consumer perceptions in navigating the complexities of today’s hospitality industry.

Arthritis and Public Health Monitoring: Longitudinal Changes of Triglyceride-Glucose Index Associated with Arthritis in a Cohort of Older Chinese Adults.

The current decade 2021-2030 was designated by the United Nations as the decade of healthy aging, which underlines the need for public health innovation for arthritis clinical care. The triglyceride-glucose (TyG) index is a novel and emerging parameter closely associated with diabetes and cardiovascular diseases and has been suggested to indicate the risk of arthritis. This study examined the longitudinal changes of TyG levels in relation to arthritis among a nationwide cohort of older Chinese adults. We recruited 1257 participants from a national cohort of older Chinese adults, the Chinese Longitudinal Healthy Longevity Survey. On the basis of the longitudinal changes in TyG between 2012 and 2014, we performed a k-means clustering analysis to classify the participants into four TyG groups: Class 1 with moderate and stable levels of TyG; Class 2 with low but rising level of TyG; Class 3 with consistently high TyG; and Class 4 with high and TyG-level rise compared with the baseline. After a 2-year follow-up, logistic regression was used to identify the association between TyG and the onset of arthritis. Compared with individuals in Class 1, those in Class 3 and Class 4 experienced a higher risk of arthritis, with an odds ratio (OR) of 2.823 (95% confidence interval [CI]: 1.113-7.160) and 2.848 (95% CI: 1.299-6.246), respectively. To the best of our knowledge, this is the first study exploring the association between dynamic longitudinal changes in TyG and arthritis. Further studies on world populations are called for.

Machine Learning and Deep Learning for Crop Disease Diagnosis: Performance Analysis and Review

Crop diseases pose a significant threat to global food security, with both economic and environmental consequences. Early and accurate detection is essential for timely intervention and sustainable farming. This paper presents a review of machine learning (ML) and deep learning (DL) techniques for crop disease diagnosis, focusing on Support Vector Machines (SVMs), Random Forest (RF), k-Nearest Neighbors (KNNs), and deep models like VGG16, ResNet50, and DenseNet121. The review method includes an in-depth analysis of algorithm performance using key metrics such as accuracy, precision, recall, and F1 score across various datasets. We also highlight the data imbalances in commonly used datasets, particularly PlantVillage, and discuss the challenges posed by these imbalances. The research highlights critical insights regarding ML and DL models in crop disease detection. A primary challenge identified is the imbalance in the PlantVillage dataset, with a high number of healthy images and a strong bias toward certain disease categories like fungi, leaving other categories like mites and molds underrepresented. This imbalance complicates model generalization, indicating a need for preprocessing steps to enhance performance. This study also shows that combining Vision Transformers (ViTs) with Green Chromatic Coordinates and hybridizing these with SVM achieves high classification accuracy, emphasizing the value of advanced feature extraction techniques in improving model efficacy. In terms of comparative performance, DL architectures like ResNet50, VGG16, and convolutional neural network demonstrated robust accuracy (95–99%) across diverse datasets, underscoring their effectiveness in managing complex image data. Additionally, traditional ML models exhibited varied strengths; for instance, SVM performed better on balanced datasets, while RF excelled with imbalanced data. Preprocessing methods like K-means clustering, Fuzzy C-Means, and PCA, along with ensemble approaches, further improved model accuracy. Lastly, the study underscores that high-quality, well-labeled datasets, stakeholder involvement, and comprehensive evaluation metrics such as F1 score and precision are crucial for optimizing ML and DL models, making them more effective for real-world applications in sustainable agriculture.

A Snow-Based Hydroclimatic Aggregate Drought Index for Snow Drought Identification

Climate change has increased the risk of snow drought, which is associated with a deficit in snowfall and snowpack. The objectives of this research are to improve drought identification in a warming climate by developing a new snow-based hydroclimatic aggregate drought index (SHADI) and to assess the impacts of snowpack and snowmelt in drought analyses. To derive the SHADI, an R-mode principal component analysis is performed on precipitation, snowpack, surface runoff, and soil water storage. Then, a joint probability distribution function of drought frequencies and drought classes, conditional expectation, and k-means clustering are used to categorize droughts. The SHADI was applied to the Red River of the North Basin (RRB), a typical cold climate region, to characterize droughts in a mostly dry period from 2003 to 2007. The SHADI was compared with the hydroclimatic aggregate drought index (HADI) and U.S. drought monitor (USDM) data. Cluster analysis was also utilized as a benchmark to compare the results of the HADI and SHADI. The SHADI showed better alignment with cluster analysis results than the HADI, closely matching the identified dry/wet conditions in the RRB. The major differences between the SHADI and HADI were observed in cold seasons and in transition periods (dry to wet or wet to dry). The derived variable threshold levels for different categories of drought based on the SHADI were close to, but different from, those of the HADI. The SHADI can be used for short-term lead prediction of droughts in cold climate regions and, in particular, can provide an early warning for drought in the warming climate.

SK-PSO: A Particle Swarm Optimization Framework with SOM and K-Means for Inverse Kinematics of Manipulators

In this paper, a particle swarm optimizer that integrates self-organizing maps and k-means clustering (SK-PSO) is proposed. This optimizer generates an asymmetric Cartesian space from random joint configurations when addressing the inverse kinematics of manipulators, followed by K-means clustering applied to the Cartesian space. The resulting clusters are used to reduce the dimensionality of the corresponding joint space using Self-Organizing Maps (SOM). During the solving process, the target point’s clustering region is determined first, and then the joint space point closest to the target point is selected as the initial population for the particle swarm algorithm. The simulation results demonstrate the effectiveness of the SK-PSO algorithm. Given the inherent asymmetry among different algorithms in handling the problem, SK-PSO achieves an average fitness value that is 0.02–0.62 times better than five other algorithms, with an asymmetric solving time that is only 0.03–0.34 times that of the other algorithms. Therefore, compared to the other algorithms, the SK-PSO algorithm offers high accuracy, speed, and precision.

Ecosystem Services Trade-Offs in the Chaohu Lake Basin Based on Land-Use Scenario Simulations

Amid global environmental degradation, understanding the spatiotemporal dynamics and trade-offs of ecosystem services (ESs) under varying land-use scenarios is critical for advancing the sustainable development of social–ecological systems. This study analyzed the Chaohu Lake Basin (CLB), focusing on four scenarios: natural development (ND), economic priority (ED), ecological protection (EP), and sustainable development (SD). Using the PLUS model and multi-objective genetic algorithm (MOGA), land-use changes for 2030 were simulated, and their effects on ESs were assessed quantitatively and qualitatively. The ND scenario led to significant declines in cropland (3.73%) and forest areas (0.18%), primarily due to construction land expansion. The EP scenario curbed construction land growth, promoted ecosystem recovery, and slightly increased cropland by 0.05%. The SD scenario achieved a balance between ecological and economic goals, maintaining relative stability in ES provision. Between 2010 and 2020, construction land expansion, mainly concentrated in central Hefei City, led to a marked decline in habitat quality (HQ) and landscape aesthetics (LA), whereas water yield (WY) and soil retention (SR) improved. K-means clustering analysis identified seven ecosystem service bundles (ESBs), revealing significant spatial heterogeneity. Bundles 4 through 7, concentrated in mountainous and water regions, offered high biodiversity maintenance and ecological regulation. In contrast, critical ES areas in the ND and ED scenarios faced significant encroachment, resulting in diminished ecological functions. The SD scenario effectively mitigated these impacts, maintaining stable ES provision and ESB distribution. This study highlights the profound effects of different land-use scenarios on ESs, offering insights into sustainable planning and ecological restoration strategies in the CLB and comparable regions.

Interactive Geographic Visualization and Unsupervised Learning for Optimal Assignment of Preachers to Appropriate Congregations

Riau Province has a population of 6,642,874 and a diverse geography, which poses significant challenges in optimizing Islamic preaching activities. Traditional assignment methods often lead to inefficiencies due to misalignment between the preacher’s expertise and congregational needs, as well as logistical issues. This study integrates K-Means clustering and DBSCAN algorithms with interactive geographic visualization to optimize the assignment of preachers to mosques. We collected 435 data points, including 185 mosques and 250 preachers. K-Means was evaluated using the Elbow Method and Silhouette Score, identifying 10 clusters as optimal with a Silhouette Score of 0.435654. However, K-Means does not handle outliers effectively, as indicated by zero outliers in all configurations. DBSCAN was tested with various epsilon (eps) and minimum sample values. The optimal configuration with eps of 1.5 and 5 minimum samples resulted in 10 clusters with a Silhouette Score of 0.381108 and 60 outliers. DBSCAN effectively manages outliers and varying densities. Although K-Means is advantageous for its simplicity and higher Silhouette Scores, it is unable to handle outliers effectively. DBSCAN provides robust clustering for noisy data. Therefore, it can be concluded that hybridizing unsupervised learning algorithms with geographic visualization can potentially improve the effectiveness of preaching activities in Riau Province and enhance preacher assignment.

A Study on Wild and Domestic Animal Detection for Farm Protection by using Computer Vision

Crop protection against wild animal intrusion has become a pressing challenge with significant social and economic implications, particularly in agricultural-dependent nations like India. In response, an innovative AI-driven surveillance system is designed to detect and determine potential threats from animals to farm environments. The system accurately identifies and classifies animals in farm images by leveraging advanced computer vision techniques and machine learning algorithms, including Support Vector Machines, K-Means clustering, Random Forest, Decision Trees, and Logistic Regression. The model generalizes effectively by analyzing a diverse dataset comprising various animal species. Key features such as accuracy, precision, recall, F1-score, and confusion matrices are employed to assess model performance comprehensively. The results showcase high accuracy across multiple algorithms. The proposed system offers a promising solution to protect crops, minimize losses, and foster harmonious coexistence between farming and wildlife. The results demonstrate good accuracy for various algorithms: 92.75% for Logistic Regression, 86.47% for Decision Trees, 95.65% for Random Forests, and 94.20% for Support Vector Machines. This highlights how reliable the system is in classifying animals, providing a viable way to safeguard crops, reduce losses, and promote peaceful cohabitation between agriculture and wildlife.

Prediction of soft tissue sarcoma grading using intratumoral habitats and a peritumoral radiomics nomogram: a multi-center preliminary study

BackgroundAccurate identification of pathologic grade before operation is helpful for guiding clinical treatment decisions and improving the prognosis for soft tissue sarcoma (STS).PurposeTo construct and assess a magnetic resonance imaging (MRI)-based radiomics nomogram incorporating intratumoral habitats (subregions of clusters of voxels containing similar features) and peritumoral features for the preoperative prediction of the pathological grade of STS.MethodsThe MRI data of 145 patients with STS (74 low-grade and 71 high-grade) from 4 hospitals were retrospectively collected, including enhanced T1-weighted and fat-suppressed-T2-weighted sequences. The patients were divided into training cohort (n = 102) and validation cohort (n = 43). K-means clustering was used to divide intratumoral voxels into three habitats according to signal intensity. A number of radiomics features were extracted from tumor-related regions to construct radiomics prediction signatures for seven subgroups. Logistic regression analysis identified peritumoral edema as an independent risk factor. A nomogram was created by merging the best radiomics signature with the peritumoral edema. We evaluated the performance and clinical value of the model using area under the curve (AUC), calibration curves, and decision curve analysis.ResultsA multi-layer perceptron classifier model based on intratumoral habitats and peritumoral features combined gave the best radiomics signature, with an AUC of 0.856 for the validation cohort. The AUC of the nomogram in the validation cohort was 0.868, which was superior to the radiomics signature and the clinical model established by peritumoral edema. The calibration curves and decision curve analyses revealed good calibration and a high clinical application value for this nomogram.ConclusionThe MRI-based nomogram is accurate and effective for predicting preoperative grading in patients with STS.

BUSINESS INTELLIGENCE FOR DETERMINING PROMOTIONAL MEDIA

Abstract—In 2021-2022, SMK Dirgantara Putra Bangsa experienced a decrease in the number of prospective students who registered. This condition encourages schools to innovate and be creative in choosing effective promotional media in disseminating information on New Student Admissions (PPDB) to the public widely and routinely, with the aim of attracting more new students. This promotional effort involves the use of various types of promotional media. Business intelligence plays a role in processing organizational data into useful information to improve performance, by analyzing historical data which is then used to support decision making and planning. The K-Means algorithm is one of the clustering methods that is often used because of its ease of implementation and its ability to minimize the sum of squared error (SSE) value between data and the specified centroid. The collaboration between Business Intelligence and K-Means clustering is expected to help SMK Dirgantara Putra Bangsa in choosing the right promotional media and creating new innovations in disseminating PPDB information to the public.Keywords— PPDB, Business intelligence, K-Means clustering, Media Promosi

Modified ensemble machine learning-based plant leaf disease detection model with optimized K-Means clustering

ABSTRACT In the farming sector, the automatic detection of plant leaf disease is considered a vital landmark. Farmers move long distances to consult pathologists to observe the disease, which is expensive and time-consuming. Moreover, detection of disease in a premature period is a difficult process in the existing model. Thus, all these challenges motivate us to develop an inventive plant leaf disease detection model. In the developed model, the data is gathered initially and given as input to the pre-processing step using Contrast Limited Adaptive Histogram Equalization (CLAHE). Next, the leaves are segmented from the pre-processed images, and then abnormality segmentation is done by the K-means clustering system. Here, parameters are optimized using the Opposition-based Bird Swarm Algorithm (O-BSA). Further, features were extracted from abnormality-segmented images in feature extraction. The extracted features are given in the classification step, where leaf disease detection is carried out using Optimized Ensemble Machine Learning (OEML), where, parameter optimization is done by O-BSA. Finally, the developed plant leaf detection approach is evaluated with various performance metrics, and given an accuracy of up to 92.26. These findings show that the developed model is promising over conventional methods and its effectiveness in detecting plant leaf disease.

Machine Learning Reveals Demographic Disparities in Palliative Care Timing Among Patients With Traumatic Brain Injury Receiving Neurosurgical Consultation.

Timely palliative care (PC) consultations offer demonstrable benefits for patients with traumatic brain injury (TBI), yet their implementation remains inconsistent. This study employs machine learning methods to identify distinct patient phenotypes and elucidate the primary drivers of PC consultation timing variability in TBI management, aiming to uncover disparities and inform more equitable care strategies. Data on admission, hospital course, and outcomes were collected for a cohort of 232 patients with TBI who received both PC consultations and neurosurgical consultations during the same hospitalization. Patient phenotypes were uncovered using principal component analysis and K-means clustering; time-to-PC consultation for each phenotype was subsequently compared by Kaplan-Meier analysis. An extreme gradient boosting model with Shapley Additive Explanations identified key factors influencing PC consultation timing. Three distinct patient clusters emerged: cluster A (n = 86), comprising older adult White women (median 87years) with mild TBI, received the earliest PC consultations (median 2.5days); cluster B (n = 108), older adult White men (median 81years) with mild TBI, experienced delayed PC consultations (median 5.0days); and cluster C (n = 38), middle-aged (median: 46.5years), severely injured, non-White patients, had the latest PC consultations (median 9.0days). The clusters did not differ by discharge disposition (p = 0.4) or inpatient mortality (p > 0.9); however, Kaplan-Meier analysis revealed a significant difference in time-to-PC consultation (p < 0.001), despite no differences in time-to-mortality (p = 0.18). Shapley Additive Explanations analysis of the extreme gradient boosting model identified age, sex, and race as the most influential drivers of PC consultation timing. This study unveils crucial disparities in PC consultation timing for patients with TBI, primarily driven by demographic factors rather than clinical presentation or injury characteristics. The identification of distinct patient phenotypes and quantification of factors influencing PC consultation timing provide a foundation for developing for standardized protocols and decision support tools to ensure timely and equitable palliative care access for patients with TBI.

A Climate Adaptation Asset Risk Management Approach for Resilient Roadway Infrastructure

As climate change intensifies, roadway infrastructure is increasingly at risk from extreme weather events including floods, hurricanes, and wildfires. This paper presents a system-of-systems performance-based asset risk management approach, designed to integrate various elements for effective investment prioritization and infrastructure resilience. Central to this approach are an Asset Inventory Database and a Risk Registry Database, supported by a Common Reference Location System (GIS). These components are the foundation for analytical modules to assess vulnerability and resilience based on exposure, sensitivity, and adaptive capacity. The approach includes an actionable framework to support a proactive data-driven performance-based management process for prioritizing investments. The project prioritization process consists of four steps: identifying risk factors, integrating climate data, conducting advanced risk assessments, and project prioritization. The goal is to prioritize resource allocation and develop climate-adaptive risk mitigation management strategies. Key performance indicators (KPIs) are recommended for setting goals, monitoring the outcomes of these strategies, and measuring their benefits. A Climate Impact Vulnerability Score (CIVS) is proposed to assess the susceptibility of infrastructure assets to environmental conditions. The approach also leverages artificial intelligence (AI) tools to analyze roadway infrastructure vulnerabilities and climate risk exposure. A case study applied to bridges using k-means clustering and multi-criteria decision analysis (MCDA) demonstrates the potential of advanced analytical methods in improving decision-making. This research concludes that the approach will contribute to enhancing resource allocation, supporting strategic decisions, aligning goals with budgets prioritizing investments, and strengthening the resilience and sustainability of roadway infrastructure.

Wind and Photovoltaic Power Generation Forecasting for Virtual Power Plants Based on the Fusion of Improved K-Means Cluster Analysis and Deep Learning

Virtual power plants (VPPs) have emerged as an innovative solution for modern power systems, particularly for integrating renewable energy sources. This study proposes a novel prediction approach combining improved K-means clustering with Time Convolutional Networks (TCNs), a Bi-directional Gated Recurrent Unit (BiGRU), and an attention mechanism to enhance the forecasting accuracy of wind and photovoltaic power generation in VPPs. The proposed TCN-BiGRU-Attention model demonstrates superior predictive performance compared to traditional models, achieving high accuracy and robustness. These results provide a reliable basis for optimizing VPP operations and integrating renewable energy sources effectively.

Classification of Mandarin-speaking persons with aphasia: a discussion on validating the classification function of WAB-R

ABSTRACT Background The classical aphasia taxonomy has been incorporated into several widely utilised aphasia assessment tools, such as the Western Aphasia Battery (WAB). Validation of the WAB’s classification typically involves comparing it with statistical clustering analysis results, using overall agreement rates as the referential index. Nevertheless, previous studies have documented diverse agreement rates. The classification function of the Mandarin version of the revised WAB (WAB-R) has not been validated. Additionally, the discussion on validating classification function is inadequate. Aim The current study adopts the argument-based validation framework to validate the classification function of the Mandarin version of the WAB-R and discuss the efficacy of using cluster analysis as evidence for the validation. Methods & Procedures A validation argument for the classification function was developed, utilising the k-means cluster analysis and within-group linkage cluster analysis as statistical procedures. WAB-R testing score data were collected from 122 Mandarin-speaking persons with acquired aphasia (non-acute). Eight clusters were expected to be generated from statistical procedures as a confirmatory test. To explore the impact of cluster numbers, solutions of generating six and ten clusters were conducted for comparative analysis. The potential reasons for mismatches were analysed. A proposed modified fluency scale (raising the cutoff score from 4 to 5) was also tested on the current dataset. Outcomes & Results Under the solution of eight clusters, the overall agreement was 62.3% with the k-means cluster analysis and 56.6% with the within-group linkage cluster analysis. Agreement rates slightly increased with the number of clusters in the within-group linkage method and remained almost unchanged in the k-means method. Anomic aphasia presented the highest agreements, while the agreements of other subtypes varied across different solutions. The fundamental differences between the clustering algorithm and the rationale of the WAB-R classification criteria were the primary reason for mismatched cases, undermining the reliability of the validation procedure. The modified fluency scale was found to significantly improve the overall agreement rates. Conclusions The classification function of the WAB-R’s Mandarin adaptation was considered acceptable under the current method. The validation argument is suggested to be modified to enhance the rationale as the statistical cluster analysis showed reliability issues when being solely employed for validation. The mismatch rate did not form direct challenges to the validity of the classification function. Additionally, modifications to the classification criteria are suggested for further exploration as the modified fluency scale has demonstrated positive results.

A New Use Strategy of Artificial Intelligence Algorithms for Energy Optimization in Plastic Injection Molding

Plastic injection molding is a widespread industrial process in manufacturing. This article investigates the energy consumption in the injection molding process of fruit containers, proposing a new use strategy for the application of artificial intelligence algorithms. The aim is to optimize the process parameters, such as the mold temperatures, the injector temperatures, and the cycle time, to minimize energy consumption. This new use strategy, a hybrid use strategy, combines an unsupervised autoencoder with the K-Means algorithm to analyze production data and identify factors influencing energy consumption. The results show the capability of discovering different operating modes at different levels of energy requirements. An analysis of the process parameters reveals that the number of parts left to complete production, the current cycle counter, the number of shots left to complete the production, the material needed to complete the production, and the total time dedicated to production, so far, are the most relevant features for the optimization of the energy consumption per single piece. The study demonstrates the potential of common artificial intelligence algorithms if appropriately used to improve the sustainability of the plastic injection molding process.

The impact of neglecting feature scaling in k-means clustering.

Despite the popularity of k-means clustering, feature scaling before applying it can be an essential yet often neglected step. In this study, feature scaling via five methods: Z-score, Min-Max normalization, Percentile transformation, Maximum absolute scaling, or RobustScaler beforehand was compared with using the raw (i.e., non-scaled) data to analyze datasets having features with different or the same units via k-means clustering. The results of an experimental study show that, for features with different units, scaling them before k-means clustering provided better accuracy, precision, recall, and F-score values than when using the raw data. Meanwhile, when features in the dataset had the same unit, scaling them beforehand provided similar results to using the raw data. Thus, scaling the features beforehand is a very important step for datasets with different units, which improves the clustering results and accuracy. Of the five feature-scaling methods used in the dataset with different units, Z-score standardization and Percentile transformation provided similar performances that were superior to the other or using the raw data. While Maximum absolute scaling, slightly more performances than the other scaling methods and raw data when the dataset contains features with the same unit, the improvement was not significant.