Development Of Assessment Model Research Articles

Development of a Deep Learning-Based Model for Pressure Injury Surface Assessment.

To develop a deep learning-based smart assessment model for pressure injury surface. Exploratory analysis study. Pressure injury images from four Guangzhou hospitals were labelled and used to train a neural network model. Evaluation metrics included mean intersection over union (MIoU), pixel accuracy (PA), and accuracy. Model performance was tested by comparing wound number, maximum dimensions and area extent. From 1063 images, the model achieved 74% IoU, 88% PA and 83% accuracy for wound bed segmentation. Cohen's kappa coefficient for wound number was 0.810. Correlation coefficients were 0.900 for maximum length (mean difference 0.068 cm), 0.814 for maximum width (mean difference 0.108 cm) and 0.930 for regional extent (mean difference 0.527 cm2). The model demonstrated exceptional automated estimation capabilities, potentially serving as a crucial tool for informed decision-making in wound assessment. This study promotes precision nursing and equitable resource use. The AI-based assessment model serves clinical work by assisting healthcare professionals in decision-making and facilitating wound assessment resource sharing. The STROBE checklist guided study reporting. Patients provided image resources for model training.

Development of an experimental model for assessment of palatal tissue decomposition by intraoral scanner.

Intraoral scanning of the palate is considered reliable for human identification; however, its accuracy on postmortem tissue remains dubious. This study aimed to investigate the effect of tissue decomposition on the precision of the intraoral scanner and the deviation of the scan. Ten fresh lamb (Ovies aries) maxillae were either unwashed or washed, selected, and stored at 20.5 °C and 80 % humidity for 20 days. Each palate was scanned three times a day with an Emerald S intraoral scanner. The anterior rugae area was cropped for analysis. The three scans of each day for each lamb were digitally aligned using the iterative closest point algorithm to ensure precision. The day one mesh was compared to each subsequent day to assess the postmortem scan deterioration, and a quadratic curve was fitted to the data. The mesh from different lambs was compared on day one to calculate the differences between the lambs. The length, location, and value of the largest curvatures of five randomly chosen rugae on each specimen were determined. A supervised machine learning procedure using linear discriminant classification assessed the specificity and sensitivity of singular ruga discrimination. Precision was significantly lower (p < 0.001) in the unwashed group (0.025 mm) compared to the washed group (0.013 mm), but the postmortem days had no effect. The deviation curve for the unwashed samples had a significantly higher quadratic term (p < 0.05) compared to the washed sample, indicating a slightly greater deterioration after day 11. The least difference between lambs was 0.484 mm. The deterioration curves crossed the minimum value on day 6 in both groups. The sensitivity of rugae detection was 0.89 on day one and decreased to 0.69 on day 20; the specificity ranged from 0.59 to 0.66. Intraoral scanning is an accurate approach for postmortem palatal imaging. Superimposition of the anterior palatal scan can accurately distinguish between lambs for up to six days. Nevertheless, deteriorated rugae can still be distinguished with moderate accuracy for up to 20 days.

Transfer Learning Estimation and Transferability of LNC and LMA Across Different Datasets

Leaf mass per area (LMA) and leaf nitrogen concentration (LNC) are both essential parameters in plant ecology, which can reflect the growth status of plants. The features of LMA and LNC can be captured using spectral reflectance in a remote sensing approach. While the relationships between spectra and leaf trait variance across different species with estimation performance are unclear, the development of assessment and transferable models to predicate LMA and LNC are prevented. Hence, we analyzed the variance of raw spectra and spectral data difference with four pretreated approaches (SG—Savitzky–Golay filter, SNV—Standard Normalized Variate, MSC—Multiplicative Scatter Correction analysis, and normalize), LMA, and LNC over six remote sensing datasets by a transfer component analysis (TCA) approach. Spectra combined with the Successive Projections Algorithm (SPA) were also presented to extract wavelengths with higher important coefficients to minimize the redundancy of datasets. The variance of normalized spectra between different datasets showed a minor degree of variance, and LNC spectra variance was decreased by the SPA. The results also showed that a smaller LMA and LNC variance is presented over different datasets when the trait values with higher distribution probabilities are close to each other. The LNC and LMA estimation performance in transfer models established by partial least squares regression (PLS), support vector regression (SVR), extreme gradient boosting (XGB), and random forest regression (RFR) algorithms across different datasets were employed, in which the RFR transfer models performed good prediction results. The relationships between spectra and leaf trait variance and estimation performance in RFR transfer models over different datasets were evaluated. LMA distance has a significant influence on estimation performance in the transfer model, and the variance of spectra with all pretreated approaches showed a very significant effect on LNC accession performance. Furthermore, we proposed a weight coefficient of spectral data updating combined with the TCA and RFR approach (WDT-RFR) transfer model to improve transferability between datasets and promote estimation performance in the transfer model. Compared to the RFR transfer model using spectra without updating, the root mean square error (RMSE) of the WDT-RFR transfer model with 5% samples transferred to estimate LMA and LNC increased by 7.9% and 4.8% on average, respectively. The estimation results showed that our transfer model showed a superior estimation performance.

Mitigating Health Risks Through Environmental Tracking of Pseudomonas aeruginosa.

Pseudomonas aeruginosa is a prevalent nosocomial pathogen and a significant reservoir of antimicrobial resistance genes in residential and built environments. It is also widespread in various indoor and outdoor settings, including sewage, surface waters, soil, recreational waters (both treated and untreated), and industrial effluents. Surveillance efforts for P. aeruginosa are primarily focused on hospitals rather than built environments. However, evidence links multidrug-resistant P. aeruginosa of human origin with activity in built environments and hospital settings. Consequently, tracking this pathogen across all environments is crucial for understanding the mechanisms of reverse transmission from built environments to humans. This review explores public health hygiene by examining the prevalence of P. aeruginosa in various environments, its sequence types, the factors contributing to multidrug resistance, and the identification methods through global surveillance. Whole-genome sequencing with sequence typing and real-time quantitative PCR are widely used to identify and study antimicrobial-resistant strains worldwide. Additionally, advanced techniques such as functional metagenomics, next-generation sequencing, MALDI-TOF, and biosensors are being extensively employed to detect antimicrobial-resistant strains and mitigate the ongoing evolution of bacterial resistance to antibiotics. Our review strongly underscores the importance of environmental monitoring of P. aeruginosa in preventing human infections. Furthermore, strategic planning in built environments is essential for effective epidemiological surveillance of P. aeruginosa and the development of comprehensive risk assessment models.

International organisations and global security: Evaluating decision-making effectiveness amid military risks

The purpose of this publication is a comprehensive study of the legal analysis of the effectiveness of international organisations in ensuring global security, the identification of critical problems, and proposals to improve the effectiveness of their activities, particularly decision-making, taking into account the provisions of national and international legislation under conditions of military risks. The research methodology consists of scientific cognition methods, highlighting specific effective strategies for improving global security. These include the dialectical method within the framework of interconnection of opposites and unities in the study of critical issues of international organisations in ensuring global security under military risks; the system-structural method studying complex systems and their interaction in the context of global security, considering specific political, economic, and social factors; descriptive method for a thorough characterisation of international organisations and their primary areas of activity, considering military risks; modelling development of appropriate models for risk assessment and the development of security strategies. The article's scientific novelty and practical significance lie in the fact that it highlights the cooperation of international organisations with Ukraine for the benefit of global security, analyses individual international organisations, and identifies their critical tasks considering military risks. Significant attention is paid to specific provisions of legal acts regulating the activities of international organisations and legal cases from Ukrainian courts (criminal, civil, and commercial) in which specific provisions of international acts are applied, as well as the use of corresponding norms in Ukrainian legislation.Additionally, specific proposals and mechanisms for the participation of international organisations in preventing and resolving military conflicts are suggested. Based on the research findings, conclusions are drawn regarding the overall assessment of the effectiveness of international organisations in ensuring global security under military risks and the possibilities for further development.

Grading adaptation for students with hearing impairments in WBL (Work-based learning) subjects: A preliminary study

The implementation of adaptive assessment models for students with hearing impairments in work-based learning (WBL) courses is essential to fostering an inclusive educational environment that accommodates diverse learning needs. This study purposes to identify and describe the adaptive assessment requirements for deaf students in inclusive schools, providing valuable insights for teachers in creating fair and accommodating assessment methods. The study method used a qualitative descriptive research design with observation, interviews and documentation techniques. Data analysis was carried out using the Miles and Huberman model including data collection, data reduction, data display and drawing conclusion or verification. The finding shows that the teachers at SMK Muhammadiyah 3 Yogyakarta and Pondok Pesantren Tuna Rungu emphasize the importance of adaptation in the assessment and learning system for students with hearing impairments, especially in the field of welding skills. Teachers express the necessity of an assessment approach that is not only fair but also allows students to showcase their competencies effectively despite their hearing limitations. The conclusion is a more effective and inclusive learning environment for people with hearing impairments can develop students' skills and make them feel valued in their learning process. The practical implications are designing and developing assessment models with inclusive standards to ensure effective learning outcomes for students with hearing impairments in vocational education environments.

Integrating Fuzzy-Based Evaluation Method to Analyse Attributes and Parameters for the Assessment Model Development

In this paper, an assessment model was developed based on the proposed integrated fuzzy-based evaluation method on students' mathematics learning ability. This model classifies six main attributes that structure the overall evaluation model into several parameters. The weightings of these main attributes and parameters were collected through fuzzy questionnaires among teachers and experts based on triangular fuzzy conjoint and fuzzy Delphi methodology. This highlighted integration contributes to a more reasonable and effective procedure for developing a structured and dynamic assessment model. It can reduce the problem of the measurement results obtained straying from the structure of the developed model due to procedural errors in identifying and analyzing the attributes and parameters of the model when it was developed. In addition, the presented case application also provides an analysis protocol that is simpler and easier compared to other complicated and complex approaches to developing assessment models.

Development and validation of a deep learning model for morphological assessment of myeloproliferative neoplasms using clinical data and digital pathology.

The subjectivity of morphological assessment and the overlapping pathological features of different subtypes of myeloproliferative neoplasms (MPNs) make accurate diagnosis challenging. To improve the pathological assessment of MPNs, we developed a diagnosis model (fusion model) based on the combination of bone marrow whole-slide images (deep learning [DL] model) and clinical parameters (clinical model). Thousand and fifty-one MPN and non-MPN patients were divided into the training, internal testing and one internal and two external validation cohorts (the combined validation cohort). In the combined validation cohort, fusion model achieved higher areas under curve (AUCs) than clinical or DL model or both for MPNs and subtype identification. Compared with haematopathologists with different experience, clinical model achieved AUCwhich was comparable to seniors and higher than juniors (p = 0.0208) for polycythaemia vera. The AUCs of fusion model were comparable to seniors and higher than juniors for essential thrombocytosis (p = 0.0141), prefibrotic primary myelofibrosis (p = 0.0085) and overt primary myelofibrosis (p = 0.0330) identification. In conclusion, the performances of our proposed models are equivalent to senior haematopathologists and better than juniors, providing a new perspective on the utilization of DL algorithms in MPN morphological assessment.

Basement Neo-Tectonics of Western Himalayas from Seismic and Gravity Data Perspective

An earthquake of magnitude (Mw) 4.3 occurring on April 6, 2024 near Sargodha (Mianwali NW Punjab, Pakistan) has been analyzed through waveform inversion to understand the subsurface geological structure. This shallow-depth (19 km) event represents a strike-slip faulting with a dextral sense of movement. Gravity data of the epicentral area depicts distinct anomalies representing two separate blocks showing an off-set in the same direction as determined by the seismic inversion validating modeling results. In our opinion, these structures represent second-order tectonics, potentially emerging as a response to the hindrance caused by the Sargodha High to southward movement of the Himalayan deformation front. Alternatively, R-shears associated with the western boundary of the Indian plate could provide another explanation for such strike-slip mechanism events. Crustal shortening along the deformation front is being accommodated through aseismic slip along a viscous décollement in the Salt Range and seismic slip within the brittle basement rocks of the Sargodha region as represented by the analyzed seismic event. This dual process plays a key role in shaping the tectonic features in study area. Detailed studies of small to moderate seismic events can help in delineating the subsurface seismogenic structures for development of better seismo-tectonic model for realistic seismic hazard assessment in the region.

The development of classification-based machine-learning models for the toxicity assessment of chemicals associated with plastic packaging

Assessing chemical toxicity in materials like plastic packaging is critical to safeguarding public health. This study presents the development of classification-based machine learning models to predict the toxicity of chemicals associated with plastic packaging. Using an extensive dataset of chemical structures, we trained multiple machine learning models—Random Forest, Support Vector Machine, Linear Discriminant Analysis, and Logistic Regression—targeting endpoints such as Neurotoxicity, Hepatotoxicity, Dermatotoxicity, Carcinogenicity, Reproductive Toxicity, Skin Sensitization, and Toxic Pneumonitis. The dataset was pre-processed by selecting 2D molecular descriptors as feature inputs, with resampling methods (ADASYN, Borderline SMOTE, Random Over-sampler, SVMSMOTE Cluster Centroid, Near Miss, Random Under Sampler) applied to balance classes for accurate classification. A five-fold cross-validation technique was used to optimize model performance, with model parameters fine-tuned using grid search. The model performance was evaluated using accuracy (Acc), sensitivity (Se), specificity (Sp), and area under the receiver operating characteristic curve (AUC-ROC) metrics. In most of the cases, the model accuracy was 0.8 or above for both training and test sets. Additionally, SHAP (SHapley Additive exPlanations) values were utilized for feature importance analysis, highlighting significant descriptors contributing to toxicity predictions. The models were ranked using the Sum of Ranking Differences (SRD) method to systematically select the most effective model. The optimal models demonstrated high predictive accuracy and interpretability, providing a scalable and efficient solution for toxicity assessment compared to traditional methods. This approach offers a valuable tool for rapidly screening potentially hazardous chemicals in plastic packaging.

Quantitative Seismic Damage Assessment of Resilient Concrete Columns Using Drift Ratio-Based Fractal Dimension.

The objective of this paper is to develop assessment models to quantitatively evaluate the seismic damage caused to resilient concrete columns intended for buildings located in strong-earthquake-prone regions such as Japan and China. The proposed damage assessment models are based on the fractal analysis of crack patterns on the surface of damaged concrete columns and expressed in the form of a fractal dimension (FD) versus transient drift ratio relationship. To calibrate the proposed damage assessment models, a total of eighty images of crack patterns for eight concrete columns were utilized. All the columns were reinforced by weakly bonded ultra-high-strength (WBUHS) rebars and tested under reversed cyclic loading. The experimental variables covered the shear span ratio of the column, the concrete strength, the axial load ratio, and the amount of steel in the WBUHS rebars. A box-counting algorithm was adopted to calculate or derive the FD of the crack pattern corresponding to each transient drift ratio. The test results reveal that the FD is an efficient image-based quantitative indicator of seismic damage degree for resilient concrete columns and correlates strongly with the transient drift ratio and is subjected to the influence of the shear span ratio. The influence of the other experimental variables on the derived FDs is, if any, little. Based on the test results, a linear equation was developed to define the relationships between the FD and transient drift ratio, and a multi-linear equation was formulated to relate the transient drift ratio to the residual drift ratio, an important index adopted in current design guidelines to measure the repairability of damaged concrete structures. To further verify the efficiency of the drift ratio-based FD in seismic damage assessment, the correlation between the FD and relative stiffness loss (RSL), an indicator used to measure the overall damage degree of concrete structures, was also examined. The driven FD exhibited very strong correlation with RSL, and an empirical equation was developed to reliably assess the overall seismic damage degree of resilient concrete columns with an FD.

Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA)

ObjectivesTotal tumor volume (TTV) is associated with overall and recurrence-free survival in patients with colorectal cancer liver metastases (CRLM). However, the labor-intensive nature of such manual assessments has hampered the clinical adoption of TTV as an imaging biomarker. This study aimed to develop and externally evaluate a CRLM auto-segmentation model on CT scans, to facilitate the clinical adoption of TTV.MethodsWe developed an auto-segmentation model to segment CRLM using 783 contrast-enhanced portal venous phase CTs (CT-PVP) of 373 patients. We used a self-learning setup whereby we first trained a teacher model on 99 manually segmented CT-PVPs from three radiologists. The teacher model was then used to segment CRLM in the remaining 663 CT-PVPs for training the student model. We used the DICE score and the intraclass correlation coefficient (ICC) to compare the student model’s segmentations and the TTV obtained from these segmentations to those obtained from the merged segmentations. We evaluated the student model in an external test set of 50 CT-PVPs from 35 patients from the Oslo University Hospital and an internal test set of 21 CT-PVPs from 10 patients from the Amsterdam University Medical Centers.ResultsThe model reached a mean DICE score of 0.85 (IQR: 0.05) and 0.83 (IQR: 0.10) on the internal and external test sets, respectively. The ICC between the segmented volumes from the student model and from the merged segmentations was 0.97 on both test sets.ConclusionThe developed colorectal cancer liver metastases auto-segmentation model achieved a high DICE score and near-perfect agreement for assessing TTV.Critical relevance statementAI model segments colorectal liver metastases on CT with high performance on two test sets. Accurate segmentation of colorectal liver metastases could facilitate the clinical adoption of total tumor volume as an imaging biomarker for prognosis and treatment response monitoring.Key PointsDeveloped colorectal liver metastases segmentation model to facilitate total tumor volume assessment.Model achieved high performance on internal and external test sets.Model can improve prognostic stratification and treatment planning for colorectal liver metastases.Graphical

Development of a machine learning-based risk assessment model for loneliness among elderly Chinese: a cross-sectional study based on Chinese longitudinal healthy longevity survey

BackgroundLoneliness is prevalent among the elderly and has intensified due to global aging trends. It adversely affects both mental and physical health. Traditional scales for measuring loneliness may yield biased results due to varying definitions. The advancements in machine learning offer new opportunities for improving the measurement and assessment of loneliness through the development of risk assessment models.MethodsData from the 2018 Chinese Longitudinal Healthy Longevity Survey, involving about 16,000 participants aged ≥ 65 years, were used. The study examined the relationships between loneliness and factors such as functional limitations, living conditions, environmental influences, age-related health issues, and health behaviors. Using R 4.4.1, seven assessment models were developed: logistic regression, ridge regression, support vector machines, K-nearest neighbors, decision trees, random forests, and multi-layer perceptron. Models were evaluated based on ROC curves, accuracy, precision, recall, F1 scores, and AUC.ResultsLoneliness prevalence among elderly Chinese was 23.4%. Analysis identified 15 evaluative factors and evaluated seven models. Multi-layer perceptron stands out for its strong nonlinear mapping capability and adaptability to complex data, making it one of the most effective models for assessing loneliness risk.ConclusionThe study found a 23.4% prevalence of loneliness among elderly individuals in China. SHAP values indicated that marital status has the strongest evaluative value across all forecasting periods. Specifically, elderly individuals who are never married, widowed, divorced, or separated are more likely to experience loneliness compared to their married counterparts.

Development and Validation of a Heat Transfer Model for Quality Assessment in Tunnel Sheet Welding Using Thermal Imaging Remote Sensing

Development and Validation of a Heat Transfer Model for Quality Assessment in Tunnel Sheet Welding Using Thermal Imaging Remote Sensing

The Development of the Lean Six Sigma Readiness Assessment Model for the Hotel Sector

ABSTRACT Lean Six Sigma (LSS) implementation still shows a high failure rate. Lack of readiness is one of the causes. Readiness assessment requires special exploration of each sector, including the hotel sector, where there is still no development of an LSS readiness assessment model. This study aims to develop a readiness assessment model for LSS implementation in the hotel sector. Data processing in the readiness assessment model uses the fuzzy logic method, is translated again into linguistic terms using Euclidean distance, and is ranked using the TOPSIS approach. The literature review produced 34 Readiness Factors (RF) that were validated by eight credible hotel practitioners and used as guidelines in conducting LSS readiness assessments in the hotel sector. Case studies were conducted on Hotel A and Hotel B, which showed that Hotel A was “Very Ready” and Hotel B was “Ready” to implement LSS. This research is perhaps the first of its kind in the hotel sector. This research also uses the Delphi method to collect data on the importance level, which may not have been done in collecting data on LSS readiness in any sector.

Beyond pain privacy and pain meters: a new vision for pain biomarkers.

To an individual, pain is unambiguously real. To a caregiver, assessing pain in others is a challenging process shrouded in doubt. To explain this challenge, many assume that pain "belongs" exclusively to the bearer of that experience and accept the dogma that pain is private. However, privacy also entails that it is not possible to identify, share, or communicate that experience with others. Obviously, this is not true and the consequences of pain privacy would be devastating for healthcare. Pain is indeed unique and subjective, but not necessarily private. Pain is in fact readily communicable, though perhaps not as effectively and reliably as caregivers would like. On the other hand, healthcare systems mandate objective metrics in pain diagnosis. Smiley face caricatures are a staple of clinical practice and a universal standard for reporting pain levels. These conditions create a double paradox: Assess a private experience that is inaccessible, and use numerical scales to measure subjective attributes. Navigating this stressful environment, medical professionals experience intellectual dissonance, patients are frustrated, and value-based care is undermined. Offering a way out, first, we refute the privacy and objectification of pain citing philosophical, behavioral, and neuroscientific arguments. We discuss Wittgensteinian views against privacy, explore the clear evolutionary advantage of communicating pain to others, and identify neural circuits in the mammalian brain that contribute to empathy. Second, we highlight the subjectivity of pain, embracing the complexity and uniqueness of an individual's pain. We also provide compelling evidence for brain mechanisms that actively shape the pain experience according to predictive coding principles. Third, we offer a vision for the development of biomarker technologies that assess pain fairly without engendering bias against the patient's narrative. Our recommendations are based on the overwhelming appreciation that "medicine by emoji" is inadequate for capturing the multidimensional nature of pain. Our view is that the most promising candidates for pain biomarkers consist of self-reports as ground truth augmented by physiological signatures of biological relevance to pain. Integration of subjective and objective multimodal features will be key for the development of comprehensive pain assessment models.

Development and validation of a recurrence risk assessment model for high-grade bladder cancer based on TCGA and GEO.

Bladder cancer is one of the most commonly diagnosed urinary cancers worldwide. Although muscle-invasive bladder cancer (MIBC) accounts for only 25% of bladder cancer cases, it has a high recurrence rate and poor prognosis, especially among high-grade cases. Despite the existence of some molecular markers, there is a clear clinical need for a robust recurrence prediction model that can assist in patient management and therapeutic decision-making. Therefore, we aimed to use public databases to develop such an effective assessment model. We developed a recurrence risk assessment model for high-grade bladder cancer based on the clinical information of 217 cases from The Cancer Genome Atlas (TCGA) and profiles of 87 samples from GSE31684 in the Gene Expression Omnibus (GEO) database. Edge R was used to analyze differences between RNAs of bladder cancer in the TCGA database, with thresholds of P<0.05 and |log2(fold change)| >1; least absolute shrinkage and selection operator (LASSO) Cox regression models were used to screen the RNAs significantly related to recurrence with minimum λ. Survival receiver operating characteristic (ROC) and area under the curve (AUC) was used to assess the predictive accuracy of the model in the training and validation sets of GSE31684. There were 2,876 differential RNAs obtained from TCGA data. Among a total of 284 RNAs identified as significantly related to recurrence of bladder cancer, 49 were obtained by LASSO regression, and 30 were finally obtained by multifactor risk regression to construct a risk assessment model. The model was found to predict the prognosis of bladder cancer recurrence well, with an AUC of 0.911 in the TCGA training set and an adjusted AUC value of 0.839 in the GEO validation set. The recurrence assessment model is a relatively accurate recurrence prediction tool for high-grade bladder cancer and could provide a guidance for the treatment of bladder cancer.

Harnessing probabilistic neural network with triple tree seed algorithm-based smart enterprise quantitative risk management framework

Enterprise risk management (ERM) frameworks convey vital principles that help create a consistent risk management culture, irrespective of employee turnover or industry standards. Enterprise Management System (EMS) are becoming a popular research area for assuring a company’s long-term success. Statistical pattern recognition, federated learning, database administration, visualization technology, and social networking are all used in this field, which includes artificial intelligence (AI), data science, and statistics. Risk assessment in EMS is critical for enterprise decision-making to be effective. Recent advancements in AI, machine learning (ML), and deep learning (DL) concepts have enabled the development of effective risk assessment models for EMS. This special issue seeks groundbreaking research articles that showcase the application of applied probability and statistics to interdisciplinary studies. This study offers Improved Metaheuristics with a Deep Learning Enabled Risk Assessment Model (IMDLRA-SES) for Smart Enterprise Systems. Using feature selection (FS) and DL models, the provided IMDLRA-SES technique estimates business risks. Preprocessing is used in the IMDLRA-SES technique to change the original financial data into a usable format. In addition, an FS technique based on oppositional lion swarm optimization (OLSO) is utilized to find the best subset of features. In addition, the presence or absence of financial hazards in firms is classified using the triple tree seed algorithm (TTSA) with a probabilistic neural network (PNN) model. The TTSA is used as a hyperparameter optimizer to improve the efficiency of the PNN-based categorization. An extensive set of experimental evaluations is performed on German and Australian credit datasets to illustrate the IMDLRA-SES model’s improved performance. The performance validation of the IMDLRA-SES model portrayed a superior accuracy value of 95.70% and 96.09% over existing techniques.

Assessment strategy based on authentic assessment to identify high school students' ability in assessing drama texts and drama performances

Drama learning plays an important role in training students to sharpen their expressive abilities in performing arts. This study aims to develop and implement an authentic assessment-based assessment strategy to identify high school students' ability to assess drama texts and drama performances. The research method used is research and development (R&amp;D) which involves several stages, namely needs analysis, instrument design, and assessment model development. The R&amp;D model used in this research is the ADDIE model (Analysis-Design-Develop-Implement-Evaluate). The results showed that the developed authentic assessment model can improve students' ability to assess drama texts and performances. Teachers who use this model find it helpful in developing more effective and comprehensive assessment instruments. In addition, students showed improvement in critical thinking and evaluation skills, as well as the ability to identify and assess important elements in drama and performance texts. This study suggests that the implementation of authentic assessment strategies can make a positive contribution towards improving the quality of assessment in a secondary school setting.

Development of Digital Transformation Maturity Assessment Model for Collaborative Factory Involving Multiple Companies

Recent advancements in digital transformation (DX) in the industrial sector have spotlighted digital collaborative factories, which emphasize relationships with partners, particularly in the manufacturing sector. However, existing DX maturity assessment models primarily focus on evaluating individual companies, lacking consideration of partnerships and thereby failing to reflect the complexities of collaborative systems. To address this limitation, this study aims to develop a DX maturity assessment model tailored to digital collaborative factories while accounting for collaborative relationships. Initially, 25 existing DX maturity assessment models were reviewed, and the evaluation elements related to collaboration were extracted from each. Accordingly, the maturity assessment model was created with 15 evaluation factors, including organizational aspects, process management, quality control, and logistics operations. Finally, to verify the applicability of the model, the DX maturity levels of a lead company—a forklift-manufacturing company—and its partner—an automotive component manufacturer—within the same value chain were assessed, and the model’s suitability was evaluated. The results indicate that the lead company needed to improve on the intelligence, connectivity, and automation aspects, while its partner needs to streamline production process operations and technological connectivity. This approach enables manufacturers to obtain more reliable information in resolving issues arising from collaboration with partners, as well as in establishing future strategies. The findings suggest that strengthening collaboration systems among partners and advancing DX based on digital collaboration will raise competitiveness within the manufacturing sector.