Management Decision-making Research Articles

Two decades of stakeholder voices: Exploring engagement in Romania's FSC forest management certification

Stakeholders' engagement in forest management decision-making is a critical tool for enhancing the business acceptability of the forest sector, and the Forest Stewardship Certification (FSC) scheme proactively involves stakeholders in its implementation. Based on the stakeholder theory, this study examined stakeholder's engagement in the FSC forest management certification in Romania over the past two decades to identify the extent and inputs of their involvement in the process. Using in-depth content analysis and text mining techniques, we explored publicly available information from 209 public reports covering 45 forest management certificates. According to data available in 178 reports, the average number of stakeholders notified per audit was 50.7. However, response evidence was found in 128 reports, with an average of 1.2 responses per audit, suggesting a limited engagement in the process. Additional stakeholders' feedback was received as part of the on-site audits, with an average of 10.2 responses per audit. Given the inconsistencies in the reporting format between certification bodies, we set a structured framework to analyse the findings on stakeholders' engagement from different report sections. The employed analytical framework sheds light on stakeholder and legitimacy theories in forest certification. Our findings highlighted stakeholders' predominantly positive feedback tone, evenly distributed across all stakeholder types and the four analysis domains. Negative feedback accounted for only 9.4% of the findings, highlighting areas for improvement for certificate holders, companies in the timber supply chain and public authorities. This study's findings may assist FSC in refining its stakeholder engagement practices, contributing to enhanced participation and better risk mitigation of non-compliance with standard requirements.

Developing a Novel Prognostic Model Based on Muscle-Invasive Bladder Cancer Types: A Multicenter RetrospectiveCohort Study of Patients Who Received Radical Cystectomy and Chemotherapy.

To develop a prognostic model to manage patients with muscle-invasive bladder cancer (MIBC) undergoing radical cystectomy (RC) and chemotherapy. Clinicopathologic characteristics and survival data were collated from a North American database to develop a model. Genomic and clinicopathologic data were also obtained from European and Asian databases to externally validate the model. Patients were classified as either "primary" or "progressive" MIBC according to non-muscle invasive stage history. Optimized cancer-specific survival (CSS) models, based on MIBC types, were constructed using Cox's proportional hazard regression. Differences of biological function and tumor immunity, between two risk-based groups stratified according to the prognostic model, were estimated. There were 2631 participants in the American cohort, 291 in the European cohort and 142 in the Asian cohort. Under Cox's regression analysis, tumor stage, lymph node stage, age, ethnicity, and MIBC types were independent CSS predictors (all p < 0.05). The constructed nomogram, whichintegratedthese variables, improved the predictivepower. This model had good discrimination and calibration. Patients were categorized into high- or low-risk groups according to the total points calculated. Kaplan-Meier curves revealed that patients in the high-risk group had poorer survival (p < 0.001). This was confirmed with two external validation cohorts (both with p < 0.001). Higher stromal scores and increased M0 and M2 macrophage numbers were observed in samples from the high-risk group, whereas regulatory T cells had lower infiltration in these populations (all with p < 0.05). This MIBC type-based nomogram provides accurate CSS predictions, which could help improve patient management and clinical decision-making.

Optimizing Inventory Model for Negative Exponential and Linear Split Demand and Gompertz Distribution Deterioration with Shortages

This article introduces a mathematical model for optimizing total profit by considering various complex factors, including time-dependent shortages, split demand, Gompertz distribution degradation, a linear holding cost function, and partial backlog issues. The two stages of demand, which are time-dependent linear demand and price-dependent exponential demand, occur when there are no shortages. A comprehensive approach to inventory management decision-making is illustrated through a sensitivity analysis and numerical example, highlighting the influence of system limitations on the optimization outcomes. This model is an effective tool for improving inventory management practices and assessing concavity while maximizing profitability. With MATLAB, relationships between model parameters are graphically represented.

Actuation Drones in Agriculture: Advancing Precision Pest Management through Biocontrol and Modern Techniques

As global food demand surges, agricultural technology is essential for addressing challenges like environmental degradation, pollution, and water scarcity. Drones, or Unmanned Aerial Vehicles (UAVs), present a promising solution for precision agriculture by providing real-time, accurate data that enhances decision-making in crop management. In pest control, drones offer targeted delivery of natural enemies and biopesticides, improving efficiency and reducing reliance on chemical pesticides. This precision can lead to increased crop yields, reduced environmental impact, and improved livelihoods for farmers by lowering operational costs and optimizing resource use. Despite their potential, adopting drone technology in agriculture faces regulatory challenges, such as the need for certifications, flight restrictions, and operational guidelines. Addressing these regulatory hurdles is crucial for broader implementation. Moreover, collaboration among stakeholders—including researchers, policymakers, agricultural extension workers, and industry players—is vital for advancing drone-assisted pest management and ensuring its practical adoption in diverse farming environments. As we navigate these challenges, actuation drones hold immense promise for transforming pest management practices globally, contributing to sustainable agriculture and enhanced food security. Further research, development, and stakeholder engagement are necessary to fully realize the potential of drones in integrated pest management (IPM) systems.

Statistical and machine learning models for predicting spalling in CRCP

Continuously reinforced concrete pavement (CRCP), crucial for the resilience of transportation infrastructure owing to its continuous steel reinforcement, confronts a critical challenge in the form of spalling—a distress phenomenon posing a threat to pavement durability and overall structural integrity. The detachment or breakage of concrete from the surface compromises CRCP’s functionality and raises safety concerns and escalating maintenance costs. To address this pressing issue, our study investigates the multifaceted factors influencing spalling, employing a comprehensive approach that integrates statistical and machine learning techniques for predictive modeling. Descriptive statistics meticulously profile the dataset, emphasizing age, thickness, precipitation, temperature, and traffic parameters. Regression analysis unveils key relationships, emphasizing the significance of age, annual temperature, annual precipitation, maximum humidity, and the initial International Roughness Index (IRI) as influential factors. The correlation matrix heatmap guides feature selection, elucidating intricate interdependencies. Simultaneously, feature importance analysis identifies age, Average Annual Daily Traffic (AADT), and total pavement thickness as crucial contributors to spalling. In machine learning, adopting models, including Gaussian Process Regression and ensemble tree models, is grounded in their diverse capabilities and suitability for the complex task at hand. Their varying predictive accuracies underscore the importance of judicious model selection. This research advances pavement engineering practices by offering nuanced insights into factors influencing spalling in CRCP, refining our understanding of spalling influences. Consequently, the study not only opens avenues for developing improved predictive methodologies but also enhances the durability of CRCP infrastructure, addressing broader implications for informed decision-making in transportation infrastructure management. The selection of Gaussian Process Regression and ensemble tree models stems from their adaptability to capture intricate relationships within the dataset, and their comparative performance provides valuable insights into the diverse predictive capabilities of these models in the context of CRCP spalling.

A novel coal quality index and its estimation using diffuse reflectance spectroscopy

ABSTRACT An essential component of coal’s efficient use and large-scale environmental impact management is evaluating its quality. This study introduces a novel quality indexing technique that incorporates multiple coal properties, providing a comprehensive measure of coal quality. Conventional methods for assessing coal quality, such as proximate and ultimate analyses, are often time-consuming, costly, and require extensive sample preparation, prompting the need for a more efficient approach. In this study, we used the minimum dataset (MDS) approach to estimate a comprehensive coal quality index (CQI) and show that the diffuse reflectance spectroscopy (DRS) may be used as a rapid, nondestructive technique for estimating CQI as a single quality indicator for coal. A total of 212 coal samples of different ranks and grades are collected from the Tertiary and Gondwana coal basins of India. Ten chemical properties of coal were measured following the conventional laboratory-based methods. The spectral responses of the coal samples were measured across the visible-NIR-SWIR (350–2500 nm) range. The MDS approach was adopted while estimating the CQI from the lab-based coal quality parameters. We also examined different chemometric models for estimating CQI values from spectroscopic data. Results showed that the feature selection-based partial-least-square regression (PLSRFS) model may be used to estimate CQI with coefficient of determination (R2) values as high as 0.7 with root-mean-squared error (RMSE) of 0.06. While CQI serves as a single coal quality parameter, the capability to use the DRS approach as a rapid and noninvasive sensing approach for coal quality assessment provides new opportunity to characterize coal quality in an instant and cost-effective manner, especially, when a large number of coal samples have to be tested. The integration of the CQI with DRS could facilitate better decision-making in coal utilization and management, leading to optimized performance and reduced environmental impact.

Real world data for real world problems: Importance of appropriate spatial resolution modelling to inform decision makers in marine management

Effective management of marine ecosystems requires informed decision-making based on accurate, comprehensive and appropriate data. Mapping habitats can form an important part of these processes so that decision makers can ensure the pressures exerted by human activities can be assessed while considering the sensitivity of the environment. Predictive models can be utilised to understand the distribution of species and habitats (e.g. biotopes) without incurring the expense of wide scale surveys. If predictive models are used in decision-making care must be taken in interpreting model results. The spatial resolution at which habitat modelling is conducted can greatly influence the decision outcomes. Whilst national resolution habitat maps serve as valuable resources for informing overarching policy making, for development level decisions fine resolution habitat information is needed. This paper explores the importance of spatial resolution modelling in marine management decision-making processes, using four spatial resolutions (50 m, 100 m, 200 m and 500 m) to model the presence of a protected habitat, maerl beds, within the Fetlar-Haroldswick Marine Protected Area in the Shetland Islands, Scotland. Outputs were compared for model performance between the resolutions and area of modelled maerl bed coverage. Simulations of real-world marine activities, explore the magnitude of overlap attributable to varied spatial resolution models, with an emphasis on the presumed ‘need’ for management. This study shows the importance of considering spatial resolution in modelling outputs and highlights the challenges associated with using models to guide decision-making, direct pressures on protected habitats, and cumulative impacts. It carries significance for maximising economic opportunity while safeguarding marine features. For real-world applications coarse resolution data may suffice for strategic, large-scale decisions, but finer resolutions are imperative for consenting or managing individual marine activities. By emphasising the need for appropriate spatial resolution modelling, these findings contribute to the development of sustainable management strategies that are appropriate to the scale of the decision. Addressing the complexities of real-world decision-making and understanding the magnitude of spatial resolution required for the marine environment are a crucial principle that can also enhance and be applied to other disciplines including, terrestrial ecology, urban planning and the assessment of potential climate change impacts. Failing to model appropriately means that real-world pressures and impacts occurring on a finer scale then the available data may have their impacts over or underestimated, hindering effective governance. Whilst we are striving to meet our national and international obligations and objectives through effective marine governance, this paper highlights the challenges of real-world decision-making where data is not yet available at a suitable resolution to address these issues.

The Impact of Prospect Theory on Asset Forecasting: A Comparative Study Based on Random Forest and Linear Regression

This study focuses on the application of predictive models and prospect theory in the field of machine learning to predict financial asset prices. Here, the linear regression and random forest algorithms were employed to forecast the price values and fluctuations of two different financial assets: the S&amp;P 500 index and Bitcoin prices. Meanwhile, this study compared the performance of different financial asset datasets before and after the introduction of prospect theory models. Through calculation and comparative analysis, this article provides an in-depth discussion on the predictive performance of regression models and classification models. The research results indicate that in most cases, simple linear regression models have high prediction accuracy. Meanwhile, this paper also found that introducing prospect theory can effectively improve the accuracy of prediction models for specific financial assets. This result has a positive impact on the financial industry, helping to optimize risk management and investment decision-making, improving efficiency at the market level and promoting information transparency, while also promoting the development of emerging financial formats in financial innovation

Evaluation of Pedotransfer Functions to Estimate Soil Water Retention Curve: A Conceptual Review

The soil water retention curve (SWRC) is a vital soil property used to evaluate the soil’s water holding capacity, a critical factor in various applications such as determining soil water availability for plants, soil conservation and management, climate change adaptation, and mitigation of flood risks. Estimating SWRC directly in the field and laboratory is a time-consuming and laborious process and requires numerous instruments and measurements at a specific location. In this context, various estimation approaches have been developed, including pedotransfer functions (PTFs), over the past three decades to estimate soil water retention and its associated properties. Despite the efficiencies, PTFs and semi-physical approach-based models often have several limitations, particularly in the dry range of the SWRC. PTFs-based modeling has become a key research topic due to readily available soil data and cost-effective methods for deriving essential soil parameters, which enable more efficient decision-making in sustainable land-use management. Therefore, advancement and adjustment are necessary for reliable estimations of the SWRC from readily available data. This article reviews the evaluation of the current and past PTFs for estimating the SWRC. This study aims to evaluate PTF techniques and semi-physical approaches based on soil texture, bulk density, porosity, and other related factors. Additionally, it also assesses the performance and limitations of various common semi-physical models proposed and developed by Arya and Paris, Haverkamp and Parlange, the Modified Kovács model by Aubertin et al., Chang and Cheng, Meskini-Vishkaee et al., Vidler et al., and Zhai et al. This assessment will be effective for researchers in this field and provide valuable insight into the importance of new PTFs for modeling SWRC.

Leveraging deep learning and computer vision technologies to enhance management of coastal fisheries in the Pacific region

This paper presents the design and development of a coastal fisheries monitoring system that harnesses artificial intelligence technologies. Application of the system across the Pacific region promises to revolutionize coastal fisheries management. The program is built on a centralized, cloud-based monitoring system to automate data extraction and analysis processes. The system leverages YoloV4, OpenCV, and ResNet101 to extract information from images of fish and invertebrates collected as part of in-country monitoring programs overseen by national fisheries authorities. As of December 2023, the system has facilitated automated identification of over six hundred nearshore finfish species, and automated length and weight measurements of more than 80,000 specimens across the Pacific. The system integrates other key fisheries monitoring data such as catch rates, fishing locations and habitats, volumes, pricing, and market characteristics. The collection of these metrics supports much needed rapid fishery assessments. The system’s co-development with national fisheries authorities and the geographic extent of its application enables capacity development and broader local inclusion of fishing communities in fisheries management. In doing so, the system empowers fishers to work with fisheries authorities to enable data-informed decision-making for more effective adaptive fisheries management. The system overcomes historically entrenched technical and financial barriers in fisheries management in many Pacific island communities.

Strategic Accounting for Innovation: Empowering Entrepreneurship in the Modern Era

This study explores how modern accounting practices drive entrepreneurial success. Through a comprehensive literature review, case study analysis of successful entrepreneurial firms, and interviews with companies that have implemented innovative accounting practices, this research uncovers the pivotal role of adaptive accounting in financial planning, risk management, and strategic decision-making. The findings highlight that companies utilizing advanced accounting tools are better equipped to handle the complexities of modern business, achieve greater financial transparency, and drive continuous innovation. The study also emphasizes the importance of accounting education and professional development in leveraging technology for these purposes. Additionally, the implications for policymakers and stakeholders underscore the necessity of a regulatory framework that supports advanced accounting practices. This study provides valuable insights for practitioners aiming to utilize modern accounting as a catalyst for business innovation and entrepreneurial success.

Crop Growth Analysis Using Automatic Annotations and Transfer Learning in Multi-Date Aerial Images and Ortho-Mosaics

Growth monitoring of crops is a crucial aspect of precision agriculture, essential for optimal yield prediction and resource allocation. Traditional crop growth monitoring methods are labor-intensive and prone to errors. This study introduces an automated segmentation pipeline utilizing multi-date aerial images and ortho-mosaics to monitor the growth of cauliflower crops (Brassica Oleracea var. Botrytis) using an object-based image analysis approach. The methodology employs YOLOv8, a Grounding Detection Transformer with Improved Denoising Anchor Boxes (DINO), and the Segment Anything Model (SAM) for automatic annotation and segmentation. The YOLOv8 model was trained using aerial image datasets, which then facilitated the training of the Grounded Segment Anything Model framework. This approach generated automatic annotations and segmentation masks, classifying crop rows for temporal monitoring and growth estimation. The study’s findings utilized a multi-modal monitoring approach to highlight the efficiency of this automated system in providing accurate crop growth analysis, promoting informed decision-making in crop management and sustainable agricultural practices. The results indicate consistent and comparable growth patterns between aerial images and ortho-mosaics, with significant periods of rapid expansion and minor fluctuations over time. The results also indicated a correlation between the time and method of observation which paves a future possibility of integration of such techniques aimed at increasing the accuracy in crop growth monitoring based on automatically derived temporal crop row segmentation masks.

PREVENTION OF TECHNOLOGICAL EMERGENCIES IN THE WARFARE ZONE

In a war zone, there are potential risks of the spread of an emergency due to harmful (polluting) substances in the environment above the maximum permissible concentrations. The causes of the danger are explosions, detonations, chemical spills, military vehicles, shelling or destruction of the infrastructure of oil facilities, and damage to the infrastructure of water supply and drainage. Method of preventing emergencies of a technological nature includes procedures using modern technologies and information systems to ensure timely response and minimise risks for the population and the environment. The algorithm for implementing the method of technological emergency prevention due to harmful (polluting) substances in the atmospheric air above the maximum permissible concentration in the combat zone consists of procedures. Procedures include work on planning and preparation, measurement and data collection, data analysis and processing, management decision-making, and control. Using a laser complex to prevent emergencies is an innovative approach that helps to identify potential threats and control their development accurately and effectively. The laser complex solves the dual task of detecting and immediately evaluating polluting gases and aerosols. The article also describes the algorithm for preventing technological emergencies due to harmful (polluting) substances in drinking water above the maximum permissible concentration in the combat zone. Groundwater is the predominant object of danger. The procedures consist of collecting and analysing statistical data, deciding the priority of monitoring areas, determining goals by types of hazards, setting tasks, choosing a monitoring scheme, determining monitoring procedures and their characteristics, solving monitoring issues, monitoring, making management decisions to limit the spread of the consequences of hazards. Effective emergency prevention procedures planned and carried out using modern tools and instruments can contain the spread of the consequences of a technological emergency, limiting the number of victims and injured and the area of hazard spread. Keywords: soil, air, monitoring, laser complex, emergency.

Therapeutic inertia in obesity management among people living with obesity from the perspective of general/family practitioners in Canada: A mixed-methods study.

This mixed-methods study aimed to explore factors contributing to therapeutic inertia among people living with obesity in Canada from the perspective of general/family practitioners (GP/FPs). One-on-one interviews and online surveys guided by the Theoretical Domains Framework were conducted. A total of 20 general/family practitioners were interviewed and 200 general/family practitioners were surveyed. Key findings from interviews were used to guide the development of the survey. Spearman's correlation analysis evaluated the association between general/family practitioners theme domain scores and their familiarity with the 2020 Canadian Adult Obesity Clinical Practice Guidelines. The 200 general/family practitioners surveyed provided representation across Canada, with diversity in age, background, and gender. The most prominent domains related to therapeutic inertia that were positively influenced by familiarity with Clinical Practice Guidelines were Beliefs about Capabilities (rs = .27; p < .01), Skills (rs = .23; p < .01), Behavioural Regulation (rs = .24; p < .01) and Emotions (rs = .23; p < .01). Irrespective of their familiarity with Clinical Practice Guidelines, most general/family practitioners reported that environmental and contextual barriers impact obesity management. Particularly, while financial barriers were reported by participants regardless of Clinical Practice Guidelines familiarity, general/family practitioners familiar with Clinical Practice Guidelines more often reported having time to discuss obesity management with patients. This study identified perceptions, resource and training considerations that contribute to healthcare decision-making and therapeutic inertia in obesity management among general/family practitioners and highlighted key areas to target with interventions in primary care to facilitate obesity management, which should be multi-faceted, with a focus on incorporating obesity education into healthcare providers training programs and improving systemic and financial support.

Deep learning infused SIRVD model for COVID-19 prediction: XGBoost-SIRVD-LSTM approach.

The global impact of the ongoing COVID-19 pandemic, while somewhat contained, remains a critical challenge that has tested the resilience of humanity. Accurate and timely prediction of COVID-19 transmission dynamics and future trends is essential for informed decision-making in public health. Deep learning and mathematical models have emerged as promising tools, yet concerns regarding accuracy persist. This research suggests a novel model for forecasting the COVID-19's future trajectory. The model combines the benefits of machine learning models and mathematical models. The SIRVD model, a mathematical based model that depicts the reach of the infection via population, serves as basis for the proposed model. A deep prediction model for COVID-19 using XGBoost-SIRVD-LSTM is presented. The suggested approach combines Susceptible-Infected-Recovered-Vaccinated-Deceased (SIRVD), and a deep learning model, which includes Long Short-Term Memory (LSTM) and other prediction models, including feature selection using XGBoost method. The model keeps track of changes in each group's membership over time. To increase the SIRVD model's accuracy, machine learning is applied. The key properties for forecasting the spread of the infection are found using a method called feature selection. Then, in order to learn from these features and create predictions, a model involving deep learning is applied. The performance of the model proposed was assessed with prediction metrics such as R 2, root mean square error (RMSE), mean absolute percentage error (MAPE), and normalized root mean square error (NRMSE). The results are also validated to those of other prediction models. The empirical results show that the suggested model outperforms similar models. Findings suggest its potential as a valuable tool for pandemic management and public health decision-making.

Improving ML-based landslide susceptibility using ensemble method for sample selection: a case study of Kangra district in Himachal Pradesh, India.

Developing effective strategies to predict areas susceptible to landslides and reducing risk is vital. This involves using ensemble methods to meet the precise prediction and addressing challenges like data limitation. Recent studies have highlighted the potential of using ensemble methods to enhance the prediction of landslide susceptibility maps (LSM). Ensemble methods present a sampling of landslides and non-landslide points from high and low susceptible areas, respectively. Extensive research has explored their application in machine learning processes, particularly in classification-related problems. This study delves into strategies of ensemble as a promising method in future landslide applications. The proposed method was tested considering Kangra district of Himachal Pradesh as study area where three datasets were prepared consisting of presence and absence points. Dataset 1 consisted of initial landslide and randomly generated non-landslide points. In dataset 2, additional landslide points obtained from the very high susceptibility of initial LSM were supplemented with initial landslide data, while the non-landslide points were generated randomly from the study area. Finally, dataset 3 was composed of the landslide points as in dataset 2, and the non-landslide points were obtained from the very low susceptible areas of initial LSM. These datasets are used with random forest (RF) and support vector machine (SVM), thereby preparing six landslide susceptibility maps. To analyze the applicability of the proposed method, we have used metrics such as AUC-ROC, precision, recall, F-score, accuracy and Mathew's correlation coefficient (MCC). The AUC for dataset 1 with SVM and RF is 0.89, which increased to 0.898 and 0.952 for datasets 2 and 3 with SVM and 0.937 and 0.954 with RF. Among all the methods, the precision and recall values were highest for dataset 3 with SVM as well as RF. Hence, based on several accuracy metrics, we conclude that when the landslides and non-landslides samples were sampled from very high and very low susceptible areas respectively, the LSM performed better than all the other methods. Sampling landslides from very high susceptible areas only (dataset 2) does not perform well thereby committing misclassification error. The study demonstrated that the landslide and non-landslide data were obtained from very high and very low susceptibility; the predictive capability of the LSM increased significantly. Thus, the results demonstrate the effectiveness of the proposed ensemble approach in providing precise delineation of landslide zones, facilitating informed decision-making for land and hazard management.

Hotel demand forecasting with multi-scale spatiotemporal features

Accurate demand forecasting is critical to hotel revenue management and related decision-making. Considering the heterogeneity and dynamics of spatial effects across different time scales, this study introduces a novel model which can deeply extract these features to improve the forecasting performance of hotel demand. Specifically, the model constructs input variables with different periodicities and then integrates a Transformer neural network and long short-term memory to extract multi-scale and dynamic spatiotemporal features to generate accurate forecasts. The effectiveness of the model is verified through an empirical case in Xiamen, China. Results suggest our model significantly outperforms benchmarks in terms of accuracy and robustness. The findings extend the application of spatial-temporal modeling in hotel demand forecasting. Hotel managers can use our forecasts to optimize operations, improve revenues, and control risks. The extracted spatiotemporal features can also help managers examine cooperation and competition relationships with neighbor hotels.

Multiscale Conditional Adversarial Networks based domain-adaptive method for rotating machinery fault diagnosis under variable working conditions

Deep learning has been increasingly used in health management and maintenance decision-making for rotating machinery. However, some challenges must be addressed to make this technology more effective. For example, the collected data is assumed to follow the same feature distribution, and sufficient labeled training data are available. Unfortunately, domain shifts occur inevitably in real-world scenarios due to different working conditions, and acquiring sufficient labeled samples is time-consuming and expensive in complex environments. This study proposes a novel domain adaptive framework called deep Multiscale Conditional Adversarial Networks (MCAN) for machinery fault diagnosis to address these shortcomings. The MCAN model comprises two key components. Constructed by a novel multiscale module with an attention mechanism, the first component is a shared feature generator that captures rich features at different internal perceptual scales, and the attention mechanism determines the weights assigned to each scale, enhancing the model’s dynamic adjustment and self-adaptation capabilities. The second component consists of two domain classifiers based on Bidirectional Long Short-Term Memory (BiLSTM) leveraging spatiotemporal features at various levels to achieve domain adaptation in the output space. The deep domain classifier also captures the cross-covariance dependencies between feature representations and classifier predictions, thereby improving the predictions’ discriminability. The proposed method has been evaluated using two publicly available fault diagnosis datasets and one condition monitoring experiment. The results of cross-domain transfer tasks demonstrated that the proposed method outperformed several state-of-the-art methods in terms of transferability and stability. This result is a significant step forward in deep learning for health management and maintenance decision-making for rotating machinery, and it has the potential to revolutionize its future application.

Examining the importance of neighborhood natural, and built environment factors in predicting older adults' mental well-being: An XGBoost-SHAP approach

BackgroundPrevious studies have shown that urban neighborhood environmental factors significantly influence the health outcomes of urban older adults. However, most cross-sectional studies exploring the health effects of these factors have failed to quantify the relative importance of each factor. MethodsWe use XGBoost machine learning techniques and SHAPley Additive Interpretation (SHAP) to rank the importance of urban neighborhood environmental factors in shaping the mental health of urban older adults. To address self-selection bias in housing choice, we distinguish older adults living in private housing from those living in public as residents in private housing have more freedom to choose where to live. ResultsThe results show that both natural and built environmental factors in urban neighborhoods are important predictors of mental well-being scores. Five natural environmental factors (blue space, perceived greenery quantity, NDVI, street view greenness, aesthetic quality) and three built environmental factors (physical activity facilities quality, physical activity facilities quantity, neighborhood disorder) had considerable predictive power for mental well-being scores in two groups. Among them, blue space, perceived greenery quantity and street view greenness quantity became less important after controlling for self-selection bias, possibly because of the unequal distribution of quantity and quality, and the performance of neighborhood disorder, aesthetic quality and physical activity facilities quality was more sensitive in public housing. ConclusionsThese results highlight the nuanced and differential effects of neighborhood environmental exposures on mental well-being outcomes, depending on housing preferences. The results of this study can provide support for decision makers in urban planning, landscape design and environmental management in order to improve the mental well-being status of urban older adults.

Perceptions of Faculty Members at Jordanian Universities for the Efficiency of Crisis Management at the University (Corona Pandemic as a Model)

This study aims to find out the perceptions and opinions for faculty members from Jordanian universities about the efficiency of crisis management at the university, through (planning in crisis management, information in crisis management, communications in crisis management, decision-making in crisis management, and the crisis management team). Corona crisis as a model for crises. The study followed the descriptive and analytical approach, whereby the study population consisted of all faculty members at Jordanian universities, and the questionnaire was used as a tool for data collection. Then it was distributed to the sample of the study randomly that its (163) members. Then the data analyzed through the statistical program SPSS. The results showed that the perceptions of faculty members from Jordanian universities are that the level of efficiency crisis management in the university is moderate, especially during the Corona pandemic crisis. So that crisis management at the university needs to be restructured. The study recommended variable future studies in the same for a different population in the sample