Consistent Ranking Research Articles

Application of Multi Criteria Decision Making Methods for the Determination of the Best Dressing Factors for Surface Grinding Hardox 500

This study applies Multi-Criteria Decision-Making (MCDM) methods to identify the optimal dressing parameters for the surface grinding of Hardox 500 steel. The investigation focuses on three key objectives: Surface Roughness (SR), Material Removal Rate (MRR), and Wheel lifespan (Lw). Five dressing variables were considered: non-feeding dressing (nn), fine dressing depth (df), fine dressing times (nf), rough dressing depth (dr), and rough dressing times (nr). Three MCDM methods—Measurement of Alternatives and Ranking according to Compromise Solution (MARCOS), Simple Additive Weighting (SAW), and Evaluation based on Distance from Average Solution (EDAS)—were employed to solve the MCDM problem. Additionally, the Entropy technique was used to determine the criterion weights. A total of 16 experimental runs were conducted based on the L16 (44 x 21) design configuration. The analysis identified Option 7 as the optimal dressing mode, characterized by the input parameters: dr = 0.02 mm, nr = 3 times, df = 0.05 mm, nf = 3 times, and nn = 0. To validate the consistency of rankings obtained from the three MCDM methods, the Spearman’s rank correlation coefficient (R) was employed. The results demonstrated a strong correlation among the rankings, confirming the reliability of the proposed approach. These findings provide a robust framework for optimizing surface grinding parameters to enhance performance and productivity.

Enhancing energy resilience in enterprises: a multi-criteria approach

Unreliable energy supply disrupts productivity and escalates costs in manufacturing enterprises, highlighting the need for robust energy resilience strategies. Existing multi-criteria decision-making (MCDM) methods, such as the analytic hierarchy process (AHP), best–worst method (BWM), and unaugmented TOPSIS, often lack advanced risk prioritization and objective criteria weighting, limiting their effectiveness in addressing complex, multidimensional energy challenges. This study proposes an integrated framework that combines Failure Mode and Effects Analysis (FMEA) for risk prioritization, the CRITIC-method for objective criteria weighting based on the 4A’s energy resilience dimensions—availability, accessibility, affordability, and acceptability—and fuzzy-TOPSIS for strategy ranking. The framework bridges theoretical rigor with operational applicability, addressing the unique challenges faced by manufacturing enterprises. Validated through a real-world case study and sensitivity analysis, it identifies actionable strategies, such as flexible scheduling, demonstrating consistent rankings across comparative analyses with fuzzy VIKOR, WASPAS, and MARCOS. This sector-specific approach advances both academic understanding and industrial practice by providing a scalable, multidimensional tool for enhancing energy resilience.

Cell clone selection-impact of operation modes and medium exchange strategies on clone ranking.

Bioprocessing has been transitioning from batch to continuous processes. As a result, a considerable amount of resource was dedicated to optimising strategies for continuous production. However, the focus has been on developing a suitable and scalable perfusion strategy with little attention given to the selection of optimal cell clones. Cell line development and lead clone selection are critical to bioprocess development. The screening and selection process is typically performed in stages. Microwell plates (MWP) are used to narrow down the number of clone candidates, which will undergo further selective screening in progressively larger small-scale bioreactors (12mL-3L) to identify the top clone for GMP production. Perfusion mode is typically applied at bench-scale for optimisation purposes, while process development and cell clone screening studies at mL-scale still commonly use fed-batch methods. The change of operation mode from bolus feeding to perfusion with a regular exchange of medium, leads to questions regarding the reliability and fit of initial clone selection. Is the early-stage clone ranking impacted by the discrepancy in the operation mode, and does this potentially result in the exclusion of cell clones suitable for perfusion processes? To address this question, we evaluated various CHO cell clones expressing two antibody products using MWP methodologies in fed-batch and semi-perfusion mode. We assessed growth, metabolic, and productivity performance, and ranked cell clones using two different strategies. The first strategy evaluated clones based on a single parameter: the cell-specific productivity (qP). The second considered a collection of multiple parameters using the metric of the Manufacturability index (MICL). Both ranking strategies showed an impact of operation mode and perfusion rate on the clone ranking. Notably, depending on the chosen operation mode, different sets of candidate clones might have been selected for further, more extensive screening. Additionally, we evaluated the reproducibility of our results demonstrating consistency in cell clone growth performance and ranking.

Machine learning-based prediction of tree crown development in competitive urban environments

In urban forestry, managing trees is crucial for sustainable urban environments, especially in the context of climate change and the urban heat island effect. This research explores the complex dynamics of tree crown geometry development by asking the question: how do surrounding objects, such as nearby trees, buildings, and other urban structures, affect the shape of tree crowns? It aims to uncover how competition for light and space influences tree crown development in competitive urban environments. Our study employs machine learning models on six main species in Munich, using the measured data from the LiDAR scans, with the Hist Gradient Boosting Regressor (HGBR) emerging as the most promising performer across various metrics. Notably, the evaluation of 13 models reveals the HGBR’s consistent ranking as the best or second-best across all tree crown dimensions assessed, with R2 values reaching 0.83 for the tree height model and 0.7 on average for crown radiuses in eight directions. Employing SHapley Additive exPlanations (SHAP) values elucidate factors influencing model predictions, emphasising the significant impact of adjacent trees and buildings. After evaluating the models to include additional tree species in Munich, the models show strong predictive capabilities for some additional species. Despite the studies’ limitations - the models are only valid for selected species, and there are constraints in predicting tree crown start height - our findings contribute valuable insights for urban forestry management and planning.

The impact of trait number and correlation on functional diversity metrics in real-world ecosystems.

The use of trait-based approaches to understand ecological communities has increased in the past two decades because of their promise to preserve more information about community structure than taxonomic methods and their potential to connect community responses to subsequent effects of ecosystem functioning. Though trait-based approaches are a powerful tool for describing ecological communities, many important properties of commonly-used trait metrics remain unexamined. Previous work with simulated communities and trait distributions shows sensitivity of functional diversity measures to the number and correlation of traits used to calculate them, but these relationships have yet to be studied in actual plant communities with a realistic distribution of trait values, ecologically meaningful covariation of traits, and a realistic number of traits available for analysis. To address this gap, we used data from six grassland plant communities in Minnesota and New Mexico, USA to test how the number of traits and the correlation between traits used in the calculation of eight functional diversity indices impact the magnitude of functional diversity metrics in real plant communities. We found that most metrics were sensitive to the number of traits used to calculate them, but functional dispersion (FDis), kernel density estimation dispersion (KDE dispersion), and Rao's quadratic entropy (Rao's Q) maintained consistent rankings of communities across the range of trait numbers. Despite sensitivity of metrics to trait correlation, there was no consistent pattern between communities as to how metrics were affected by the correlation of traits used to calculate them. We recommend that future use of evenness metrics include sensitivity analyses to ensure results are robust to the number of traits used to calculate them. In addition, we recommend use of FDis, KDE dispersion, and Rao's Q when ecologically applicable due to their ability to produce consistent rankings among communities across a range of the numbers of traits used to calculate them.

The Diagnostic Histopathological Techniques of Prostate Cancer

The histology of the prostate is critical for understanding both normal prostate function and the pathogenesis of prostate cancer. The prostate gland comprises a complex architecture that includes a functional secretory epithelium, a basal epithelium, and a supporting stroma with a variety of cell types. Prostate adenocarcinoma is the most common form of prostate cancer, characterized by acinar-type architecture. The consistent ranking of prostate cancer as a leading cause of cancer diagnosis and mortality reflects an urgent need for ongoing research into its etiology, risk factors, and effective treatment modalities. This review article cast a light on the diagnostic histopathological techniques of prostate cancer.

Machine Learning Predicts Peripherally Inserted Central Catheters-Related Deep Vein Thrombosis Using Patient Features and Catheterization Technology Features.

This study aims to use patient feature and catheterization technology feature variables to train the corresponding machine learning (ML) models to predict peripherally inserted central catheters-deep vein thrombosis (PICCs-DVT) and analyze the importance of the two types of features to PICCs-DVT from the aspect of "input-output" correlation. To comprehensively and systematically summarize the variables used to describe patient features and catheterization technical features, this study combined 18 literature involving the two types of features in predicting PICCs-DVT. A total of 21 variables used to describe the two types of features were summarized, and feature values were extracted from the data of 1,065 PICCs patients from January 1, 2021 to August 31, 2022, to construct a data sample set. Then, 70% of the sample set is used for model training and hyperparameter optimization, and 30% of the sample set is used for PICCs-DVT prediction and feature importance analysis of three common ML classification models (i.e. support vector classifier [SVC], random forest [RF], and artificial neural network [ANN]). In terms of prediction performance, this study selected four metrics to evaluate the prediction performance of the model: precision (P), recall (R), accuracy (ACC), and area under the curve (AUC). In terms of feature importance analysis, this study chooses a single feature analysis method based on the "input-output" sensitivity principle-Permutation Importance. For the mean model performance, the three ML models on the test set are P = 0.92, R = 0.95, ACC = 0.88, and AUC = 0.81. Specifically, the RF model is P = 0.95, R = 0.96, ACC = 0.92, AUC = 0.86; the ANN model is P = 0.92, R = 0.95, ACC = 0.88, AUC = 0.81; the SVC model is P = 0.88, R = 0.94, ACC = 0.85, AUC = 0.77. For feature importance analysis, Catheter-to-vein rate (RF: 91.55%, ANN: 82.25%, SVC: 87.71%), Zubrod-ECOG-WHO score (RF: 66.35%, ANN: 82.25%, SVC: 44.35%), and insertion attempt (RF: 44.35%, ANN: 37.65%, SVC: 65.80%) all occupy the top three in the ML models prediction task of PICCs-DVT, showing relatively consistent ranking results. The ML models show good performance in predicting PICCs-DVT and reveal a relatively consistent ranking of feature importance from the data. The important features revealed might help clinical medical staff to better understand and analyze the formation mechanism of PICCs-DVT from a data-driven perspective.

Agronomic performance of novel, nitrogen-rich biobased fertilizers across European field trial sites

Context or problemSubstituting mineral fertilizers with novel biobased fertilizers (BBFs) produced from various organic waste and side streams could contribute to a reduction in the environmental and climate impacts of fertilizer production and use and the recycling of otherwise potentially wasted nutrients. For the substitution to be beneficial for farmers, the environment, and food security, the BBFs need to be effective, reliable and safe. However, the agronomic performance of novel, nitrogen (N) rich BBFs has not yet been well studied. Objectives or research questionThe main objective of this study was to determine the agronomic efficiency of N in a relevant range of commercially available BBFs. We hypothesised that they can function as effective substitutes for mineral N fertilizers, independent of the agricultural and geographic settings. MethodsField trials (fully randomized block design) were conducted at four field sites across Europe covering different climates, soil types, and crop sequences. In total 18 BBFs were tested, 7 of which were common BBFs tested at all sites, while the other 11 (2–3 per site) were local BBFs at individual sites. The design included 4–5 increasing levels of mineral N reference. Trials with BBF application were conducted over 2 years, and the agronomic performance (crop yield and N offtake) was determined to estimate 1st year mineral N fertilizer replacement value (NFRV) in both years, while residual NFRV was estimated only in the 2nd year. ResultsThe BBFs showed an average N fertilizer replacement value (NFRV) of 70 % across sites and years, with variations in the agronomic performance between the trial sites and years. Compared with the mineral N fertilizer reference applied at the same total N level, no consistent ranking of BBF and no significant differences in yields were found. The BBFs tended to have a higher NFRV when incorporated compared to surface application. Of the 18 BBFs tested, 8 had a NFRV above 75 %, 6 were in the range 60–75 % and 4 were in the low range of 10–60 %. The residual effect of BBFs in the year after application was not significantly higher for any of the BBFs than that of the mineral N fertilizer. ConclusionsGenerally, the BBFs performed similar to the mineral reference applied at the same total N level. The performance of BBFs was not significantly affected by climate or soil type. The BBFs appeared to have higher agronomic performance when incorporated into the soil compared to surface application. The second year residual effect of BBF was not significantly higher than that of the mineral reference fertilizer. Implications or significanceIn general, most of the investigated BBFs can be considered reasonably effective substitutes for mineral N fertilizers. The results suggest that soil incorporation of BBFs will result in better agronomic performance than surface application.

Green Supplier Selection Using Fuzzy AHP, Fuzzy TOSIS, and Fuzzy WASPAS: A Case Study of the Moroccan Automotive Industry

The green supplier selection presents numerous challenges, from initial assessment to final selection, which specialists in this field of supplier management often encounter. Among the techniques that aim to meet these challenges that are continually progressing is the creation and development of high-quality decision-making tools. In this study, the assessment of suppliers hinges on both traditional and environmental factors. A framework of multi-criteria decision-making (MCDM) is announced in order to appraise green supplier selection. This framework integrates Fuzzy Analytical Hierarchy Process (AHP) combined with two additional methods: WASPAS (“Weighted Aggregated Sum-Product Assessment”) and TOPSIS (“Technique for Order Preference by Similarity to Ideal Solution”). At the outset, there were five environmental criteria for green supplier selection: “Health and Safety”, “Sustainable Product Design”, “ISO 14001 Certification”, “Investment Recovery”, and “Green Packaging”, along with three conventional criteria including quality, price, and delivery, were pinpointed through a review of literature and expert input to facilitate the MCDM approach. As part of demonstrating the pertinency of the recommended framework, a practical case study of the automotive industry in Morocco is discussed. The results demonstrate that the utilized Fuzzy hybrid methods yield consistent rankings for green suppliers. Additionally, among the four green suppliers, number three obtained the best ranking, which indicates the robustness and performance of the chosen models. Furthermore, this study offers a unified platform for selecting green suppliers under a Fuzzy environment. Therefore, the chosen strategy and its analysis provide relevant data and information to decision-makers for the choice and selection of suppliers. It can also provide and help procurement departments and decision-makers to choose and select the efficient ecological supplier in the global market supply chain.

To disclose or to protect? Predicting social media users’ behavioral intention toward privacy

PurposeIn the paradox of personalized services and privacy risks, what factors influence users’ decisions is considered an interesting issue worth exploring. The current study aims to empirically explore privacy behavior of social media users by developing a theoretical model based on privacy calculus theory.Design/methodology/approachPrivacy risks, conceptualized as natural risks and integrated risks, were proposed to affect the intention of privacy disclosure and protection. The model was validated through a hybrid approach of structural equation modeling (SEM)-artificial neural network (ANN) to analyze the data collected from 527 effective responses.FindingsThe results from the SEM analysis indicated that social interaction and perceived enjoyment were strong determinants of perceived benefits, which in turn played a dominant role in the intention to disclose the privacy in social media. Similarly, trust and privacy invasion experience were significantly related to perceived risks that had the most considerable effect on users’ privacy protection intention. And the following ANN models revealed consistent relationships and rankings with the SEM results.Originality/valueThis study broadened the application perspective of privacy calculus theory to identify both linear and non-linear effects of privacy risks and privacy benefits on users’ intention to disclose or protect their privacy by using a state-of-the-art methodological approach combining SEM and ANN.

Comparative effectiveness of first-line systemic treatments for metastatic castration-resistant prostate cancer: a systematic review and network meta-analysis.

No head-to-head trials had been performed to estimate the relative effectiveness of poly ADP-ribose polymerase inhibitor (PARPi) and androgen receptor signaling inhibitor (ARSi) in the first-line treatment for metastatic castration-resistant prostate cancer (mCRPC). We aimed to perform a systematic review and network meta-analysis to evaluate the comparative effectiveness of various systemic treatment agents for patients with mCRPC. A comprehensive literature search was conducted for abstracts and full-text articles from the database's inception through April 27, 2023. The study concentrated on assessing radiographic progression-free survival (rPFS) for both overall and homologous recombination repair mutation (HRRm) population, with overall survival (OS) as the secondary measure. Under the Bayesian framework, the overall effect was pooled using the fixed-effects model in base case analysis. Scenario analysis using restricted mean survival time (RMST) methods was performed to test the robustness of the results. Nine studies with 6,830 patients and 8 unique treatment options were included. Network meta-analysis demonstrated that talazoparib in combination with enzalutamide (TALA + ENZA; overall population, hazard ratio [HR], 0.20; 95% credible interval [CrI]: 0.16-0.26; RMST, 3.51; 95% confidence interval [CI] 2.46-4.60; HRRm population, HR, 0.15; 95% CrI: 0.09-0.23; RMST, 4.14; 95% CI 2.84-5.39) was superior to other treatments in the first-line setting in terms of rPFS. The results of Bayesian framework and RMST models showed consistent efficacy ranks. When extrapolated to overall survival benefit, within the Bayesian framework, olaparib plus abiraterone acetate and prednisone (OLAP + AAP) achieved the highest OS benefit for the overall population, which was not statistically significant when compared to TALA + ENZA. However, TALA + ENZA achieved the highest OS benefit at 3years by applying RMST. We suggest that talazoparib in combination with enzalutamide is probably a preferred treatment agent for the overall population and HRRm patients with mCRPC. Given the limitations of network framework and the modeling assumptions undertaken to finalize the analyses, results should be cautiously interpreted.

Comparison of multi-task ergonomic assessment methods for risk of upper extremity and low back musculoskeletal disorders

Work-related musculoskeletal disorder of upper extremity multi-task assessment methods (Revised Strain Index [RSI], Distal Upper Extremity Tool [DUET]) and manual handling multi-task assessment methods (Revised NIOSH Lifting Equation [RNLE], Lifting Fatigue Failure Tool [LiFFT]) were compared. RSI and DUET showed a strong correlation (rs = 0.933, p < 0.001) where increasing risk factor exposure resulted in increasing outputs for both methods. RSI and DUET demonstrated fair agreement (κ = 0.299) in how the two methods classified outputs into risk categories (high, moderate or low) when assessing the same tasks. The RNLE and LiFFT showed a strong correlation (rs = 0.903, p = 0.001) where increasing risk factor exposure resulted in increasing outputs, and moderate agreement (κ = 0.574) in classifying the outputs into risk categories (high, moderate or low) when assessing the same tasks. The multi-task assessment methods provide consistent output magnitude rankings in terms of increasing exposure, however some differences exist between how different methods classify the outputs into risk categories.

Effects of Leaf Species and Conditioning State of Fresh Leaves on Colonization by Stream and Pond Macroinvertebrates

Fresh, green leaves are increasing as resources in aquatic ecosystems due to more frequent severe spring and summer storms, but research on allochthonous resources typically uses senescent leaves. We examined macroinvertebrate colonization of green leaves of three native deciduous trees (red maple, red oak, and tulip poplar) over two weeks within both a stream and fishless pond. Leaf colonization varied depending on the taxa of leaves and colonizers, submersion time, and the ecosystem examined. Within the stream, the densities of isopods (Lirceus sp.) and snails (mostly the invasive Potamopyrgus antipodarum) did not vary significantly across leaf species. In contrast, mayflies (Tricorythodes sp.) in the stream colonized tulip poplar in greater numbers than red oak leaves, while higher densities of planarians (order Tricladida) occurred within red oak leaves. The numbers of mayflies and snails decreased significantly by the second week, but the densities of isopods and planaria within stream leaf packs were consistent. In contrast, within the pond, significantly more isopods (Caecidotea communis) were collected after the first than after the second week of submersion and in tulip poplar leaves. Clams (Sphaeriidae) in the pond, on the other hand, were more prevalent in the second week but did not discriminate among leaf species. While the number of leeches (mostly Helobdella stagnalis) was consistent across weeks, significantly fewer leeches resided within tulip poplar leaves than within red oak leaves. Our results suggest that there are no consistent colonization-preference rankings of species of fresh leaves across freshwater benthic macroinvertebrate taxa. Even within a functional feeding group (e.g., the two types of isopods and snails, all detritivore-herbivores), there were differences in colonization patterns. Therefore, increased allochthonous inputs of fresh leaf litter due to severe spring- and summer-time storms are likely to promote the populations of various taxa to different extents.

Assessing climate change vulnerability of coastal roads

Climate change is a global phenomenon, which affects in several ways different regions all around the world, beyond the rise in global temperature. Among the different climate change issues, the management of transport infrastructures is crucial. Particularly, their vulnerability against changes in climatic conditions should be assessed. Vulnerability indicators are based on the IPCC concept of vulnerability and can be defined as a function of Climate Exposure, Sensitivity, and Adaptive Capacity. These dimensions need to be addressed during the assessment making and can be modelled as a Multiple Criteria Decision Analysis (MCDA) problem. This study proposes an integrated approach of several MCDA methods as a possible tool for ranking the climate change vulnerability of coastal roads in Malta. The application covers six coastal roads in the islands of Malta, classified by three different MCDA methods. The results indicate that the proposed approach can produce a consistent ranking of the climate change vulnerability of coastal roads. The study provides policy and decision-makers with a definition of a coastal road, an inventory of such roads, a list of climate change impacts, and a mathematical model incorporating climate change vulnerability indicators. The model can be used to prioritize investment and plan climate change adaptation strategies for infrastructural works on coastal roads.

Assessing Drought Stress of Sugarcane Cultivars Using Unmanned Vehicle System (UAS)-Based Vegetation Indices and Physiological Parameters

Sugarcane breeding for drought tolerance is a sustainable strategy to cope with drought. In addition to biotechnology, high-throughput phenotyping has become an emerging tool for plant breeders. The objectives of the present study were to (1) identify drought-tolerant cultivars using vegetation indices (VIs), compared to the traditional method and (2) assess the accuracy of VIs-based prediction model estimating stomatal conductance (Gs) and chlorophyll content (Chl). A field trial was arranged in a randomized complete block design, consisting of seven cultivars of sugarcane. At the tillering and elongation stages, irrigation was withheld, and then furrow irrigation was applied to relieve sugarcane from stress. The physiological assessment measuring Gs and Chl using a handheld device and VIs were recorded under stress and recovery periods. The results showed that the same cultivars were identified as drought-tolerant cultivars when VIs and traditional methods were used for identification. Likewise, the results derived from genotype by trait biplot and heatmap were comparable, in which TCP93-4245 and CP72-1210 cultivars were classified as tolerant cultivars, while sensitive cultivars were CP06-2400 and CP89-2143 for both physiological parameters and VIs-based identification. In the prediction model, the random forest outperformed linear models in predicting the performance of cultivars in untested crops/environments for both Gs and Chl. In contrast, it underperformed linear models in the tested crops/environments. The identification of tolerant cultivars through prediction models revealed that at least two out of three cultivars had consistent rankings in both measured and predicted outcomes for both traits. This study shows the possibility of using UAS mounted with sensors to assist plant breeders in their decision-making.

Revisiting methods for estimating interregional input-output accounts: It's not just about trade flows

A basic underlying assumption in most of the research to date is that intermediate industry accounts of the economies in multiregional input-output (MRIO) tables exist and are accurate. In fact, if they exist at the subnational level, such accounts are, at best, roughly estimated and predicated on far less empirical information than is available for economies of nations. Moreover, intra-economy intermediate-industry flows are typically larger than the set of a region's commodity in- and out-flows. So, if intermediate industry flows in a set of MRIO accounts are noticeably mis-estimated, it follows that interregional trade coincidentally derived using them must be even more conspicuously in error.We hypothesize as more information is used to estimate MRIO accounts, the better the estimates should be. We start our experiment by consolidating 2019 FIGARO accounts of the 27 member states of the European Union, while maintaining sectoral detail, to produce a “national account”. We then test several approaches to constructing MRIO tables. The approaches distribute interregional trade fully by receiving industry, as in FIGARO, as well as strictly in the form of a diagonalized matrix as if the commodity inflows are competitive imports. To do this, both a gravity model and RAS are applied to each approach. We then test to see how well the approaches estimate main features of FIGARO's MRIO accounts and detail a rather consistent ranking of the relative accuracy of them. We also find that the level of error inherent to the estimated MRIOs is markedly similar across approaches, particularly for multipliers. Further, relaxing interregional trade to a diagonalized matrix tends to add very little error. The approach that uses the least data is, however, markedly worse in replicating countries’ direct requirements matrices and Leontief inverses, which suggests its use in a more-limited set of applications.

A multi-model evaluation of probabilistic streamflow predictions via residual error modelling

Probabilistic streamflow predictions are valuable tools for predictive uncertainty estimation, hydrologic risk management, and support for decision-making in water resources. Usually, predictive uncertainty quantification is developed and assessed using only a single hydrological model, making it difficult to generalize to other model configurations. To tackle this issue, we assess changes in the model performance ranking of diverse streamflow models by applying a residual error model post-processing approach to multiple basins and multiple models. This assessment employed 141 basins from the Great Lakes watershed covering the USA and Canada, and 13 diverse streamflow models, which are evaluated using deterministic and probabilistic performance metrics. As the first study to implement probabilistic methods to diverse streamflow models applied to a multitude of basins, the analysis here examines the dependence of probabilistic streamflow estimation quality on model quality. Our findings show that streamflow model choice influences the robustness of probabilistic predictions. It was found that moving from deterministic to probabilistic predictions using a post-processing approach does not change the streamflow model performance ranking for the best and worst deterministic models, but models of intermediate rank in deterministic evaluation do not have consistent ranking when evaluated in probabilistic mode. Post-processing residual errors of long short-term memory (LSTM) network models are consistently the best-performing model in terms of deterministic and probabilistic metrics. This study highlights the significance of combining deterministic streamflow model predictions with residual error models for improving the quality and increasing the value of hydrological predictions, quantifying uncertainty, and facilitating decision-making in operational water management. It also clarifies the degree to which probabilistic predictions depend upon good model performance and can compensate for poor model performance.

Pairwise difference relational distillation for object re-identification

Most relationship knowledge distillation methods individually optimize pairwise similarities to improve the accuracy performance of a lightweight student network. However, this optimization approach may not be optimal for object re-identification (Re-ID) which prioritizes ranking. This is because it does not guarantee consistent ranking results between a lightweight student network and a large teacher network. For that, we propose a novel method called pairwise difference relational distillation (PDRD) for object Re-ID. First, we theoretically prove that minimizing the difference relationship between pairwise similarities resulting from student and teacher networks ensures consistent ranking results between the two networks. Second, based on this theoretical foundation, we combine non-linear activation functions on pairwise similarity discrepancies to create a non-linear pairwise difference rational knowledge loss function, which enhances knowledge transfer. Extensive experiments on four public datasets demonstrate that our method achieves state-of-the-art performance. For example, on Market-1501, using ResNet18 as a lightweight student network, our method acquires a rank-1 identification rate of 93.62%.

Predicting mechanical neck pain intensity in computer professionals using machine learning: identification and correlation of key features.

Mechanical neck pain has become prevalent among computer professionals possibly because of prolonged computer use. This study aimed to investigate the relationship between neck pain intensity, anthropometric metrics, cervical range of motion, and related disabilities using advanced machine learning techniques. This study involved 75 computer professionals, comprising 27 men and 48 women, aged between 25 and 44 years, all of whom reported neck pain following extended computer sessions. The study utilized various tools, including the visual analog scale (VAS) for pain measurement, anthropometric tools for body metrics, a Universal Goniometer for cervical ROM, and the Neck Disability Index (NDI). For data analysis, the study employed SPSS (v16.0) for basic statistics and a suite of machine-learning algorithms to discern feature importance. The capability of the kNN algorithm is evaluated using its confusion matrix. The "NDI Score (%)" consistently emerged as the most significant feature across various algorithms, while metrics like age and computer usage hours varied in their rankings. Anthropometric results, such as BMI and body circumference, did not maintain consistent ranks across algorithms. The confusion matrix notably demonstrated its classification process for different VAS scores (mild, moderate, and severe). The findings indicated that 56% of the pain intensity, as measured by the VAS, could be accurately predicted by the dataset. Machine learning clarifies the system dynamics of neck pain among computer professionals and highlights the need for different algorithms to gain a comprehensive understanding. Such insights pave the way for creating tailored ergonomic solutions and health campaigns for this population.

Convergence of polarized self-attention with consistent rank Chinese text classification

Utilizing the powerful feature extraction capabilities of deep learning, a text classification algorithm with multi-dimensional and high-domain adaptability is designed in this study. This method enhances the models understanding of topics and content by incorporating the Polarized Self-Attention (PSA) module, which strengthens the spatial structure and semantic features of textual information. The loss function is redesigned to assign smaller losses to misclassifications of neighboring categories, allowing the model to optimize classification accuracy while learning hierarchical structural information between categories. Finally, experimental verification is conducted on a publicly available news dataset, demonstrating improved results in text classification achieved by the proposed algorithm.