Ranking Model Research Articles

Machine Learning: A Multicentre Study on Predicting Lateral Lymph Node Metastasis in cN0 Papillary Thyroid Carcinoma.

The necessity of prophylactic lateral neck dissection for cN0 papillary thyroid carcinoma (PTC) remains debated. This study aimed to compare traditional nomograms with machine learning (ML) models for predicting ipsilateral lateral and level II, III, and IV lymph node metastasis (LNM). Data from 1616 PTC patients diagnosed via fine needle aspiration biopsy from Hospital A were split into training and testing sets (7:3). 243 patients from Hospital B served as validation set. Four dependent variables-ipsilateral lateral, level II, III, and IV LNM-were analyzed. Eight ML models (Logistic Regression, Decision Tree, Random Forest-RF, Gradient Boosting, Support Vector Machine, K-Nearest Neighbor, Gaussian Naive Bayes, Neural Networks) were developed and validated using 10-fold cross-validation and grid search hyperparameter tuning. Models were assessed using 11 metrics including accuracy, area under the curve (AUC), specificity, and sensitivity. The best was compared with nomograms using the Probability-based Ranking Model Approach (PMRA). RF outperformed other approaches achieving accuracy, AUC, specificity, and sensitivity of 0.773/0.728, 0.858/0.799, 0.984/0.935, 0.757/0.807 in the testing/validation sets respectively for ipsilateral LLNM. A streamlined model based on the top ten contributing features that includes ipsilateral central lymph node metastasis rate, extrathyroidal extension, and ipsilateral central lymph node metastasis number retained strong performance and clearly surpassed a traditional nomogram approach based on multiple metrics and PMRA analysis. Similar results were obtained for the other dependent variables, with the RF models relying on distinct but overlapping sets of features. Clinical tool implementation is facilitated via a web-based calculator for each of the four dependent variables. ML, especially RF, reliably predicts lateral LNM in cN0 PTC patients, outperforming traditional nomograms.

Proposal of an objective formula-based model for equitable ranking of veterinary colleges

IntroductionWe suggest an objective ranking formula that has wide national and international application. The new formula is presented with U.S. Colleges of Veterinary Medicine as an example. Methods used by ranking agencies differ, as do the ranks they generate. In some instances, relatively narrow information is collected from a limited number of polled contributors, raising questions about strength and validity of the generated ranks.MethodsA new formula-based weighted model for ranking of veterinary colleges is proposed. Numbers fed into the formula parameters, for instance teaching hospital case load, faculty number and research expenditures, derive from real and measurable qualities of each college and drive an objective final ranking score for each veterinary college. This formula is designed to be readily modified within and beyond the veterinary profession.ResultsThe new ranking system works from calculations that are straightforward and transparent with little room for subjective interpretation. It is designed to provide a rigorous and defendable institutional rank for all veterinary colleges.DiscussionThe new ranking system is designed to be readily adaptable within veterinary colleges as the profession changes, as well as to academic institutions with focuses other than veterinary medicine. The goal is to provide a new model that is useful for objective comparisons.

Modeling Preferences: A Bayesian Mixture of Finite Mixtures for Rankings and Ratings

Rankings and ratings are commonly used to express preferences but provide distinct and complementary information. Rankings give ordinal and scale-free comparisons but lack granularity; ratings provide cardinal and granular assessments but may be highly subjective or inconsistent. Collecting and analyzing rankings and ratings jointly has not been performed until recently due to a lack of principled methods. In this work, we propose a flexible, joint statistical model for rankings and ratings—the Bradley-Terry-Luce-Binomial (BTL-Binomial). The model captures rater effects and preference heterogeneity, respectively, with judge-specific random effects and a latent class mixture framework where the number of classes is unknown a priori. We propose computationally-efficient estimation via a Bayesian mixture of finite mixtures (MFM) approach. Finally, we demonstrate statistical inference and decision-making based on rankings and ratings jointly through applications to real and simulated datasets in academic peer review. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

Global decline in net primary production underestimated by climate models

Marine net primary production supports critical ecosystem services and the carbon cycle. However, the lack of consensus in the direction and magnitude of projected change in net primary production from models undermines efforts to assess climate impacts on marine ecosystems with confidence. Here we use contemporary remote sensing net primary production trends (1998–2023) from six remote sensing algorithms to discriminate amongst fifteen divergent model projections. A model ranking scheme, based on the similarity of linear responses of net primary production to changes in sea surface temperature, chlorophyll-a and the mixed layer, finds that future declines in net primary production are more likely than presently predicted. Even the best ranking models still underestimate the sensitivity of declines in net primary production to ocean warming, suggesting shortcomings remain. Reproducing this greater temperature sensitivity may lead to even larger declines in future net primary production than presently considered for impact assessment.

Multi-source data driven decision-support model for product ranking with consumer psychology behavior

Multi-source data driven decision-support model for product ranking with consumer psychology behavior

AlphaFold and Docking Approaches for Antibody-Antigen and Other Targets: Insights From CAPRI Rounds 47-55.

Accurate modeling of the structures of protein-protein complexes and other biomolecular interactions represents a longstanding and important challenge for computational biology. The Critical Assessment of PRedicted Interactions (CAPRI) experiment has served for over two decades as a key means to assess and compare current approaches and methods through blind predictive scenarios, highlighting useful strategies, and new developments. Here we describe the performance of our laboratory's team in recent CAPRI rounds, which included submissions for 10 modeling targets. Our team utilized a range of docking and modeling approaches, including ZDOCK, Rosetta, and ZRANK, to model, refine, and score protein-protein and protein-DNA complexes. For recent targets we utilized adaptations of AlphaFold to generate models, leading to near-native models for an antibody-peptide target, and a highly accurate (but low ranked) model for an antibody-MHC complex. These results underscore the utility of AlphaFold-based protocols for predictive protein complex modeling, including for immune recognition, and highlight considerations regarding the use of AlphaFold confidence metrics in model selection.

A novel approach to prioritizing health technology investments using integrated AI-based ranking model.

Health technologies are an issue that directly affects the sustainability and quality of health services. Due to budget constraints, it is not financially possible for businesses to apply comprehensive improvement strategies to all these criteria. In this case, it is possible for businesses to implement more priority strategies. Accordingly, the main purpose of this study is to evaluate the important performance indicators of health technology investments. Firstly, with the help of the artificial intelligence system, a decision matrix is established. Secondly, spherical fuzzy total order of preference decision-making trial and evaluation laboratory methodology is taken into consideration for weighting the criteria. Thirdly, emerging seven countries are ranked by using spherical fuzzy MultiAtributive Ideal-Real Comparative Analysis (MAIRCA). The findings demonstrate that the criteria of health policies and research and development are defined as the most significant factor in this regard. China and Turkey are also found to be the most successful emerging countries with respect to the performance of health technology investments. The main contribution of this study is that a novel decision-making model is generated by integrating artificial methodology into the spherical fuzzy sets.

Evaluating crash severity at highway-rail grade crossings using an analytic hierarchy process-based hazard index model.

Due to the substantial mass disparity between trains and highway vehicles, crashes at Highway-Rail Grade Crossings (HRGCs) are often severe. Therefore, it is essential to develop systematic frameworks for allocating federal and state funds to improve safety at the highest-risk grade crossings. Common techniques for hazard prioritization at HRGCs include the hazard index and the collision prediction formula. A few research projects and state departments of transportation (DOTs) have employed hybrid models that integrate crash hazard indices with prediction models to create comprehensive safety decision-making frameworks. In addition, ranking grade crossings based on their forecasted crash severity likelihood remains largely unexplored, partly due to the complexity of integrating crash severity outputs with hazard indices. This research introduces a new mixed hazard ranking model, the Analytic Hierarchy Process Hazard Index (AHP-HI), which serves as a decision-making tool for ranking grade crossings based on their potential for crash severity. The AHP-HI model combines the analytic hierarchy process (AHP) and the competing risk model (CRM), a prediction model that estimates the likelihood of crash severity for crossings. Risk analysis using the AHP-HI model categorizes public grade crossings in North Dakota into four risk levels, with 4.73% of the crossings identified as high risk.

Detection of Energetic Low Dimensional Subspaces in Spatio-Temporal Space in Turbulent Pipe Flow

AbstractLow dimensional subspaces are extracted out of highly complex turbulent pipe flow at $$Re_{\tau }=181$$ R e τ = 181 using a Characteristic Dynamic Mode Decomposition (CDMD). Having lower degrees of freedom, the subspaces provide a more clear basis to detect events which meet our understanding of large-scale coherent structures. To this end, a temporal sequence of state vectors from direct numerical simulations are rotated in space-time such that persistent dynamical modes on a hyper-surface are found travelling along its normal in space-time, which serves as the new time-like coordinate. The main flow features are captured with a minimal number of modes on a moving frame of reference whose velocity matches that of the most energetic scale. Reconstruction of the candidate modes in physical space gives the low rank model of the flow. The structures living in this subspace have long lifetimes, posses wide range of length-scales and travel at group velocities close to that of the moving frame of reference. The modes within this subspace are highly aligned, but are separated from the remaining modes by larger angles. We are able to capture the essential features of the flow like the spectral energy distribution and Reynolds stresses with a subspace consisting of about 10 modes. The remaining modes are collected in two further subspaces, which distinguish themselves by their axial length scale and degree of isotropy.

Making It Tractable to Detect and Correct Errors in Graphs

This article develops Hercules, a system for entity resolution (ER), conflict resolution (CR), timeliness deduction (TD), and missing value/link imputation (MI) in graphs. It proposes GCR + s, a class of graph cleaning rules (GCR) that support not only predicates for ER and CR but also temporal orders to deduce timeliness and data extraction to impute missing data. As opposed to previous graph rules, GCR + s are defined with a dual graph pattern to accommodate irregular structures of schemaless graphs and adopt patterns of a star form to reduce the complexity. We show that while the implication and satisfiability problems are intractable for GCR + s, it is in polynomial time to detect and correct errors with GCR + s. Underlying Hercules, we train a ranking model to predict the temporal orders on attributes and embed it as a predicate of GCR + s. We provide an algorithm for discovering GCR + s by combining the generations of patterns and predicates. We also develop a method for conducting ER, CR, TD, and MI in the same process to improve the overall quality of graphs by leveraging their interactions and chasing with GCR + s; we show that the method has the Church–Rosser property under certain conditions. Using real-life and synthetic graphs, we empirically verify that Hercules is 53% more accurate than the state-of-the-art graph cleaning systems and performs comparably in efficiency and scalability.

Meta-Learning to Rank for Sparsely Supervised Queries

Supervisory signals are a critical resource for training learning to rank models. In many real-world search and retrieval scenarios, these signals may not be readily available or could be costly to obtain for some queries. The examples include domains where labeling requires professional expertise, applications with strong privacy constraints, and user engagement information that are too scarce. We refer to these scenarios as sparsely supervised queries which pose significant challenges to traditional learning to rank models. In this work, we address sparsely supervised queries by proposing a novel meta-learning to rank framework which leverages fast learning and adaption capability of meta-learning. The proposed approach accounts for the fact that different queries have different optimal parameters for their rankers, in contrast to traditional learning to rank models which only learn a global ranking model applied to all the queries. In consequence, the proposed method would yield significant advantages especially when new queries are of different characteristics with the training queries. Moreover, the proposed meta-learning to rank framework is generic and flexible. We conduct a set of comprehensive experiments on both public datasets and a real-world e-commerce dataset. The results demonstrate that the proposed meta-learning approach can significantly enhance the performance of learning to rank models with sparsely labeled queries.

An integrated approach to a predictive and ranking model of use error using fuzzy BWM and fuzzy TOPSIS

Avoiding error in handling artifacts is crucial for achieving a high level of system reliability and safety assessment. This study develops a predictive and ranking model of use error (PRUE). In the first phase, use errors are systematically detected and anticipated via an inquiry process in two levels (activity and function). In the second phase, the fuzzy best–worst method (F-BWM) is employed to determine relative weights of three criteria including consequence of use error (CUE), detection of use error (DUE) and probability of use error (PUE). Fuzzy TOPSIS is then employed to rank use errors according to their risk level. The use errors of an infant ventilator device are assessed to demonstrate applicability of the PRUE method. The results of the present study confirm the reliability and applicability of this approach to assess artifact use errors. Moreover, the PRUE method can be utilized in investigation of user interface design.

ExCS: accelerating code search with code expansion

Efficiently searching and reusing code from expansive codebases is pivotal for enhancing developers’ productivity. In recent times, the emergence of deep learning-driven neural ranking models, characterized by their vast dimensions and intricate interaction mechanisms, has been noteworthy. Yet, these models, in real-world scenarios, pose computational challenges due to their high dimensionality. Moreover, models rooted in interaction necessitate querying every piece of code within a voluminous corpus. While these methodologies offer superior accuracy, their online retrieval process is considerably more time-consuming compared to traditional Information Retrieval (IR) techniques. Addressing this, we introduce “ExCS”, an innovative code search tool designed to expedite the code search process without compromising on accuracy. ExCS innovatively employs code expansion in its offline phase, leveraging predictions on potential queries for specific codes, thereby enriching the code’s semantic depth. During online retrieval, ExCS prioritizes IR-based methods to pinpoint a concise set of persuasive candidates. Our evaluations, conducted on the Java dataset from CodeSearchNet, reveal that ExCS achieves a remarkable 90% reduction in retrieval duration while maintaining an impressive 99% retrieval accuracy.

Enhancing environmental sustainability: Optimal municipal-industrial waste burial site selection in Bandar Abbas, Iran using a fuzzy multi-criteria approach incorporating physical-geotechnical factor

Bandar Abbas, Iran faces a significant challenge with the disposal of approximately 500 tons of waste daily, often leading to severe environmental contamination due to improper disposal practices. Existing methodologies for waste management site selection in the region have largely overlooked critical physical-geotechnical factors, focusing primarily on ecological and structural criteria. This study aims to fill this gap by employing a novel fuzzy multi-criteria decision-making approach that integrates environmental, ecological, structural, and physical-geotechnical factors for optimal burial site identification. Using the Analytic Network Process (ANP) to weigh the criteria, this research develops information layers for each aspect. Euclidean distance mapping, combined with fuzzy operators (AND, OR, SUM, Product) and varied gamma values, generates a superposition map for site suitability analysis. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is then applied to rank potential sites and identify the most suitable locations. The results indicate that ecological criteria have the greatest influence on site selection, followed by structural, environmental, and physical-geotechnical factors. Key sub-criteria affecting site selection include proximity to sensitive habitats, residential areas, rivers, and fault lines. Based on the TOPSIS ranking model, five suitable burial locations in Bandar Abbas were identified, with Area 4 (west of Tal Siah Village) emerging as the optimal site. This study contributes to advancing waste management practices by offering a comprehensive, data-driven framework that balances environmental sustainability and geotechnical considerations, providing valuable insights for global application.

Intelligence-assisted college English teaching: The application of artificial intelligence technology in personalized learning path design

English learning is an integrated learning process in which listening, speaking, reading, writing and other parts are interrelated. Because of this feature of English learning, higher requirements are put forward for the design of English learning assistance systems. On the other hand, the wide application of advanced science and technology such as automation and cloud computing in all walks of life has promoted the development of society into the era of artificial intelligence. Under such a large development background, how to build a multifunctional integrated English learning system to realize the personalized learning of learners with different levels and different needs has become a focus of current English teaching research. With the increasing abundance of English learning materials, it has become very important to help users find suitable English learning resources from the massive materials, which directly affects the cost of learning time and interest of users. Based on this, this paper introduces a multi-similarity ranking model to achieve personalized design, and then uses artificial intelligence technology to design and implement a personalized intelligent assistant system for college English teaching.

Two-stage group ordinal consensus optimization ranking approach considering multiple optimal consistency adjustment solutions

In group decision making, decision makers can use pairwise comparisons to express their preferences. Reaching the consistency of decision makers and consensus of decision groups are two important processes for obtaining reliable decision-making results. Consistency and consensus optimization approach based on minimizing preference adjustment is one of the dominant approaches to obtaining ranking results by deriving priorities. In existing researches, maintaining consistency in preference adjustment during ordinal consensus optimization processes has been rarely noticed, and the choice of the consistency adjusted preferences from multiple optimal solutions has not been considered. To deal with these issues, this paper proposes a two-stage group ordinal consensus optimization ranking approach which considers multiple optimal consistency adjustment solutions to achieve individual preference consistency and group ordinal consensus. In the first stage, a minimum adjustment consistency optimization model is developed to obtain the minimum adjustment based on the concept of strong ordinal consistency. In the second stage, an ordinal consensus optimization ranking model is developed to obtain the optimal consistency and consensus adjustment solutions by minimizing the preference adjustments based on an improved consensus measure. Finally, a numerical example about lithium-ion battery recycling strategy selection is applied to illustrate the feasibility of the proposed approach. Moreover, the comparisons with other approaches are given to show the advantage and the sensitivity analysis is used to verify the effectiveness of the proposed approach.

Knowledge enhanced edge-driven graph neural ranking for biomedical information retrieval

Neural networks used for information retrieval tend to capture textual matching signals between a query and a document. However, neural ranking models for biomedical information retrieval often struggle to semantically well match the query to the documents. The main reasons are that biomedical terms have many different representations and the fact description related to the query is non-consecutive and non-local in the documents. In this paper, we present an edge-driven graph neural ranking method for biomedical information retrieval by incorporating knowledge from medical databases. First, we propose to form an edge-driven graph by connecting some biomedical terms in the query and the document through different types of edges. Then, we design a novel way of knowledge integration to introduce knowledge related to biomedical terms into the graph and construct a knowledge-query-doc graph. Finally, a graph neural ranking model is applied to capture non-local and non-contiguous match signals between the query and the document. Experimental results show on the biomedical datasets that our method outperforms the advanced neural models. And further analysis shows that the knowledge integration method can well reduce the semantic gap between the query and the document, and our graph model can provide interpretation for matching between the query and the document.

Minimum deviation distribution ranking model and fairness concern-based consensus building for group decision-making

Group decision-making refers to the collective decision-making of multiple decision-makers to solve a common problem. However, decision-makers typically exhibit different psychological attitudes and behaviors in the decision-making process, which leads to actual decisions deviating from the solution recommendations obtained by traditional quantitative methods. More importantly, most existing studies on consensus fail to simultaneously consider the internal process of consensus building and psychological behaviors of decision-makers. To address this gap, this paper proposes a novel group decision-making method using a minimum deviation distribution ranking model and fairness concern-based consensus building. First, a fairness utility function is established to compare evaluation information from different decision-makers capturing fairness concern between individuals. Then, an optimization model is developed to determine decision-makers’ weights. Additionally, a fairness-based consensus model is proposed, which considers decision-makers’ acceptable adjustment range to avoid excessive information loss. To derive the priority vector, we develop a ranking model based on minimum deviation distribution by controlling the deviation in the minimum range. Finally, we provide a numerical example and comparative analysis to evaluate the effectiveness and superiority of our method, and conduct a robustness test to verify the stability and reliability of the ranking model.

Estimation of dominance genetic effects on pre-weaning efficiency-related traits in Baluchi sheep

Abstract This study was conducted to estimate the relative contribution of dominance genetic effects to efficiency-related traits including Kleiber ratio (KR), efficiency of growth (EF) and relative growth rate (RGR) in Baluchi sheep. To this end, each trait was analysed with a series of 12 animal models which were identical for fixed and additive genetic effects but differed for combinations of dominance genetic and maternal effects. The Akaike's information criterion (AIC) was used to rank models. (Co)variances between traits were estimated using bivariate analyses. For all traits studied, according to AIC values, models containing the dominance genetic effects provided a better data fit than otherwise identical models. By including dominance genetic effects in the model, additive genetic variance did not change, but a significant decrease was observed in the residual variance (24, 19 and 25% for KR, EF and RGR, respectively). Estimates of dominance heritability $( {\boldsymbol h}_{\boldsymbol d}^ 2 )$ were 0.20 ± 0.05, 0.17 ± 0.05 and 0.19 ± 0.07 for KR, EF and RGR, respectively, more than corresponding estimates of additive heritability ${\bf ( }{\boldsymbol h}_{\boldsymbol a}^{\bf 2} {\bf ) }$ as 0.14 ± 0.02, 0.09 ± 0.03 and 0.13 ± 0.02, respectively. Dominance genetic correlations between traits were 0.89 ± 0.17 (KR-EF), 0.86 ± 0.20 (KR-RGR) and 0.93 ± 0.21 (EF-RGR). Additive genetic correlations between traits were 0.84 ± 0.05 (KR-EF), 0.78 ± 0.04 (KR-RGR) and 0.83 ± 0.04 (EF-RGR). The Spearman correlation between additive breeding values including and excluding dominance genetic effects were close to unity either for all animals or top ranked animals. Since presence of dominance genetic effects increased the model power to fit the data, inclusion of these effects in the genetic evaluation models for Baluchi sheep was recommended.

Optimal ranking model of fuzzy preference relations with self-confidence for addressing self-confidence failure

Fuzzy preference relation with self-confidence (FPR-SC) uses semantic self-confidence to illustrate the hesitation of experts in affirming given preference values. However, extant ranking derivation methods of FPRs-SC suffer from self-confidence failure problem. Specifically, when the logical operations of self-confidence levels are replaced by algebraic operations on semantic subscripts, the derived rankings may be unstable or independent of the self-confidence. To address this issue, an optimal ranking model of FPR-SC with chance-constrained is proposed and extended to group decision-making. Based on the concept of ‘reliability level’ in parameter estimation, the evaluation information expressed by ‘preference values + self-confidence levels’ is first explained using probability distributions to achieve dimensional unity between qualitative self-confidence and quantitative preference. A multiplicative consistency-driven optimal model is then designed to assess the individuality of self-confidence. Guided by the ‘3σ’ principle, FPR-SC is further replaced by random variables following asymmetric bilateral truncated normal distributions. This transformation captures the inner cognition of individuals during subjective judgment, and ensures effective constraints on the numerical range through the asymmetric design. Finally, motivated by the minimization of information deviation, an FPR-SC optimal ranking model with chance-constrained is constructed, and its effectiveness is verified.