Ranking Framework Research Articles

Grey preferences selection index with trimmed group preference for evaluating university dormitory renovation design.

Renovating old buildings is a strategic approach to resource optimization and sustainability. However, dormitory design decisions are often made by a limited panel of experts, which risks excluding student preferences-key to the design process. Expert assumptions about student needs can lead to biased outcomes, and attempts to gather student input may suffer from respondent bias and inconsistent engagement, introducing data noise. This paper presents the Grey Trimmed Preferences Selection Index (GTPSI) Multi-Criteria Decision Making (MCDM) method, an improved preference selection index MCDM method that integrates expert weights and refines student feedback by filtering outliers, using interval grey numbers to address uncertainty. Applied to dormitory renovation proposals, GTPSI provides a stable ranking framework, as confirmed by whitening sensitivity analysis, ensuring consistency across grey bounds. To further validate the selected alternative, results are cross-verified with TOPSIS and ELECTRE-III, reinforcing GTPSI's robustness in aligning renovation designs with actual student needs. The GTPSI method thus offers a comprehensive solution for integrating user-centered preferences into expert evaluations, promoting designs that better meet stakeholder expectations.

Rain event detection and magnitude estimation during Indian summer monsoon: Comprehensive assessment of gridded precipitation datasets across hydroclimatically diverse regions

Accurate precipitation estimates are quintessential for hydrologic modeling and climate studies. Different gridded precipitation products are available in any region, and selecting the best one is essential for hydroclimatic modeling and analysis. In the current study, observation- (APHRODITE), reanalysis- (IMDAA, ERA5-Land, PGF), satellite-based (IMERG, CHIRPS, PERSIANN-CDR), and hybrid (MSWEP) gridded precipitation products with different spatial and temporal resolutions are evaluated using several continuous, categorical, graphical, and interval-based performance measures towards detecting Indian Summer Monsoon Rainfall (ISMR) events and estimating their magnitudes for the subcontinent of India, considering IMD gauge-based gridded as reference product. We confine our analysis to the monsoon season (i.e., June to September), the principal rainy season in the Indian sub-continent. The dearth of data and limited rain gauge-based observations from non-uniform sparse monitoring networks across India necessitated grid-to-grid comparative evaluations instead of point-to-grid assessments. We propose a new ranking framework to determine the suitability of precipitation datasets for twenty-seven hydroclimatic regions comprising homogeneous rainfall zones, Köppen-Geiger climate zones, and major river basins. Results from the comprehensive evaluation suggest that (1) APHRODITE, MSWEP, and ERA5-Land best approximate precipitation event occurrences across India, (2) MSWEP and ERA5-Land are most suitable (highest rank) alternatives at the regional level, while APHRODITE is found to be next suitable dataset owing to its persistent dry bias, (3) performances of CHIRPS and IMERG have reasonably lower rank score across India, (4) close agreement of examined datasets is noted over semi-arid and sub-humid regions (e.g., peninsular and central India), whereas ERA5-Land, IMDAA, and APHRODITE fail to detect and reproduce the intensity of the events along the west coast and northeastern India, (5) PGF and PERSIANN-CDR are the least situated datasets. Moreover, the present study provides a unique and innovative perspective to characterise the precipitation over a vast topographic, ecologic, and climatic gradient region like India.

A Self-Distilled Learning to Rank Model for Ad Hoc Retrieval

Learning to rank models are broadly applied in ad hoc retrieval for scoring and sorting documents based on their relevance to textual queries. The generalizability of the trained model in the learning to rank approach, however, can have an impact on the retrieval performance, particularly when data includes noise and outliers, or is incorrectly collected or measured. In this paper, we introduce a Self-Distilled Learning to Rank (SDLR) framework for ad hoc retrieval, and analyze its performance over a range of retrieval datasets and also in the presence of features’ noise. SDLR assigns a confidence weight to each training sample, aiming at reducing the impact of noisy and outlier data in the training process. The confidence weight is approximated based on the feature’s distributions derived from the values observed for the features of the documents labeled for a query in a listwise training sample. SDLR includes a distillation process that facilitates passing on the underlying patterns in assigning confidence weights from the teacher model to the student one. We empirically illustrate that SDLR outperforms state-of-the-art learning to rank models in ad hoc retrieval. We thoroughly investigate the SDLR performance in different settings including when no distillation strategy is applied; when different portion of data are used for training the teacher and the student models, and when both teacher and student models are trained over identical data. We show that SDLR is more effective when training data are split between a teacher and a student model. We also show that SDLR’s performance is robust when data features are noisy.

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.

NFT 미술작품 가치 평가 기반하의 랭크 프레임워크 연구

The objective of this study is to devise and propose a ranking framework for NFT artworks and artists, based on the valuation of NFT artworks. The findings of this study can be summarised as follows. Firstly, the results demonstrate that the cost production, S2F method, and quint algorithm approaches, which are commonly employed in classical economics, are the most effective models for valuing NFT artworks. Secondly, quantitative evaluation criteria for NFT artworks were proposed, including factors such as exhibitions and awards, copyrights, exhibition planning, career achievements and assigned weights. Additionally, qualitative evaluation criteria were put forth, encompassing aspects such as content, expression, originality, collectible value and assigned weights. The results of the recognition evaluation criteria were also derived. Furthermore, a framework was put forth to guarantee the rationality of the NFT artist ranking through verification. The anticipated outcomes of this research can be leveraged for the equitable utilisation of NFT artworks for purchase and sale, the establishment of guidelines for the calculation, settlement, and distribution of artworks, and the encouragement of new NFT art creation.

Female entrepreneurial support requirements: post pandemic ecosystems in India

PurposeThe corona virus outbreak has affected the entrepreneurial ecosystem adversely. This in particular has impacted on females. This study aims to identify the factors affecting the entrepreneurial intention (EI) of females under post-COVID adverse conditions.Design/methodology/approachA total of 340 articles were screened applying the preferred reporting items for systematic reviews and meta-analyses method. The EI of individuals undertaking different professional courses from three top National Institute Ranking Framework (NIRF) government institutes were then analyzed. In the expert analysis, the nominal group technique (NGT) and analytic hierarchy process (AHP) were used to identify and rank the crucial factors. Subsequently, in the exploratory analysis, a 19-item questionnaire was framed. The data was analyzed using SmartPLS 3.FindingsResilience, entrepreneurial education, self-concept and self-efficacy, social influence and opportunity perception were identified as critical indicators. Resilience was identified as the most significant factor. The partial least square structural equation modeling (PLS-SEM) revealed that all the factors except social influence had significant effect on the EI of females.Research limitations/implicationsThis study focuses primarily on factors affecting females in India. As ecosystems and support vary by region and country, the authors suggest that this study be replicated in different regions/countries in the future.Practical implicationsThe potential entrepreneurs can use this study's reference to identify the abilities they need. The government and academic institutions can have skill/training programs to enhance the effect of important factors identified in the study.Originality/valueWhile there is growing research of entrepreneurship and entrepreneurial marketing post-pandemic, there are a lack of Indian studies and female entrepreneurship studies.

Ranking guidance actions to support engineers in fulfilling process constraints

AbstractIn safety‐critical systems engineering, regulations such as Automotive SPICE, ISO26262, or ED‐109A mandate software quality assurance measures to provide evidence that the developed system is high quality. The constraints that define quality assurance conditions during the engineering life cycle are often non‐trivial. This paper addresses the challenges, engineers face who are unfamiliar with the precise constraints of various projects (e.g., when newly joining a company or switching between departments). Understanding how to fulfill a constraint is a time‐consuming and challenging task as an engineer needs to determine the most suitable option (out of potentially many) to fulfill a constraint violation. To this end, we propose a guidance action ranking framework to provide engineers with the most relevant guidance actions. Our primary ranking algorithm analyzes in the background the actions that engineers have made in the past to resolve a constraint violation without requiring explicit feedback from them. We evaluated our framework on two real‐world data sets: an open‐source drone management and an industrial air traffic control software system. Concretely, we replay past engineering activities and measured whether, in the case of a constraint violation, our suggested guidance actions were indeed selected by the engineer. The evaluation results revealed that learning from prior guidance actions effectively identifies the most appropriate guidance actions (ranked top 1 or 2) when compared to ranking algorithms based on action simplicity and artifact property change frequency. Specifically, we achieve a median MRR of 0.95 for the first case study and 0.94 for the second case study: an improvement of 80% and 100% over the baseline. Additionally, we observed that the simplicity of a guidance action does not reliably indicate its suitability for fulfilling a constraint, whereas learning from prior change operation property out‐performed simplicity‐based ranking but did not surpass guidance frequency‐based ranking.

An empirical investigation of open access scholarly publishing trends in social sciences at high-ranked central universities of India

Purpose This study aims to analyze the adoption of open access (OA) publishing in social sciences within central universities in India, focusing on various aspects such as the growth of OA literature, the use of different OA routes and collaboration patterns in OA publications. Design/methodology/approach Ten central universities were selected based on their rankings in the National Institute Ranking Framework 2022. Data on OA publishing in social sciences were collected from the Social Science Citation Index of the Web of Science (WoS) database using the advanced search query “(CU=India OR AD=India) AND PY=(2003–2022) NOT PY=(2023).” Data analysis was conducted using MS Excel (v16.0), BibExcel (version 2017), Biblioshiny (version 4.1.2) and Google Open Refine (version 3.7). Findings The study found that 30.40% of total publications were OA, with BHU as leading institute in OA publishing. OA publishing in social sciences saw a consistent increase, peaking in 2022 with 209 publications. “Sustainability” and “Plos One” were among the top ten journals, with 103 and 34 OA papers, respectively. OA publications had a higher mean citation rate than closed access publications. Collaboration with seven and nine authors had higher mean citation rates, while six-author collaborations were lower. Indian researchers received the most citations collaborating with the USA, UK and Australia. The Netherlands and Saudi Arabia received the fewer citations, when collaborating with Indian authors. Research limitations/implications The study’s main limitation is its reliance on WoS data, excluding many OA publications from smaller or specialized journals. Additionally, the focus on high-ranked central universities may not represent the entire academic landscape, as OA publishing patterns vary across other institutions and disciplines. Practical implications The study’s findings suggest that advancing OA publishing in social sciences at Indian universities requires raising awareness of OA concepts, enhancing institutional support and policies and informing researchers about funding opportunities. Emphasizing Gold OA and funding publication fees can broaden access to research. Universities with low OA ratios should adopt similar policies, mandate public research deposits and develop technical infrastructure. Encouraging multi-author collaborations can boost research impact and citation rates. Insights from the study can help institutions and policymakers shape effective OA strategies, enhancing the visibility and impact of social science research. Originality/value This is the first study analyzing the adoption of OA in the field of social sciences in high-ranked central universities in India. It has implications for promoting OA and increasing accessibility to research outputs. Universities with higher OA ratios can lead in this regard and encourage others to adopt similar practices for overall OA growth.

Assessing the Suitability of Different Testing and Specimen Preparation Approaches for Indirect Tensile Cracking Test (IDT-CT) Using a Simple Ranking Framework

Abstract The advent of new additives such as polymers, rubber, and warm mix additives, as well as emphasis on the use of reclaimed asphalt materials, has rendered the traditional volumetric mix design of asphalt mixtures inadequate. As a result, the need for incorporating performance tests in the mix design process and adopting a balanced mix design (BMD) approach is now being widely recognized. One of the major challenges in adopting and implementing the BMD process is the selection of performance tests for rutting and cracking evaluation. Oregon is in the preimplementation phase of BMD. The Oregon Department of Transportation has been working on the development of a BMD method since 2015 and is now exploring the use of the indirect tensile cracking test (IDT-CT) (formerly called the IDEAL-CT), which is a simple, practical, and rapid cracking performance test. However, the results of this test have been found to be sensitive to the loading equipment, aging conditions, temperature conditioning methods, and specimen's air voids, among other factors. In this study, the IDT-CT results of the two mix types were compared for different aging conditions, temperature conditioning methods, sample sitting time (the time that lapsed between the production of the sample and the cracking test), and device type, and the most suitable testing approach was determined using a simple ranking approach. Among all the testing approaches, testing the samples in a low-cost load frame after conditioning them in a dry conditioning chamber can be considered the most suitable method.

A Quantitative Computational Framework for Allopolyploid Single-Cell Data Integration and Core Gene Ranking in Development.

Polyploidization drives regulatory and phenotypic innovation. How the merger of different genomes contributes to polyploid development is a fundamental issue in evolutionary developmental biology and breeding research. Clarifying this issue is challenging because of genome complexity and the difficulty in tracking stochastic subgenome divergence during development. Recent single-cell sequencing techniques enabled probing subgenome-divergent regulation in the context of cellular differentiation. However, analyzing single-cell data suffers from high error rates due to high dimensionality, noise, and sparsity, and the errors stack up in polyploid analysis due to the increased dimensionality of comparisons between subgenomes of each cell, hindering deeper mechanistic understandings. In this study, we develop a quantitative computational framework, called "pseudo-genome divergence quantification" (pgDQ), for quantifying and tracking subgenome divergence directly at the cellular level. Further comparing with cellular differentiation trajectories derived from single-cell RNA sequencing data allows for an examination of the relationship between subgenome divergence and the progression of development. pgDQ produces robust results and is insensitive to data dropout and noise, avoiding high error rates due to multiple comparisons of genes, cells, and subgenomes. A statistical diagnostic approach is proposed to identify genes that are central to subgenome divergence during development, which facilitates the integration of different data modalities, enabling the identification of factors and pathways that mediate subgenome-divergent activity during development. Case studies have demonstrated that applying pgDQ to single-cell and bulk tissue transcriptomic data promotes a systematic and deeper understanding of how dynamic subgenome divergence contributes to developmental trajectories in polyploid evolution.

A ranking framework for the selection of IoT cloud platforms using hybrid multi-attribute decision-making method

PurposeThe Internet of Things (IoT) cloud platforms provide end-to-end solutions that integrate various capabilities such as application development, device and connectivity management, data storage, data analysis and data visualization. The high use of these platforms results in their huge availability provided by different capabilities. Therefore, choosing the optimal IoT cloud platform to develop IoT applications successfully has become crucial. The key purpose of the present study is to implement a hybrid multi-attribute decision-making approach (MADM) to evaluate and select IoT cloud platforms.Design/methodology/approachThe optimal selection of the IoT cloud platforms seems to be dependent on multiple attributes. Hence, the optimal selection of IoT cloud platforms problem is modeled as a MADM problem, and a hybrid approach named neutrosophic fuzzy set-Euclidean taxicab distance-based approach (NFS-ETDBA) is implemented to solve the same. NFS-ETDBA works on the calculation of assessment score for each alternative, i.e. IoT cloud platforms, by combining two different measures: Euclidean and taxicab distance.FindingsA case study to illustrate the working of the proposed NFS-ETDBA for optimal selection of IoT cloud platforms is given. The results obtained on the basis of calculated assessment scores depict that “Azure IoT suite” is the most preferable IoT cloud platform, whereas “Salesman IoT cloud” is the least preferable.Originality/valueThe proposed NFS-ETDBA methodology for the IoT cloud platform selection is implemented for the first time in this field. ETDBA is highly capable of handling the large number of alternatives and the selection attributes involved in any decision-making process. Further, the use of fuzzy set theory (FST) makes it very easy to handle the impreciseness that may occur during the data collection through a questionnaire from a group of experts.

GRAMP: A gene ranking and model prioritisation framework for building consensus genetic networks

Despite significant recent advancements in computational and statistical methods, different methods have specific strengths and weaknesses in the accurate reconstruction of gene regulatory networks (GRNs), making it difficult to determine the best method for each specific problem. To overcome these challenges, ensemble approaches, which combine the strengths of individual inference methods, are valuable. However, existing ensemble methods for GRN inference lack a sophisticated network aggregation method and generally rely solely on ranking approaches. These ensemble methods have no reliable mechanisms to identify highly performing inference methods specific to a given problem. They therefore tend to aggregate weak methods, diminishing the overall accuracy of the approach. Thus, developing a reliable mechanism to identify the most effective methods for specific problems and prioritize them in consensus network building is important. This paper presents a novel ensemble approach for reconstructing GRNs by integrating previously developed diverse GRN inference approaches. A novel network aggregation method called GRAMP, Gene Ranking And Model Prioritisation framework was developed, taking into consideration both local and global gene ranking and the performance of different inference approaches on a specific network. The proposed ensemble approach demonstrated performance superior to those of other state-of-the-art methods, as evidenced by results from simulated datasets and a real-world gene expression dataset.

An enclosure quality ranking framework for terrestrial animals in captivity

There is a burgeoning interest in measuring and improving animal welfare in captive settings. Recent work has emphasized how enclosure design elements directly impact animal welfare (e.g., from health, behavioral, and reproductive standpoints). Yet, there is no published systematic way for practitioners to quantitatively rank enclosure quality. To address this critical need, we developed a flexible enclosure quality ranking framework for terrestrial animals in captivity. Our enclosure framework comprises 11 broadly applicable and measurable components of enclosure design that have relevance to animal welfare: Display, Size, Shelter, Materials, Environment, Climate, Viewshed, Social, People, Other, and Complexity. Each of these components relates to one or more of the “Five Freedoms” and “Opportunities to Thrive”. In addition to developing the enclosure quality ranking framework, we provide an example of how to apply the framework, and offer suggestions on how to conduct empirical analyses with the ranking data derived from our framework. Once applied, our framework can be used to generate measurable outcomes that practitioners can use to make informed decisions, leading to optimal animal welfare.

Developing a Comprehensive Framework for Assessing Airports’ Environmental Sustainability

The background of this research is environmental sustainability assessments in the aviation ecosystem, particularly concerning airports, which are getting significant attention from industry representatives, regulators, and researchers. A standardized and comprehensive approach is essential to uniformly address the global impact of these assessments across the industry. The main objective of this study is to propose a framework that encompasses the requirements of aviation regulators, as well as industry and academic metrics, aiming for a standardized approach to environmental sustainability assessments at airports. The methodology employs the Sum of Rankings Method to rank each airport across various environmental indicators. This approach was applied to five globally distributed airports, offering a diverse testing ground for assessing the applicability and effectiveness of the proposed metrics and validating the ranking framework. The results show that applying the framework across varied airport environments demonstrated its ranking viability and effectiveness, indicating that it can be successfully applied to different airport realities. The conclusion shows that the developed framework can be successfully applied, suggesting that it is a valid method for adoption in environmental airport sustainability rankings.

Preface

5th International Conference on Civil Engineering Trends and Challenges for Sustainability (CTCS-2023) (Under the Aegis of ICETE 2023 Multi-Conference Platform) 19th & 20th December 2023 Organized by Department of Civil Engineering About NITTE (Deemed to be University) Nitte (Deemed-to-be University) has its roots in a group of Institutions established by the Nitte Education Trust. The Trust was established in 1979 by one of India’s respected Statesman, Late Justice KS Hegde, Supreme Court Judge and Speaker of Lok Sabha, with the mission of empowering rural youth through quality education and healthcare. The Trust has established 36 institutions spread in three campuses at Nitte, Mangalore and Bangalore. It offers education in diverse areas of learning including health professions education, engineering, management, humanities, general education, vocational training, and school/pre-university education. The University offers a total of 98 programs in the disciplines of engineering, medicine, allied health sciences, dentistry, pharmacy, nursing, physiotherapy, speech and audiology, biological sciences, media & communication, commerce, science, management, and Architecture. It has 10,000+ students, over 875 faculty members and over 2475 support staff on roll. The University campuses are spread over 52 acres in Deralakatte-Paneer areas of Mangalore and 110 acres in Nitte. The University received A+ Grading in NAAC accreditation in 2021. It has been consistently placed in the Top 65-80 rank band in NIRF. The University is placed in the 401 to 450 Rank Band in the QS Rankings for Asia Region. It has received Diamond rating in the QS I-Gauge India Ratings. The Constituent colleges of the university have good standing in their disciplines in the NIRF rankings. In 2023, Nitte University has obtained 65th Rank, the dental college ranked 5th and pharmacy colleges ranked 46th in NIRF. The BPharm program of the University is accredited by NBA. The teaching hospital is accredited by both NABH and NABL. About the Institute Nitte Mahalinga Adyantaya Memorial Institute of Technology(NMAMIT), Nitte, established in 1986 and recognized by the All India Council for Technical Education, New Delhi, has been a constituent college of Nitte (Deemed to be University), Mangaluru, since June 2022. Rank band 101-150 in the National Institutional Ranking Framework (NIRF) 2023 by Ministry of Education, Government of India, the College has been placed under ‘Platinum’ category for having high industry linkages by the AICTE-CII Survey of Industry-Linked Technical Institutes 2020. NMAMIT, the off-campus centre of Nitte DU located at Nitte village, has active collaborations with several international universities and organizations for faculty and student exchanges, research, internships and placements. The Institute offers UG engineering program in eleven disciplines; Artificial Intelligence & Machine Learning (AI&ML), Artificial Intelligence & Data Science (AI&DS), Biotechnology (BT), Civil Engineering(CIV), Computer & Communication Engineering (CCE), Computer Science & Engineering(CS), Electrical & Electronics Engineering (E&E), Electronics & Communication Engineering (E&C), Information Science & Engineering (IS), Mechanical Engineering(MECH) and Robotics & Artificial Intelligence (R&AI ). Out of these programs, seven UG programs i.e., BT, CIV, CS, E&E, E&C, IS and MECH are accredited by NBA, New Delhi under Tier - I category till 30 June 2025. The institute also offers PG program M.Tech. in seven disciplines namely Construction Technology, Computer Science & Engineering, Cyber Security, Electric Vehicle Technology, Machine Design, Structural Engineering and VLSI Design & Embedded Systems as well as MCA program. All the departments have qualified research guides for students interested in taking up research work leading to Ph.D. List of About the Organizing Department, About the Conference, Keynote Speakers, Theme of the Conference, Thrust Areas, Publication Partner, Paper Submission, Accommodation, Conference Location and Contact Us are available in this Pdf.

E-SERS: An Enhanced Approach to Trust-Based Ranking of Apps

The number of mobile applications (“Apps”) has grown significantly in recent years. App Stores rank/recommend Apps based on factors such as average star ratings and the number of installs. Such rankings do not focus on the internal artifacts of Apps (e.g., security vulnerabilities). If internal artifacts are ignored, users may fail to estimate the potential risks associated with installing Apps. In this research, we present a framework called E-SERS (Enhanced Security-related and Evidence-based Ranking Scheme) for comparing Android Apps that offer similar functionalities. E-SERS uses internal and external artifacts of Apps in the ranking process. E-SERS is a significant enhancement of our past evidence-based ranking framework called SERS. We have evaluated E-SERS on publicly accessible Apps from the Google Play Store and compared our rankings with prevalent ranking techniques. Our experiments demonstrate that E-SERS, leveraging its holistic approach, excels in identifying malicious Apps and consistently outperforms existing alternatives in ranking accuracy. By emphasizing comprehensive assessment, E-SERS empowers users, particularly those less experienced with technology, to make informed decisions and avoid potentially harmful Apps. This contribution addresses a critical gap in current App-ranking methodologies, enhancing the safety and security of today’s technologically dependent society.

From quantitative metrics to clinical success: assessing the utility of deep learning for tumor segmentation in breast surgery.

Preventing positive margins is essential for ensuring favorable patient outcomes following breast-conserving surgery (BCS). Deep learning has the potential to enable this by automatically contouring the tumor and guiding resection in real time. However, evaluation of such models with respect to pathology outcomes is necessary for their successful translation into clinical practice. Sixteen deep learning models based on established architectures in the literature are trained on 7318 ultrasound images from 33 patients. Models are ranked by an expert based on their contours generated from images in our test set. Generated contours from each model are also analyzed using recorded cautery trajectories of five navigated BCS cases to predict margin status. Predicted margins are compared with pathology reports. The best-performing model using both quantitative evaluation and our visual ranking framework achieved a mean Dice score of 0.959. Quantitative metrics are positively associated with expert visual rankings. However, the predictive value of generated contours was limited with a sensitivity of 0.750 and a specificity of 0.433 when tested against pathology reports. We present a clinical evaluation of deep learning models trained for intraoperative tumor segmentation in breast-conserving surgery. We demonstrate that automatic contouring is limited in predicting pathology margins despite achieving high performance on quantitative metrics.

Beyond throughput: Evaluating maritime port competitiveness using MABAC and Bayesian methods

The performance ranking framework of maritime ports conducted by the World Shipping Council relies solely on a singular criterion, such as container throughput. This ranking method lacks a comprehensive assessment of port competitiveness and may have biases. Therefore, this work proposes a new approach to measure the competitiveness of maritime ports by considering multiple performance criteria, such as port processing time, bunker fuel quality, bunker fuel suppliers, geographical advantages, and port security. To ensure fairness in weight estimation, both objective method (using the Entropy method) and subjective method (using the Best Worst method) are employed and integrated using Bayes’ theorem. Furthermore, the Multi-Attributive Border Approximation Area Comparison (MABAC) method is utilized to evaluate the ranking of ports based on the combined effect of these criteria, referred to as the Port Competitiveness Index (PCI). To test the effectiveness of the proposed methodology, the top 20 major maritime ports on the Asia-Europe service route are determined. This finding highlights the practical insights gained from the study, which can be applied to improve the performance of ports across different service routes worldwide.

ESG integration in portfolio selection: A robust preference-based multicriteria approach

We present a framework for multi-objective optimization where the classical mean–variance portfolio model is extended to integrate the environmental, social and governance (ESG) criteria on the same playing field as risk and return and, at the same time, to reflect the investors’ preferences in the optimal portfolio allocation. To obtain the three–dimensional Pareto front, we apply an efficient multi-objective genetic algorithm, which is based on the concept of ɛ-dominance. We next address the issue of how to incorporate investors’ preferences to express the relative importance of each objective through a robust weighting scheme in a multicriteria ranking framework. The new proposal has been applied to real data to find optimal portfolios of socially responsible investment funds, and the main conclusion from the empirical tests is that it is possible to provide the investors with a robust solution in the mean–variance–ESG surface according to their preferences.

Framework for Ranking Machine Learning Predictions of Limited, Multimodal, and Longitudinal Behavioral Passive Sensing Data: Combining User-Agnostic and Personalized Modeling.

Passive mobile sensing provides opportunities for measuring and monitoring health status in the wild and outside of clinics. However, longitudinal, multimodal mobile sensor data can be small, noisy, and incomplete. This makes processing, modeling, and prediction of these data challenging. The small size of the data set restricts it from being modeled using complex deep learning networks. The current state of the art (SOTA) tackles small sensor data sets following a singular modeling paradigm based on traditional machine learning (ML) algorithms. These opt for either a user-agnostic modeling approach, making the model susceptible to a larger degree of noise, or a personalized approach, where training on individual data alludes to a more limited data set, giving rise to overfitting, therefore, ultimately, having to seek a trade-off by choosing 1 of the 2 modeling approaches to reach predictions. The objective of this study was to filter, rank, and output the best predictions for small, multimodal, longitudinal sensor data using a framework that is designed to tackle data sets that are limited in size (particularly targeting health studies that use passive multimodal sensors) and that combines both user agnostic and personalized approaches, along with a combination of ranking strategies to filter predictions. In this paper, we introduced a novel ranking framework for longitudinal multimodal sensors (FLMS) to address challenges encountered in health studies involving passive multimodal sensors. Using the FLMS, we (1) built a tensor-based aggregation and ranking strategy for final interpretation, (2) processed various combinations of sensor fusions, and (3) balanced user-agnostic and personalized modeling approaches with appropriate cross-validation strategies. The performance of the FLMS was validated with the help of a real data set of adolescents diagnosed with major depressive disorder for the prediction of change in depression in the adolescent participants. Predictions output by the proposed FLMS achieved a 7% increase in accuracy and a 13% increase in recall for the real data set. Experiments with existing SOTA ML algorithms showed an 11% increase in accuracy for the depression data set and how overfitting and sparsity were handled. The FLMS aims to fill the gap that currently exists when modeling passive sensor data with a small number of data points. It achieves this through leveraging both user-agnostic and personalized modeling techniques in tandem with an effective ranking strategy to filter predictions.