Multiple Experts Research Articles

An ontology-based knowledge representation using OWL for Indonesian local regulations

<div class="WordSection1"><p>Inconsistencies in legislation can significantly hinder the effectiveness and efficiency of the central and local government administrations. The Indonesian government requires standard harmonization of each piece of legislation to prevent such problems. However, this process is often manual and requires the involvement of multiple experts with varying backgrounds. This leads to high resource expenses regarding human resources, cost, and time. To address this, a software system should be developed to detect potential disharmony among legislation. However, the system requires a well-constructed legislation conceptual model represented in an appropriate modeling language. This research aims to develop the Indonesian local regulation ontology in web ontology language (OWL), where no such ontology exists. The ontology was created using the Ontology Development 101 methodology and evaluated using competency questions and expert judgment approaches. The resulting ontology becomes a basis for developing an automatic recommendation system to detect potentially inconsistent legislation in future works.</p></div>

Solving Table-based fact verification with mixture of logical reasoning

Table-based fact verification (TFV) is a binary classification task that requires understanding and reasoning about both table and text. This task poses many challenges, such as table parsing, text comprehension, and numerical reasoning. However, existing methods tend to depend solely on pre-trained models for tables, treating all types of reasoning equally and disregarding the importance of identifying logic types in inference process. In this regard, we propose MoETFV, an efficient and explanatory approach to solving TFV, which is based on a Mixture-of-Experts (MoE) framework. This approach can detect the underlying logic types of statements and leverage multiple independent experts to emulate diverse logical reasoning. It consists of one shared expert for general semantic understanding and several specific experts with distinct responsibilities for different logical inferences. Moreover, the practical applications of the MoE method in TFV are thoroughly investigated. This model doesn’t necessitate any table pre-trained models, and aligns closely with human cognitive processes in addressing such issues. Experimental results demonstrate the innovation and feasibility of the proposed approach.

Youth Work, Youth Studies, and Co-design: Sustaining a Dynamic Nexus to Progress Youth Participation

Youth work practitioners and youth researchers both share a keen interest in the lives, experiences, and well-being of young people; however, the skills and expertise held by practitioners and researchers have not always been mutually valued leading to tensions and a research-practice gap. The rise of co-design methods that prioritise relational skills and ethics appears to mark a moment for closing or reducing this gap. Rather than accepting this convergence at face value, in this paper, we examine some of the key tensions around (1) relational ethics and decision-making, (2) holding multiple roles and expertise, and (3) structures that constrain or sustain participation to argue for sustaining a dynamic research-practice nexus. Drawing on our experience and practitioner-researchers, we argue that rather than simply overlooking the practical and ethical tensions between practice and research, sustaining a dynamic nexus comprising of continuing dialogue and collaboration can foster and progress co-design methods in pursuit of the aims of youth participation.

Consensus on the rational implementation of laparoscopic surgery after conversion therapy in far-advanced gastric cancer (first edition)

Far-advanced gastric cancer has always been a challenging problem in clinical treatment and a key direction for breakthrough research. Non-surgical treatments are primarily managed in patients with far-advanced gastric cancer. However, with the advancement of therapeutic methods in recent years, tumor foci can be significantly regressed after effective preoperative treatment, in prospect ofregaining the opportunity of radical gastrectomy. In the surgical field, laparoscopic surgery, as one of the routine methods for gastric cancer, has proven effective in the treatment of initially resectable gastric cancer. However, its application in far-advanced gastric cancer still lacks high-level medical evidence. Nevertheless, global clinicians have widely participated in research exploration, achieving certain progress. This consensus, formulated based on the latest research developments and adopting through the international Delphi method with multiple expert votes and amendments, divides the perioperative period after conversion therapy for far-advanced gastric cancer into three parts, i.e., preoperative assessment, rational implementation of laparoscopic surgery, and postoperative assessment and treatment. It forms a preliminary consensus of 18 items, aiming to provide a basic reference and guidance for clinicians.

Synergistic Strategy of Sustainable Hospital Site Selection in Saudi Arabia Using Spherical Fuzzy MCDM Methodology

Site selection for a hospital is demanding and challenging work. It’s become more complicated when considering various infectious diseases. Multiple criteria and sub-criteria are considered for selecting the most suitable and efficient hospital location. In this paper, we find the most suitable location for multiple disease-related hospitals using the multi-criteria decision-making (MCDM) methodologies. The proposed study is done by the MCDM techniques, namely spherical Entropy and spherical VIekriterijumsko KOmpromisno Rangiranje (VIKOR) methods. The decision-making for site selection is based on multiple experts’ opinions. Also, we use real data sources in spherical fuzzy numbers (SFN) to capture all its uncertainty. We proposed a new score function and an accuracy function of the SFN to evaluate crisp value from fuzzy numbers. The most prioritized criteria and sub-criteria are determined with their weights. We optimized the proposed site based on demand and criterion weight. Finally, sensitivity analysis and comparative analysis are conducted to check the stability and robustness of the result.

Exploring the impact of cardiologists expertise on publication metrics

BackgroundIn the field of academic cardiology, the assessment of an author's scholarly impact and professional progression heavily relies on publications and citations. This study investigates whether specific cardiology expertise correlates with accelerated professional growth. MethodsUsing data from the 2023 European Society of Cardiology congress, 948 faculty attendees with an h-index of 30 or higher were analyzed. Expertises were categorized into six groups, and their association with publications and citations peaks was explored. ResultsInterventional cardiologists exhibited the highest annual publication peak, followed by imaging and electrophysiology experts. However, no significant differences were observed in citation peaks among expertise groups. While imaging experts initially appeared to reach citation peaks faster, this effect diminished after statistical adjustments. Additionally, holding multiple expertise areas prolonged the time to reach publication and citation peaks by approximately six years. ConclusionThis study underscores the influence of expertise in interventional cardiology on publication peaks but suggests that citation peaks and career progression velocity remain unaffected by expertise type. Furthermore, it highlights that holding multiple areas of expertise slowers the attainment of career peak for scholarly authors.

Constructing selection hyper-heuristics for open vehicle routing with time delay neural networks using multiple experts

Hyper-heuristics are general purpose search methods for solving computationally difficult problems. A selection hyper-heuristic is composed of two key components: a heuristic selection method and move acceptance criterion. Under an iterative single-point search framework, a solution is modified by selecting and applying a predefined low-level heuristic, with a decision then taken to accept or reject the resulting solution. Designing a selection hyper-heuristic is an extremely challenging task. In this study, we investigate computer-aided design of a selection hyper-heuristic for the open vehicle routing problem. A time delay neural network is used as an offline apprenticeship learning method. Our approach first observes the search behaviour of multiple expert human-designed selection hyper-heuristics on a selected sample of training instances, before automatically generating a selection hyper-heuristic capable of solving unseen instances effectively. The proposed approach is tested on open vehicle routing problem instances of different sizes to examine the performance and generality of the selection hyper-heuristics generated. Improved performance is demonstrated over a set of well-known benchmarks from the literature when compared to using the existing expert systems directly.

Crisis resilience assessment and management of public utility companies

Currently, the most frequently used models for forecasting the probability of company bankruptcy in the housing and utilities sector lack accuracy. The hypothesis is put forward that crisis resilience of a company can be assessed based on its adaptive capabilities. The paper aims to construct a more accurate compared to the known regression model for predicting bankruptcies, as well as develop models for assessing the quality of crisis adaptation management at public utility companies allowing for the stakeholders’ interests and peculiarities of their interface. The methodological basis of the study consists of the theory of crisis management and a stakeholder approach. The methods include multiple regression analysis, stakeholder mapping, sociological survey, and expert assessments. The evidence comes from the accounting and statistical reporting of 49 public utility companies, materials of arbitration cases, survey results of 33 heads of organisations obtained in the period from February to March 2023. The theoretical developments are implemented within the empirical studies of public utility companies. To improve crisis adaptation and resilience of public utility companies the findings recommend to launch staff training programmes, establish mechanisms for horizontal intra-sectoral connections and maintain cooperation at the level of public authorities in order to control investments in the housing and utilities sector.

Weight Averaging and re-adjustment ensemble for QRCD

Question Answering (QA) is a prominent task in the field of Natural Language Processing (NLP) with extensive applications. Recently, there has been a notable surge in research interest concerning the development of QA systems for the Holy Qur’an, an Islamic religious text. The Qur’an Reading Comprehension Dataset (QRCD) Malhas and Elsayed (2020) is a highly commendable effort in this respect. It stands as the first benchmark dataset specifically designed for a set of directly answerable questions from the Qur’an. Each question in the dataset is meticulously labeled with all potential answers sourced from the Holy Qur’an. From our perspective, the main challenge in QRCD stems from the limited volume of training data it offers. As a solution we propose an innovative approach to build a Deep Neural Network (DNN) ensemble, centered around Ara-Electra model (Antoun et al., 2021), that we called Weight Averaging and Re-adjustment (WAR) model. The model is constructed by computing running averages of all model states that evolve during a single training session and ensuring that model weights are readjusted prior to each training epoch, in order to hold it back from over fitting the training data. The scheme results in a single standalone model that exhibits the benefits of multi-model ensembles. It is distinguished from other ensembles proposed for QRCD that accumulates outputs from multiple expert models and employs classic techniques like hard voting or score averaging on output probabilities to build unified results. Each expert model costs individual training time and compute resources. The WAR model outperforms existing systems with improved generalization over unseen data. It achieves F1, partial Reciprocal Rank (pRR), and exact-match (EM) scores of 0.567, 0.60 and 0.29 respectively, exceeding best reported QRCD scores by 3%, 1.5% and 0.69% respectively. Notably, we are comparing our results with the top scores from different models, highlighting our model’s consistent performance across all three metrics.

Design of Remote Slit Lamp Diagnosis Platform Based on IoT Technology

In order to realize the diagnosis of slit lamp in cross-regional patients and improve the real-time and convenience of diagnosis, a remote slit lamp diagnosis platform based on Internet of Things (IoT) technology is designed. Firstly, the feasibility of remote slit lamp is analyzed. Secondly, the IoT platform architecture of doctor/server/facility (D/S/F) is proposed and a remote slit lamp is designed. Finally, the performance of the remote slit lamp diagnostic platform is tested. The platform solves the communication problem of distributed slit lamps and realizes respectively numerical control of multi-area slit lamp by multi-eye experts. The test results show that the remote control delay of the platform is less than 20 ms, which supports multiple experts to diagnose multiple patients separately.

Risk assessment of fire safety in large-scale commercial and high-rise buildings based on intuitionistic fuzzy and social graph

Fire risk assessment is a useful method to identify potential fire risks and improve safety management, especially for those large-scale commercial and high-rise buildings. However, after the establishment of the fire risk indexing system, the weight assignment in the existing assessment methods is not scientific and objective enough to synthesize the opinions of multiple experts with different knowledge backgrounds and working experience. To solve this problem, a novel fire risk assessment for large-scale commercial and high-rise buildings is proposed with intuitionistic fuzzy and social graph. First, based on the national standards of fire safety management, the monthly maintenance and the annual fire assessment reports, the indexing system is established. Then, a scientific and objective weight assignment method called Social Graph based Intuitionistic Fuzzy Analytic Hierarchy Process (SGIFAHP) is proposed such that (1) by utilizing the intuitionistic fuzzy and social graph, it can synthesize the positive, negative and hesitant opinions from multiple experts by considering the importance of experts; (2) a novel mechanism is designed to automatically check and repair the consistency of the opinions of each expert when the expert compares the importance of risk factors. To validate the performance of the proposed method, eleven buildings are selected and their fire safety data are collected. A comparison analysis is carried out with the existing methods to compare the assigned weights. The comparison and score validation conclude that the proposed method can assign more reasonable, scientific and objective weights than the existing methods while the scores are comprehensive and strongly interpretable. In the end, a guide is offered to help safety owners and inspectors improve fire safety with the proposed method.

Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation

The Mixture-of-Experts (MoE) approach has demonstrated outstanding scalability in multi-task learning including low-level upstream tasks such as concurrent removal of multiple adverse weather effects. However, the conventional MoE architecture with parallel Feed Forward Network (FFN) experts leads to significant parameter and computational overheads that hinder its efficient deployment. In addition, the naive MoE linear router is suboptimal in assigning task-specific features to multiple experts which limits its further scalability. In this work, we propose an efficient MoE architecture with weight sharing across the experts. Inspired by the idea of linear feature modulation (FM), our architecture implicitly instantiates multiple experts via learnable activation modulations on a single shared expert block. The proposed Feature Modulated Expert (FME) serves as a building block for the novel Mixture-of-Feature-Modulation-Experts (MoFME) architecture, which can scale up the number of experts with low overhead. We further propose an Uncertainty-aware Router (UaR) to assign task-specific features to different FM modules with well-calibrated weights. This enables MoFME to effectively learn diverse expert functions for multiple tasks. The conducted experiments on the multi-deweather task show that our MoFME outperforms the state-of-the-art in the image restoration quality by 0.1-0.2 dB while saving more than 74% of parameters and 20% inference time over the conventional MoE counterpart. Experiments on the downstream segmentation and classification tasks further demonstrate the generalizability of MoFME to real open-world applications.

AACP: Aesthetics Assessment of Children’s Paintings Based on Self-Supervised Learning

The Aesthetics Assessment of Children's Paintings (AACP) is an important branch of the image aesthetics assessment (IAA), playing a significant role in children's education. This task presents unique challenges, such as limited available data and the requirement for evaluation metrics from multiple perspectives. However, previous approaches have relied on training large datasets and subsequently providing an aesthetics score to the image, which is not applicable to AACP. To solve this problem, we construct an aesthetics assessment dataset of children's paintings and a model based on self-supervised learning. 1) We build a novel dataset composed of two parts: the first part contains more than 20k unlabeled images of children's paintings; the second part contains 1.2k images of children's paintings, and each image contains eight attributes labeled by multiple design experts. 2) We design a pipeline that includes a feature extraction module, perception modules and a disentangled evaluation module. 3) We conduct both qualitative and quantitative experiments to compare our model's performance with five other methods using the AACP dataset. Our experiments reveal that our method can accurately capture aesthetic features and achieve state-of-the-art performance.

Recent Advancements in Inverse Reinforcement Learning

Inverse reinforcement learning (IRL) has seen significant advancements in recent years. This class of approaches aims to efficiently learn the underlying reward function that rationalizes the behavior exhibited by expert agents, often represented by humans. In contrast to mere behavioral cloning, the reconstruction of a reward function yields appealing implications, as it allows for more effective interpretability of the expert’s decisions and provides a transferable specification of the expert’s objectives for application in even different environments. Unlike the well-understood field of reinforcement learning (RL) from a theoretical perspective, IRL still grapples with limited understanding, significantly constraining its applicability. A fundamental challenge in IRL is the inherent ambiguity in selecting a reward function, given the existence of multiple candidate functions, all explaining the expert’s behavior. In this talk, I will survey three of my papers that have made notable contributions to the IRL field: “Provably Efficient Learning of Transferable Rewards”, “Towards Theoretical Understanding of Inverse Reinforcement Learning”, and “Inverse Reinforcement Learning with Sub-optimal Experts". The central innovation introduced by the first paper is a novel formulation of the IRL problem that overcomes the issue of ambiguity. IRL is reframed as the problem of learning the feasible reward set, which is the set of all rewards that can explain the expert’s behavior. This approach postpones the selection of the reward function, thereby circumventing the ambiguity issues. Furthermore, the feasible reward set exhibits convenient geometric properties that enable the development of efficient algorithms for its computation. Building on this novel formulation of IRL, the second paper addresses the problem of efficiently learning the feasible reward set when the environment and the expert’s policy are not known in advance. It introduces a novel way to assess the dissimilarity between feasible reward sets based on the Hausdorff distance and presents a new PAC (probabilistic approximately correct) framework. The most significant contribution of this paper is the introduction of the first sample complexity lower bound, which highlights the challenges inherent in the IRL problem. Deriving this lower bound necessitated the development of novel technical tools. The paper also demonstrates that when a generative model of the environment is available, a uniform sampling strategy achieves a sample complexity that matches the lower bound, up to logarithmic factors. Finally, in the third paper, the IRL problem in the presence of sub-optimal experts is investigated. Specifically, the paper assumes the availability of multiple sub-optimal experts, in addition to the expert agent, which provides additional demonstrations, associated with a known quantification of the maximum amount of sub-optimality. The paper shows that this richer information mitigates the ambiguity problem, significantly reducing the size of the feasible reward set while retaining its favorable geometric properties. Furthermore, the paper explores the associated statistical problem and derives novel lower bounds for sample complexity, along with almost matching algorithms. These selected papers represent notable advancements in IRL, contributing to the establishment of a solid theoretical foundation for IRL and extending the framework to accommodate scenarios with sub-optimal experts.

Exploring Diverse Representations for Open Set Recognition

Open set recognition (OSR) requires the model to classify samples that belong to closed sets while rejecting unknown samples during test. Currently, generative models often perform better than discriminative models in OSR, but recent studies show that generative models may be computationally infeasible or unstable on complex tasks. In this paper, we provide insights into OSR and find that learning supplementary representations can theoretically reduce the open space risk. Based on the analysis, we propose a new model, namely Multi-Expert Diverse Attention Fusion (MEDAF), that learns diverse representations in a discriminative way. MEDAF consists of multiple experts that are learned with an attention diversity regularization term to ensure the attention maps are mutually different. The logits learned by each expert are adaptively fused and used to identify the unknowns through the score function. We show that the differences in attention maps can lead to diverse representations so that the fused representations can well handle the open space. Extensive experiments are conducted on standard and OSR large-scale benchmarks. Results show that the proposed discriminative method can outperform existing generative models by up to 9.5% on AUROC and achieve new state-of-the-art performance with little computational cost. Our method can also seamlessly integrate existing classification models. Code is available at https://github.com/Vanixxz/MEDAF.

Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning

We address the challenging problem of Long-Tailed Semi-Supervised Learning (LTSSL) where labeled data exhibit imbalanced class distribution and unlabeled data follow an unknown distribution. Unlike in balanced SSL, the generated pseudo-labels are skewed towards head classes, intensifying the training bias. Such a phenomenon is even amplified as more unlabeled data will be mislabeled as head classes when the class distribution of labeled and unlabeled datasets are mismatched. To solve this problem, we propose a novel method named ComPlementary Experts (CPE). Specifically, we train multiple experts to model various class distributions, each of them yielding high-quality pseudo-labels within one form of class distribution. Besides, we introduce Classwise Batch Normalization for CPE to avoid performance degradation caused by feature distribution mismatch between head and non-head classes. CPE achieves state-of-the-art performances on CIFAR-10-LT, CIFAR-100-LT, and STL-10-LT dataset benchmarks. For instance, on CIFAR-10-LT, CPE improves test accuracy by over >2.22% compared to baselines. Code is available at https://github.com/machengcheng2016/CPE-LTSSL.

Stability risk early warning for mine goaf: Based on D-RES and asymmetric fuzzy connection cloud model

To prevent and mitigate safety risks in the mining goaf and achieve risk prevention and shifting the control frontier forward, a novel goaf stability risk early warning model is developed based on D-RES and asymmetric fuzzy association cloud. Taking into consideration the intrinsic characteristics of the goaf, an indicator system covering 12 indicators from three aspects, namely goaf morphology, rock mass physical-mechanical parameters, and goaf development status, is constructed to assess goaf stability. To address the vagueness and randomness issues in the classification criteria for goaf stability early warning, a fuzzy interval-based model is proposed to quantify warning indicators and determine their fuzzy interval range and optimal boundary information. The RES theory is introduced to analyze the interaction relationships among warning indicators, and the D numbers theory is utilized to comprehensively synthesize opinions from multiple experts, establishing a D-RES coupled weight calculation model for collaborative decision-making. Additionally, the asymmetric fuzzy association cloud is introduced to represent the uncertainties and vagueness among different risk levels, considering the finite interval and asymmetric distribution features of warning indicator levels. By integrating the D-RES-derived coupled weights, early warning of goaf stability is achieved. The validation on mining goafs demonstrates that the warning results of the model are consistent with the actual safety conditions, indicating the high applicability and accuracy of the proposed early warning model. The developed model provides a theoretical foundation for formulating safety management policies relevant to mining goafs.

Flexible global forecast combinations

Forecast combination – the aggregation of individual forecasts from multiple experts or models – is a proven approach to economic forecasting. To date, research on economic forecasting has concentrated on local combination methods, which handle separate but related forecasting tasks in isolation. Yet, it has been known for over two decades in the machine learning community that global methods, which exploit task-relatedness, can improve on local methods that ignore it. Motivated by the possibility for improvement, this paper introduces a framework for globally combining forecasts while being flexible to the level of task-relatedness. Through our framework, we develop global versions of several existing forecast combinations. To evaluate the efficacy of these new global forecast combinations, we conduct extensive comparisons using synthetic and real data. Our real data comparisons, which involve forecasts of core economic indicators in the Eurozone, provide empirical evidence that the accuracy of global combinations of economic forecasts can surpass local combinations.

Equilibrium information in credence goods

We study credence goods in a general model. A consumer may suffer a loss which is a continuous random variable. Privately observing the loss value, an expert can provide a repair at a price to eliminate the consumer's loss. All perfect-Bayesian equilibria are inefficient, in that some losses are not repaired. In closed form, we derive a pooling equilibrium (where losses are inferred to be in an interval), and a separating equilibrium (where losses are precisely inferred). If the expert can acquire an information structure on losses, the first best is achieved by a binary signal. Results are robust when cost and loss are random and correlated, and when there are multiple experts.

Evaluating potential quality of e-commerce order fulfillment service: A collective intelligence-driven approach

E-commerce order fulfillment service (E-COFS) plays a pivotal role in shaping consumer behavior in online marketplaces. The strategic outsourcing of the service allows e-commerce sellers to prioritize their core business areas, enhance customer satisfaction, and minimize fulfillment costs. However, a critical challenge lies in appraising the potential quality of E-COFS provided by third parties, especially when lacking historical information. To address this, this paper first designs a generalized framework for guiding the construction of the quantitative model for evaluating the potential quality of E-COFS. The proposed framework unfolds in three stages: (1) evaluating potential effectiveness of an E-COFS through quantifying stakeholders’ potential satisfaction from the E-COFS plan tailored by its provider, (2) evaluating its potential feasibility by quantifying the potential performance of the E-COFS quality management system (E-COFS-QMS) built by the provider on supporting the plan, and (3) integrating the above two parts to gauge the potential quality of the E-COFS. Building upon this framework, this paper then designs a novel quantitative model. Specifically, this model adopts the linguistic subjective judgment representation method and introduces basic uncertain linguistic information to achieve computing with words. Multiple stakeholders within e-commerce sellers are tasked with articulating their requirements, their preferences and expectations, and consensus reaching process is conducted to obtain the acceptable consensus among these stakeholders. Multiple experts from various domains are tasked with giving their subjective judgements on the performances of E-COFS and E-COFS-QMS, and a method of weighting individual judgments, which respects the reliabilities of individual judgements and the overall similarity in knowledge structures among the experts, is adopted to effectively tap into collective intelligence. Finally, a case study is conducted to validate the validity and feasibility of the proposed quantitative model.