First-order logic (FOL) is a fundamental formalism for factual reasoning over knowledge graphs (KGs), e.g. in researches of KG-based fact verification and logical consistency or reasoning of large language models (LLM).However, existing benchmarks and approaches insufficiently capture many claims that require comparison or counting, and lack support for several FOL quantifiers and connectives.To address these challenges and expand the expressive capacity of FOL for KG-based reasoning, we introduce FOLX-KG, a novel extended FOL σ-structure over KGs that incorporates comparison predicates and counting quantifiers.Using this extended logic, we construct Fact-FOLX-KG, a fact verification dataset consisting of 43,821 KG-based claim-formula pairs designed to enable systematic study of richer logical forms and reasoning types.We further propose FOLX Prover, an executable program-guided logic reasoning pipeline adapted for KG-based factual reasoning under the extended FOL.Experimental results show that our method achieves state-ofthe-art performance on Fact-FOLX-KG, while previous methods experience performance drop on claims requiring comparison and counting.These findings demonstrate the importance of extended logical expressiveness for robust factual reasoning over KGs. 1

When building knowledge bases using relation classification (RC) techniques, it is essential to handle data from various languages and domains. However, most existing multilingual RC methods require parallel corpora and some may lead to obviously increased computation overhead. To address these challenges, we propose a multilingual RC method based on PLMs, called PLM$^{3}$RC. Our method first introduce entity prompts and multilingual PLMs to construct a shared encoder network, and capture shared language-invariant knowledge of relation classification. Then multiple domain-specific classifiers are introduced to capture language- and domain-specific knowledge. For realizing multilingual knowledge transfer, we further introduce adversarial learning and design linear discriminators. We conducted a series of experiments to verify the effectiveness of our method. Our experiments show that PLM$^{3}$RC outperform other mainstream RC method in multilingual scenarios, with regular computing resources. Besides, the results clearly demonstrate that our method can effectively leverages multilingual data for knowledge transfer, without using parallel corpora.

Text generated by Large Language Models (LLMs) now rivals human writing, raising concerns about its misuse.However, mainstream AI-generated text detection (AGTD) methods primarily target document-level long texts and struggle to generalize effectively to sentencelevel short texts.And current sentence-level AGTD (S-AGTD) research faces two significant limitations: (1) lack of a comprehensive evaluation on complex human-AI hybrid content, where human-written text (HWT) and AI-generated text (AGT) alternate irregularly, and (2) failure to incorporate contextual information, which serves as a crucial supplementary feature for identifying the origin of the detected sentence.Therefore, in our work, we propose AutoFill-Refine, a high-quality synthesis strategy for human-AI hybrid texts, and then construct a dedicated S-AGTD benchmark dataset.Besides, we introduce SenDe-tEX, a novel framework for sentence-level AIgenerated text detection via style and context fusion.Extensive experiments demonstrate that SenDetEX significantly outperforms all baseline models in detection accuracy, while exhibiting remarkable transferability and robustness.

This special issue deals with research related to applications of and methods to support Big Data analytics in complex social information networks. The digital age and the rise of social media have sped up changes to social systems with unforeseen consequences. However, there are major challenges created.

Risk-sensitive reinforcement learning (RL) aims to optimize policies that balance the expected reward and risk. In this paper, we present a novel risk-sensitive RL framework that employs an Iterated Conditional Value-at-Risk (CVaR) objective under both linear and general function approximations, enriched by human feedback. These new formulations provide a principled way to guarantee safety in each decision making step throughout the control process. Moreover, integrating human feedback into risk-sensitive RL framework bridges the gap between algorithmic decision-making and human participation, allowing us to also guarantee safety for human-in-the-loop systems. We propose provably sample-efficient algorithms for this Iterated CVaR RL and provide rigorous theoretical analysis. Furthermore, we establish a matching lower bound to corroborate the optimality of our algorithms in a linear context.

The low enthusiasm for upstream and downstream pollution control is the main factor leading to poor water quality. Optimizing water pollution control strategies for multiple stakeholders/entities in river basins is challenging. Considering the dynamic change of water quality, we study the optimal decision of pollution control chain composed of upstream and downstream. We construct a stochastic differential game model of upstream and downstream efforts to determine the optimal pollution control strategy. The differential evolution algorithm is used to determine the quantity of virtual currencies issued, and the optimal control theory is employed to make decisions on pollution control efforts. We discuss the optimal-feedback equilibrium of watershed environmental quality for three scenarios: 1) no transaction; 2) downstream purchase currency; and 3) upstream purchase currency. As a result, introducing the “water quality–currency” market: 1) improves water quality, increases each entity’s pollution control efforts, and forms a mechanism between pollution control efforts and water quality; 2) increases entities’ welfare amid increasing volatility, enhancing their resistance to external interferences; and 3) enables the improvement of water and the increase of the entities’ profits to be realized at the same time in the downstream purchase scenario.

COVID-19 has had a significant impact on urban pick-up and delivery services, including meal delivery and online ride-hailing. In this article, we propose a decision framework for minimizing the indirect contact in pick-up and delivery services as a way to control the cost of precautionary measures, manage the risk of resurgence, and contain the spread of COVID-19. We present integer linear programming models of the order assignment and vehicle routing problems to minimize indirect contact as well as its extension with multiple objectives. We prove that the problem is NP-hard even with a fixed number of drivers, but polynomial under two special cases that are commonly seen in real-life situations. Exact methods with dominance rules and a heuristic algorithm for the dynamic problem are proposed. We conducted an extensive numerical study on real-world meal delivery data. Apart from the computational advancement of our algorithms, the experimental results also show that minimizing indirect contact does not significantly increase the transportation cost and is applicable to the vehicle routing system of service providers.

Abstract As an important sector of national economy, the industrial sector accounts for 33.4% of gross domestic product while consuming 70% of energy and causing serious air pollution in China. It is meaningful to measure the productivity of industrial sector in China with air pollution consideration. The range‐adjusted measure of the nonradial data envelopment analysis, as with natural disposability and managerial disposability, is adopted in order to measure the productivity of provincial industrial sector in China during 2011–2014. The results explain that the unified efficiency under managerial disposability is lower than the unified efficiency under natural disposability and the unified efficiency under natural and managerial disposability, which means that management improvement and technology innovation should be obtained more attention from the government. As modernization of economic restructuring, there is not a trend of unified efficiency under natural disposability. Eastern China has highest unified efficiency under managerial disposability, whereas unified efficiency under natural and managerial disposability are improving in eastern China and western China in period of 2013–2014. The results also describe that more than 20 provinces and nearly half of provinces are suitable for the industrial pollution control investment and research and development investment, respectively. On the basis of the results of the truncated regression model, we can identify the influencing factors of unified efficiency. According to above results, suggestions are proposed in order to improve the productivity.

We are living in a global service economy where services account for an increasing percentage of a country's GDP year on year. As the growth of services has also become a global phenomenon, service science and service systems engineering are attracting much-needed research attention. Modern industry urgently needs advanced products, services, and technologies, such as data analysis, problem solving and artificial intelligence, to promote service and production processes. In this special issue, original results, and achievements are presented by active researchers working on various issues and challenges related to expert systems and risk analytics in service engineering. With growing economic globalization, services are becoming a rich form of value creation. This growth in service provision has also become a global phenomenon and this has brought much-needed attention to Service Science and Service Systems Engineering (SSE) (Pineda et al., 2012). The modern service sector is in great need of advanced products, services and technologies, such as data analytics, problem solving and artificial intelligence, to promote service and production processes. The combination of technologies like big data analytics and expert systems allows the engineering of advanced service systems to become 'smart' and more efficient. Service industries such as retail, finance, media and mobile are also transforming into high-tech enterprises, and grow through advances in information technology. Hence, the characteristic of today's world economies is the widespread popularity of complex service systems. As the complexity of service systems engineering increases, effectively preempting, preventing, and combating the threats involved in service system engineering has attracted widespread attention from academia and industry. Artificial Intelligence techniques for managing engineering risk and analytics decisions is a fast-growing and promising multidisciplinary research area (Olson & Wu, 2017). Costantini et al. (2021), using modern problem solving techniques, provide a complementary approach to managing risk. Anke et al. (2020) explore the inter-organizational setups of 14 projects by interviewing experts who are involved in smart service systems engineering. Their analysis results in a conceptualisation of 13 roles that they further cluster into three main groups. Their insights are helpful for practitioners in setting up and managing inter-organizational projects for their digital service innovation initiatives. Wolff et al. () propose the concept of system-oriented service delivery that creates additional value by delivering service such that total system costs are minimized. Via the introduction of a monetary reallocation mechanism between individual participants, any individual disadvantage due to the shift towards system-oriented service delivery can fully be compensated. The purpose of this special issue is to provide indicate insights and viewpoints from scholars regarding the challenges of engineering modern service systems with expert systems in the face of uncertainty and risk. After a rigorous peer-review process, the four papers for this special issue were selected from among all the received papers by the special issue guest editors, based on the relevance to the journal and the reviews of conference versions of the papers. Luo (2018) presents a hybrid approach for credit scoring, and the classification performance of this approach is compared with four base learners in machine learning. A large credit default swap dataset covering the period from 2006 to 2016 is used to build classifiers and test their performance. The results from this empirical study indicate that the bagging ensemble method can substantially improve individual base learners such as decision tree, multilayer perceptron, and k-nearest neighbours. The performance of support vector machine does not change after applying bagging ensemble. The overall results demonstrate that k-nearest neighbours are more suitable than any other method when dealing with large unbalanced datasets in credit scoring. In Amelian et al. (2019), multi-objective optimisation of the stochastic failure-prone job-shop scheduling problem is sought wherein the job processing time appears to be controllable. It endeavours to determine the best sequence of jobs, optimal production rate, and optimum preventive maintenance period for simultaneous optimisation of three criteria of sum of earliness and tardiness, system reliability, and energy consumption. First, a new mixed integer programming model is proposed to formulate the problem. Then, by combining simulation and NSGA-II algorithms, a new algorithm is proposed for solving the problem. The computational results reveal that the proposed meta-heuristic algorithm converges into optimal or near-optimal solution. Finally, results and managerial insights for the problem are presented. Lu and Qiao (2021) deals with energy saving in the hybrid flow shop scheduling problem with batch production at the last stage, which has important application for the energy-intensive steelmaking-continuous casting (SCC) process. They first establish a mixed-integer programming model to reduce extra energy consumption and then adopt a genetic algorithm to solve the scheduling problem. Based on a traditional genetic algorithm (TGA), the calculation of the fitness function, as well as adaptive crossover and mutation, are designed. Due to the complexity of the problem in this article, they then propose an efficient adaptive genetic algorithm (EAGA) to improve the searchability of TGA. The EAGA has new features including layered strategies and enhanced adaptive adjustment methods. The results illustrate that scheduling with their model can greatly reduce extra energy consumption. Meanwhile, the proposed EAGA is very efficient in comparison. Finally, Liu and Huang (2019) choose one driving force for social development, high-tech industries, as an example to illustrate a new method, the virtual frontier DEA model, an improvement over the traditional DEA model. Additionally, they decompose the Malmquist productivity index with the virtual frontier DEA model to find out the drivers of high-tech efficiency change. We would like to extend our thanks and appreciation to all authors who submitted their research to this special issue and to the peer reviewers that freely gave their time to support it. We hope you will enjoy reading this selection of papers, as did we. This work was supported in part by the Ministry of Science and Technology of China under Grant no. 2020AAA0108400 and Grant no. 2020AAA0108402, in part by the Chinese Academy of Sciences Frontier Scientific Research Key Project under Grant no. QYZDB-SSW-SYS021, and supported by the International Partnership Program of Chinese Academy of Sciences, Grant no. 211211KYSB20180042 and the Strategic Priority Research Program of CAS under Grant no. XDA2302020.

Gastroscopy is a widely adopted method for locating gastric lesions and performing the early screening and diagnosis of gastric cancer (GC). However, the effectiveness of traditional GC screening methods depends on the medical skills of the gastroscopy specialist. A lack of knowledge and experience may lead to misdiagnosis and mistreatment, especially in small-scale hospitals. Recently, there has been a significant increase in studies on data-driven computer-aided diagnosis techniques. In this article, we propose a novel intelligent decision-making method for GC screening (ID-GCS), a multimodal semantic fusion-based data-driven decision-making system. ID-GCS exploits a hybrid attention mechanism to extract textual semantics from multimodal gastroscopy reports and performs semantic fusion to integrate the semantics of textual gastroscopy reports and images, resulting in improved interpretability of gastroscopy findings. We evaluated ID-GCS using a real gastroscopy report dataset, and experimental results show that compared with state-of-the-art methods, ID-GCS achieves better sensitivity and accuracy in GC screening.

With the rampaging of Coronavirus disease 2019 (COVID-19) across the world, analyzing the dynamic characteristics and understanding the evolutionary patterns of clusters are becoming even more crucial for people and policymakers to make timely responses for avoiding injury caused by COVID-19. To solve the scarcity of the fine-grained spatiotemporal data, we construct a novel dataset about the spread of patients during the resurgent period of the COVID-19 epidemic at the Xinfadi Market in Beijing. Leveraging our self-build dataset, we analyze the evolutionary characteristics of the cluster of COVID-19 under anti-contagion policies and obtained some remarkable evolution patterns. These findings can provide significant insights for policymakers and researchers to understand the evolutionary characteristics regarding the cluster of COVID-19 and deploy effective anti-contagion policies.

This paper investigates the debt clearing problem in a debt network with complicated debt relations among various debtors. Each pair of debt relations is modeled with both forward debt chain and backward debt chain to simplify the whole debt network with a developed algorithm. A debt clearing strategy is derived and its benefits and managerial implications are shown in risk management. This paper further demonstrates the validation of the approach for sovereign debt analysis and risk analytics using real debt data from ten developed countries.

Decision-making is a major element in running an organization. Most decisions are made under pressure of time, without the opportunity for humans to thoroughly analyze problems. Unaided decision-making is oftenad-hoc, relying upon managerial experience and judgment. Operational research models provide a more complete analysis that hopefully lead to more reliable decisions. Individual decision makers may rely on staffs to aid them. Collecting individuals into groups may result in safer decision-making, albeit at the cost of time. Computers have provided an additional level of support in the form of automation, much faster than humans, although less resilient. Artificial intelligence research continues to expand the ability of computers to perform well in decision-making environments.Table Iprovides a comparison of our view of decision-making levels.

We propose an innovative and forward-looking method to examine investor herd behavior and identify fundamental-driven spurious herding. A sentence-based sentiment analysis approach is conceived to automatically extract attitudes or emotions from textual documents. Then we build a mathematical model to discern herd behavior by exploiting the sentiment indices. Empirical tests in the Chinese stock market indicate that there exists significant true herd behavior among blue-chips. Investors with pessimistic sentiment are more likely to herd than those with optimistic sentiment. Moreover, macroeconomic information tends to play a dominant role in the decision-making processes, and the lack of rapid and efficient firm-specific information enables people to herd around the market consensus.

Blockchain, as an emerging decentralized architecture and distributed computing paradigm underlying Bitcoin and other cryptocurrencies, has attracted intensive attention in both research and applications recently. Blockchain, especially powered by chain-coded smart contracts, has the full potential of revolutionizing increasingly centralized cyber-physical-social systems (CPSSs) for constructions and applications, and reshaping traditional knowledge automation workflows. The key advantage of blockchain technology lies in the fact that it can enable the establishment of secured, trusted, and decentralized autonomous ecosystems for various scenarios, especially for better usage of the legacy devices, infrastructure, and resources.

Large, sudden influxes of individuals represent critical resource stressors to the food, energy, and water (FEW) systems that provide critical services to the region in which they serve. This paper describes progress in identification and monitoring of emergent and future conditions for FEW interdependent infrastructures of coastal cities. The approach seeks to identify combinations of conditions that are most and least disruptive to investments, assets, policies, locations, organizations, etc. The philosophy and methods build on the latest Systems Engineering Body of Knowledge of IEEE, INCOSE, et al. The effort should be of interest to systems engineers, researchers, and policy makers regarding principles, methods, and factors to consider to enhance FEW system resilience, reduce the impacts of population dislocation, and otherwise explore science and technology innovations for FEW infrastructures.

Risks exist in every aspect of our lives, and can mean different things to different people, while negatively in general they always cause a great deal of potential damage and inconvenience for the enterprise stakeholders. Investigation of risk analytics tools in today’s big data era is beneficial to both practitioners and academic researchers from industrial systems. The current special issue provides some view of how risk-based business intelligence can be applied to industrial systems faced with big data issues.

This paper investigates the pricing strategy of firms in the context of uncertain demand. In particular, there are two factors that affect demand dynamics, the influence of reference prices and the price of the competition. In the monopoly case, pricing policy is affected by reference-price effects and in the duopoly case, both competitive pricing and reference-price effects are present. In each case, the optimal price paths are derived and simulated. The implications of uncertainty are analyzed by comparing the deterministic policy with the stochastic policy. The random variations in price paths are investigated to provide a risk analysis for firms that work in such market conditions. With the advent of the big data era, information about consumers and competitors gives firms a greater control over uncertainty than ever before. Simulations will demonstrate that firms can lower the volatility of their price path if they gather and process this information. Furthermore, the feedback forms of the optimal price path are derived in both the absence and the presence of both competition and reference-price effects. In general, the impact that demand uncertainty has over the firm's pricing strategy is determined by a combination of the firm's discount rate, demand uncertainty, and demand-side/cost-side dynamics.

The financing of supply chains involves decisions by supply chain members as well as by lending institutions. The optimality of lending decisions in this environment depends on the loss aversion on the part of supply chain members as well as the availability of capital. The purpose of this paper is to understand the impact of capital constraint and loss aversion on operational decisions in supply chains. Traditional models have the bank external to the supply chain, with the bank's interest rate exogenous. This research concerns a capital-constrained supply chain with the manufacturer selling to a loss averse newsvendor-like retailer, and a bank financing both the manufacturer and the retailer. The existence of supply chain finance equilibrium is proven by the use of Stackelberg game analysis. The best pricing and ordering decisions of both manufacturer and retailer are determined, and results demonstrate how these key decisions are influenced by their initial capital and the bank's financial decisions. For instance, the optimal order quantity increases or decreases with initial capital, and it is interesting that bankruptcy protection encourages a cash-constrained retailer to adopt an aggressive ordering strategy. Moreover, it is shown that the retailer's loss aversion has a significant impact on the capital constraint problem. With an increase in loss aversion, the required initial working capital decreases. Loss aversion can even change the retailer's situation from one of capital constraint to one of capital sufficiency. An extension with double orders is given for comparison. Numerical examples are given to demonstrate the impact of initial capital and loss aversion on the optimal decisions and some other managerial insights are discussed.

This paper studies the newsvendor problem in the presence of consumer behavior, specifically, social interaction. We show that deterministic consumer valuation on products derived from social interaction can be an advantage for firms. This paper examines the implications of random consumer product valuation and a lower threshold number of subscribers to the proposed deal. Several implications have been yielded.

Fuzziness is inherent in decision data and decision making process. In this paper, interval-valued intuitionistic fuzzy set is used to capture fuzziness in multi-criteria decision making problems. The purpose of this paper is to develop a new method for solving multi-criteria decision making problem in interval-valued intuitionistic fuzzy environments. First, we introduce and discuss the concept of interval-valued intuitionistic fuzzy point operators. Using the interval-valued intuitionistic fuzzy point operators, we can reduce the degree of uncertainty of the elements in a universe corresponding to an interval-valued intuitionistic fuzzy set. Then, we define an evaluation function for the decision-making problem to measure the degrees to which alternatives satisfy and do not satisfy the decision-maker's requirement. Furthermore, a series of new score functions are defined for multi-criteria decision making problem based on the interval-valued intuitionistic fuzzy point operators and the evaluation function and their effectiveness and advantage are illustrated by examples.

The outputs of upstream individual processes (members) become the inputs of downstream members in supply chains. When multiple inputs and outputs are present, data envelopment analysis has been widely applied to assess efficiency. In cooperative groups, such as supply chains, a maximin decision approach can reflect not only overall system efficiency, but also efficiency of system elements. This paper discusses a maximin efficiency multistage supply chain model capable of measuring supply chain members performance as well as overall supply chain performance.

Financial disasters in private firms led to increased emphasis on various forms of risk management, to include market risk management, operational risk management, and credit risk management. Financial institutions are motivated by the need to meet increased regulatory requirements for risk measurement and capital reserves. This paper describes and demonstrates a model to support risk management of accounts receivable. We present a decision support model for a large bank enabling assessment of risk of default on the part of loan recipients. A credit scoring model is presented to assess account creditworthiness. Alternative methods of risk measurement for fault detection are compared, and a logistic regression model selected to analyze accounts receivable risk. Accuracy results of this model are presented, enabling accounts receivable managers to confidently apply statistical analysis through data mining to manage their risk.

The Internet provides the opportunity for investors to post online opinions that they share with fellow investors. Sentiment analysis of online opinion posts can facilitate both investors' investment decision making and stock companies' risk perception. This paper develops a novel sentiment ontology to conduct context-sensitive sentiment analysis of online opinion posts in stock markets. The methodology integrates popular sentiment analysis into machine learning approaches based on support vector machine and generalized autoregressive conditional heteroskedasticity modeling. A typical financial website called Sina Finance has been selected as an experimental platform where a corpus of financial review data was collected. Empirical results suggest solid correlations between stock price volatility trends and stock forum sentiment. Computational results show that the statistical machine learning approach has a higher classification accuracy than that of the semantic approach. Results also imply that investor sentiment has a particularly strong effect for value stocks relative to growth stocks.

Ordinal regression has wide applications in many domains where the human evaluation plays a major role. Most current ordinal regression methods are based on Support Vector Machines (SVM) and suffer from the problems of ignoring the global information of the data and the high computational complexity. Linear Discriminant Analysis (LDA) and its kernel version, Kernel Discriminant Analysis (KDA), take into consideration the global information of the data together with the distribution of the classes for classification, but they have not been utilized for ordinal regression yet. In this paper, we propose a novel regression method by extending the Kernel Discriminant Learning using a rank constraint. The proposed algorithm is very efficient since the computational complexity is significantly lower than other ordinal regression methods. We demonstrate experimentally that the proposed method is capable of preserving the rank of data classes in a projected data space. In comparison to other benchmark ordinal regression methods, the proposed method is competitive in accuracy.