Search

A machine learning technique provides rapid access to various information models, approaches, complex systems, and algorithms. In the present scenario the artificial neural network, multiple linear regression, support vector machine, water cycle algorithm, and linear regression have much accessible. Continuously advancements of these techniques become a high impact on civil engineering, especially for the construction and infrastructure sector. In the present study, the historical perspective of research and development and application of machine learning techniques on fly ash-based concrete is presented. The models, algorithms, and approaches developed for predicting engineering properties of fly ash-based concrete were also discussed. These predictions using machine learning techniques have been much impacted on fly ash utilization in concrete. The utilization of fly ash in concrete also has revolutionary impacts on the environment and human health in the future. Machine learning is a useful and powerful technique that can predict concrete engineering properties and represent the scientific challenge in the construction and infrastructure sectors.

Systems integration is a central element of the complex systems development effort. The integration readiness levels (IRL) scale complements technology readiness levels (TRL) to assess the system development maturity, representing risk levels for integrating technologies in a system. The increasing complexity of systems, due to multiple interfaces and an information-centric architecture, demands new systemic approaches to analyze the architecture and communicate IRL assessments. Therefore, this article developed a methodology to apply IRL using architecture views through the design structure matrix and domain mapping matrix. A case study analyzed technology introduction impacts and different integration strategies for space systems from China–Brazil Earth Resources Satellite program at the system and system-of-systems levels. Through the design science method, results show the pragmatic evaluation and validation for the proposed method and for the IRL scale itself, by professionals of the case study projects. The research draws suggestions for holistic system analysis and managerial communication applications using the proposed method and suggests a rationale for IRL assessment of legacy systems.

Computational experiments are an important method for carrying out the quantitative analysis of complex systems and play a major role in mapping the real world to the virtual world. However, the flexibility of computational experiments leads to arbitrary modeling processes and unconvincing results, which greatly hinder the large-scale application of this method. In this context, the verification of computational models has become an urgent problem in this field. Currently, model evaluation is still in its infancy and the existing evaluation methods are not mature enough. Thus, we took epidemic models as the research object and proposed a capability maturity evaluation framework for computational models of artificial society. The framework differs from previous assessment methods that focus on the validity of results, but instead provides a comprehensive evaluation from two perspectives: 1) evaluation of the model itself--by comparing the expectation with the final implementation, we can obtain whether the model meets the expectation and 2) comparison between different models--by evaluating the implementation process of each model and comparing the results, we can identify more mature models. The implementation of the model is evaluated from input, process, and output. Further, specific analyses and evaluations are conducted for several representative COVID-19 models to verify the validity of this evaluation framework. The results of the case study show that the proposed evaluation framework can help decision-makers identify more mature and referential models, and point out the directions where modelers can improve their models. IEEE

It is indispensable for professional traffic signal engineers to perform manual operations of traffic signal control (TSC) to mitigate traffic congestion, especially with complicated scenarios. However, such a task is time-consuming, and the level of congestion mitigation heavily relies on individual expertise in engineering practice. Therefore, it is cost-effective to learn traffic engineers' knowledge to enhance the problem-solving skills for a large-scale urban traffic network. In this paper, a data augmented deep behavioral cloning (DADBC) method is proposed to imitate the problem-solving skills of traffic engineers. The method is under a conceptual framework, parallel learning (PL) framework, that incorporates machine learning techniques for solving decision-making problems in complex systems. The DADBC method enhances a hybrid demonstration by exploiting a generative adversarial network (GAN) and then uses the deep behavioral cloning (DBC) model to learn traffic engineers' control schemes. According to the validation results using the real manipulation data from Hangzhou, China, our method can imitate complex human behaviors in intervening traffic signal control operations to improve traffic efficiency in urban areas.

The revolution of Industry 4.0 and Internet of Things facilitate large and cheap data acquisition from complex systems. However, the online processing and analytics of such multi-stream data still suffer difficulties. The key reason is that data from different sensors (multi-stream data) contain nonlinear within-and-cross sensor correlations, which poses challenges in the modeling and analysis of such data, especially for the online scenarios. To jointly model multi-stream data, multi-output Gaussian Process (MGP) has become popular and achieved great success. However, existing methods assume different outputs are linearly correlated, which significantly limits their applications. In this paper, we propose a nonlinear online MGP framework to simultaneously realize nonlinear correlation modeling and online processing of multi-stream data. Specifically, a tailored co-variance structure is developed based on the convolution process, which can capture nonlinear self-and-cross correlations. To realize online processing, Bayesian analysis and marginalized particle filter are applied to estimate function values and model parameters. Comparing to existing methods, the proposed method features superiorities in i) the non-linear characterization of self-and-cross correlations, and ii) the efficient modeling and prediction capability. These features make the proposed method especially appropriate for industrial informatics with complex relationship and large-scale data sets. The proposed method is validated with simulation studies and a real-case study of biophysical signals.

State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences

Highly automated driving (HAD) vehicles are complex systems operating in an open context. Complexity of these systems as well as limitations and insufficiencies in sensing and understanding the open context may result in unsafe and uncertain behavior. The safety critical nature of the HAD vehicles demands to model limitations, insufficiencies and triggering conditions to argue safe behavior. Standardization activities such as ISO/PAS 21448 provide guidelines on the safety of the intended functionality (SOTIF) and focus on the performance limitations and triggering conditions. Although, SOTIF provides a non-exhaustive list of scenario factors that may serve as a starting point to identify and analyze performance limitations and triggering conditions, yet no concrete methodology is provided to model these factors. We propose a novel methodology to model triggering conditions and performance limitations in a scene to assess SOTIF. We utilize Bayesian network (BN) in this regard. The experts provide the BN structure and conditional belief tables are learned using the maximum likelihood estimator. We provide performance limitation maps (PLMs) and conditional performance limitation maps (CPLMs), given a scene. As a case study, we provide PLMs and CPLMs of LIDAR in a defined scene using real world data.

Today organizations increasingly rely on working teams to compete in complex and turbulent environments since they exhibit high resilience, the ability to change, and secure desirable conditions after disruptions occurred. Improving team resilience is thus becoming a critical question and understanding its determinants a mandatory issue in literature. In this article, we contribute to this topic by investigating whether and how the pattern of social interactions among team members influences team resilience. To this aim, we conceptualize the team as a complex network solving a combinatorial decision-making task on complex and turbulent environments. We model the process of decision-making by means of a continuous-time Markov chain, whereby the decision flip is governed by the combination of two forces, consensus-seeking and search for high-performing solutions. Two alternative patterns of the social network are compared, respectively, the random and scale-free, and their effect on team resilience simulated. The results show that teams, where social interactions are randomly and evenly distributed outperform teams with a scale-free-like pattern, in any condition of turbulence and complexity. However, when complexity is high and environmental turbulence is low, the superiority of random pattern is more pronounced. Theoretical and managerial implications of these findings are finally discussed.

This paper addresses the cyber resilience issues of multi-vector energy distribution systems (MEDS) caused by false data injection FDI, considering the uncertainty from renewable resources. A novel two-stage distributionally robust optimization (DRO) is proposed to realize the day-ahead and real-time resilience improvement. The first stage determines an initial plan for day-ahead reserve preparation and the second stage makes adjustment and takes resilience-based actions after potential load redistribution (LR) attacks and renewable output deviation. The ambiguity set is based on both the Wasserstein distance and moment information. Compared to robust optimization which considers the worst case, DRO yields less-conservative solutions and thus provides more economic operation schemes. The Wasserstein-metric based ambiguity set enables to provide additional flexibility hedging against renewable uncertainty. Case studies are demonstrated on two representative MEDS networked with energy hubs, i.e., a 33-bus-20-node MEDS and a 69-bus-20-node-MEDS, illustrating the effectiveness of the proposed cyber-secured model.

Most incidents in complex systems such as process plants are not-chance events and weak signals emerge for a long time before incidents occur. It is necessary to identify and respond to the weak signals as early as possible for preventing incidents. However, in the era of Industry 4.0, recognizing weak signals from the abundance of data is challenging. Since the terminology “weak signal” was not precisely defined, the study first proposed a formal definition of “weak signal” and discussed its characteristics. Additionally, a framework was developed to address the challenges of observing, evaluating, and responding to weak signals in complex systems. The framework first utilized Function Resonance Analysis Method (FRAM) to determine the information to be collected for observing weak signals. Then, the relevance of weak signals and the corresponding responses were evaluated by utilizing Balanced Random Forest (BRF), Weighted Random Forest (WRF) and Decision Tree (DT) classification models. The case study of a hypothetical batch process showed great potentials for applying the framework in real operations. Based on the potential weak signals that were indicated by FRAM, probabilities of temperature deviations in the process were predicted with high accuracy by the optimal BRF model. Underlying weak signals and the corresponding responses to reduce the probabilities were identified from the DT.

Software-Defined Networking (SDN) is a modern paradigm that provides a platform for implementing reliable, centrally managed, and automated security solutions for conventional and new generation networks, such as IoT, cloud computing, 5G/6G mobile communication networks, and vehicular communications. In these complex systems, manual security operations can delay or obstruct the identification, mitigation, and prevention of ever-increasing sophisticated threats. Thus, the idea of security automation for networks using the SDN paradigm has become fundamental, given that SDN was created to facilitate the operation and management of complex networks with minimal human intervention, which is considered error-prone. This survey studies the state-of-the-art research efforts concerned with security automation in SDN environments. We identified and ranked various classes of security solutions with different levels of automation and complexity. The level of automation is measured using four well-defined qualitative parameters: self-healing, self-adaptation, self-configuration, and self-optimization. The complexity is characterized by the amount of processing and storage resources and implementation requirements. This work represents the first endeavor to analyze the level of automation and complexity of security solutions in SDN environments. Our findings reveal important advances in the area of security automation in SDN. However, there are still several open problems and challenges, which we detail in this work.

Product innovation can result from the novel design and combination of product components as well as from changing the underlying architecture: that is, the way components interact with each other. Even though previous studies have shown that architectural change can constitute a powerful source of innovation, little insight exists on how organizations should engage in architectural search itself. In this paper, using computer simulation, we explore underlying mechanisms of architectural search. We find that contrary to search for component combinations, architectural search provides greater performance improvements the narrower the search scope, regardless of product complexity. Moreover, our theory and findings suggest a more differentiated typology of architectural innovation. Although narrow architectural search often leads to pure architectural innovations that do not require substantial component changes, broader architectural search often leads to composite architectural innovation (i.e., architectural innovations that typically render existing component designs suboptimal but allow for new high-performing component combinations to arise). Lastly, although narrow architectural search outperforms broad architectural search in the long run, in the short run broad architectural search can have performance advantages.

The conception and treatment of complex classifications or typologies (as hierarchical tables), mainly of nature components, has for long constituted a major concern for researchers. Hence, several codification methods were developed in order to address and facilitate the management of such tables. Most of these methods uses alphanumeric codes, that remain specific to each case (type of entity), in the sense that their transposition to other cases is rarely feasible. This article proposes a new standardized codification method, applicable to various hierarchical schemas. Implemented in the development of a complex system of biodiversity data management, this method consists in creating for each table a fixed number of levels, coded using the same type of strings, based on ’numeric characters’. This method makes it possible to manage different tables with the same module and facilitates the automatic incrementation and updating of the code (=position). The new model has the advantage of offering possibilities to generate, update or delete a code, without disrupting the codes of the other elements, in addition to the gain in response time of the requests. It gives hope that in some cases (as geo-databases) to merge different tables whose merger was not previously obvious.

Industrial processes are becoming increasingly large and complex, thus introducing potential safety risks and requiring an effective approach to maintain safe production. Intelligent process monitoring is critical to prevent losses and avoid casualties in modern industry. As the digitalization of process industry deepens, data-driven methods offer an exciting avenue to address the demands for monitoring complex systems. Nevertheless, many of these methods still suffer from low accuracy and slow response. Besides, most black-box models based on deep learning can only predict the existence of faults, but cannot provide further interpretable analysis, which greatly confines their usage in decision-critical scenarios. In this paper, we propose a novel orthogonal self-attentive variational autoencoder (OSAVA) model for process monitoring, consisting of two components, orthogonal attention (OA) and variational self-attentive autoencoder (VSAE). Specifically, OA is utilized to extract the correlations between different variables and the temporal dependency among different timesteps; VSAE is trained to detect faults through a reconstruction-based method, which employs self-attention mechanisms to comprehensively consider information from all timesteps and enhance detection performance. By jointly leveraging these two models, the OSAVA model can effectively perform fault detection and identification tasks simultaneously and deliver interpretable results. Finally, extensive evaluation on the Tennessee Eastman process (TEP) demonstrates that the proposed OSAVA-based fault detection and identification method shows promising fault detection rate as well as low detection delay and can provide interpretable identification of the abnormal variables, compared with representative statistical methods and state-of-the-art deep learning methods.

In dynamic analysis of complex systems usually simplified models are used. In case of floor vibration, an SDOF model is used to calculate the acceleration of the structure, in the seismic design of structures lumped parameter models are recommended to include the effect of the soil-structure interaction (SSI) in the analysis. Nonetheless, for rib stiffened floors, and for finite depth soil layers under the structure these models can be very inaccurate. In these cases (infinitely) long constrained bars (or beams) are recommended as simplified models. In this article an infinitely long, axially constrained bar connected parallelly to a mass-spring system is analysed. An analytical solution is derived, and the impedance functions are determined, which are significantly different from those of simple lumped parameter models. It is shown that this simple model, which depends only on three parameters, is an excellent tool for determining the response of structures excited by horizontal harmonic or earthquake loads, where SSI plays an important role.

In recent years, because the complex system discrete model has brought good results in the application of many research directions such as human management analysis, control system prediction, and animal group prediction, how to combine the complex system discrete model with the prediction of enterprise brand communication effect has become a current research hotspot. Based on this, this paper studies the application of the discrete model based on the complex system in sports club to enterprise brand communication and designs a model of the impact of professional sports club on enterprise brand communication based on the SIR model and PSO algorithm. Firstly, this paper analyzes the research status of the impact on enterprise brand communication at home and abroad and optimizes and improves the impact of professional sports clubs on enterprise brand communication and the shortcomings of big data analysis technology in the current research. The complex system discrete model can accurately analyze the enterprise brand communication and conduct big data mining analysis with known professional sports clubs to achieve accurate calculation. The results show that in the process of analyzing the impact of professional sports clubs and enterprise brand communication, the communication mode design of professional sports clubs based on SIR-PSO algorithm can not only effectively deal with various complex discrete data evaluated by club users but also analyze and evaluate the impact of professional sports clubs on enterprise brand communication.

The optimal scale selection is the key problem in the study of multi-scale decision information systems. Dynamic change is one of the main features of big data, and the amount of information will often increase sharply with the passing of time. As is well known, the issue of updating the optimal scale of a multi-scale decision information system has been becoming a challenging problem in recent years, and it indeed has important theoretical and practical research values. Note that adding multiple objects can be viewed as adding one object multiple times. So, it just needs to clarify the change laws of optimal scale under the case of adding one object. Although the existing work has considered this problem in terms of the sufficient condition of updating the optimal scale, the results seem to be inaccurate. In other words, both sufficient and necessary conditions are still missing. In this paper, using sequential three-way decisions, the sufficient and necessary conditions of updating the optimal scale of a multi-scale decision information system are developed for the addition of an object, which makes the theoretical study on updating the optimal scale more complete.

With the rapid development of the Internet, the amount of data increases sharply. In this network age, data have been generated, such as multimedia, social networks, and search records. Due to the generation of data, complex system discrete model technology is also widely used in all walks of life. Multimedia learning is a popular teaching mode in the world. Through the discrete model technology of the complex system, this paper deeply studies the impact of multimedia input on college students’ English ability. Because the modeling and sampling of complex systems are abstract and not fixed, approximation and control methods are adopted in discrete time, which greatly improves the reliability of the final research results. Compared with the original discrete modeling technology, this paper adds data sampling compression and assimilation technology on the basis of the original discrete modeling technology of the complex system. The results show that, by adding the technical application of controllable and observable systems, the discrete model of the whole complex system can reduce the error of the final output data. At the same time, this paper compresses and simplifies the data nodes at the microlevel. Macroscopically, it reduces the scale, especially the number of node data compression. The final result also realizes the data scale and greatly shortens the calculation time. This study has greatly improved the accuracy of the impact of multimedia on Chinese college students’ English ability in practical application.

Machine Learning (ML) has gained much importance in recent years as many of its effective applications are involved in different fields, healthcare, banking, trading, gaming, etc. Similarly, Combinatorial Optimisation (CO) keeps challenging researchers by new problems with more complex constraints. Merging both fields opens new horizons for development in many areas. This study investigates how effective is to solve CO problems by ML methods. The work considers the Multidimensional Knapsack Problem (MKP) as a study case, which is an np-hard CO problem well-known for its multiple applications. The proposed approach suggests to use solutions of small-size MKP to build models with different ML methods; then, to apply the obtained models on large-size MKP to predict their solutions. The features consist of scores calculated based on information about items while the labels consist of decision variables of optimal solutions calculated from applying CPLEX Solver on small-size MKP. Supervised ML methods build models that help to predict structures of large-size MKP solutions and build them accordingly. A comparison of five ML methods is conducted on standard data set. The experiments showed that the tested methods were able to reach encouraging results. In addition, the study proposes a Genetic Algorithm (GA) that exploits ML outputs essentially in initialisation operator and to repair unfeasible solutions. The algorithm denoted GaPR explores the ML solution neighbourhood as a way of intensification to approach optimal solutions. The carried out experiments indicated that the approach was effective and competitive.

Unconstrained face alignment is still a challenging problem due to the large poses, partial occlusions and complicated illuminations. To address these issues, in this paper, we propose a mixed attention hourglass network (MAttHG) to learn more discriminative representations by modeling the correlated relationships between features. Specifically, by integrating the attention module from features of different levels in the stacked hourglass networks, MAttHG can capture rich contextual correlations, which can be further used to combine local features to better model the spatial position relationship of facial landmarks. Furthermore, by combining the hourglass network and the attention module, MAttHG can effectively model the global attention and local attention to enhance the facial shape constraints for robust face alignment. Moreover, a head pose prediction module is designed to adaptively adjust the weight of each sample in the training set and redefine the loss function for addressing the problem of data imbalance. Experimental results on challenging benchmark datasets demonstrate the superiority of our MAttHG over state-of-the-art face alignment methods.

Achieving community immunity against the coronavirus disease 2019 (COVID-19) depends on vaccinating the largest number of people within a specific period while taking all precautionary measures. To address this problem, this paper presents a smart parking system that will help the health crisis management committee to vaccinate the largest number of people with the minimum period of time while ensuring that all precautionary measures are followed, through a set of algorithms. These algorithms seek to ensure a uniform distribution of persons in parking. This paper proposes a novel complex system for smart parking and nine algorithms to address the NP-hard problem. The experimental results demonstrate the performance of the proposed algorithms in terms of gap and time. Applying these algorithms to smart cities to ensure precautionary measures against COVID-19 can help fight against this pandemic.

A hidden Markov model (HMM) comprises a state with Markovian dynamics that can only be observed via noisy sensors. This paper considers three problems connected to HMMs, namely, inverse filtering, belief estimation from actions, and privacy enforcement in such a context. First, the authors discuss how HMM parameters and sensor measurements can be reconstructed from posterior distributions of an HMM filter. Next, the authors consider a rational decision-maker that forms a private belief (posterior distribution) on the state of the world by filtering private information. The authors show how to estimate such posterior distributions from observed optimal actions taken by the agent. In the setting of adversarial systems, the authors finally show how the decision-maker can protect its private belief by confusing the adversary using slightly sub-optimal actions. Applications range from financial portfolio investments to life science decision systems.

Networks are an adequate representation for modeling and analyzing a great variety of complex systems. However, understanding networks with millions of nodes and billions of connections can be pretty challenging due to memory and time constraints. Therefore, selecting the relevant nodes and edges of these large-scale networks while preserving their core information is a major issue. In most cases, the so-called backbone extraction methods are based either on coarse-graining or filtering approaches. Coarse-graining techniques reduce the network size by gathering similar nodes into super-nodes, while filter-based methods eliminate nodes or edges according to a statistical property.In this work, a filter-based method is proposed and investigated. It uses the overlapping community structure to build the backbone in weighted networks. While most filtering techniques rely on link features to extract the backbone, the proposed method exploits both nodes and links. It takes advantage of the network communities through their main features (overlapping nodes, hubs, and bridging connections) to select influential edges and nodes while preserving the ability of the information dissemination of the original network. The so-called “Modular filtering backbone” combines two components. The first one is the network connecting the overlapping nodes and the top connected nodes (also called the hubs).One discards the edges with the lowest weights as long as connected components are maintained. The second component uses the network of the inter-community links with the nodes at their extremities. The disparity filter algorithm allows preserving only its most crucial connections. An extensive investigation is performed on a set of real-world weighted networks of various sizes and a wide range of origin. Results show the advantage of the proposed method over alternative filtering-based methods used for comparative purposes. Furthermore, this sheds new light on the most relevant parts of empirical networks hidden by their complexity.

In the scientific community, discussions about emergence are motivated by a need to understand the process by which complex systems exhibit novel characteristics that cannot be reduced to those of their parts. The whole is thus said to be greater than the sum of the parts. We borrow from this framework in order to explore a different understanding of communication. Instead of seeing the whole as the result of a communication process between the parts, we take a step back and propose to understand communication as the process through which both parts and whole emerge. This perspective opens the possibility to think of a communication that is not the result of an exchange between pre-existing individual agents, but the very process by which individuals emerge in the first place. From the perspective of social sciences in general, and of communication studies in particular, this theoretical experimentation points towards a model that is not subordinated to the traditional opposition between parts and wholes, individuals and collectives.

The Internet-of-Things (IoT) triggers data protection questions and new types of cyber risks. Cyber risk regulations for the IoT, however, are still in their infancy. This is concerning, because companies integrating IoT devices and services need to perform a self-assessment of its IoT cyber security posture. At present, there are no self-assessment methods for quantifying IoT cyber risk posture. It is considered that IoT represent a complex system with too many uncontrollable risk states for quantitative risk assessment. To enable quantitative risk assessment of uncontrollable risk states in complex and coupled IoT systems, a new epistemological equation is designed and tested though comparative and empirical analysis. The comparative analysis is conducted on national digital strategies, followed by an empirical analysis of cyber risk assessment approaches. The results from the analysis present the current and a target state for IoT systems, followed by a transformation roadmap, describing how IoT systems can achieve the target state with a new epistemological analysis model. The new epistemological analysis approach enables the assessment of uncontrollable risk states in complex IoT systems—which begin to resemble artificial intelligence—and can be used for a quantitative self-assessment of IoT cyber risk posture.

Agent-based models provide a promising new tool in macroeconomic research. Questions have been raised, however, regarding the validity of such models. A methodology of macroeconomic agent-based model (MABM) validation, that provides a deeper understanding of validation practices, is required. This paper takes steps towards such a methodology by connecting three elements. First, is a foundation of model validation in general. Second is a classification of models dependent on how the model is validated. An important distinction in this classification is the difference between mechanism and target validation. Third, is a framework that revolves around the relationship between the structure of models of complex systems with emergent properties and validation in practice. Important in this framework is to consider MABMs as modelling multiple non-trivial levels. Connecting these three elements provides us with a methodology of the validation of MABMs and allows us to come to the following conclusions regarding MABM validation. First, in MABMs, mechanisms at a lower level are distinct from, but provide input to higher levels of mechanisms. Since mechanisms at different levels are validated in different ways we can come to a specific characterization of MABMs within the model classification framework. Second, because the mechanisms of MABMs are validated in a direct way at the level of the agent, MABMs can be seen as a move towards a more realist approach to modelling compared to DSGE.

Dispersal and foodweb dynamics have long been studied in separate models. However, over the past decades, it has become abundantly clear that there are intricate interactions between local dynamics and spatial patterns. Trophic meta-communities, i.e. meta-foodwebs, are very complex systems that exhibit complex and often counterintuitive dynamics. Over the past decade, a broad range of modelling approaches have been used to study these systems. In this paper, we review these approaches and the insights that they have revealed. We focus particularly on recent papers that study trophic interactions in spatially extensive settings and highlight the common themes that emerged in different models. There is overwhelming evidence that dispersal (and particularly intermediate levels of dispersal) benefits the maintenance of biodiversity in several different ways. Moreover, some insights have been gained into the effect of different habitat topologies, but these results also show that the exact relationships are much more complex than previously thought, highlighting the need for further research in this area.This article is part of the theme issue ‘Integrative research perspectives on marine conservation’.

Custom-built microscopes often require control of multiple hardware devices and precise hardware coordination. It is also desirable to have a solution that is scalable to complex systems and that is translatable between components from different manufacturers. Here we report Python-Microscope, a free and open-source Python library for high-performance control of arbitrarily complex and scalable custom microscope systems. Python-Microscope offers simple to use Python-based tools, abstracting differences between physical devices by providing a defined interface for different device types. Concrete implementations are provided for a range of specific hardware, and a framework exists for further expansion. Python-Microscope supports the distribution of devices over multiple computers while maintaining synchronisation via highly precise hardware triggers. We discuss the architectural features of Python-Microscope that overcome the performance problems often raised against Python and demonstrate the different use cases that drove its design: integration with user-facing projects, namely the Microscope-Cockpit project; control of complex microscopes at high speed while using the Python programming language; and use as a microscope simulation tool for software development., Summary: An open-source Python library for accessing a range of hardware devices used in microscopy.

The purpose of the work is to study the complex essence of higher education as an integral part of the anthroposphere (technosphere); to define the main fundamental tasks of innovative academic (university) entrepreneurship; to study the main types of innovations initiated by academic capitalism in the higher education system, which can lead to innovative changes and its classification; to determine the main objects of innovation activity in the field of higher education and science and expedient directions of further innovative development of higher education in Ukraine; to study the types of innovations in the higher education system. Innovative transformations in the sphere of higher education and science are considered by the authors as objectively conditioned transformational changes caused by the environment of academic capitalism. The core of the study is academic or university entrepreneurship based on the market relations spread by academic capitalism in the sphere of scientific and educational activities of universities, research institutes and other institutions and organizations of this field. An important basis of scientific work is the application to national conditions of the Triple helix model of innovation of N. Etzkowitz on the innovative development of society. Scientific novelty consists of the following: the world experience of innovative transformations in the sphere of higher education and science occurring under conditions of academic capitalism is studied; theoretical data for new approaches in understanding of innovative transformations in the sphere of higher education and science which are economic categories and occur under market laws are formulated and offered; new approaches for further innovative reformation of higher education and science under conditions of academic capitalism are offered. A new scientific term of “innovatics of higher education” has been put into circulation. Provisions on the uniqueness of the essence of higher education, the main fundamental tasks of innovative academic (university) entrepreneurship, the types of innovations initiated by academic capitalism in higher education that can lead to innovative changes, and their classification of both theoretical and practical importance for the development of domestic science and higher education are proposed. The main objects of innovative activity in the sphere of higher education and science, the corresponding directions of further innovative development of higher education in Ukraine, as well as the types of innovations in higher education that can lead to innovative changes are also defined.

Auditors' skills and ways of working must adapt to constantly changing conditions in the workplace, and the COVID-19 pandemic has brought further complexity. This paper uses a complexity theory lens to investigate changes in audit practice in recent years. A qualitative research method, using semi-structured interviews, was applied: first to investigate how audit practice (skillsets and ways of working) needs to be reformed and second to suggest implications for audit practice stemming from a disruptive macro-level event such as the current COVID-19 pandemic. It was found that audit firms are framed as complex adaptive systems and new skillsets and ways of working in audit practice are well known for their adaptation, co-evolution and emerging behaviours, which include virtual audits and remote working that have been brought about by the COVID-19 pandemic.

Today, as social networks play an increasingly important role, people are more likely to use them to discuss hot topics. Thus, reposting behavior plays a crucial role in such networks for information diffusion. However, the existing models do not consider the impact of some important numerical features on the spread of tweets. In addition, the potential correlation of the user information in different groups and their tweets will also affect the effect of retweet prediction. Considering the above problems, in this article, we propose a novel deep multitask learning-based method, CH-Transformer, for retweet prediction. First, we extract numerical features to represent tweet information features and social features. Then, the numerical features are concatenated with textual features. After feature extraction, we obtain the feature embeddings and feed them into our model to achieve propagation prediction. Finally, we evaluate the proposed method using well-known evaluation measures. The experimental results demonstrate the effectiveness of our method.

We briefly review properties of explainable AI proposed by various researchers. We take a structural approach to the problem of explainable AI, examine the feasibility of these aspects and extend them where appropriate. Afterwards, we review combinatorial methods for explainable AI which are based on combinatorial testing-based approaches to fault localization. Last, we view the combinatorial methods for explainable AI through the lens provided by the properties of explainable AI that are elaborated in this work. We pose resulting research questions that need to be answered and point towards possible solutions, which involve a hypothesis about a potential parallel between software testing, human cognition and brain capacity.

Studies on the possibility of predicting critical transitions with statistical methods known as early warning signals (EWS) are often conducted on data generated with equation-based models (EBMs). These models base on difference or differential equations, which aggregate a system’s components in a mathematical term and therefore do not allow for a detailed analysis of interactions on micro-level. As an alternative, we suggest a simple, but highly flexible agent-based model (ABM), which, when applying EWS-analysis, gives reason to (a) consider social interaction, in particular negative feedback effects, as an essential trigger of critical transitions, and (b) to differentiate social interactions, for example in network representations, into a core and a periphery of agents and focus attention on the periphery. Results are tested against time series from a networked version of the Ising-model, which is often used as example for generating hysteretic critical transitions.

A puzzle lies behind password authentication (PA) and blockchain proof of work (PoW). A cryptographic hash function is commonly used to implement them. The potential problem with secure hash functions is their complexity and rigidity. We explore the use of complex systems constructs such as a cellular automaton (CA) to provide puzzle functionality. The analysis shows that computational irreducibility and sensitivity to initial state phenomena are enough to create simple puzzle systems that can be used for PA and PoW. Moreover, we present puzzle schemata using CA and n-body problems.

The coordination of multi-robot system (MRS) are applied commonly to various fields of the automotive industry. In a variety of cooperative modes, online path planning with obstacles avoidance is a fundamentally important hotspot, especially in a 3-D, complex, or dynamic environment. In the paper, an improved neural dynamics based approach with territorial mechanism is proposed to online path planning of MRS, which can be used as the online path planner for multi-AUVs and multi-UAVs in complex and dynamic environments. This approach integrates biological neural network, computational fluid dynamics, and territorial mechanism of animals, which has the characteristics and advantages of the biological nervous system, namely self-regulation, self-adaptation, self-organization, etc. It can cope with a variety of accidents during path planning, such as the disappearance of targets, the breakdown of robots, the change of environments, and so forth. Meanwhile, the proposed approach has better time performance and is insensitive to the number of robots in MRS. During the path planning of MRS, it can also guarantee to balance workload and to reduce entire workload and total time, which enhance robustness and fairness. The effectiveness and efficiency of the proposed approach are demonstrated by simulations and comparative studies.

PurposeThis paper aims to use systems mapping as a tool to develop an organisation-wide approach to public mental health to inform strategic direction within a national public health agency. Design/methodology/approachTwo workshops were facilitated with internal staff from a wide range of public health policy teams working in small groups to produce paper-based maps. These were collated and refined by the project team and digitised. FindingsThe approach engaged a range of teams in forming a shared understanding and producing a complex system map of the influences on population mental health and well-being, where current policy initiatives were addressing them and what the gaps and priorities were. Participants valued the approach which led to further study and organisational commitment to the whole system working as part of national public mental health strategy. Research limitations/implicationsThe approach was limited to internal stakeholders and wider engagement with other sectors and community members would help further the application of complex system approaches to public mental health. Originality/valueIt was a valuable process for developing a whole-organisation approach and stimulating thinking and practice in complex system approaches. The paper provides a practical example of how to apply systems mapping and its benefits for organising public mental health practice.

Drug-Target Binding Affinity (DTBA) prediction is one class of Drug-Target Interaction problem (DTI), where the focus is to predict the binding strength of a drug-target pair. Several machine learning approaches have been developed for this purpose. However, almost all rely on the use of increasingly sophisticated inputs to improve the obtained results besides that they don’t allow any analysis or interpretation due to their black-box characteristic. This work is an attempt to address these limitations by leveraging the use of attention mechanisms with convolution-deconvolution architecture. In this paper, we define two multilevel attention-based models for DTBA prediction. Our two approaches attempt to get advantage of the attention concept, by probing different abstraction levels of drug-target feature maps. We evaluate the performance of our methods on two benchmark datasets, KIBA and Davis. The results show that both approaches are very effective. Compared to other well-known methods, they achieved excellent results regarding the considered performance metrics, while using merely sequences as inputs and providing a potential way of results interpretation.

The fourteen papers in this special section focus on data-drive management of complex systems via plant-wide performance supervision. Currently, massive amounts of data are continuously being produced by social and industrial activities. Consequently, data-driven techniques have received considerable attention both in industry and academia in recent years, aiding scientists to manage and interpret the available data. The reasons behind such popularity of data-driven techniques are twofold. On the one hand, advanced data processing and information acquisition technologies have been developed to the extent that large amounts of data in different forms are available for big data analysis from descriptive to prescriptive. On the other hand, with the help of machine learning methodologies, the supervision and management systems can provide effective decisions for plant-wide optimal performance. Compared to the conventional model-based techniques, the data-driven ones can not only save the costly modeling procedures but also extract valuable information from available process data for real-time analysis and management. However, there are many complex and challenging problems in the data-driven supervision and management techniques, such as data-driven supervision on the safety, security, and robustness, as well as the performance-supervised management and their distributed designs. The papers in this section target recent results, trends, and practical developments in the data-driven methodologies of plant-wide performance supervision and management for complex systems, especially those related to process monitoring and machine learning activities with their industrial applications.

Enterprise system users are required to improve competence to gain the system’s value. The development of user competence to effectively use a complex system is socially constructed. Based on the job demands-resources model, we propose and empirically validate how two types of work contextual factors, namely, job demands and job resources, are directly and interactively related to user competence. Results of a longitudinal survey from users in six organizations suggest that all three job resource factors considered—leader–member exchange, traditional support structures, and peer support structure—allow users to acquire both the technical and business knowledge needed for effective application of the system for work. But, work overload, as the job demand factor, has no significant effect on user competence. Further analysis shows the relationship between work overload and user competence is moderated by leader–member exchange, but not the two support structures. Our findings are of great importance for practice, as they suggest job resources are conducive to the development of user competence, whereas work overload is an inevitable, acute problem.

The probabilistic modelling is widely used in engineering practices, especially for assessing the safety and reliability of complex systems. Dynamic evidential network (DEN) can efficiently deal with epistemic uncertainty based on Dempster-Shafer theory. This work proposes an extended discrete-time DEN model along with an extensive review of its applications in engineering. The proposed model combines the Dempster-Shafer theory, used for handling epistemic uncertainty across a new state-space reconstruction of components, and the dynamic Bayesian network is used for multi-state system reliability. The model application is demonstrated on a real case study from the aviation field. The application quantifies reliability and availability parameters that help to prioritize maintenance activities and avoid failures of complex redundant systems. The proposed model can serve as a tool to assess the reliability and availability of industrial systems suffering from parameter uncertainty and common cause failures.

Hierarchical reinforcement learning (HRL) is a promising method, which decomposes complex tasks into a series of sub-tasks. However, at present, most HRL methods have slow convergence speed and are difficult to be widely applied to such scenarios in real life. In this paper, we propose an efficient hierarchical reinforcement learning algorithm with fuzzy rules (HFR), a novel framework for integrating human prior knowledge with hierarchical policy network, which can effectively accelerate the optimization of policy. The model presented in this paper uses fuzzy rules to represent the human prior knowledge, making the rules trainable because of the derivability of the fuzzy rules. In addition, a switch module that adaptively adjusts the decision-making frequency of the upper-level policy is proposed to solve the limitation of manual tuning. Experiment results demonstrate that HFR has a faster convergence rate than the current state-of-the-art HRL algorithms, especially in complex scenarios, such as robot control tasks.

Macroscopic differential equations that accurately account for microscopic phenomena can be systematically generated using rigorous upscaling methods. However, such methods are time-consuming, prone to error, and become quickly intractable for complex systems with tens or hundreds of equations. To ease these complications, we propose a method of automatic upscaling through symbolic computation. By streamlining the upscaling procedure and derivation of applicability conditions to just a few minutes, the potential for democratization and broad utilization of upscaling methods in real-world applications emerges. We demonstrate the ability of our software prototype, Symbolica, by reproducing homogenized advective–diffusive–reactive (ADR) systems from earlier studies and homogenizing a large ADR system deemed impractical for manual homogenization. Novel upscaling scenarios previously restricted by unnecessarily conservative assumptions are discovered, and numerical validation of the models derived by Symbolica is provided.

The development of the aviation transport system is characterized by sophistication of interacting objects, the multi-criteria nature of the tasks to be solved and difficulties in making management decisions. For example, modern medium haul aircraft are fitted with up to 25,000 sensors to monitor the performance capabilities of functional systems components. Numerous ground-based instrumental methods and means of diagnosing the technical condition are used. This requires the development of methods and algorithms for determining and monitoring the criteria of limiting state of the monitored components and functional systems of aeronautical equipment. In this regard, analytical models of predictive estimate for the technical condition of aeronautical equipment, determination of aircraft maintenance modes and provision of spare parts and materials become essential. The paper proposes a scheme of the aircraft fleet maintenance system modeling algorithm and deducing the mathematical model of the optimal number of aircraft states in order to exclude secondary and subjective factors. The method of statistical modeling based on Markov processes with discrete states and continuous time is the basis of the proposed analytical model. The proposed method is reduced to the synthesis of some modeling algorithm of the investigated process that simulates the complex system components behavior and interaction as well as random perturbing factors. A distinctive feature of the presented algorithm is determination of the predominant estimated dependences of transition probabilities and intensities taking into account the requirements of the modern regulatory framework in terms of reliability of equipment and diagnosing the technical condition. The analysis of the predominant estimated dependencies study results in the conditions of operation of the aircraft maintenance system confirmed a high degree of correlation of the time duration effect on the particular states in order to diagnose the technical condition depending on the diagnostic concept. The proposed simulation model can be used for the aircraft technical condition predictive estimate, aircraft gas turbine engines and functional systems.

High-risk buildings can be considered as complex systems involving various social actors and technology, which draws attention to the organisational and social underpinnings of their safety. This r...

In this paper, we propose a multi-stage genetic algorithm that allows to automatically initialize deep multilayer perceptron neural network models to train it for prediction of robot execution failures. The proposed genetic algorithm system is divided on three stages, the first stage consists of initializing number of hidden layers. The second stage aims to fix number of neurons in each hidden layer. The final stage generates the activation function and the optimizer used to train neural network models. The next step is the application of the generated neural network models to predict robot execution failures. The aim of this approach is giving a robot many models so it can better take a more precise decision, since there is no scientific method to choose neural network model, genetic algorithm allows to generate many models automatically. Results obtained in this study show the efficiency of deep neural networks on robotic failures detection, as well as the efficiency of genetic algorithms to generate different models automatically which prevent the manual setup.

Dense depth estimation based on a single image is a basic problem in computer vision and has exciting applications in many robotic tasks. Modelling fully supervised methods requires the acquisition of accurate and large ground truth data sets, which is often complex and expensive. On the other hand, self-supervised learning has emerged as a promising alternative to monocular depth estimation as it does not require ground truth depth data. In this paper, we propose a novel self-supervised joint learning framework for depth estimation using consecutive frames from monocular and stereo videos. Our architecture leverages two new ideas for improvement: (1) triplet attention and (2) funnel activation (FReLU). By adding triplet attention to the deep and pose networks, this module captures the importance of features across dimensions in a tensor without any information bottlenecks, making the optimisation learning framework more reliable. FReLU is used at the non-linear activation layer to grasp the local context adaptively in images, rather than using more complex convolutions at the convolution layer. FReLU extracts the spatial structure of objects by the pixel-wise modeling capacity provided by the spatial condition, making the details of the complex image richer. The experimental results show that the proposed method is comparable with the state-of-the-art self-supervised monocular depth estimation method.

We survey the progress in data mining methods for spacecraft health monitoring. The main emphasis is placed on the analysis of telemetry data enabling the identification of spacecraft states that are atypical during normal operation and the prediction of possible failures in the operation of the spacecraft or its components. The main stages required for the creation of general-purpose spacecraft state monitoring systems are considered; methods for detecting anomalies in telemetry data taking into account the specific features of the spacecraft are presented in detail; and publications on this topic known to the authors are analyzed. Examples of the implementation of such systems in flight control centers of various countries are given. The promising areas of development of methods for analyzing the technical state of complex systems relevant for solving problems in space technology are discussed, and the main factors that hinder the development of machine learning methods for analyzing telemetry data are noted.

The belief rule-base (BRB) model is a new intelligent expert system with the characteristics of both expert system and data-driven model. In BRB there are many if-then rules which use belief degrees to express various types of uncertain information, including fuzziness, randomness, and ignorance. As a semi-quantitative modeling tool for complex systems, BRB has the superiorities of dealing both numerical quantitative data and linguistic qualitative knowledge that are derived from heterogeneous sources. Moreover, it is also a white box approach which can provide direct access and transparency to decision makers and stakeholders. Currently, BRB has been widely applied in many fields, such as decision making, reliability evaluation, network security situation awareness, fault diagnosis, and so on. To fully demonstrate the progress of BRB, the original BRB, and some evolution forms are introduced in this article.

Purpose Because the discontinuous and uncertain characteristics of knowledge-based innovation cannot be reasonably interpreted by conventional management approaches, quantum mechanics which begins with uncertainty and concerns with a dynamic process of the complex system, has been exploratorily used in the management field. Although the theoretical new insights are provided by pioneering studies, quantitative research is in short supply. This paper aims to propose a quantum mechanics-based framework for quantitative research, thus extending the application of quantum mechanics in the knowledge management area from a dynamic system evolutionary standpoint. Design/methodology/approach Based on the similarity comparison between knowledge-based system evolution and atomic motion, the authors construct the atom-like structure of the knowledge-based system and elaborate the evolutionary mechanism of the knowledge-based system, thereby establishing the quantitative model. Apple and Zhongxing Telecom Equipment were selected for an empirical study to demonstrate the usefulness of the models for research on knowledge-based innovation and explore the unique knowledge-based innovation characteristics of the two firms. Findings First, the transition force of dynamic knowledge shows an inverted U shape; accumulating dynamic knowledge to a moderate degree not only facilitates transforming dynamic knowledge into static knowledge but also balances the relationship between the influence of knowledge force range and dynamic knowledge transformation. Second, existing knowledge is gradually substituted by new knowledge and knowledge density at a high knowledge energy level distinctly increases with a narrower bandwidth. Third, the investment loss is associated with resource configuration, resource utilization and the amount of accumulative dynamic knowledge before investment. Knowledge loss is negatively correlated with the knowledge compatibility coefficient. Research limitations/implications The authors use the advanced method in quantum mechanics to legitimately unveil the emergence mechanism of knowledge-based innovation. Meanwhile, the authors capture the non-linear transformation relationship of heterogeneous knowledge and expose the change in ways of both investment loss and knowledge loss that cannot be quantified by conventional models. In doing so, the authors not only reveal the principle of qualitative knowledge change but also offer practical implications for developing flexible and targeted innovation strategies. Originality/value First, by proposing a complete quantum mechanics-based framework, the authors not only supplement the quantitative research contents to knowledge-based innovation literature which proposed calls to conduct research in way of quantum mechanics but also overcome the difficulties of knowledge-based system conceptualization and measurement. Second, the authors reveal the uncertain change of knowledge transformation and measure the loss of investment and knowledge, which contribute to identifying defects of firms in knowledge-based innovation. Third, the authors explore the internal mechanism that led to knowledge-based innovation exhibits non-linear characteristics and capture unique dynamic relationships between different variables which affect the emergence of knowledge-based innovation.