Older partner selection promotes the prevalence of cooperation in evolutionary games.

Evolutionary games typically come with the interplays between evolution of individual strategy and adaptation to network structure. How these dynamics in the co-evolution promote (or obstruct) the cooperation is regarded as an important topic in social, economic, and biological fields. Combining spatial selection with partner choice, the focus of this paper is to identify which neighbour should be selected as a role to imitate during the process of co-evolution. Age, an internal attribute and kind of local piece of information regarding the survivability of the agent, is a significant consideration for the selection strategy. The analysis and simulations presented, demonstrate that older partner selection for strategy imitation could foster the evolution of cooperation. The younger partner selection, however, may decrease the level of cooperation. Our model highlights the importance of agent׳s age on the promotion of cooperation in evolutionary games, both efficiently and effectively.

A few-shot link prediction framework to drug repurposing using multi-level attention network.

Drug repurposing is a strategy aiming at uncovering novel medical indications of approved drugs. This process of discovery can be effectively represented as a link prediction task within a medical knowledge graph by predicting the missing relation between the disease entity and the drug entity. Typically, the links to be predicted pertain to rare types, thereby necessitating the task of few-shot link prediction. However, the sparsity of neighborhood information and weak triplet interactions result in less effective representations, which brings great challenges to the few-shot link prediction. Therefore, in this paper, we proposed a meta-learning framework based on a multi-level attention network (MLAN) to capture valuable information in the few-shot scenario for drug repurposing. First, the proposed method utilized a gating mechanism and a graph attention network to effectively filter noise information and highlight the valuable neighborhood information, respectively. Second, the proposed commonality relation learner, employing a set transformer, effectively captured triplet-level interactions while remaining insensitive to the size of the support set. Finally, a model-agnostic meta-learning training strategy was employed to optimize the model quickly on each meta task. We conducted validation of the proposed method on two datasets specifically designed for few-shot link prediction in medical field: COVID19-One and BIOKG-One. Experimental results showed that the proposed model had significant advantages over state-of-the-art few-shot link prediction methods. Results also highlighted the valuable insights of the proposed method, which successfully integrated the components within a unified meta-learning framework for drug repurposing.

Hyperparameter optimization: Classics, acceleration, online, multi-objective, and tools.

Hyperparameter optimization (HPO) has been well-developed and evolved into a well-established research topic over the decades. With the success and wide application of deep learning, HPO has garnered increased attention, particularly within the realm of machine learning model training and inference. The primary objective is to mitigate the challenges associated with manual hyperparameter tuning, which can be ad-hoc, reliant on human expertise, and consequently hinders reproducibility while inflating deployment costs. Recognizing the growing significance of HPO, this paper surveyed classical HPO methods, approaches for accelerating the optimization process, HPO in an online setting (dynamic algorithm configuration, DAC), and when there is more than one objective to optimize (multi-objective HPO). Acceleration strategies were categorized into multi-fidelity, bandit-based, and early stopping; DAC algorithms encompassed gradient-based, population-based, and reinforcement learning-based methods; multi-objective HPO can be approached via scalarization, metaheuristics, and model-based algorithms tailored for multi-objective situation. A tabulated overview of popular frameworks and tools for HPO was provided, catering to the interests of practitioners.

Laser-upgraded coal tar for smart pavements in road and bridge monitoring applications.

The implementation of an intelligent road network system requires many sensors for acquiring data from roads, bridges, and vehicles, thereby enabling comprehensive monitoring and regulation of road networks. Given this large number of required sensors, the sensors must be cost-effective, dependable, and environmentally friendly. Here, we show a laser upgrading strategy for coal tar, a low-value byproduct of coal distillation, to manufacture flexible strain-gauge sensors with maximum gauge factors of 15.20 and 254.17 for tension and compression respectively. Furthermore, we completely designed the supporting processes of sensor placement, data acquisition, processing, wireless communication, and information decoding to demonstrate the application of our sensors in traffic and bridge vibration monitoring. Our novel strategy of using lasers to upgrade coal tar for use as a sensor not only achieves the goal of turning waste into a resource but also provides an approach to satisfy large-scale application requirements for enabling intelligent road networks.

Heuristic search for planning with different forced goal-ordering constraints.

Planning with forced goal-ordering (FGO) constraints has been proposed many times over the years, but there are still major difficulties in realizing these FGOs in plan generation. In certain planning domains, all the FGOs exist in the initial state. No matter which approach is adopted to achieve a subgoal, all the subgoals should be achieved in a given sequence from the initial state. Otherwise, the planning may arrive at a deadlock. For some other planning domains, there is no FGO in the initial state. However, FGO may occur during the planning process if certain subgoal is achieved by an inappropriate approach. This paper contributes to illustrate that it is the excludable constraints among the goal achievement operations (GAO) of different subgoals that introduce the FGOs into the planning problem, and planning with FGO is still a challenge for the heuristic search based planners. Then, a novel multistep forward search algorithm is proposed which can solve the planning problem with different FGOs efficiently.

Graph-Attention-Based Casual Discovery With Trust Region-Navigated Clipping Policy Optimization.

In many domains of empirical sciences, discovering the causal structure within variables remains an indispensable task. Recently, to tackle unoriented edges or latent assumptions violation suffered by conventional methods, researchers formulated a reinforcement learning (RL) procedure for causal discovery and equipped a REINFORCE algorithm to search for the best rewarded directed acyclic graph. The two keys to the overall performance of the procedure are the robustness of RL methods and the efficient encoding of variables. However, on the one hand, REINFORCE is prone to local convergence and unstable performance during training. Neither trust region policy optimization, being computationally expensive, nor proximal policy optimization (PPO), suffering from aggregate constraint deviation, is a decent alternative for combinatory optimization problems with considerable individual subactions. We propose a trust region-navigated clipping policy optimization method for causal discovery that guarantees both better search efficiency and steadiness in policy optimization, in comparison with REINFORCE, PPO, and our prioritized sampling-guided REINFORCE implementation. On the other hand, to boost the efficient encoding of variables, we propose a refined graph attention encoder called SDGAT that can grasp more feature information without priori neighborhood information. With these improvements, the proposed method outperforms the former RL method in both synthetic and benchmark datasets in terms of output results and optimization robustness.

Active Client Selection for Clustered Federated Learning.

Federated learning (FL) is an emerging distributed machine learning (ML) framework that operates under privacy and communication constraints. To mitigate the data heterogeneity underlying FL, clustered FL (CFL) was proposed to learn customized models for different client groups. However, due to the lack of effective client selection strategies, the CFL process is relatively slow, and the model performance is also limited in the presence of nonindependent and identically distributed (non-IID) client data. In this work, for the first time, we propose selecting participating clients for each cluster with active learning (AL) and call our method active client selection for CFL (ACFL). More specifically, in each ACFL round, each cluster filters out a small set of clients, which are the most informative clients according to some AL metrics e.g., uncertainty sampling, query-by-committee (QBC), loss, and aggregates only its model updates to update the cluster-specific model. We empirically evaluate our ACFL approach on the public MNIST, CIFAR-10, and LEAF synthetic datasets with class-imbalanced settings. Compared with several FL and CFL baselines, the results reveal that ACFL can dramatically speed up the learning process while requiring less client participation and significantly improving model accuracy with a relatively low communication overhead.

How to prevent malicious use of intelligent unmanned swarms?

With advancements in swarm intelligence, artificial intelligence, and wireless mobile network technology, unmanned swarms such as unmanned aerial vehicles, ground vehicles, ships, and other unmanned systems are becoming increasingly autonomous and intelligent. Benefiting from these technologies, intelligent unmanned swarms are able to efficiently perform complex tasks through collaboration in various fields. However, malicious use of intelligent unmanned swarms raises concerns about the potential for significant damage to national infrastructures such as airports and power facilities. Defending against malicious activities is essential but challenging due to the swarms' abilities to perceive, understand complex environments, and make accurate decisions through multi-system collaboration. This perspective sheds light on recent research in counter-measures and provides new trends and insights on how to prevent malicious actions by intelligent unmanned swarms.

Toward parallel intelligence: An interdisciplinary solution for complex systems.

The growing complexity of real-world systems necessitates interdisciplinary solutions to confront myriad challenges in modeling, analysis, management, and control. To meet these demands, the parallel systems method rooted in the artificial systems, computational experiments, and parallel execution (ACP) approach has been developed. The method cultivates a cycle termed parallel intelligence, which iteratively creates data, acquires knowledge, and refines the actual system. Over the past two decades, the parallel systems method has continuously woven advanced knowledge and technologies from various disciplines, offering versatile interdisciplinary solutions for complex systems across diverse fields. This review explores the origins and fundamental concepts of the parallel systems method, showcasing its accomplishments as a diverse array of parallel technologies and applications while also prognosticating potential challenges. We posit that this method will considerably augment sustainable development while enhancing interdisciplinary communication and cooperation.

Deep Reinforcement Learning: A Survey.

Deep reinforcement learning (DRL) integrates the feature representation ability of deep learning with the decision-making ability of reinforcement learning so that it can achieve powerful end-to-end learning control capabilities. In the past decade, DRL has made substantial advances in many tasks that require perceiving high-dimensional input and making optimal or near-optimal decisions. However, there are still many challenging problems in the theory and applications of DRL, especially in learning control tasks with limited samples, sparse rewards, and multiple agents. Researchers have proposed various solutions and new theories to solve these problems and promote the development of DRL. In addition, deep learning has stimulated the further development of many subfields of reinforcement learning, such as hierarchical reinforcement learning (HRL), multiagent reinforcement learning, and imitation learning. This article gives a comprehensive overview of the fundamental theories, key algorithms, and primary research domains of DRL. In addition to value-based and policy-based DRL algorithms, the advances in maximum entropy-based DRL are summarized. The future research topics of DRL are also analyzed and discussed.

Laser Direct-Write Sensors on Carbon-Fiber-Reinforced Poly-Ether-Ether-Ketone for Smart Orthopedic Implants.

Mechanically close-to-bone carbon-fiber-reinforced poly-ether-ether-ketone (CFR-PEEK)-based orthopedic implants are rising to compete with metal implants, due to their X-ray transparency, superior biocompatibility, and body-environment stability. While real-time strain assessment of implants is crucial for the postsurgery study of fracture union and failure of prostheses, integrating precise and durable sensors on orthopedic implants remains a great challenge. Herein, a laser direct-write technique is presented to pattern conductive features (minimum sheet resistance <1.7 Ω sq-1 ) on CRF-PEEK-based parts, which can act as strain sensors. The as-fabricated sensors exhibit excellent linearity (R2  = 0.997) over the working range (0-2.5% strain). While rigid silicon- or metal-based sensor chips have to be packaged onto flat surfaces, all-carbon-based sensors can be written on the complex curved surfaces of CFR-PEEK joints using a portable laser mounted on a six-axis robotic manipulator. A wireless transmission prototype is also demonstrated using a Bluetooth module. Such results will allow a wider space to design sensors (and arrays) for detailed loading progressing monitoring and personalized diagnostic applications.

Mobile augmented reality based indoor map for improving geo-visualization.

Unlike traditional visualization methods, augmented reality (AR) inserts virtual objects and information directly into digital representations of the real world, which makes these objects and data more easily understood and interactive. The integration of AR and GIS is a promising way to display spatial information in context. However, most existing AR-GIS applications only provide local spatial information in a fixed location, which is exposed to a set of problems, limited legibility, information clutter and the incomplete spatial relationships. In addition, the indoor space structure is complex and GPS is unavailable, so that indoor AR systems are further impeded by the limited capacity of these systems to detect and display location and semantic information. To address this problem, the localization technique for tracking the camera positions was fused by Bluetooth low energy (BLE) and pedestrian dead reckoning (PDR). The multi-sensor fusion-based algorithm employs a particle filter. Based on the direction and position of the phone, the spatial information is automatically registered onto a live camera view. The proposed algorithm extracts and matches a bounding box of the indoor map to a real world scene. Finally, the indoor map and semantic information were rendered into the real world, based on the real-time computed spatial relationship between the indoor map and live camera view. Experimental results demonstrate that the average positioning error of our approach is 1.47 m, and 80% of proposed method error is within approximately 1.8 m. The positioning result can effectively support that AR and indoor map fusion technique links rich indoor spatial information to real world scenes. The method is not only suitable for traditional tasks related to indoor navigation, but it is also promising method for crowdsourcing data collection and indoor map reconstruction.

Construction and confirmatory factor analysis of the core cognitive ability index system of ship C2 system operators.

BACKGROUND: Cognitive ability refers to the ability to receive, process, store, and extract information. It is the most important psychological condition for people to successfully complete activities. Previous studies have shown that the design of the human-computer interface of the command and control system cannot exceed the cognitive ability of the operator of the command and control system, and it must match the cognitive ability of the operator in order to reduce the mental load intensity, and improve the accuracy, timeliness and work efficiency. However, previous researchers in the field of cognitive science have not put forward a core index system that can represent the cognitive ability of ship command and control system operators and the importance of each index, and there are few achievements that can be used for reference. OBJECTIVE: To explore the core index system of cognitive ability that affecting the cognitive process of command and control system operators, and to verify the index system. METHODS: Based on the classic O*NET questionnaire, two indexes of O*NET were revised, three indexes of response ability were added, and then a questionnaire on the importance evaluation of cognitive abilities index was formed. The questionnaire includes 24 indexes in six aspects: verbal abilities, idea generation and reasoning abilities, quantitative abilities, visual perception abilities, mnemonic and attentive abilities, and response abilities. The cognitive ability importance evaluation data of 202 people from different positions in the ship command and control system were collected. These data reflect the overall level of cognitive ability of operators in the whole ship command and control field. RESULTS: The data analysis results show that: firstly, the most important cognitive abilities affecting command and control system operators were visual perception abilities, mnemonic and attentive abilities, and response abilities. Secondly, the results of confirmatory factor analysis show that CMIN/DF, GFI, CFI, TLI, RMSEA, RMR and other indicators used in the model test all meet the requirements. The model has a good fitting degree, and the overall index extraction method is feasible. Thirdly, the independence T test results show that for beginners and experienced experts, there is a significant difference in the important evaluation of mnemonic and attentive abilities, while there is no significant difference in the important evaluation of response and visual perception abilities. Fourthly, the results of Bi-group confirmatory factor analysis experiment show that the structural model has good stability and factor invariance. CONCLUSIONS: Through the research of this paper, the index system which can express the core cognitive ability of the commander of command and control system is successfully constructed, and the index system has been fully verified by mathematics. The 3 abilities and 10 indexes in the index system are closely related to the work tasks of operators, which also reflects the correctness of our construction results to a certain extent. According to the results of data analysis, there are differences between assistant commanders and professional commanders in the evaluation of the importance of some indexes, which reflects the importance of working age and experience to the promotion of position skills. The results of this research are of great significance for the subsequent acquisition of cognitive ability data and assessment of post cognitive ability of command and control system operators.

Heterogeneity and effectiveness analysis of COVID-19 prevention and control in major cities in China through time-varying reproduction number estimation.

Beginning on December 31, 2019, the large-scale novel coronavirus disease 2019 (COVID-19) emerged in China. Tracking and analysing the heterogeneity and effectiveness of cities' prevention and control of the COVID-19 epidemic is essential to design and adjust epidemic prevention and control measures. The number of newly confirmed cases in 25 of China's most-affected cities for the COVID-19 epidemic from January 11 to February 10 was collected. The heterogeneity and effectiveness of these 25 cities' prevention and control measures for COVID-19 were analysed by using an estimated time-varying reproduction number method and a serial correlation method. The results showed that the effective reproduction number (R) in 25 cities showed a downward trend overall, but there was a significant difference in the R change trends among cities, indicating that there was heterogeneity in the spread and control of COVID-19 in cities. Moreover, the COVID-19 control in 21 of 25 cities was effective, and the risk of infection decreased because their R had dropped below 1 by February 10, 2020. In contrast, the cities of Wuhan, Tianmen, Ezhou and Enshi still had difficulty effectively controlling the COVID-19 epidemic in a short period of time because their R was greater than 1.

Spatio-Temporal Patterns of the 2019-nCoV Epidemic at the County Level in Hubei Province, China.

Understanding the spatio-temporal characteristics or patterns of the 2019 novel coronavirus (2019-nCoV) epidemic is critical in effectively preventing and controlling this epidemic. However, no research analyzed the spatial dependency and temporal dynamics of 2019-nCoV. Consequently, this research aims to detect the spatio-temporal patterns of the 2019-nCoV epidemic using spatio-temporal analysis methods at the county level in Hubei province. The Mann-Kendall and Pettitt methods were used to identify the temporal trends and abrupt changes in the time series of daily new confirmed cases, respectively. The local Moran's I index was applied to uncover the spatial patterns of the incidence rate, including spatial clusters and outliers. On the basis of the data from January 26 to February 11, 2020, we found that there were 11 areas with different types of temporal patterns of daily new confirmed cases. The pattern characterized by an increasing trend and abrupt change is mainly attributed to the improvement in the ability to diagnose the disease. Spatial clusters with high incidence rates during the period were concentrated in Wuhan Metropolitan Area due to the high intensity of spatial interaction of the population. Therefore, enhancing the ability to diagnose the disease and controlling the movement of the population can be confirmed as effective measures to prevent and control the regional outbreak of the epidemic.

On the improvement of reinforcement active learning with the involvement of cross entropy to address one-shot learning problem.

As a promising research direction in recent decades, active learning allows an oracle to assign labels to typical examples for performance improvement in learning systems. Existing works mainly focus on designing criteria for screening examples of high value to be labeled in a handcrafted manner. Instead of manually developing strategies of querying the user to access labels for the desired examples, we utilized the reinforcement learning algorithm parameterized with the neural network to automatically explore query strategies in active learning when addressing stream-based one-shot classification problems. With the involvement of cross-entropy in the loss function of Q-learning, an efficient policy to decide when and where to predict or query an instance is learned through the developed framework. Compared with a former influential work, the advantages of our method are demonstrated experimentally with two image classification tasks, and it exhibited better performance, quick convergence, relatively good stability and fewer requests for labels.

Identification of influential invaders in evolutionary populations.

The identification of the most influential nodes has been a vibrant subject of research across the whole of network science. Here we map this problem to structured evolutionary populations, where strategies and the interaction network are both subject to change over time based on social inheritance. We study cooperative communities, which cheaters can invade because they avoid the cost of contributions that are associated with cooperation. The question that we seek to answer is at which nodes cheaters invade most successfully. We propose the weighted degree decomposition to identify and rank the most influential invaders. More specifically, we distinguish two kinds of ranking based on the weighted degree decomposition. We show that a ranking strategy based on negative-weighted degree allows to successfully identify the most influential invaders in the case of weak selection, while a ranking strategy based on positive-weighted degree performs better when the selection is strong. Our research thus reveals how to identify the most influential invaders based on statistical measures in dynamically evolving cooperative communities.

A novel framework for the identification of drug target proteins: Combining stacked auto-encoders with a biased support vector machine.

The identification of drug target proteins (IDTP) plays a critical role in biometrics. The aim of this study was to retrieve potential drug target proteins (DTPs) from a collected protein dataset, which represents an overwhelming task of great significance. Previously reported methodologies for this task generally employ protein-protein interactive networks but neglect informative biochemical attributes. We formulated a novel framework utilizing biochemical attributes to address this problem. In the framework, a biased support vector machine (BSVM) was combined with the deep embedded representation extracted using a deep learning model, stacked auto-encoders (SAEs). In cases of non-drug target proteins (NDTPs) contaminated by DTPs, the framework is beneficial due to the efficient representation of the SAE and relief of the imbalance effect by the BSVM. The experimental results demonstrated the effectiveness of our framework, and the generalization capability was confirmed via comparisons to other models. This study is the first to exploit a deep learning model for IDTP. In summary, nearly 23% of the NDTPs were predicted as likely DTPs, which are awaiting further verification based on biomedical experiments.

A Novel Ensemble Method for Imbalanced Data Learning: Bagging of Extrapolation-SMOTE SVM.

Class imbalance ubiquitously exists in real life, which has attracted much interest from various domains. Direct learning from imbalanced dataset may pose unsatisfying results overfocusing on the accuracy of identification and deriving a suboptimal model. Various methodologies have been developed in tackling this problem including sampling, cost-sensitive, and other hybrid ones. However, the samples near the decision boundary which contain more discriminative information should be valued and the skew of the boundary would be corrected by constructing synthetic samples. Inspired by the truth and sense of geometry, we designed a new synthetic minority oversampling technique to incorporate the borderline information. What is more, ensemble model always tends to capture more complicated and robust decision boundary in practice. Taking these factors into considerations, a novel ensemble method, called Bagging of Extrapolation Borderline-SMOTE SVM (BEBS), has been proposed in dealing with imbalanced data learning (IDL) problems. Experiments on open access datasets showed significant superior performance using our model and a persuasive and intuitive explanation behind the method was illustrated. As far as we know, this is the first model combining ensemble of SVMs with borderline information for solving such condition.