Effective agent coordination is crucial in cooperative Multiagent Reinforcement Learning (MARL). While recent advances have significantly improved cooperation by modeling agent interactions through various graph structures, most existing approaches primarily focus on homogeneous agents. Despite the ubiquity of heterogeneous agents, constructing a comprehensive graph that captures their diverse attributes and relationships from scratch is notoriously labor-intensive for both humans and agents, which makes policy learning extremely challenging. To tackle this difficulty, we propose a novel method that utilizes a fuzzy human attention-guided graph to model inter-agent relationships. Instead of learning the graph entirely from scratch, we incorporate abstract human attention, with its uncertainty captured through fuzzy logic, to guide the graph development process. To further accommodate the varying attributes and objectives of heterogeneous agents while maintaining their learning capabilities, the attention-guided graph is fine-tuned through a hyper-network. Our proposed approach is end-to-end trainable and agnostic to specific MARL methods. Empirical evaluations conducted on challenging heterogeneous scenarios from the StarCraft Multiagent Challenge (SMAC) and SMACv2 validate the effectiveness of the proposed method.

Transparent TCP acceleration has been a subject of extensive academic research for years, aiming to bypass kernel overhead without modifying legacy applications. Prior work, however, largely emphasizes performance under idealized settings and provides limited discussion of how costs and gains manifest in real production environments.

Abstract Due to its exceptional learning ability, multi-agent deep reinforcement learning (MADRL) has garnered widespread research interest. However, since the learning is data-driven and involves sampling from millions of steps, training a large number of agents is inherently challenging and inefficient. Inspired by the human learning process, we aim to transfer knowledge from humans to avoid starting from scratch. Given the growing emphasis on the Human-on-the-Loop concept, this study focuses on addressing the challenges of large-population learning by incorporating suboptimal human knowledge into the cooperative multi-agent environment. To leverage human experience, we integrate human knowledge into the training process of MADRL, representing it in natural language rather than specific action-state pairs. Compared to previous works, we further consider the attributes of transferred knowledge to assess its impact on algorithm scalability. Additionally, we examine several features of knowledge mapping to effectively convert human knowledge to the action space where agent learning occurs. In reaction to the disparity in knowledge construction between humans and agents, our approach allows agents to decide freely which portions of the state space to leverage human knowledge. From the challenging domains of the StarCraft Multi-agent Challenge, our method successfully alleviates the scalability issue in MADRL. Furthermore, we find that, despite individual-type knowledge significantly accelerating the training process, cooperative-type knowledge is more desirable for addressing a large agent population. We hope this study provides valuable insights into applying and mapping human knowledge, ultimately enhancing the interpretability of agent behavior.

Knowledge graph technology is widely used in network security design, analysis, and detection. By collecting, organizing, and mining various security knowledge, it provides scientific support for security decisions. Some public Security Knowledge Repositories (SKRs) are frequently used to construct security knowledge graphs. The quality of SKRs affects the efficiency and effectiveness of security analysis. However, the current situation is that the identification of relational information among security knowledge elements is not sufficient and timely, and a large number of key relational information is missing. In view of this, we propose a security knowledge graph relational reasoning method, based on the fusion embedding of semantic correlation and structure correlation, named SecKG2vec . By SecKG2vec , the embedded vector simultaneously presents both semantic and structural characteristics, and it can exhibit better relational reasoning performance. In qualitative evaluation and quantitative experiments with baseline methods , SecKG2vec has better performance in relationship reasoning task and entity reasoning task, and potential capability of 0-shot scenario prediction.

Most research investigating how social influence affects election results mainly uses diffusion models for binary opinions. However, these diffusion models are progressive and focus on the diffusion of one opinion. In this article, we introduce a general diffusion model for ordinal opinions expressed as linear orderings over a finite set of candidates. We employ agent-based modeling to simulate a nonprogressive diffusion process, allowing multiple types of opinion diffusion about different candidates. The proposed agent-based diffusion model can forecast long-term trends of opinion diffusion in social networks by capturing voters’ personalized features and incorporating dynamic social contexts. Furthermore, we examine the possibility of affecting election outcomes by externally changing the ordinal opinions of certain vertices, i.e., campaigning. Since finding influential voters from the social network is computationally challenging, we propose a heuristic approach, i.e., backward influence rank (BIR). Experimental results demonstrate that the proposed BIR approach is superior to the classic greedy approach for campaigning by achieving a similar margin of victory to that of the greedy approach but running two orders of magnitude faster than the greedy approach did.

Vocabulary learning that incorporates visual information has become widely recognized as an alternative to context-based methods. However, few studies focus on learners' incorrect answers. On the Other hand, fossilization caused by repeated errors has been a concern. Our proposed system, L-VEIGe, effectively prevents repeated errors by visualizing learners' incorrect answers through image generation, which encourages introspection. However, there exists a 'Feature Disappearance' problem, where the generated images for incorrect answers lack sufficient information for comprehension. This study proposes a method for quantitatively evaluating these error images from a cognitive perspective.

Research surveys have always posed a challenge for novice researchers who lack research training. These researchers struggle to understand the directions within their research topic and the discovery of new research findings within a short time. One way to provide intuitive assistance to novice researchers is by offering relevant knowledge graphs $(KG)$ and recommending related academic papers. However, existing navigation knowledge graphs mainly rely on keywords or meta information in the research field to guide researchers, which makes it difficult to clearly present the hierarchical relationships, such as inheritance and relevance between multiple related papers. Moreover, most recommendation systems for academic papers simply rely on high text similarity, confusing researchers as to why a particular article is recommended. They may lack the grasp of important information about the insight connection between ‘Issue resolved’ and ‘Issue finding’ that they hope to obtain. This study aims to support research insight surveys for novice researchers by establishing a hierarchical tree-structured knowledge graph that reflects the inheritance insight and the relevance insight among multiple academic papers on specific research topics to address these issues.

Due to the exponential growth of agent interactions and the curse of dimensionality, learning efficient coordination from scratch is inherently challenging in large-scale multi-agent systems. While agents' learning is data-driven, sampling from millions of steps, human learning processes are quite different. Inspired by the concept of Human-on-the-Loop and the daily human hierarchical control, we propose a novel knowledge-guided multi-agent reinforcement learning framework (hhk-MARL), which combines human abstract knowledge with hierarchical reinforcement learning to address the learning difficulties among a large number of agents. In this work, fuzzy logic is applied to represent human suboptimal knowledge, and agents are allowed to freely decide how to leverage the proposed prior knowledge. Additionally, a graph-based group controller is built to enhance agent coordination. The proposed framework is end-to-end and compatible with various existing algorithms. We conduct experiments in challenging domains of the StarCraft Multi-agent Challenge combined with three famous algorithms: IQL, QMIX, and Qatten. The results show that our approach can greatly accelerate the training process and improve the final performance, even based on low-performance human prior knowledge.

With the exponential growth in the number of papers and the trend of AI research, the use of Generative AI for information retrieval and question-answering has become popular for conducting research surveys. However, novice researchers unfamiliar with a particular field may not significantly improve their interaction efficiency with Generative AI because they have not developed divergent thinking in that field. This study aims to develop an in-depth Survey Forest Diagram that guides novice researchers in divergent thinking about the research topic by indicating the citation clues among multiple papers to help expand the survey perspective for novice researchers.

Novice researchers often face difficulties in understanding a multitude of academic papers and grasping the fundamentals of a new research field. To solve such problems, the knowledge graph supporting research survey is gradually being developed. Existing keyword-based knowledge graphs make it difficult for researchers to deeply understand abstract concepts. Meanwhile, novice researchers may find it difficult to use ChatGPT effectively for research surveys due to their limited understanding of the research field. Without the ability to ask proficient questions that align with key concepts, obtaining desired and accurate answers from this large language model (LLM) could be inefficient. This study aims to help novice researchers by providing a fish-bone diagram that includes causal relationships, offering an overview of the research topic. The diagram is constructed using the issue ontology from academic papers, and it offers a broad, highly generalized perspective of the research field, based on relevance and logical factors. Furthermore, we evaluate the strengths and improvable points of the fish-bone diagram derived from this study's development pattern, emphasizing its potential as a viable tool for supporting research survey.

Characteristics of Highly Sensitive Persons (HSPs), such as “depth of processing,” “overstimulation,” “emotional reactivity and empathy,” and “sensitivity to subtleties,” often present challenges due to their high Sensory Processing Sensitivity (SPS) to environmental stimuli. This study investigates the differences in SPS among learners and the impact of various avatars on video presentations, a medium that has seen increased use due to COVID-19. We surveyed 20 participants who engaged with SDG instructional videos featuring four different avatars. Using the HSPS-J19 self-assessment tool, analysis of their SPS responses revealed a normal distribution of SPS scores, indicating individual differences. Additionally, correlations were found between HSPS-J19 scores and participants' impressions and motivation regarding avatar presentations. Cluster analysis results suggested that the group with a higher tendency towards HSP traits benefited more from appropriate avatar use. Based on these findings, we designed an online lecture support environment that allows for the control of video stimuli. This research explores an underexamined area and aims to enhance online lectures for HSPs, who constitute approximately 15% to 20% of the population. Supporting high SPS learners is particularly significant in the post-COVID-19 era.

The Industrial Internet of Things (IIoT) is one of the typical application scenarios in the beyond fifth generation (B5G) wireless communication systems. Due to numerous metal obstacles and machines, the industrial channel, especially at the millimeter-wave (mmWave) bands, exhibits complex characteristics that have not been considered in existing literature. This article proposes an innovative 3-D nonstationary geometry-based stochastic model (GBSM) for IIoT scenarios at mmWave bands. In the proposed model, device reflections (DRs) caused by massive metal machines are modeled based on geometrical optics. Furthermore, the generalized extreme value (GEV) distribution and generalized Pareto (GP) distribution are used to parameterize the number of clusters and rays within a cluster, respectively. Further, the Doppler shift is modeled and analyzed using the Gaussian distribution. Some channel statistical characteristics are captured by the proposed model, such as the power delay profile, root-mean-square delay spread, root-mean-square angle spread, intercluster delay, and space–time–frequency correlation function. Then, these channel statistical characteristics are well fitted to the ray-tracing simulations and the channel measurements. The excellent fitting results demonstrate the high accuracy of the proposed model, which is crucial for future IIoT communication system design. What is more, this article shows the antenna height and propagation scenarios can significantly affect the DR ratio, which should adapt to various IIoT communication scenarios.

In multi-agent systems, agents with limited capabilities need to find a cooperation partner to accomplish complex tasks. Evaluating the trustworthiness of potential partners is vital in partner selection. Current approaches are mainly averaged-based, aggregating advisors’ information on partners. These methods have limitations, such as vulnerability to unfair rating attacks, and may be locally convergent that cannot always select the best partner. Therefore, we propose a ranking-based partner selection (RPS) mechanism, which clusters advisors into groups according to their ranking of trustees and gives recommendations based on groups. Besides, RPS is an online-learning method that can adjust model parameters based on feedback and evaluate the stability of advisors’ ranking behaviours. Experiments demonstrate that RPS performs better than state-of-the-art models in dealing with unfair rating attacks, especially when dishonest advisors are the majority.

STGs, a longstanding video game subgenre, have grown more intricate over time, deterring new players. To address this, a training system is required to improve character control skills in STG games. Bayesian Knowledge Tracing (BKT) is a common approach researchers use to monitor and assess students' progress. While BKT is effective in evaluating intellectual knowledge, it falls short in assessing character control skills in STG, a form of motion knowledge. This study proposes a Skill Tracing (ST) model that combines BKT approaches to monitor both cognitive knowledge and character control abilities. Results indicate its superiority in skill-tracking tasks over traditional BKT, offering a more accurate prediction of players' skill levels.

Neuro-Fuzzy (NF) model is capable of learning the nonlinear mapping between inputs and outputs accurately from training data and is thus a powerful tool for identification of nonlinear dynamic systems. However, when deploying the trained model, the noisy measurement leads to bias model predictions. Besides, training data is insufficient to cover the whole operating space for nonlinear systems. To well capture the system response, this paper proposes a recursive least squares algorithm to enable the NF model self-adaptive to different operating conditions whilst being robustness against measurement noise. Building on the data filtering technique and the auxiliary model theory, the proposed algorithm achieves high model prediction accuracy for online implementations. Efficacy of the algorithm is demonstrated by two simulation cases.

With the widespread use of the internet, it has become increasingly crucial to extract specific information from vast amounts of academic articles efficiently. Data mining techniques are generally employed to solve this issue. However, data mining for academic articles is challenging since it requires automatically extracting specific patterns in complex and unstructured layout documents. Current data mining methods for academic articles employ rule-based (RB) or machine learning (ML) approaches. However, using rule-based methods incurs a high coding cost for complex typesetting articles. On the other hand, simply using machine learning methods requires annotation work for complex content types within the paper, which can be costly. Furthermore, only using machine learning can lead to cases where patterns easily recognized by rule-based methods are mistakenly extracted. To overcome these issues, from the perspective of analyzing the standard layout and typesetting used in the specified publication, we emphasize implementing specific methods for specific characteristics in academic articles. We have developed a novel Text Block Refinement Framework (TBRF), a machine learning and rule-based scheme hybrid. We used the well-known ACL proceeding articles as experimental data for the validation experiment. The experiment shows that our approach achieved over 95% classification accuracy and 90% detection accuracy for tables and figures.

The final objective of this research project is to develop a lecture archive summarization platform that can extend learners' experience by automatically estimating and providing temporal and spatial ROI (Regions of Interest) according to multimodal features and learners' learning logs in lecture archives that record face-to-face lectures. To develop this platform, we (a) establish a method for extracting spatiotemporal multimodal features of lecture archives and (b) construct a method for estimating a learning style model based on the learning logs when watching the archives with the extracted features. Furthermore, to maximize the learning effect, we will (c) develop a prototype system to adaptively control the spatiotemporal ROI at the terminal side according to the learning style model as an adaptive summarization. This article describes the concept of the proposed platform and the initial analysis of learners' learning logs.

Due to the COVID-19 pandemic, most universities endeavored to adopt online education as an alternative to conventional face-to-face classroom instruction. However, capturing students' Temporal Region of Interest (T-ROI) in long-duration video lectures poses a significant challenge. Therefore, lecture archive summarization becomes essential from an online perspective. The results of lecture archive summarization still require further improvement. This research aims to distinguish T-ROI using a speech processing approach h. Our plan is divided into collecting instructors'/presenters' voice datasets, clarifying the T-ROIs through sound processing technology, and building a suitable deep neural network architecture to detect the T-ROIs in the actual lecture archives automatically. We will inevitably encounter various challenges to achieve the objective, such as individual differences. This article describes the experimental dataset collection design considering individual differences and lecture room environments. It summarizes how such efforts will be effective in realizing personalized voice style detection and improving the accuracy of speech processing in real environments.

Virtual reality technology has the potential to revolutionize immersive experiences in various applications, including office settings. However, efficient text entry in VR remains a significant challenge. This study addresses this challenge by proposing a machine learning-based solution, the 2S-LSTM typing method, to enhance text entry performance in VR. The 2S-LSTM leverages the back of the hand image. It employs a two-stream Long Short-Term Memory (LSTM) network, combined with a Kalman Filter (KF), to improve hand position tracking accuracy and reduce jitter. The results from questionnaire-based evaluations and typing data analysis demonstrate the superiority of the 2S-LSTM solution over existing solutions like Oculus Quest 2 and Leap Motion in terms of typing efficiency, fatigue reduction, accurate hand position replication, and positive user experience. These findings contribute to the advancement of text entry in VR environments and pave the way for immersive work experiences in the office and beyond.

This article investigates the local linear model tree (LOLIMOT), a typical neural fuzzy model, in the multiple-input–multiple-output model predictive control (MPC). In the conventional LOLIMOT, the structural parameters including centers and variances of its Gaussian kernels are set based on equally dividing the input data space. In this article, after the structural parameters are initially obtained from the input space partition, they are optimized by the gradient descent search, from which the space partitions are further adjusted. This makes it better for the model structure to fit the input data statistics, leading to improved modeling performance with a small model size. The MPC based on the proposed structurally optimized LOLIMOT is then implemented and verified with both numerical and diesel engine plants. Validation results show that the proposed MPC has significantly a better controlling performance than the MPC based on the conventional LOLIMOT, making it an attractive solution in practice.

For nonlinear systems, Nonlinear Model Predictive Control (NMPC) is preferred to linear Model Predictive Control(MPC) since the nonlinear dynamics of the plant and the control performance index can be incorporated directly. In certain applications the computational resources available for calculating the control solution are severely restricted or the solution is required at high frequency. To overcome these computational challenges this paper presents a computationally efficient update scheme for NMPC using the Forward Dif-ference Generalized Minimum RESidual (FDGMRES) method with a neuro-fuzzy nonlinear dynamic model to describe the plant. Following a description of the FDGMRES approach and a simple case study, an evaluation of the algorithms computational performance is presented using the example of a reference tracking controller for control of a nonlinear Continuously Stirred Tank Reactor (CSTR) system. The online execution time of the FDGMRES algorithm based controller is compared in real time with the more conventional approach of the Sequential Quadratic Programming (SQP) algorithm using Rapid Controls Prototyping hardware.

Positive-unlabeled learning (PU learning) aims to deal with the problem that only a fraction of positive instances are known. Due to the absence of negative instances, ordinary learning models cannot be directly applied. Existing PU learning methods either explicitly choose some unlabeled instances as negative instances in advance or reformulate the task as a weighted learning problem. Since working in such an ad-hoc fashion, these methods often suffer a bad performance and only have limited usage. This paper proposes a novel instance-dependent weighting method entropy weight allocation (EWA) for PU learning by optimal transport (OT). More specifically, we allocate each unlabeled instance an elaborate weight indicating the possibility that it is an underlying negative instance. Then any ordinary weighted learning models can be used to obtain a PU classifier. By concatenating EWA with four celebrated classification models, we show that EWA is a broad-spectrum weighting method that can boost almost all the mainstream machine learning models for PU learning.

Online forum that gathers participants together to solve the common issues that they are facing is considered as a promising application of utilizing collective intelligence to solve complicated real-world problems. To facilitate the discussions in online forum to proceed smoothly and to build consensus efficiently, human facilitators are introduced into the system. With the increasing sophistication of online forum, human facilitators related problems such as human bias and restricted scale become critical. Therefore, it is critical to explore approaches to support human facilitators in conducting facilitation. However, most of the existing facilitation support techniques only support predefined facilitation tasks that could be defined by static rules. In this research, we aim to explore potential solutions for supporting the human facilitators to conduct facilitation in online forum. As the first step, we have proposed a case-based reasoning (CBR)-based framework that targets support facilitation by utilizing past successful facilitation experience. Currently, our work is focusing on the specific facilitation task of detecting influential user in the online forum. In the future work, we are planning to propose approaches of solving other specific facilitation tasks such as measuring the level of agreement and encouraging participants to reach a consensus.

BACKGROUND: A number of predictive models for aquatic toxicity are available, however, the accuracy and extent of easy to use of these in silico tools in risk assessment still need further studied. This study evaluated the performance of seven in silico tools to daphnia and fish: ECOSAR, T.E.S.T., Danish QSAR Database, VEGA, KATE, Read Across and Trent Analysis. 37 Priority Controlled Chemicals in China (PCCs) and 92 New Chemicals (NCs) were used as validation dataset. RESULTS: In the quantitative evaluation to PCCs with the criteria of 10-fold difference between experimental value and estimated value, the accuracies of VEGA is the highest among all of the models, both in prediction of daphnia and fish acute toxicity, with accuracies of 100% and 90% after considering AD, respectively. The performance of KATE, ECOSAR and T.E.S.T. is similar, with accuracies are slightly lower than VEGA. The accuracy of Danish Q.D. is the lowest among the above tools with which QSAR is the main mechanism. The performance of Read Across and Trent Analysis is lowest among all of the tested in silico tools. The predictive ability of models to NCs was lower than that of PCCs possibly because never appeared in training set of the models, and ECOSAR perform best than other in silico tools. CONCLUSION: QSAR based in silico tools had the greater prediction accuracy than category approach (Read Across and Trent Analysis) in predicting the acute toxicity of daphnia and fish. Category approach (Read Across and Trent Analysis) requires expert knowledge to be utilized effectively. ECOSAR performs well in both PCCs and NCs, and the application shoud be promoted in both risk assessment and priority activities. We suggest that distribution of multiple data and water solubility should be considered when developing in silico models. Both more intelligent in silico tools and testing are necessary to identify hazards of Chemicals.

Recently, face image hashing has been proposed in large-scale face image retrieval due to its storage and computational efficiency. However, owing to the large intra-identity variation (same identity with different poses, illuminations, and facial expressions) and the small inter-identity separability (different identities look similar) of face images, existing face image hashing methods have limited power to generate discriminative hash codes. In this work, we propose a deep hashing method specially designed for face image retrieval named deep Discrete Attention Guided Hashing (DAGH). In DAGH, the discriminative power of hash codes is enhanced by a well-designed discrete identity loss, where not only the separability of the learned hash codes for different identities is encouraged, but also the intra-identity variation of the hash codes for the same identities is compacted. Besides, to obtain the fine-grained face features, DAGH employs a multi-attention cascade network structure to highlight discriminative face features. Moreover, we introduce a discrete hash layer into the network, along with the proposed modified backpropagation algorithm, our model can be optimized under discrete constraint. Experiments on two widely used face image retrieval datasets demonstrate the inspiring performance of DAGH over the state-of-the-art face image hashing methods.

This paper presents a novel case-based reasoning (CBR) application to crowd-scale deliberation. We propose a CBR approach to facilitating online discussion for crowd-scale deliberation. The objective is to smooth the discussion by avoiding flaming and to efficiently achieve a consensus. Accordingly, several challenging issues are addressed, including case definition and its structure, case creation, and implementation by incorporating with COLLAGREE, a crowd-scale deliberation platform supporting online discussion with the help of facilitators. After introducing an overview of the crowd-scale deliberation and the COLLAGREE, the paper presents the details of the proposed CBR approach for facilitation of online discussion along with some preliminary results. The feasibility of CBR-based facilitation support for crowd-scale deliberations is demonstrated.

Cross-modal hashing has attracted considerable attention for large-scale multimodal retrieval task. A majority of hashing methods have been proposed for cross-modal retrieval. However, these methods inadequately focus on feature learning process and cannot fully preserve higher-ranking correlation of various item pairs as well as the multi-label semantics of each item, so that the quality of binary codes may be downgraded. To tackle these problems, in this paper, we propose a novel deep cross-modal hashing method, called Adversary Guided Asymmetric Hashing (AGAH). Specifically, it employs an adversarial learning guided multi-label attention module to enhance the feature learning part which can learn discriminative feature representations and keep the cross-modal invariability. Furthermore, in order to generate hash codes which can fully preserve the multi-label semantics of all items, we propose an asymmetric hashing method which utilizes a multi-label binary code map that can equip the hash codes with multi-label semantic information. In addition, to ensure higher-ranking correlation of all similar item pairs than those of dissimilar ones, we adopt a new triplet-margin constraint and a cosine quantization technique for Hamming space similarity preservation. Extensive empirical studies show that AGAH outperforms several state-of-the-art methods for cross-modal retrieval.

In this paper, we propose an integrated Mobile WiMAX and free space optics (FSO) broadband access network where the FSO network is used to provide high capacity backhaul for the Mobile WiMAX front end. The integrated network extends the coverage of Mobile WiMAX networks to larger areas in applications where the fiber network is expensive and difficult to deploy. We present a unified EAP-based security framework, and we evaluate and compare the performance of EAP-TLS and EAP-TTLS for this integrated FSO-WiMAX access network. Furthermore, we evaluate the impact of the point-to-point FSO link in the integrated access network. Our measurement shows that compared to EAP-TLS, EAP-TTLS provides a more flexible, efficient, and secure way to protect the integrated FSO-WiMAX access network. Our experiment also demonstrates that the point-to-point FSO link does not degrade the performance of EAP authentication in the integrated network.

Abstract Passive optical networks (PONs) offer a popular broadband access solution allowing for high bandwidth and long transmission range to meet user fast evolving needs. However, in certain applications, PON deployment cannot reach the end user, because geographic restrictions make fiber installation non‐cost effective. Recently, hybrid fiber–wireless (FiWi) access networks have been proposed to combine the advantages of optical and wireless technologies and integrate them seamlessly. However, this integrated wired and wireless access network raises new security issues that need to be addressed. This paper reviews the architectures of currently proposed integrated access networks, proposes a new Worldwide Interoperability for Microwave Access (WiMAX) over Ethernet PON (EPON) architecture which achieves simplified and efficient system management. We present a unified security framework for the proposed architecture using Public Key Infrastructure (PKI). Through our analysis, we show that this security framework enhances the system security and realizes unified key management. Copyright © 2010 John Wiley & Sons, Ltd.