QN-ACES: Integrating Queueing Network and ACT-R,CAPS, EPIC,and Soar Architectures for Multitask Cognitive Modeling

Comprehensive and computational models of human performance have both scientific and practical importance to human–machine system design and human-centered computing. This article describes QN-ACES, a cognitive architecture that aims to integrate two complementary classes of cognitive architectures: Queueing network (QN) mathematical architecture and ACT–R, CAPS, EPIC, and Soar (ACES) symbolic architectures. QN-ACES represents the fourth major step along the QN architecture development for theoretical and methodological unification in cognitive and human–computer interaction modeling. The first three steps—QN architecture for response time, QN-RMD (Reflected Multidimensional Diffusions) for response time, response accuracy, and mental architecture, and QN-MHP (Model Human Processor) for mathematical analysis and real time simulation of procedural tasks—are summarized first, followed by a discussion of the rationale, importance and specific research issues of QN-ACES.     

Cognitive architectures: choreographing the dance of mental operations with the task environment

OBJECTIVE: In this article, I present the ideas and trends that have given rise to the use of cognitive architectures in human factors and provide a cognitive engineering-oriented taxonomy of these architectures and a snapshot of their use for cognitive engineering. BACKGROUND: Architectures of cognition have had a long history in human factors but a brief past. The long history entails a 50-year preamble, whereas the explosion of work in the current decade reflects the brief past. Understanding this history is key to understanding the current and future prospects for applying cognitive science theory to human factors practice. METHOD: The review defines three formative eras in cognitive engineering research: the 1950s, 1980s, and now. RESULTS: In the first era, the fledging fields of cognitive science and human factors emphasized characteristics of the dancer the limited capacity or bounded rationality view of the mind, and the ballroom, the task environment. The second era emphasized the dance (i.e., the dynamic interaction between mental operations and task environment). The third era has seen the rise of cognitive architectures as tools for choreographing the dance of mental operations within the complex environments posed by human factors practice. CONCLUSIONS: Hybrid architectures present the best vector for introducing cognitive science theories into a renewed engineering-based human factors. APPLICATION: The taxonomy provided in this article may provide guidance on when and whether to apply a cognitive science or a hybrid architecture to a human factors issue.     

Computational modeling of human performance in multiple monitor environments with ACT-R cognitive architecture

Much research on modeling human performance associated with visual perception is formulated by schematic models based on neural mechanisms or cognitive architectures. But, these two modeling paradigms are limited in the domains of multiple monitor environments. Although the schematic model based on neural mechanisms can represent human visual systems in multiple monitor environments by providing a detailed account of eye and head movements, these models cannot easily be applied in complex cognitive interactions. On the other hand, the cognitive architectures can model the interaction of multiple aspects of cognition, but these architectures have not focused on modeling the visual orienting behavior of eye and head movements. Thus, in this study, a specific cognitive architecture, which is ACT-R, is extended by an existing schematic model of human visual systems based on neural mechanisms in order to model human performance in multiple monitor environments more accurately. And, this study proposes a method of modeling human performance using the extended ACT-R. The proposed method is validated by an experiment, confirming that the proposed method is able to predict human performance more accurately in multiple monitor environments.Relevance to industryPredicting human performance with a computational model can be used as an alternative method to implementing iterative user testing for developing a system interface. The computational model in this study can predict human performance in multiple monitor environments, so that the model can be applied early on in the design phase, to evaluate the system interface in multiple monitor environments.     

A Hybrid Theory of Event Memory

Amongst philosophers, there is ongoing debate about what successful event remembering requires. Causal theorists argue that it requires a causal connection to the past event. Simulation theorists argue, in contrast, that successful remembering requires only production by a reliable memory system. Both views must contend with the fact that people can remember past events they have experienced with varying degrees of accuracy. The debate between them thus concerns not only the account of successful remembering, but how each account explains the various forms of memory error as well. Advancing the debate therefore must include exploration of the cognitive architecture implicated by each view and whether that architecture is capable of producing the range of event representations seen in human remembering. Our paper begins by exploring these architectures, framing casual theories as best suited to the storage of event instances and simulation theories as best suited to store schemas. While each approach has its advantages, neither can account for the full range of our event remembering abilities. We then propose a novel hybrid theory that combines both instance and schematic elements in the event memory. In addition, we provide an implementation of our theory in the context of a cognitive architecture. We also discuss an agent we developed using this system and its ability to remember events in the blocks world domain.

     

Modeling driver behavior in a cognitive architecture

OBJECTIVE: This paper explores the development of a rigorous computational model of driver behavior in a cognitive architecture--a computational framework with underlying psychological theories that incorporate basic properties and limitations of the human system. BACKGROUND: Computational modeling has emerged as a powerful tool for studying the complex task of driving, allowing researchers to simulate driver behavior and explore the parameters and constraints of this behavior. METHOD: An integrated driver model developed in the ACT-R (Adaptive Control of Thought-Rational) cognitive architecture is described that focuses on the component processes of control, monitoring, and decision making in a multilane highway environment. RESULTS: This model accounts for the steering profiles, lateral position profiles, and gaze distributions of human drivers during lane keeping, curve negotiation, and lane changing. CONCLUSION: The model demonstrates how cognitive architectures facilitate understanding of driver behavior in the context of general human abilities and constraints and how the driving domain benefits cognitive architectures by pushing model development toward more complex, realistic tasks. APPLICATION: The model can also serve as a core computational engine for practical applications that predict and recognize driver behavior and distraction.     

Equipping the ACT-R cognitive architecture with a temporal ratio model of memory and using it in a new intelligent adaptive interface

ACT-R, as a useful and well-known cognitive architecture, is a theory for simulating and understanding human cognition. However, the standard version of this architecture uses a deprecated forgetting model. So, we equipped it with a temporal ratio model of memory that has been named as SIMPLE (Scale-Independent Memory, Perception, and Learning). On the other hand, one of the usages of cognitive architectures is to model the user in an Intelligent Adaptive Interface (IAI) implementation. Thus, our motivation for this effort is to use this equipped ACT-R in an IAI to deliver the right information at the right time to users based on their cognitive needs. So, to test our proposed equipped ACT-R, we designed and implemented a new IAI to control a swarm of Unmanned Aerial Vehicles (UAVs). This IAI uses the equipped ACT-R for user cognitive modeling, to deliver the right information to the users based on their forgetting model. Thus, our contributions are: equipping the ACT-R cognitive architecture with the SIMPLE memory model and using this equipped version of ACT-R for user modeling in a new IAI to control a group of UAVs. Simulation results, which have been obtained using different subjective and objective measures, show that we significantly improved situation awareness of the users using the IAI empowered by our equipped ACT-R.

     

Cognitive Social Simulation Incorporating Cognitive Architectures

Agent-based social simulation modeling, a social phenomena on the basis of models of autonomous agents has grown tremendously in recent decades. Researchers use this approach to study a wide range of social and economic issues, including social beliefs and norms, resource allocation, traffic patterns, social cooperation, stock market dynamics, group interaction and dynamics, and organizational decision making. Agent-based social simulation with multiagent systems in social computing can benefit from incorporating cognitive architectures. A cognitive architecture is a domain-generic computational cognitive model that captures essential structures and processes of the individual mind for the purpose of a broad (multiple-domain) analysis of cognition and behaviour.     

A multi-agent architecture with cooperative fuzzy control for a mobile robot

The challenges of robotics have led the researchers to develop control architectures composed of distributed, independent and asynchronous behaviors. One way to approach decentralization is through cooperative control, since it allows the development of complex behavior based on several controllers combined to achieve the desired result. Robots, however, require high-level cognitive capacities, and multi-agent architectures provide the appropriate level of abstraction to define them. This article describes a multi-agent architecture combined with cooperative control developed within the agent. The experiments were carried out on an ActivMedia Pioneer 2DX mobile robot.     

An Empirical Methodology for Exploring Reconfigurable Architectures

Recent research in reduced instruction set computer architectures has emphasized the importance of the empirical approach to designing computer architectures: architectural features are analyzed for utility and cost with respect to the system software that uses them. This approach has resulted in architectural simulators that allow computer designers to vary the features of the architecture being simulated and to analyze how the addition or removal of these features affects the cost and performance of the architecture. In this paper we apply this technique to a new area: reconfigurable architectures. Our approach is to use an empirical methodology that emphasizes the interaction between the target software and the reconfigurability features of parallel architectures. We have developed a set of tools, the reconfigurable architecture workbench, that assists in this methodology by allowing parallel programs to be simulated on a target architecture in order to study the performance implications of various reconfigurability features. The workbench is based on a framework, the PCI model, which describes the range of parallel programs, parallel architectures, and reconfiguration features. We present details of the design and implementation of a prototype workbench, GT-RAW. GT-RAW is being used to study the utility of one dimension of reconfiguration for image processing and image understanding applications. We present an example of the experiments that are being conducted with GT-RAW as a demonstration of our empirical methodology.     

Network architecture design and implementation

Progress in communications technology has produced a wide range of communications techniques for different applications. All these methods basically perform the same operation; transferring information between users. Little uniformity exists, however, and the main computer manufacturers have each produced their own network architectures, all incompatible with each other. The paper describes a network architecture designed by NCR. The requirements of such a network architecture are listed, and the need for an architecture to be compatible with international standards is emphasized by comparing NCR's architecture with the open systems interconnection reference model from the ISO. The structure and operations of the layered architecture is described and compared to the OSI reference model.     

基于会话的安全、鲁棒共享控制方法

在共享控制系统中，比如智能服务机器人，操作员和自动化专门系统相互配合，共同控制．有效的共享控制需要复杂的系统体系结构，该结构可以提供安全鲁棒的运行，提供对用户友好的界面．满足这两项需求是一个不寻常的任务．介绍了解决这些问题的方法．首先给出一个以会话为中心采用面向代理编程和形式化方法的认知控制体系结构．采用混成设计的SharC认知控制体系结构，可以区分协同代理群体中每一个遥控设备的控制．安全性对共享控制系统来说是极为重要的，因此这种体系结构必须能够保证较高的安全性．最后，描述了作为控制系统核心的形式化建模会话管理器，通过示范平台中自动轮椅的例子说明这些不同的软件范例的应用。     

深度神经网络结构搜索综述

深度神经网络在图像识别、语言识别和机器翻译等人工智能任务中取得了巨大进展,很大程度上归功于优秀的神经网络结构设计。神经网络大都由手工设计,需要专业的机器学习知识以及大量的试错。为此,自动化的神经网络结构搜索成为研究热点。神经网络结构搜索（neural architecture search,NAS）主要由搜索空间、搜索策略与性能评估方法3部分组成。在搜索空间设计上,出于计算量的考虑,通常不会搜索整个网络结构,而是先将网络分成几块,然后搜索块中的结构。根据实际情况的不同,可以共享不同块中的结构,也可以对每个块单独搜索不同的结构。在搜索策略上,主流的优化方法包含强化学习、进化算法、贝叶斯优化和基于梯度的优化等。在性能评估上,为了节省计算时间,通常不会将每一个网络都充分训练到收敛,而是通过权值共享、早停等方法尽可能减小单个网络的训练时间。与手工设计的网络相比,神经网络结构搜索得到的深度神经网络具有更好的性能。在ImageNet分类任务上,与手工设计的MobileNetV2相比,通过神经网络结构搜索得到的MobileNetV3减少了近30%的计算量,并且top-1分类精度提升了3.2%;在Cityscapes语义分割任务上,与手工设计的DeepLabv3+相比,通过神经网络结构搜索得到的Auto-DeepLab-L可以在没有ImageNet预训练的情况下,达到比DeepLabv3+更高的平均交并比（mean intersection over union,mIOU）,同时减小一半以上的计算量。神经网络结构搜索得到的深度神经网络通常比手工设计的神经网络有着更好的表现,是未来神经网络设计的发展趋势。     

Implementing heuristics as an optimization criterion in neural networks for job-shop scheduling

Recently neural network architectures have been developed that are capable of solving deterministic job-shop scheduling problems, part of the large class of NP-complete problems. In these architectures, however, no valid optimization criterion has been implemented. In this paper an enhanced neural network architecture for job-shop scheduling is proposed in which general rules of thumb for job-shop scheduling have been incorporated as a local optimization criterion. Implementation of the rules of thumb, by adaptation of the network architecture, results in a network that actually incorporates the optimization criterion, enabling parallel hardware implementation. Owing to the implemented local optimization criterion the performance of the network architecture is superior to previously presented architectures. Comparison with advanced heuristic sequential schedulers showed equal performance with respect to the quality of the solutions and better performance with respect to calculation speed.     

Touring Machines: autonomous agents with attitudes

A multilayered integrated architecture for controlling autonomous mobile agents, or Touring Machines, is introduced. This architecture combines capabilities for producing a range of reactive and deliberative behaviors in dynamic, unpredictable domains. The approach is influenced by recent work on reactive and behavior-based agent architectures. Touring Machines blend sophisticated and simplified control features. Experience shows that this layered architecture can be configured to behave with robustness and flexibility simultaneously in dynamic settings. The implementation of the control architecture on a testbed is reported     

Communication Architectures for Massive Multi-Player Games

Massive multi-player games are characterized by a large number of participating players. It is therefore essential that an appropriate communication architecture is deployed in order to support an ever growing number of players. Several such architectures have been proposed, including client-server and peer-to-peer architectures. In this paper, we propose a systematic method to assess the scalability of different architectures in order to identify the most appropriate one for specific game types. The model proposed is very general in that it covers centralized, distributed, and hybrid architectures and it is applied to the client-server, peer-to-peer and the newly introduced federated peer-to-peer architecture. Quantitative expressions that capture the effect of various game types are derived, and the trade-offs among the architectures are identified.     

运行时软件体系结构的建模与维护

运行时体系结构是系统运行时刻的一个动态、结构化的抽象,描述系统当前的组成成分、各成分的状态和配置以及不同成分之间的关系.运行时体系结构与目标系统间具有动态的因果关联,即系统的变化及时体现在体系结构上,而对体系结构的修改及时影响当前系统.运行时体系结构允许开发者以读写体系结构的方式实现系统的监测和调整,是体系结构层次系统动态适应与在线演化的基础.构造运行时体系结构的关键是针对不同的目标系统和体系结构风格实现合适的基础设施,以维护二者之间的因果关联.由于目标系统和体系结构的多样性以及因果关联维护逻辑的复杂性,这一构造过程往往过于繁琐、易错、难以复用和维护.提出一种模型驱动的运行时体系结构构造方法.开发者只需针对目标系统、体系结构以及两者之间的关系分别进行建模,根据这些模型,支撑框架自动构造合法而高效的运行时体系结构基础设施.基于MOF 和QVT 标准建模语言定义了一组运行时体系结构建模语言,并基于通用的模型与系统间同步技术实现了相应的支撑框架.一系列实例研究表明,该方法具有广泛的适用性,并显著提高了运行时体系结构构造过程的效率与可复用性.     

Enabling the human in the loop: Linked data and knowledge in industrial cyber-physical systems

Industrial Cyber-Physical Systems have benefitted substantially from the introduction of a range of technology enablers. These include web-based and semantic computing, ubiquitous sensing, internet of things (IoT) with multi-connectivity, advanced computing architectures and digital platforms, coupled with edge or cloud side data management and analytics, and have contributed to shaping up enhanced or new data value chains in manufacturing. While parts of such data flows are increasingly automated, there is now a greater demand for more effectively integrating, rather than eliminating, human cognitive capabilities in the loop of production related processes. Human integration in Cyber-Physical environments can already be digitally supported in various ways. However, incorporating human skills and tangible knowledge requires approaches and technological solutions that facilitate the engagement of personnel within technical systems in ways that take advantage or amplify their cognitive capabilities to achieve more effective sociotechnical systems. After analysing related research, this paper introduces a novel viewpoint for enabling human in the loop engagement linked to cognitive capabilities and highlighting the role of context information management in industrial systems. Furthermore, it presents examples of technology enablers for placing the human in the loop at selected application cases relevant to production environments. Such placement benefits from the joint management of linked maintenance data and knowledge, expands the power of machine learning for asset awareness with embedded event detection, and facilitates IoT-driven analytics for product lifecycle management.     

A framework to generate domain-specific manycore architectures from dataflow programs

In the last 15 years we have seen, as a response to power and thermal limits for current chip technologies, an explosion in the use of multiple and even many computer cores on a single chip. But now, to further improve performance and energy efficiency, when there are potentially hundreds of computing cores on a chip, we see a need for a specialization of individual cores and the development of heterogeneous manycore computer architectures.However, developing such heterogeneous architectures is a significant challenge. Therefore, we propose a design method to generate domain specific manycore architectures based on RISC-V instruction set architecture and automate the main steps of this method with software tools. The design method allows generation of manycore architectures with different configurations including core augmentation through instruction extensions and custom accelerators. The method starts from developing applications in a high-level dataflow language and ends by generating synthesizable Verilog code and cycle accurate emulator for the generated architecture.We evaluate the design method and the software tools by generating several architectures specialized for two different applications and measure their performance and hardware resource usages. Our results show that the design method can be used to generate specialized manycore architectures targeting applications from different domains. The specialized architectures show at least 3 to 4 times better performance than the general purpose counterparts. In certain cases, replacing general purpose components with specialized components saves hardware resources. Automating the method increases the speed of architecture development and facilitates the design space exploration of manycore architectures.