Journal articles on the topic 'Complex Systems Learning Environments'
To see the other types of publications on this topic, follow the link: Complex Systems Learning Environments.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Complex Systems Learning Environments.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Jovancevic, J., B. Sullivan, and M. Hayhoe. "Learning gaze allocation priorities in complex environments." Journal of Vision 6, no. 6 (March 19, 2010): 480. http://dx.doi.org/10.1167/6.6.480.
Full text
2
Moglia, M., K. S. Alexander, and A. Sharma. "Discussion of the enabling environments for decentralised water systems." Water Science and Technology 63, no. 10 (May 1, 2011): 2331–39. http://dx.doi.org/10.2166/wst.2011.443.
Full textAbstract:
Decentralised water supply systems are becoming increasingly affordable and commonplace in Australia and have the potential to alleviate urban water shortages and reduce pollution into natural receiving marine and freshwater streams. Learning processes are necessary to support the efficient implementation of decentralised systems. These processes reveal the complex socio-technical and institutional factors to be considered when developing an enabling environment supporting decentralised water and wastewater servicing solutions. Critical to the technological transition towards established decentralised systems is the ability to create strategic and adaptive capacity to promote learning and dialogue. Learning processes require institutional mechanisms to ensure the lessons are incorporated into the formulation of policy and regulation, through constructive involvement of key government institutions. Engagement of stakeholders is essential to the enabling environment. Collaborative learning environments using systems analysis with communities (social learning) and adaptive management techniques are useful in refining and applying scientists' and managers' knowledge (knowledge management).
3
Liu, Zhe, Zhijian Qiao, Chuanzhe Suo, Yingtian Liu, and Kefan Jin. "Map-less long-term localization in complex industrial environments." Assembly Automation 41, no. 6 (October 4, 2021): 714–24. http://dx.doi.org/10.1108/aa-06-2021-0088.
Full textAbstract:
Purpose This paper aims to study the localization problem for autonomous industrial vehicles in the complex industrial environments. Aiming for practical applications, the pursuit is to build a map-less localization system which can be used in the presence of dynamic obstacles, short-term and long-term environment changes. Design/methodology/approach The proposed system contains four main modules, including long-term place graph updating, global localization and re-localization, location tracking and pose registration. The first two modules fully exploit the deep-learning based three-dimensional point cloud learning techniques to achieve the map-less global localization task in large-scale environment. The location tracking module implements the particle filter framework with a newly designed perception model to track the vehicle location during movements. Finally, the pose registration module uses visual information to exclude the influence of dynamic obstacles and short-term changes and further introduces point cloud registration network to estimate the accurate vehicle pose. Findings Comprehensive experiments in real industrial environments demonstrate the effectiveness, robustness and practical applicability of the map-less localization approach. Practical implications This paper provides comprehensive experiments in real industrial environments. Originality/value The system can be used in the practical automated industrial vehicles for long-term localization tasks. The dynamic objects, short-/long-term environment changes and hardware limitations of industrial vehicles are all considered in the system design. Thus, this work moves a big step toward achieving real implementations of the autonomous localization in practical industrial scenarios.
4
Davis, Susan. "Activity systems analysis methods: understanding complex learning environments, by Lisa C. Yamagata-Lynch." Pedagogies: An International Journal 7, no. 1 (January 2012): 95–99. http://dx.doi.org/10.1080/1554480x.2012.630575.
Full text
5
Li, Shoulin, and Weiya Guo. "Supervised Reinforcement Learning for ULV Path Planning in Complex Warehouse Environment." Wireless Communications and Mobile Computing 2022 (October 14, 2022): 1–12. http://dx.doi.org/10.1155/2022/4384954.
Full textAbstract:
The rapid development of the logistics industry leads to an urgent need for intelligent equipment to improve warehouse transportation efficiency. Recent advances in unmanned logistics vehicles (ULVs) make them particularly important in smart warehouses. However, the complex warehouse environment poses a significant challenge to ULV transportation path planning. Multiple ULVs need to transport cargoes with good coordination ability to overcome the low efficiency of a single ULV. The ULVs also need to interact with the environment to achieve optimal path planning with obstacle avoidance. In this paper, we propose a supervised deep reinforcement learning (SDRL) approach for logistics warehouses that enables autonomous ULVs path planning for cargo transportation in a complex environment. The proposed SDRL approach is featured by (1) designing the supervision module to imitate the behaviors of experts and thus improve the coordination ability of multiple ULVs, (2) optimizing the generator of the imitation learning based on the proximal policy optimization to boost the learning performance, and (3) developing the policy module via deep reinforcement learning to avoid obstacles when navigating the ULVs in warehouse environments. The experiments over dynamic and fixed-point warehouse environments show that the proposed SDRL approach outperforms its rivals regarding average reward, training speed, task completion rate, and collision times.
6
Jacobson, Michael J., and Rand J. Spiro. "Hypertext Learning Environments, Cognitive Flexibility, and the Transfer of Complex Knowledge: An Empirical Investigation." Journal of Educational Computing Research 12, no. 4 (June 1995): 301–33. http://dx.doi.org/10.2190/4t1b-hbp0-3f7e-j4pn.
Full textAbstract:
Although the use of hypertext systems for learning complex knowledge has been attracting recent attention, we currently have poor theoretical and research perspectives from which to understand special characteristics associated with learning in nonlinear and multidimensional hypertext instructional systems. A study was conducted to investigate a theory-based hypertext learning environment that provided instruction in a complex and ill-structured domain. The experimental treatment incorporated several features derived from recent cognitive learning theory, in particular a hypertext procedure that presented the instructional material in multiple contexts to highlight different facets of the knowledge. The main results of the study revealed that although the control treatment led to higher performance on the measures of memory for factual knowledge, the more hypertext-like treatment promoted superior knowledge transfer. Overall, these findings suggest hypertext learning environments that present the instructed knowledge by explicitly demonstrating critical interrelationships between abstract and case-specific knowledge components in multiple contexts will help prepare students to use knowledge in new ways and in new situations.
7
Kordova, Sigal. "Developing systems thinking in a Project-Based Learning environment." International Journal of Engineering Education 2, no. 1 (June 15, 2020): 63–81. http://dx.doi.org/10.14710/ijee.2.1.63-81.
Full textAbstract:
As science and engineering projects are becoming increasingly more complex, sophisticated, comprehensive and multidisciplinary, there is a growing need for systems thinking skills to ensure successful project management. Systems thinking plays a major role in the initiation, effective management, and in facilitating inter-organizational tasks. This research assesses the capacity for engineering systems thinking and its contribution in carrying out a multidisciplinary project. The research also reviews the cognitive process through which systems thinking skill is acquired. The study focused on a group of students who have completed their senior design projects in high-tech industry, while their plans were being integrated into existing larger projects in the respective industrial sites. The systems thinking skill of the students was examined according to a questionnaire for assessing the Capacity for Engineering Systems Thinking (CEST). Statistical analysis shows significant differences in the students capacity for systems thinking at the beginning and end of the work (p<0.001). This research demonstrates that systems thinking skills can be improved through awareness and involvement in multidisciplinary projects.
8
Schofield, Damian. "Guidelines for Learning : Using 3D Interactive Systems for Education and Training." Journal on Interactive Systems 3, no. 1 (June 15, 2012): 1. http://dx.doi.org/10.5753/jis.2012.609.
Full textAbstract:
Advanced 3D virtual environment technology, similar to that used by the film and computer games industry can allow educational developers to rapidly create realistic 3D, virtual environments. This technology has been used to generate a range of interactive learning environments across a broad spectrum of industries and educational application areas. Virtual Reality (VR) simulators represent a powerful tool for learning and teaching. The idea is not new. Flight simulators have been used for decades to train pilots for both commercial and military aviation. These systems have advanced to a point that they are integral to both the design and the operation of modern aircraft [1, 2]. There are a number of lessons that can be learned from other industries that have successfully utilised virtual training and learning systems for a number of years. Generic rules of thumb regarding the specification, development, application and operation of these learning environments can be garnered from other industrial training systems and examined in an educational context [3, 4, 5]. This paper will introduce a virtual learning environment which has been developed by the authors. During the implementation of this, and other, visual learning environments a number of complex operational problems have been encountered, these have required a number of innovative solutions and management procedures to be developed. The paper will also discuss the implementation of these systems and extrapolate the lessons learnt into general guidelines to be considered for the development of VR based educational learning resources. These guidelines will then be discussed in the context of the development of ViRILE (Virtual Reality Interactive Learning Environment). This software is designed for use by undergraduate chemical engineers and simulates the configuration and operation of a polymerisation plant.
9
Verster, Belinda, and Carolien van den Berg. "Theorising With Sociomateriality: Interdisciplinary Collaboration in Socio-Technical Learning Environments." Educational Research for Social Change 11, no. 2 (October 28, 2022): 1–18. http://dx.doi.org/10.17159/2221-4070/2021/v11i2a3.
Full textAbstract:
In this paper, we explore the possibilities offered by sociomateriality for academics to engage with complex learning environments. The focus is on a longitudinal design-based research (DBR) study that includes an interdisciplinary, collaborative student project between Information Systems (IS) and Urban Planning (URP) from two different higher education institutions in Cape Town, South Africa. In the project, student groups collaborate to find potential digital innovations for sustainability challenges in their local communities. The aim is to position the student as an active community member with intimate knowledge of local sustainability challenges, and to develop social digital innovations for the benefit of local communities. We apply sociomateriality as a theoretical lens to rethink socio-technical learning environments and propose four pedagogical propositions of relationality, reflexivity, responsiveness, and recognition to guide the pedagogical decision-making when designing complex learning environments. We conclude the paper by mapping student reflections and experiences to the four pedagogical propositions to illustrate how the theoretical sociomaterial elements translate into the learning environment.
10
Villalba-Díez, Javier, Martin Molina, Joaquín Ordieres-Meré, Shengjing Sun, Daniel Schmidt, and Wanja Wellbrock. "Geometric Deep Lean Learning: Deep Learning in Industry 4.0 Cyber–Physical Complex Networks." Sensors 20, no. 3 (January 30, 2020): 763. http://dx.doi.org/10.3390/s20030763.
Full textAbstract:
In the near future, value streams associated with Industry 4.0 will be formed by interconnected cyber–physical elements forming complex networks that generate huge amounts of data in real time. The success or failure of industry leaders interested in the continuous improvement of lean management systems in this context is determined by their ability to recognize behavioral patterns in these big data structured within non-Euclidean domains, such as these dynamic sociotechnical complex networks. We assume that artificial intelligence in general and deep learning in particular may be able to help find useful patterns of behavior in 4.0 industrial environments in the lean management of cyber–physical systems. However, although these technologies have meant a paradigm shift in the resolution of complex problems in the past, the traditional methods of deep learning, focused on image or video analysis, both with regular structures, are not able to help in this specific field. This is why this work focuses on proposing geometric deep lean learning, a mathematical methodology that describes deep-lean-learning operations such as convolution and pooling on cyber–physical Industry 4.0 graphs. Geometric deep lean learning is expected to positively support sustainable organizational growth because customers and suppliers ought to be able to reach new levels of transparency and traceability on the quality and efficiency of processes that generate new business for both, hence generating new products, services, and cooperation opportunities in a cyber–physical environment.
11
Grandio, Javier, Belén Riveiro, Mario Soilán, and Pedro Arias. "Point cloud semantic segmentation of complex railway environments using deep learning." Automation in Construction 141 (September 2022): 104425. http://dx.doi.org/10.1016/j.autcon.2022.104425.
Full text
12
Mikami, Sadayoshi, and and Mitsuo Wada. "Special Issue on Complex Systems in Robotics." Journal of Robotics and Mechatronics 10, no. 4 (August 20, 1998): 283. http://dx.doi.org/10.20965/jrm.1998.p0283.
Full textAbstract:
The Really ""intelligent"" robots predicted by science fiction have yet to appear, and robotics research seems to have reached a wall in dealing with the real-world environment. The robot is a unique device that it interfaces directly with the environments, including humans, machines, and nature. The world is very complex and changes dynamically. Robotic research must thus consider how to deal with such dynamcal complex world by means of machines. Our special issues on the complex systems in robotics introduce current representative approaches and attempts to answer these questions. The approach from a complex system point of view deals with new directions in robotics, for the above reasons and provides ways to view things dynamically, in a way that goes beyond traditional static control laws and rules. As these issues show approaches are divergent and ongoing. Modeling and forecasting the world is not haphazard. If requires direction. Even robots that navigate traffic, for example, must have a model to forecast unknown dynamics. Human interfacing requires far more difficult approaches than we take now. Recent developments in theory of chaos and non-linear predictions are expected to provide ways to enable these approaches. Robot interaction with the environment is one of the fundamental characteristics robots, and any interaction incorporates underlying dynamics; even robot-to-robot interaction exhibits deterministic dynamics. We will see how to deal with such complex phenomena through the articles predicting chaotic time series in these issues. Very rapid adaptation to the world is another way of coping using a brute-force approach. Reinforcement learning is a promising tool for working in a complex unknown environment. Learning robots affect both their environment and other robots. This is the situation in which we must think of the emergence of complexity. This may provide a rich source of possible tasks, and we must consider its dynamic nature of it. Many interesting phenomena are shown in the papers we present, applying reinforcement learning in multi-robots, for example. Finding good solutions wherever possible is a rather static solution but must incorporate the mechanism of how nature generates complexities and rich variations. Evolutionary methods, which many papers deal with in this issue, involves trends in complex systems sciences. Robotics applications must consider practical achievements such as rapidity, robustness, and appropriateness for specific applications. These issues provide a variety of robots and automation problems. Of course there are lots of other ways for this quite new approach and it should be worth cultivating because it is just the way we expect that robots should go. These special issues are organized from many papers submitted by researchers, all of whom we thank for their contributions. We hope these issues will help readers to familiarize themselves with the many trends in researches beyond engineering approaches and treat their practical implementation. This area is now very active, and we hope to see many papers related to this theme submitted to this journal in future.
13
Goldin, Daniel S., Samuel L. Venneri, and Ahmed K. Noor. "Ready for the Future?" Mechanical Engineering 121, no. 11 (November 1, 1999): 61–66. http://dx.doi.org/10.1115/1.1999-nov-2.
Full textAbstract:
The potential benefits for product development and scientific research have led many organizations to initiate programs to design collaborative distributed virtual environments. The goal of NASA's programs, Intelligent Synthesis Environment (ISE) and Intelligent Systems (IS), is to revolutionize scientific research and engineering processes by creating a distributed collaborative environment that will enable the linking of design teams and scientists from NASA, industry, and universities in the creation and operation of aerospace systelT1S and in synthesizing their missions. The programs' broad framework also will be used for scientific research and product development in complex non-aerospace applications. The advent of intelligent agents, which enabled the learner to manipulate cognitive artifacts from several perspectives or viewpoints, led to the interactive learning systems of the 1990s. The contributions of ISE and IS can be incorporated into three categories of advanced learning environments: expert-led group learning; self-paced individual learning; and collaborative learning; which, in combination, can reduce the time and cost of learning, and sustain and increase worker competencies in engineering organizations.
14
Hutsebaut-Buysse, Matthias, Kevin Mets, and Steven Latré. "Hierarchical Reinforcement Learning: A Survey and Open Research Challenges." Machine Learning and Knowledge Extraction 4, no. 1 (February 17, 2022): 172–221. http://dx.doi.org/10.3390/make4010009.
Full textAbstract:
Reinforcement learning (RL) allows an agent to solve sequential decision-making problems by interacting with an environment in a trial-and-error fashion. When these environments are very complex, pure random exploration of possible solutions often fails, or is very sample inefficient, requiring an unreasonable amount of interaction with the environment. Hierarchical reinforcement learning (HRL) utilizes forms of temporal- and state-abstractions in order to tackle these challenges, while simultaneously paving the road for behavior reuse and increased interpretability of RL systems. In this survey paper we first introduce a selection of problem-specific approaches, which provided insight in how to utilize often handcrafted abstractions in specific task settings. We then introduce the Options framework, which provides a more generic approach, allowing abstractions to be discovered and learned semi-automatically. Afterwards we introduce the goal-conditional approach, which allows sub-behaviors to be embedded in a continuous space. In order to further advance the development of HRL agents, capable of simultaneously learning abstractions and how to use them, solely from interaction with complex high dimensional environments, we also identify a set of promising research directions.
15
Žarkovič-Adlešič, Brigita, and Branco Silvar. "Collaborative learning as networking - how does it work in practice?" Pedagógusképzés 20, no. 1. (October 21, 2021): 141–50. http://dx.doi.org/10.37205/tel-hun.2021.1.09.
Full textAbstract:
The PROMISE project is addressing pedagogical dilemmas of contemporary education. Teachers who are working in complex circumstances are facing challenges which need to be discussed, reflected and faced. In such a process teachers need to meet other professionals either from their own environment or beyond. They need to cross boundaries between different fields of education, different systems, different learning environments, different professions, different roles… The purpose of the project is to expand the process of professional learning and exceed the boundaries.
16
Tassone, Valentina C., Perry den Brok, Cassandra W. S. Tho, and Arjen E. J. Wals. "Cultivating students’ sustainability-oriented learning at the interface of science and society: a configuration of interrelated enablers." International Journal of Sustainability in Higher Education 23, no. 8 (July 15, 2022): 255–71. http://dx.doi.org/10.1108/ijshe-01-2022-0014.
Full textAbstract:
Purpose By envisioning the learning environment as an eco-social system, this study aims to map interrelated enablers of students’ sustainability-oriented learning (SoL) in the context of a university course at the interface of science and society. Design/methodology/approach A case-study approach was used to delineate what enables student learning in a university-wide transdisciplinary Master of Science course. A sample of 102 students, university and societal stakeholders participated to this study, by sharing their experiences and views through focus groups and questionnaires. Findings A main finding is the development of a configuration of six intertwined enablers that through their interplay help to cultivate students’ SoL, in the course under exploration. Originality/value This study paves the way for a re-orientation of how to explore learning in complex environments. It shows that adopting a relational, situated and systems approach is not only feasible but is also desirable to understand and guide learning practices in complex environments.
17
Abouheaf, Mohammed, Wail Gueaieb, and Davide Spinello. "Online Multi-Objective Model-Independent Adaptive Tracking Mechanism for Dynamical Systems." Robotics 8, no. 4 (September 22, 2019): 82. http://dx.doi.org/10.3390/robotics8040082.
Full textAbstract:
The optimal tracking problem is addressed in the robotics literature by using a variety of robust and adaptive control approaches. However, these schemes are associated with implementation limitations such as applicability in uncertain dynamical environments with complete or partial model-based control structures, complexity and integrity in discrete-time environments, and scalability in complex coupled dynamical systems. An online adaptive learning mechanism is developed to tackle the above limitations and provide a generalized solution platform for a class of tracking control problems. This scheme minimizes the tracking errors and optimizes the overall dynamical behavior using simultaneous linear feedback control strategies. Reinforcement learning approaches based on value iteration processes are adopted to solve the underlying Bellman optimality equations. The resulting control strategies are updated in real time in an interactive manner without requiring any information about the dynamics of the underlying systems. Means of adaptive critics are employed to approximate the optimal solving value functions and the associated control strategies in real time. The proposed adaptive tracking mechanism is illustrated in simulation to control a flexible wing aircraft under uncertain aerodynamic learning environment.
18
Celik, Suleyman, and Sitki Corbacioglu. "Organizational Learning In Adapting To Dynamic Disaster Environments In Southern Turkey." Journal of Asian and African Studies 53, no. 2 (November 16, 2016): 217–32. http://dx.doi.org/10.1177/0021909616677368.
Full textAbstract:
Using a theoretical framework based on complex adaptive systems and organizational learning, the study compares and contrasts the network structures of two disaster response systems following the 2006 avian influenza crisis and the 2011 Van earthquake in Turkey. This study emphasizes the reorganization of Turkish disaster response in 2009 and its impact in response to 2011 Van earthquake. The research utilizes data from content analysis of news reports from the Turkish daily newspapers Cumhuriyet and Sabah from 28 December 2005 to 17 January 2006 for the avian influenza, and Hurriyet from 23 October 2011 to 8 November 2011 for the 2011 Van earthquake, respectively. The research has used social network analysis and small world ratio based on the content analysis data to compare and evaluate the network structures of the two response systems. Findings indicate that the Turkish disaster system, to some degree, learned from the previous disaster and was therefore better managed. However, the system still remained very centralized and multi-sectoral involvement is still weak.
19
Fu, Jingyuan, Meng Sun, and Minhong Wang. "Simulation-Assisted Learning about a Complex Economic System: Impact on Low- and High-Achieving Students." Sustainability 14, no. 10 (May 16, 2022): 6036. http://dx.doi.org/10.3390/su14106036.
Full textAbstract:
Sustainable learning requires students to develop knowledge and skills for survival in increasingly complex and dynamic environments. The development of systems thinking skills for exploring complex dynamic systems is regarded as crucial to sustainable learning. To facilitate student thinking and learning about complex systems, computer simulations have been widely promoted. However, learning using computer simulations involves complex cognitive processes, which may impose a high level of cognitive demand on learners, especially on low achievers. It remains unclear whether and how high- and low-achieving students may benefit differently from learning with computer simulations. To address the gap, we conducted this study with university students who participated in simulation-assisted learning about the economy as a complex system. The results show that the students developed subject knowledge and systems thinking skills by the end of the study; high-achievers outperformed low-achievers in a subject knowledge test, but there were no significant differences between the two groups in their systems thinking skills, cognitive load, and affective experience. The findings indicate that both low- and high-achieving students can benefit from simulation-assisted learning of a complex system. In addition to developing systems thinking skills, there is a need to help students to improve the construction of their subject knowledge when learning with computer simulations.
20
Grob, Robin, Pauline N. Fleischmann, and Wolfgang Rössler. "Learning to navigate – how desert ants calibrate their compass systems." Neuroforum 25, no. 2 (May 27, 2019): 109–20. http://dx.doi.org/10.1515/nf-2018-0011.
Full textAbstract:
Abstract Navigating through the environment is a challenging task that animals cope with on a daily basis. Many animal species have impressive capabilities to navigate in complex or even harsh environments. Cataglyphis desert ants are a famous example. These ants use a remarkable navigational repertoire to find their way home after far-reaching foraging trips. How do naïve ants calibrate their visual navigational systems? The ants perform stereotyped sequences of learning walks before switching from tasks inside the darkness of their nest, to foraging under bright sunlight. Here, naïve ants align nest-directed views using the earth’s magnetic field as a compass reference. Neuronal plasticity was mapped in two visual pathways to higher brain centers during this transition. Both their first exposure to light, and the performance of learning walks lead to distinct changes in synaptic circuits along both visual pathways, reflecting calibration and memory formation in the ants’ visual compass systems.
21
Chen, Hongyi, Yu Zhang, Uzair Aslam Bhatti, and Mengxing Huang. "Safe Decision Controller for Autonomous DrivingBased on Deep Reinforcement Learning inNondeterministic Environment." Sensors 23, no. 3 (January 20, 2023): 1198. http://dx.doi.org/10.3390/s23031198.
Full textAbstract:
Autonomous driving systems are crucial complicated cyber–physical systems that combine physical environment awareness with cognitive computing. Deep reinforcement learning is currently commonly used in the decision-making of such systems. However, black-box-based deep reinforcement learning systems do not guarantee system safety and the interpretability of the reward-function settings in the face of complex environments and the influence of uncontrolled uncertainties. Therefore, a formal security reinforcement learning method is proposed. First, we propose an environmental modeling approach based on the influence of nondeterministic environmental factors, which enables the precise quantification of environmental issues. Second, we use the environment model to formalize the reward machine’s structure, which is used to guide the reward-function setting in reinforcement learning. Third, we generate a control barrier function to ensure a safer state behavior policy for reinforcement learning. Finally, we verify the method’s effectiveness in intelligent driving using overtaking and lane-changing scenarios.
22
TUMER, KAGAN, and NEWSHA KHANI. "LEARNING FROM ACTIONS NOT TAKEN IN MULTIAGENT SYSTEMS." Advances in Complex Systems 12, no. 04n05 (August 2009): 455–73. http://dx.doi.org/10.1142/s0219525909002301.
Full textAbstract:
In large cooperative multiagent systems, coordinating the actions of the agents is critical to the overall system achieving its intended goal. Even when the agents aim to cooperate, ensuring that the agent actions lead to good system level behavior becomes increasingly difficult as systems become larger. One of the fundamental difficulties in such multiagent systems is the slow learning process where an agent not only needs to learn how to behave in a complex environment, but also needs to account for the actions of other learning agents. In this paper, we present a multiagent learning approach that significantly improves the learning speed in multiagent systems by allowing an agent to update its estimate of the rewards (e.g. value function in reinforcement learning) for all its available actions, not just the action that was taken. This approach is based on an agent estimating the counterfactual reward it would have received had it taken a particular action. Our results show that the rewards on such "actions not taken" are beneficial early in training, particularly when only particular "key" actions are used. We then present results where agent teams are leveraged to estimate those rewards. Finally, we show that the improved learning speed is critical in dynamic environments where fast learning is critical to tracking the underlying processes.
23
Salzman, Marilyn C., Chris Dede, R. Bowen Loftin, and Jim Chen. "A Model for Understanding How Virtual Reality Aids Complex Conceptual Learning." Presence: Teleoperators and Virtual Environments 8, no. 3 (June 1999): 293–316. http://dx.doi.org/10.1162/105474699566242.
Full textAbstract:
Designers and evaluators of immersive virtual reality systems have many ideas concerning how virtual reality can facilitate learning. However, we have little information concerning which of virtual reality's features provide the most leverage for enhancing understanding or how to customize those affordances for different learning environments. In part, this reflects the truly complex nature of learning. Features of a learning environment do not act in isolation; other factors such as the concepts or skills to be learned, individual characteristics, the learning experience, and the interaction experience all play a role in shaping the learning process and its outcomes. Through Project Science Space, we have been trying to identify, use, and evaluate immersive virtual reality's affordances as a means to facilitate the mastery of complex, abstract concepts. In doing so, we are beginning to understand the interplay between virtual reality's features and other important factors in shaping the learning process and learning outcomes for this type of material. In this paper, we present a general model that describes how we think these factors work together and discuss some of the lessons we are learning about virtual reality's affordances in the context of this model for complex conceptual learning.
24
Wang, Minghui, Bi Zeng, and Qiujie Wang. "Research on Motion Planning Based on Flocking Control and Reinforcement Learning for Multi-Robot Systems." Machines 9, no. 4 (April 1, 2021): 77. http://dx.doi.org/10.3390/machines9040077.
Full textAbstract:
Robots have poor adaptive ability in terms of formation control and obstacle avoidance control in unknown complex environments. To address this problem, in this paper, we propose a new motion planning method based on flocking control and reinforcement learning. It uses flocking control to implement a multi-robot orderly motion. To avoid the trap of potential fields faced during flocking control, the flocking control is optimized, and the strategy of wall-following behavior control is designed. In this paper, reinforcement learning is adopted to implement the robotic behavioral decision and to enhance the analytical and predictive abilities of the robot during motion planning in an unknown environment. A visual simulation platform is developed in this paper, on which researchers can test algorithms for multi-robot motion control, such as obstacle avoidance control, formation control, path planning and reinforcement learning strategy. As shown by the simulation experiments, the motion planning method presented in this paper can enhance the abilities of multi-robot systems to self-learn and self-adapt under a fully unknown environment with complex obstacles.
25
Juillé, Hugues, and Jordan B. Pollack. "Coevolutionary Learning and the Design of Complex Systems." Advances in Complex Systems 02, no. 04 (December 1999): 371–93. http://dx.doi.org/10.1142/s0219525999000199.
Full textAbstract:
Complex systems composed of a large number of loosely coupled entities, with no central coordination offer a number of attractive properties like scalability, robustness or massively distributed computation. However, designing such complex systems presents some challenging issues that are difficult to tackle with traditional top-down engineering methodologies. Coevolutionary learning, which involves the embedding of adaptive learning agents in a fitness environment that dynamically responds to their progress, is proposed as a paradigm to explore a space of complex system designs. It is argued that coevolution offers a flexible framework for the implementation of search heuristics that can efficiently exploit some of the structural properties exhibited by such state spaces. However, several drawbacks have to be overcome in order for coevolutionary learning to achieve continuous progress in the long term. This paper presents some of those problems and introduces a new strategy based on the concept of an "ideal" trainer to address them. This presentation is illustrated with a case study: the discovery of cellular automata rules to implement a classification task. The application of the "ideal" trainer paradigm to that problem resulted in a significant improvement over previously known best rules for this task.
26
Шульга and I. Shulga. "E-Learning Course Structure." Profession-Oriented School 3, no. 3 (June 17, 2015): 51–55. http://dx.doi.org/10.12737/11750.
Full textAbstract:
In the article we’ve tried to define the most common system of educational courses for different e-learning environments and the expediency of such systems. The research led us to anin-demand complex system of five multi-linked units: Start Unit with preliminary information on the professional sphere, Basic Unit with the main part of educational information on the professional sphere, Unit of Daily Pedagogic Diagnostics for routinepedagogic assessment, Research Unit for immersion learning, and Unit of Final Pedagogic Diagnostics containing all necessary instruments for final pedagogic assessment.
27
Tadesse, Aklilu Tilahun, and Pål Ingebrigt Davidsen. "Framework to support personalized learning in complex systems." Journal of Applied Research in Higher Education 12, no. 1 (July 22, 2019): 57–85. http://dx.doi.org/10.1108/jarhe-11-2018-0250.
Full textAbstract:
Purpose Numerous studies document that students struggle to comprehend complex dynamic systems (CDS). The purpose of this paper is to describe a design framework applied to the creation of a personalized and adaptive online interactive learning environment (OILE) to support students in their study of CDS. Design/methodology/approach A holistic instructional design is applied in five steps to create the OILE. The OILE has the following characteristics: first, it presents a complex, dynamic problem that learners should address in its entirety. It then allows learners to progress through a sequence of learning tasks from easy to complex. Second, after completion of each learning task, the OILE provides learners with supportive information based on their individual performance. The support fades away as learners gain expertise. Third, the OILE tracks and collects information on learners’ progress and generates learning analytics. The OILE was tested on 57 system dynamics students. Findings This paper provides evidence that supports the theoretical design framework from the literature. It also provides a sample from students’ progress logs to demonstrate how the OILE practically facilitated students’ cognitive development. In addition, it provides empirical evidence regarding students’ attitudes toward the OILE that was obtained from administering two questionnaires. Originality/value In light of supportive evidence from the literature, students’ progress in the cognitive domain, and confirmative response in the affective domain, the use of personalized and adaptive OILE to support learning about CDS is considered promising.
28
Dyer, Adrian G., Angelique C. Paulk, and David H. Reser. "Colour processing in complex environments: insights from the visual system of bees." Proceedings of the Royal Society B: Biological Sciences 278, no. 1707 (December 8, 2010): 952–59. http://dx.doi.org/10.1098/rspb.2010.2412.
Full textAbstract:
Colour vision enables animals to detect and discriminate differences in chromatic cues independent of brightness. How the bee visual system manages this task is of interest for understanding information processing in miniaturized systems, as well as the relationship between bee pollinators and flowering plants. Bees can quickly discriminate dissimilar colours, but can also slowly learn to discriminate very similar colours, raising the question as to how the visual system can support this, or whether it is simply a learning and memory operation. We discuss the detailed neuroanatomical layout of the brain, identify probable brain areas for colour processing, and suggest that there may be multiple systems in the bee brain that mediate either coarse or fine colour discrimination ability in a manner dependent upon individual experience. These multiple colour pathways have been identified along both functional and anatomical lines in the bee brain, providing us with some insights into how the brain may operate to support complex colour discrimination behaviours.
29
Silva, Felipe Leno Da, and Anna Helena Reali Costa. "A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems." Journal of Artificial Intelligence Research 64 (March 11, 2019): 645–703. http://dx.doi.org/10.1613/jair.1.11396.
Full textAbstract:
Multiagent Reinforcement Learning (RL) solves complex tasks that require coordination with other agents through autonomous exploration of the environment. However, learning a complex task from scratch is impractical due to the huge sample complexity of RL algorithms. For this reason, reusing knowledge that can come from previous experience or other agents is indispensable to scale up multiagent RL algorithms. This survey provides a unifying view of the literature on knowledge reuse in multiagent RL. We define a taxonomy of solutions for the general knowledge reuse problem, providing a comprehensive discussion of recent progress on knowledge reuse in Multiagent Systems (MAS) and of techniques for knowledge reuse across agents (that may be actuating in a shared environment or not). We aim at encouraging the community to work towards reusing all the knowledge sources available in a MAS. For that, we provide an in-depth discussion of current lines of research and open questions.
30
Kose, Seima, Yumi Suenaga, and Kazumasa Oida. "Real-time Attack-Scheme Visualization for Complex Exploit Technique Comprehension." International Journal of Machine Learning and Computing 11, no. 2 (March 2021): 164–69. http://dx.doi.org/10.18178/ijmlc.2021.11.2.1030.
Full textAbstract:
Recent exploit techniques are highly complex, and it is not easy for cybersecurity learners to understand the attack strategies quickly and clearly. For efficient and comprehensive learning, this paper proposes an attack-scheme visualization system that fulfills three requirements: attack progress visualization in real-time, memory and register-level description, and concise description of the attack schemes. This paper exemplifies two cases: stack buffer overflow and ROP attacks, and demonstrates how the system operates and how users can learn that existing defense technologies are effective or ineffective depending on the execution environments.
31
Deegan, Robin. "Complex Mobile Learning that Adapts to Learners' Cognitive Load." International Journal of Mobile and Blended Learning 7, no. 1 (January 2015): 13–24. http://dx.doi.org/10.4018/ijmbl.2015010102.
Full textAbstract:
Mobile learning is cognitively demanding and frequently the ubiquitous nature of mobile computing means that mobile devices are used in cognitively demanding environments. This paper examines the use of mobile devices from a Learning, Usability and Cognitive Load Theory perspective. It suggests scenarios where these fields interact and presents an experiment which determined that several sources of cognitive load can be measured simultaneously by the learner. The experiment also looked at the interaction between these cognitive load types and found that distraction did not affect the performance or cognitive load associated with a learning task but it did affect the perception of the cognitive load associated with using the application interface. This paper concludes by suggesting ways in which mobile learning can benefit by developing cognitive load aware systems that could detect and change the difficulty of the learning task based on the cognitive state of the learner.
32
Martínez, Moisés, Javier García, and Fernando Fernández. "On-Line Case-Based Policy Learning for Automated Planning in Probabilistic Environments." International Journal of Information Technology & Decision Making 17, no. 03 (May 2018): 763–800. http://dx.doi.org/10.1142/s0219622018500086.
Full textAbstract:
Many robotic control architectures perform a continuous cycle of sensing, reasoning and acting, where that reasoning can be carried out in a reactive or deliberative form. Reactive methods are fast and provide the robot with high interaction and response capabilities. Deliberative reasoning is particularly suitable in robotic systems because it employs some form of forward projection (reasoning in depth about goals, pre-conditions, resources and timing constraints) and provides the robot reasonable responses in situations unforeseen by the designer. However, this reasoning, typically conducted using Artificial Intelligence techniques like Automated Planning (AP), is not effective for controlling autonomous agents which operate in complex and dynamic environments. Deliberative planning, although feasible in stable situations, takes too long in unexpected or changing situations which require re-planning. Therefore, planning cannot be done on-line in many complex robotic problems, where quick responses are frequently required. In this paper, we propose an alternative approach based on case-based policy learning which integrates deliberative reasoning through AP and reactive response time through reactive planning policies. The method is based on learning planning knowledge from actual experiences to obtain a case-based policy. The contribution of this paper is two fold. First, it is shown that the learned case-based policy produces reasonable and timely responses in complex environments. Second, it is also shown how one case-based policy that solves a particular problem can be reused to solve a similar but more complex problem in a transfer learning scope.
33
Oruganti, Rakesh, Jeeshitha J, and Rama Koteswara Rao G. "A Extensive Study on DDosBotnet Attacks in Multiple Environments Using Deep Learning and Machine Learning Techniques." ECS Transactions 107, no. 1 (April 24, 2022): 15181–93. http://dx.doi.org/10.1149/10701.15181ecst.
Full textAbstract:
Every organization provides security for their systems, servers, and other I.T. infrastructure resources using regular anti-viruses and malware detection software. With the increase of access to smart devices and appliances through secured and unsecured networks, there is a requirement to design an intelligent detection tool using deep learning techniques to handle complex vulnerabilities efficiently. The system should have the capability to prevent and control attacks from unreliable sources. The system administrator should immediately notify the system administrator—the proposed research studies about the DDoSBot net attacks in IoT devices. BotNets are Zombie servers, which can attack an extensive network with its automation process by designing a combination of prevention and detection mechanisms in a virtual environment that can access the cloud environment.
34
Luster, Maya S., and Brandon J. Pitts. "A Preliminary Investigation into Learning Behaviors in Complex Environments for Human-in-the-Loop Cyber-Physical Systems." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 65, no. 1 (September 2021): 42–46. http://dx.doi.org/10.1177/1071181321651222.
Full textAbstract:
The field of Cyber-Physical Systems (CPS) is increasingly recognizing the importance of integrating Human Factors for Human-in-the-loop CPS (HiLCPS) developments. This is because psychological, physiological, and behavioral characteristics of humans can be used to predict human-machine interactions. The goal of this pilot study is to collect initial data to determine whether driving and eye tracking metrics can provide evidence of learning for a CPS project. Six participants performed a series of 12 repeated obstacle avoidance tasks in manual driving. Lane deviations and fixation-related eye data were recorded for each trial. Overall, participants displayed either conservation/safe or aggressive/risky in their lateral position with respect to the obstacle during successive trials. Also, eye tracking metrics were not significantly affected by trial number, but observational trends suggest their potential for aiding in understanding adjustments humans make in learning. Results can inform predictive modeling algorithms that can anticipate and mitigate potential problems in real-time.
35
Gonzalez-Rodriguez, Diego, and Jose Rodolfo Hernandez-Carrion. "Decentralization and heterogeneity in complex adaptive systems." Kybernetes 44, no. 6/7 (June 1, 2015): 1082–93. http://dx.doi.org/10.1108/k-01-2015-0030.
Full textAbstract:
Purpose – Following a bacterial-based modeling approach, the authors want to model and analyze the impact of both decentralization and heterogeneity on group behavior and collective learning. The paper aims to discuss these issues. Design/methodology/approach – Inspired by bacterial conjugation, the authors have defined an artificial society in which agents’ strategies adapt to changes in resources location, allowing migration, and survival in a dynamic sugarscape-like scenario. To study the impact of these variables the authors have simulated a scenario in which resources are limited and localized. The authors also have defined three constraints in genetic information processing (inhibition of plasmid conjugation, inhibition of plasmid reproduction and inhibition of plasmid mutation). Findings – The results affirmed the hypothesis that efficiency of group adaptation to dynamic environments is better when societies are varied and distributed than when they are homogeneous and centralized. Originality/value – The authors have demonstrated that in a model based on free interactions among autonomous agents, optimal results emerge by incrementing heterogeneity levels and decentralization of communication structures, leading to a global adaptation of the system. This organic approach to model peer-to-peer dynamics in complex adaptive systems (CAS) is what the authors have named “bacterial-based algorithms” because agents exchange strategic information in the same way that bacteria use conjugation and share genome.
36
Onyekpe, Uche, Vasile Palade, and Stratis Kanarachos. "Learning to Localise Automated Vehicles in Challenging Environments Using Inertial Navigation Systems (INS)." Applied Sciences 11, no. 3 (January 30, 2021): 1270. http://dx.doi.org/10.3390/app11031270.
Full textAbstract:
An approach based on Artificial Neural Networks is proposed in this paper to improve the localisation accuracy of Inertial Navigation Systems (INS)/Global Navigation Satellite System (GNSS) based aided navigation during the absence of GNSS signals. The INS can be used to continuously position autonomous vehicles during GNSS signal losses around urban canyons, bridges, tunnels and trees, however, it suffers from unbounded exponential error drifts cascaded over time during the multiple integrations of the accelerometer and gyroscope measurements to position. More so, the error drift is characterised by a pattern dependent on time. This paper proposes several efficient neural network-based solutions to estimate the error drifts using Recurrent Neural Networks, such as the Input Delay Neural Network (IDNN), Long Short-Term Memory (LSTM), Vanilla Recurrent Neural Network (vRNN), and Gated Recurrent Unit (GRU). In contrast to previous papers published in literature, which focused on travel routes that do not take complex driving scenarios into consideration, this paper investigates the performance of the proposed methods on challenging scenarios, such as hard brake, roundabouts, sharp cornering, successive left and right turns and quick changes in vehicular acceleration across numerous test sequences. The results obtained show that the Neural Network-based approaches are able to provide up to 89.55% improvement on the INS displacement estimation and 93.35% on the INS orientation rate estimation.
37
Lamas, Daniel, Mario Soilán, Javier Grandío, and Belén Riveiro. "Automatic Point Cloud Semantic Segmentation of Complex Railway Environments." Remote Sensing 13, no. 12 (June 14, 2021): 2332. http://dx.doi.org/10.3390/rs13122332.
Full textAbstract:
The growing development of data digitalisation methods has increased their demand and applications in the transportation infrastructure field. Currently, mobile mapping systems (MMSs) are one of the most popular technologies for the acquisition of infrastructure data, with three-dimensional (3D) point clouds as their main product. In this work, a heuristic-based workflow for semantic segmentation of complex railway environments is presented, in which their most relevant elements are classified, namely, rails, masts, wiring, droppers, traffic lights, and signals. This method takes advantage of existing methodologies in the field for point cloud processing and segmentation, taking into account the geometry and spatial context of each classified element in the railway environment. This method is applied to a 90-kilometre-long railway lane and validated against a manual reference on random sections of the case study data. The results are presented and discussed at the object level, differentiating the type of the element. The indicators F1 scores obtained for each element are superior to 85%, being higher than 99% in rails, the most significant element of the infrastructure. These metrics showcase the quality of the algorithm, which proves that this method is efficient for the classification of long and variable railway sections, and for the assisted labelling of point cloud data for future applications based on training supervised learning models.
38
Turner, John, Dave Snowden, and Nigel Thurlow. "The Substrate-Independence Theory: Advancing Constructor Theory to Scaffold Substrate Attributes for the Recursive Interaction between Knowledge and Information." Systems 10, no. 1 (January 5, 2022): 7. http://dx.doi.org/10.3390/systems10010007.
Full textAbstract:
The substrate-independence theory utilizes sensemaking techniques to provide cognitively based scaffolds that guide and structure learning. Scaffolds are cognitive abstractions of constraints that relate to information within a system. The substrate-independence theory concentrates on the flow of information as the underlying property of the host system. The substrate-independence theory views social systems as complex adaptive systems capable of repurposing their structure to combat external threats by utilizing constructors and substrates. Constructor theory is used to identify potential construction tasks, the legitimate input and output states that are possible, to map the desired change in the substrate’s attributes. Construction tasks can be mapped in advance for ordered and known environments. Construction tasks may also be mapped in either real-time or post hoc for unordered and complex environments using current sensemaking techniques. Mapping of the construction tasks in real-time becomes part of the landscape, and scaffolds are implemented to aid in achieving the desired state or move to a more manageable environment (e.g., from complex to complicated).
39
Betz, Joseph A. "Computer Games: Increase Learning in an Interactive Multidisciplinary Environment." Journal of Educational Technology Systems 24, no. 2 (December 1995): 195–205. http://dx.doi.org/10.2190/119m-brmu-j8hc-xm6f.
Full textAbstract:
Our educational system is compartmentalized into various disciplines. Students learn to solve discipline specific problems rather than complex multidisciplinary problems. Commercially available computer games and simulators do not distinguish between academic disciplines. These games illustrate interactive whole systems, organize and integrate complex skills, and show how individual actions affect complex systems. Computer games and simulators enhance learning through visualization, experimentation, and creativity of play. Increased learning occurs by problem solving in a complex interactive multidisciplinary environment and by “seeing” causal relationships between individual actions and whole systems. The broader implications of using computer games in the classroom are for students to become more effective learners and thinkers enabling them to make connections across the curriculum. This article develops the ideas from the preliminary results of an ongoing experiment in a freshman engineering technology course at SUNY Farmingdale [1].1 The experiment measured an increase in learning using the computer game Sim City 2000.
40
Zhang, Tingwei, Peng Zhang, Paris Kalathas, Guangxin Wang, and Huaping Liu. "A Machine Learning Approach to Improve Ranging Accuracy with AoA and RSSI." Sensors 22, no. 17 (August 25, 2022): 6404. http://dx.doi.org/10.3390/s22176404.
Full textAbstract:
Ranging accuracy is a critical parameter in time-based indoor positioning systems. Indoor environments often have complex structures, which make centimeter-level-accurate ranging a challenging task. This study proposes a new distance measurement method to decrease the ranging error in multipath environment. Our method uses an artificial neural network that utilizes the received signal strength indicator along with a signal’s angle of arrival to calculate the line-of-sight distance. This combination results in a significant reduction of the error caused by multipath effects that common RSSI-based methods suffer from. It outperforms traditional ranging methods while the implementation complexity is kept low.
41
Nantogma, Sulemana, Keyu Pan, Weilong Song, Renwei Luo, and Yang Xu. "Towards Realizing Intelligent Coordinated Controllers for Multi-USV Systems Using Abstract Training Environments." Journal of Marine Science and Engineering 9, no. 6 (May 22, 2021): 560. http://dx.doi.org/10.3390/jmse9060560.
Full textAbstract:
Unmanned autonomous vehicles for various civilian and military applications have become a particularly interesting research area. Despite their many potential applications, a related technological challenge is realizing realistic coordinated autonomous control and decision making in complex and multi-agent environments. Machine learning approaches have been largely employed in simplified simulations to acquire intelligent control systems in multi-agent settings. However, the complexity of the physical environment, unrealistic assumptions, and lack of abstract physical environments derail the process of transition from simulation to real systems. This work presents a modular framework for automated data acquisition, training, and the evaluation of multiple unmanned surface vehicles controllers that facilitate prior knowledge integration and human-guided learning in a closed-loop. To realize this, we first present a digital maritime environment of multiple unmanned surface vehicles that abstracts the real-world dynamics in our application domain. Then, a behavior-driven artificial immune-inspired fuzzy classifier systems approach that is capable of optimizing agents’ behaviors and action selection in a multi-agent environment is presented. Evaluation scenarios of different combat missions are presented to demonstrate the performance of the system. Simulation results show that the resulting controllers can achieved an average wining rate between 52% and 98% in all test cases, indicating the effectiveness of the proposed approach and its feasibility in realizing adaptive controllers for efficient multiple unmanned systems’ cooperative decision making. We believe that this system can facilitate the simulation, data acquisition, training, and evaluation of practical cooperative unmanned vehicles’ controllers in a closed-loop.
42
Yuan, Mingxin, Yafeng Jiang, Xiaobin Hua, Binbin Wang, and Yi Shen. "A real-time immune planning algorithm incorporating a specific immune mechanism for multi-robots in complex environments." Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering 231, no. 1 (January 2017): 29–42. http://dx.doi.org/10.1177/0959651816677198.
Full textAbstract:
To solve the real-time path planning of multi-robots in complex environments, a new immune planning algorithm incorporating a specific immune mechanism is presented. In the immune planning algorithm incorporating a specific immune mechanism, a new coding format for an antibody is first defined according to the impact of the obstacle distribution on the obstacle avoidance behaviors of multi-robots. Then, a new robot immune dynamic model for antibody selection is designed in terms of different impacts of obstacles and targets on robot behaviors. Finally, aiming at the local minimum problem in complex environments and inspired by the specific immune mechanism, a series of appropriate avoidance behaviors are selected through the calculation of a specific immune mechanism to help robots walk out of local minima. In addition, to solve deadlock situations, a learning strategy for the antibody concentration is presented. Compared with four related immune planning algorithms—an improved artificial potential field, a rapidly exploring random tree algorithm, a D* algorithm and a A* algorithm—the simulation results in four static environments show that the paths planned by immune planning algorithm incorporating a specific immune mechanism are the shortest and the path smoothness is generally the highest, which shows its strong planning capability in multi-obstacle environments. The simulation result in a dynamic environment with local minima shows that the immune planning algorithm incorporating a specific immune mechanism has strong planning ability in dynamic obstacle avoidance and in escaping from local minima. Additionally, an experiment in a multi-robot environment shows that two robots can not only avoid static obstacles but also avoid dynamic obstacles, which further supports the validity of the proposed immune planning algorithm incorporating a specific immune mechanism for multi-robots in real environments.
43
Mendes, M., C. Gomes, P. Marques-Quinteiro, P. Lind, and L. Curral. "Promoting learning and innovation in organizations through complexity leadership theory." Team Performance Management 22, no. 5/6 (August 8, 2016): 301–9. http://dx.doi.org/10.1108/tpm-02-2016-0004.
Full textAbstract:
Purpose Current organizations face a complex competitive landscape driven by globalization and technology that puts them in the course of a new economic age. This complexity stresses learning and innovation as fundamental mechanisms for organizational survival. This paper aims to propose that how learning and innovation emerge and affect organizational performance can be better understood through the complexity leadership theory. Design/methodology/approach The authors review literature on complexity leadership theory, learning and innovation in complex bureaucratic environments and then present reflections regarding how learning and innovation can be achieved through the interaction of three complexity leadership functions: adaptive, administrative and enabling. This conceptual framework suggests that individuals are in constant interaction, exchange information, influence each other and collectively produce emergent properties that promote effective learning and innovation. Findings We propose that learning and innovation can be better achieved in organizations if the complexity leadership theory is applied as an alternative to centralized forms of influence and control. Originality/value This paper presents a reflection on the benefits of the complexity leadership theory as an alternative framework to understand organizational leadership. Furthermore, this paper proposes that the complexity leadership theory is more adequate to generate learning and innovation in complex, fast-changing work environments.
44
Torrents, Carlota, Natàlia Balagué, Robert Hristovski, Maricarmen Almarcha, and J. A. Scott Kelso. "Metastable Coordination Dynamics of Collaborative Creativity in Educational Settings." Sustainability 13, no. 5 (March 2, 2021): 2696. http://dx.doi.org/10.3390/su13052696.
Full textAbstract:
Educational systems consider fostering creativity and cooperation as two essential aims to nurture future sustainable citizens. The cooperative learning approach proposes different pedagogical strategies for developing creativity in students. In this paper, we conceptualize collaborative creativity under the framework of coordination dynamics and, specifically, we base it on the formation of spontaneous multiscale synergies emerging in complex living systems when interacting with cooperative/competitive environments. This conception of educational agents (students, teachers, institutions) changes the understanding of the teaching/learning process and the traditional roles assigned to each agent. Under such an understanding, the design and co-design of challenging and meaningful learning environments is a key aspect to promote the spontaneous emergence of multiscale functional synergies and teams (of students, students and teachers, teachers, institutions, etc.). According to coordination dynamics, cooperative and competitive processes (within and between systems and their environments) are seen not as opposites but as complementary pairs, needed to develop collaborative creativity and increase the functional diversity potential of teams. Adequate manipulation of environmental and personal constraints, nested in different level and time scales, and the knowledge of their critical (tipping) points are key aspects for an adequate design of learning environments to develop synergistic creativity.
45
Hamilton, John, and Singwhat Tee. "The cone-of-learning: a visual comparison of learning systems." TQM Journal 28, no. 1 (January 11, 2016): 21–39. http://dx.doi.org/10.1108/tqm-09-2013-0111.
Full textAbstract:
Purpose – Four learning modes, interacting through students as different learning systems, are mapped into a cone-of-learning continuum that allows tertiary institutions to visually re-consider where within their cone-of-learning, they choose to position their learning approaches. Two forms of blended learning are also distinguished. The paper aims to discuss these issues. Design/methodology/approach – Undergraduate law, business, IT, and creative arts student perceptions are structural equation modelled (SEM) into traditional, blended-enabled, blended-enhanced, and flexible learning systems. Findings – Within the SEM derived learning cone-of-learning continuum, a migration from traditional learning systems towards blended and flexible learning systems typically offers higher-net levels of undergraduate student learning experiences and outcomes. Research limitations/implications – The authors do not capture learning system feedback loops, but the cone-of-learning approaches can position against chosen competitors. The authors recognise benchmark, positioning, and transferability differences may exist between different tertiary institutions; different learning areas; and different countries of operation. Cone-of-learning studies can expand to capture student perceptions of their value acquisitions, overall satisfaction, plus trust, and loyalty considerations. Practical implications – The cone-of-learning shows shifts towards flexibility as generating higher student learning experiences, higher student learning outcomes, and as flexible technologies mature this demands higher student inputs. These interactive experiential systems approaches can readily incorporate new technologies, gamifications, and engagements which are testable for additional student deep-learning contributions. Experiential deep-learning systems also have wide industrial applications. Social implications – Understanding the continuum of transitioning between and across deeper-learning systems offers general social benefit. Originality/value – Learning system studies remain complex, variable systems, dependent on instructors, students, and their shared experiential engagements environments. This cone-of-learning continuum approach is useful for educators, business, and societal life-long learners who seek to gauge learning and outcomes.
46
Ghili, Soheil, Serima Nazarian, Madjid Tavana, Sepehr Keyvanshokouhi, and Mohammad Taghi Isaai. "A Complex Systems Paradox of Organizational Learning and Knowledge Management." International Journal of Knowledge-Based Organizations 3, no. 3 (July 2013): 53–72. http://dx.doi.org/10.4018/ijkbo.2013070104.
Full textAbstract:
Many organizations are striving to survive and remain competitive in the current uncertain and rapidly changing economic environment. Businesses must innovate to face this volatility and maintain their competitiveness. Organizational learning is a complex process with many interrelated elements linking knowledge management with organizational innovation. In this paper we use several theories (i.e., organizational learning, knowledge management, organizational innovation, complexity theory, and systems theory) to discover and study the interrelationships among the organizational learning elements. The purpose of this paper is threefold: (1) We identify organizational learning as a mediating variable between knowledge management and organizational innovation; (2) We further present a paradox where decisions that are expected to improve organizational learning, surprisingly do not work; and (3) We show this paradox is not the result of overlooking organizational learning elements, but rather, caused by neglecting to consider the complex interrelationships and interdependencies among them.
47
Barberis Canonico, Lorenzo, Nathan J. McNeese, and Marissa L. Shuffler. "Stable Teamwork Marriages in Healthcare: Applying Machine Learning to Surgeon-Nurse-Patient Matching." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 62, no. 1 (September 2018): 1202–6. http://dx.doi.org/10.1177/1541931218621276.
Full textAbstract:
Hospitals are plagued with a multitude of logistical challenges amplified by a time-sensitive and high intensity environment. These conditions have resulted in burnout among both doctors and nurses as they work tirelessly to provide critical care to patients in need. We propose a new machine-learning-powered matching mechanism that manages the surgeon-nurse-patient assignment process in an efficient way that saves time and energy for hospitals, enabling them to focus almost entirely on delivering effective care. Through this design, we show how incorporating artificial intelligence into management systems enables teams of all sizes to meaningfully coordinate in highly chaotic and complex environments.
48
Martín, Diego, Borja Bordel, Ramón Alcarria, and Yone Castro. "Improving Learning Tasks for Mentally Handicapped People Using AmI Environments Based on Cyber-Physical Systems." Mobile Information Systems 2018 (2018): 1–12. http://dx.doi.org/10.1155/2018/8198379.
Full textAbstract:
A prototype to improve learning tasks for mentally handicapped people is shown in this research paper using ambient intelligence techniques and based on cyber-physical systems. The whole system is composed of a worktable, a cyber-glove (both with several RFID and NFC detection zones), and an AmI software application for modeling and workflow guidance. A case study was carried out by the authors where sixteen mentally handicapped people and 3 trainers were involved in the experiment. The experiment consisted in the execution of several memorization tasks of movements of objects using the approach presented in this paper. The results obtained were very interesting, indicating that this kind of solutions are feasible and allow the learning of complex tasks to some types of mentally handicapped people. In addition, at the end of the paper are presented some lessons learned after performing the experimentation.
49
Burov, Oleksandr. "Design features of the synthetic learning environment." Educational Technology Quarterly 2021, no. 4 (December 20, 2021): 6. http://dx.doi.org/10.55056/etq.43.
Full textAbstract:
The article considers the features of the learning transformation in the transition from the usual material-object environment to learning in the digital synthetic environment. Attention is drawn to the fact that nowadays’ students prefer online and blended learning, in which human interaction with technical learning tools not only creates new opportunities, but also requires coordination of their interaction. A brief description of the main features of learning using new technological capabilities is given, highlighting such aspects as virtual and augmented reality, as well as the use of game-oriented technologies with an emphasis on reflexive games. An analysis was made of changes in the properties of a new learning environment from the standpoint of biotechtonics, which develops the principles of accounting the human factor, i.e. the coordination of human capabilities with technical systems in a digital learning environment in which a person is transferred to a new interactive space using devices that reflect signals in his/her sensory organs and devices, accepting different actions. Variants of teaching technologies based on new principles are proposed, which make it possible to improve the quality of assimilation of educational material. It is noted that the basis for creating complex synthetic learning environments are biotechnical systems, which provide a variety of image content management tools for models of these environments, both for the researcher and the student. It is proposed to expand the concept of ``biotechnical system'' by including the so-called ``biotechnical technologies'', which becomes especially relevant in the digital world. The difference between this type of technology lies in the fact that among the technological operations included in them, great importance should be given to operations that are associated with ensuring the safety of work and creating optimal conditions for the resilience and labor activity of a person. At the same time, a person interacts mainly with information technologies, with information and knowledge that affect him/her, but not with material objects, both in the process of management and in the process of studying the outside world to use it effectively.
50
Jesus, Gonçalo, António Casimiro, and Anabela Oliveira. "Using Machine Learning for Dependable Outlier Detection in Environmental Monitoring Systems." ACM Transactions on Cyber-Physical Systems 5, no. 3 (July 2021): 1–30. http://dx.doi.org/10.1145/3445812.
Full textAbstract:
Sensor platforms used in environmental monitoring applications are often subject to harsh environmental conditions while monitoring complex phenomena. Therefore, designing dependable monitoring systems is challenging given the external disturbances affecting sensor measurements. Even the apparently simple task of outlier detection in sensor data becomes a hard problem, amplified by the difficulty in distinguishing true data errors due to sensor faults from deviations due to natural phenomenon, which look like data errors. Existing solutions for runtime outlier detection typically assume that the physical processes can be accurately modeled, or that outliers consist in large deviations that are easily detected and filtered by appropriate thresholds. Other solutions assume that it is possible to deploy multiple sensors providing redundant data to support voting-based techniques. In this article, we propose a new methodology for dependable runtime detection of outliers in environmental monitoring systems, aiming to increase data quality by treating them. We propose the use of machine learning techniques to model each sensor behavior, exploiting the existence of correlated data provided by other related sensors. Using these models, along with knowledge of processed past measurements, it is possible to obtain accurate estimations of the observed environment parameters and build failure detectors that use these estimations. When a failure is detected, these estimations also allow one to correct the erroneous measurements and hence improve the overall data quality. Our methodology not only allows one to distinguish truly abnormal measurements from deviations due to complex natural phenomena, but also allows the quantification of each measurement quality, which is relevant from a dependability perspective. We apply the methodology to real datasets from a complex aquatic monitoring system, measuring temperature and salinity parameters, through which we illustrate the process for building the machine learning prediction models using a technique based on Artificial Neural Networks, denoted ANNODE ( ANN Outlier Detection ). From this application, we also observe the effectiveness of our ANNODE approach for accurate outlier detection in harsh environments. Then we validate these positive results by comparing ANNODE with state-of-the-art solutions for outlier detection. The results show that ANNODE improves existing solutions regarding accuracy of outlier detection.