Search results

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.

This study aims to obtain methods to identify and find the place of damage, which is one of the topics that has always been discussed in structural engineering. The cost of repairing and rehabilitating massive bridges and buildings is very high, highlighting the need to monitor the structures continuously. One way to track the structure's health is to check the cracks in the concrete. Meanwhile, the current methods of concrete crack detection have complex and heavy calculations.

This paper presents a new lightweight architecture based on deep learning for crack classification in concrete structures. The proposed architecture was identified and classified in less time and with higher accuracy than other traditional and valid architectures in crack detection. This paper used a standard dataset to detect two-class and multi-class cracks.

Results show that two images were recognized with 99.53% accuracy based on the proposed method, and multi-class images were classified with 91% accuracy. The low execution time of the proposed architecture compared to other valid architectures in deep learning on the same hardware platform. The use of Adam's optimizer in this research had better performance than other optimizers.

This paper presents a framework based on a lightweight convolutional neural network for nondestructive monitoring of structural health to optimize the calculation costs and reduce execution time in processing.

This study leverages social network analysis (SNA) to visualise the way students interacted with online resources and uses the data obtained from SNA as features for supervised machine learning algorithms to predict whether a student will successfully complete a course.

The exploration and visualisation of the data were first carried out to gain a better understanding of the students, the course(s) each student was enrolled in and each course’s virtual learning resources. Following this, the construction of the social network graphs was performed to depict how each student behaved online before the degree centralities were computed for each of the nodes in a social network graph. Data pre-processing to assign labels based on the final result a student obtained in a course was then performed before we trained and tested models to predict which students did or did not graduate.

The study’s findings demonstrate that the constructed predictive model has good performance, as shown by the accuracy, precision, recall and f-measure metrics. The outcomes also showed that students’ use of online resources is a crucial element that influences how well they perform in their academics.

The similarity index is as low as 9%.

With practical entrepreneurship capabilities becoming ever more important for all university graduates, whether they are starting their own business or adding value to an organisation by innovating, improving, and problem-solving, what role do business incubators (BIs) play in helping to develop these capabilities for students? This chapter aims to better understand the role of BIs as extra-curricular entrepreneurship activity in universities through a narrative account of business incubation practice in three institutions – two in England and one in Australia. Utilising a practice-led methodology, the study is underpinned by social capital theory and a critical realist ontological perspective on incubation’s mechanisms, processes, and structures. Across these examples, there are common underpinning principles of entrepreneurial learning and socio-economic development. However, there are differences in implementation regarding space for incubation. Where the BI is on campus and closely integrated with extra-curricular entrepreneurship activity, this results in a cohesive graduate startup community and ongoing peer support. With no BI present, the opposite is observed. The chapter argues that without the infrastructure to build and maintain a community of nascent entrepreneurs to benefit from sustained peer learning, there can be negative impacts on the entrepreneurs and a visible gap affecting the entrepreneurial ecosystem. The chapter concludes with a practice note providing practical considerations for university BIs in communicating the significance of the incubator peer group to prospective entrepreneurs to improve realistic expectations and potentially improve their reach to entrepreneurs who may be experiencing isolation during their startup journey.

Unstructured data such as images have defied usage in property valuation for a long time. Instead, structured data in tabular format are commonly employed to estimate property prices. This study attempts to quantify the shape of land lots and uses the resultant output as an input variable for subsequent land valuation models.

Imagery data containing land lot shapes are fed into a convolutional neural network, and the shape of land lots is classified into two categories, regular and irregular-shaped. Then, the intermediate output (regularity score) is utilized in four downstream models to estimate land prices: random forest, gradient boosting, support vector machine and regression models.

Quantification of the land lot shapes and their exploitation in valuation led to an improvement in the predictive accuracy for all subsequent models.

The study findings are expected to promote the adoption of elusive price determinants such as the shape of a land lot, appearance of a house and the landscape of a neighborhood in property appraisal practices.

In today’s world, empowering individuals, promoting social cohesion and advancing economic development all hinge on access to high-quality education, prioritizing diversity, inclusion and equality. Rethinking current educational strategies using cyber-physical learning assets is necessary to accommodate the learning inclusivity and equity and escalating demands of a globalized world. There is a pressing demand for evidence to support the efficacy of collaborative learning in transforming curriculum and fostering learner inclusion. However, it is recognized as a pedagogical technique within the quality education domain. This study aims to address this knowledge gap by investigating how hybridized cybergogy paradigms facilitate collaborative learning, focusing on diversity, equity and inclusion, to improve educational quality in higher education.

This study used a qualitative approach with an exploratory design guided by an interpretive philosophical perspective. The data was gathered from 60 prospective teachers from the public sector university of Sindh, Pakistan. Semi-structured interviews were conducted with participants. They were then analyzed using theme analysis to understand their views on the potential of hybridized cybergogy paradigms for collaborative learning to improve the quality of education provided at institutions.

The study results confirm that learners benefit from increased access to learning resources, improved critical thinking and problem-solving skills and a more diverse and inclusive classroom working together in a collaborative hybridized cybergogy setting. By fostering SDG 4 (Quality Education) and the 21st-century skills necessary for global marketplace engagement and competing in progressive environments, this creative method equips learners with the capabilities to face modern global challenges.

The study offers valuable practical suggestions to stakeholders in higher education, including faculty, policymakers and teacher education programs, for integrating hybridized cybergogy and collaborative learning to align curricula with sustainable development goals. Additionally, it bridges a significant gap in the existing literature, which will aid future researchers interested in exploring this area.

This study stands out as it explores an underexamined area while providing novel educational insights.

The authors are developing a model for rural science teacher professional development, building teacher expertise and collaboration and creating high-quality science lessons: technology-mediated lesson study (TMLS).

TMLS provided the means for geographically distributed teachers to collaborate, develop, implement and improve lessons. TMLS uses technology to capture lesson implementation and collaborate on lesson iterations.

This paper describes the seven steps of the TMLS process with examples, showing how teachers develop their content and pedagogical knowledge while building relationships.

The TMLS approach provides an innovative option for teachers to collaborate across distances and form strong, lasting relationships with others.

This article investigates the practical implementation of the ecosystem approach in different branches of public management within an urban context. It explores how ecosystem thinking is introduced, disseminated and applied in a local government organization.

We utilize a qualitative case study methodology, relying on official documents and expert interviews. Our study focuses on the city of Espoo, Finland, which has actively embraced ecosystem thinking as a fundamental framework for its organizational development for almost a decade.

The case of Espoo highlights elements that have not been commonly attributed to the ecosystem approach in the public sector. These elements include (1) the significance of complementary services, (2) the existence of both collaborative and competitive relationships among actors in public service ecosystems and (3) the utilization of digital platforms for resource orchestration. Our study also emphasizes the need for an incremental adoption of ecosystem thinking in organizational contexts to enable its successful implementation.

The study provides valuable insights into the introduction and dissemination of ecosystem thinking in public management. It also further develops previously developed hypotheses regarding public service ecosystems.

The purpose of this paper is to systematically review the history and current state of lesson study (LS) in Germany. In particular, this paper describes the development of LS over time and its stakeholders.

Conducting a systematic literature review, we searched three scientific databases and Google Scholar, examined 806 results and included 50 articles in our final sample, which we analyzed systematically.

The spread of LS in Germany can be divided into three phases, characterized by their own LS projects as well as their own ways of understanding LS. Although interest in LS has increased significantly in recent years, it is only present at a small number of schools and universities in Germany if compared internationally. Furthermore, this paper identifies the so-called learning activity curves as a tool frequently used for observation and reflection that appears to be unknown outside German-speaking countries.

This paper may act as an outline for countries without large-scale LS projects and with limited support from policymakers. The experience from Germany demonstrates the outcomes and challenges that can arise in such a situation and shows how unique LS features and proceedings have emerged.

The purpose of this research is to achieve multi-task autonomous driving by adjusting the network architecture of the model. Meanwhile, after achieving multi-task autonomous driving, the authors found that the trained neural network model performs poorly in untrained scenarios. Therefore, the authors proposed to improve the transfer efficiency of the model for new scenarios through transfer learning.

First, the authors achieved multi-task autonomous driving by training a model combining convolutional neural network and different structured long short-term memory (LSTM) layers. Second, the authors achieved fast transfer of neural network models in new scenarios by cross-model transfer learning. Finally, the authors combined data collection and data labeling to improve the efficiency of deep learning. Furthermore, the authors verified that the model has good robustness through light and shadow test.

This research achieved road tracking, real-time acceleration–deceleration, obstacle avoidance and left/right sign recognition. The model proposed by the authors (UniBiCLSTM) outperforms the existing models tested with model cars in terms of autonomous driving performance. Furthermore, the CMTL-UniBiCL-RL model trained by the authors through cross-model transfer learning improves the efficiency of model adaptation to new scenarios. Meanwhile, this research proposed an automatic data annotation method, which can save 1/4 of the time for deep learning.

This research provided novel solutions in the achievement of multi-task autonomous driving and neural network model scenario for transfer learning. The experiment was achieved on a single camera with an embedded chip and a scale model car, which is expected to simplify the hardware for autonomous driving.