Search results

The purpose of the paper is to propose and demonstrate a novel approach for addressing the challenges of path planning and obstacle avoidance in the context of mobile robots (MR). The specific objectives and purposes outlined in the paper include: introducing a new methodology that combines Q-learning with dynamic reward to improve the efficiency of path planning and obstacle avoidance. Enhancing the navigation of MR through unfamiliar environments by reducing blind exploration and accelerating the convergence to optimal solutions and demonstrating through simulation results that the proposed method, dynamic reward-enhanced Q-learning (DRQL), outperforms existing approaches in terms of achieving convergence to an optimal action strategy more efficiently, requiring less time and improving path exploration with fewer steps and higher average rewards.

The design adopted in this paper to achieve its purposes involves the following key components: (1) Combination of Q-learning and dynamic reward: the paper’s design integrates Q-learning, a popular reinforcement learning technique, with dynamic reward mechanisms. This combination forms the foundation of the approach. Q-learning is used to learn and update the robot’s action-value function, while dynamic rewards are introduced to guide the robot’s actions effectively. (2) Data accumulation during navigation: when a MR navigates through an unfamiliar environment, it accumulates experience data. This data collection is a crucial part of the design, as it enables the robot to learn from its interactions with the environment. (3) Dynamic reward integration: dynamic reward mechanisms are integrated into the Q-learning process. These mechanisms provide feedback to the robot based on its actions, guiding it to make decisions that lead to better outcomes. Dynamic rewards help reduce blind exploration, which can be time-consuming and inefficient and promote faster convergence to optimal solutions. (4) Simulation-based evaluation: to assess the effectiveness of the proposed approach, the design includes a simulation-based evaluation. This evaluation uses simulated environments and scenarios to test the performance of the DRQL method. (5) Performance metrics: the design incorporates performance metrics to measure the success of the approach. These metrics likely include measures of convergence speed, exploration efficiency, the number of steps taken and the average rewards obtained during the robot’s navigation.

The findings of the paper can be summarized as follows: (1) Efficient path planning and obstacle avoidance: the paper’s proposed approach, DRQL, leads to more efficient path planning and obstacle avoidance for MR. This is achieved through the combination of Q-learning and dynamic reward mechanisms, which guide the robot’s actions effectively. (2) Faster convergence to optimal solutions: DRQL accelerates the convergence of the MR to optimal action strategies. Dynamic rewards help reduce the need for blind exploration, which typically consumes time and this results in a quicker attainment of optimal solutions. (3) Reduced exploration time: the integration of dynamic reward mechanisms significantly reduces the time required for exploration during navigation. This reduction in exploration time contributes to more efficient and quicker path planning. (4) Improved path exploration: the results from the simulations indicate that the DRQL method leads to improved path exploration in unknown environments. The robot takes fewer steps to reach its destination, which is a crucial indicator of efficiency. (5) Higher average rewards: the paper’s findings reveal that MR using DRQL receive higher average rewards during their navigation. This suggests that the proposed approach results in better decision-making and more successful navigation.

The paper’s originality stems from its unique combination of Q-learning and dynamic rewards, its focus on efficiency and speed in MR navigation and its ability to enhance path exploration and average rewards. These original contributions have the potential to advance the field of mobile robotics by addressing critical challenges in path planning and obstacle avoidance.

This study aims to explore the impact mechanism of the degree of innovation failure on breakthrough innovation in Chinese listed companies, and examines the moderating effect of the company’s own knowledge-based capabilities.

Based on organizational learning theory and using the innovation failure data of invention patents from Chinese A-share listed companies on the main board from 2003 to 2017 as research samples, this study constructs and examines a comprehensive framework and its impact on breakthrough innovation regarding “what kind of innovation failure will promote breakthrough innovation”, focusing on innovation failure, enterprise knowledge base, and breakthrough innovation.

Empirical research has found a U-shaped relationship between innovation failure and breakthrough innovation. In other words, both a low level of failure and an extremely high level of failure can significantly promote breakthrough innovation in enterprises. Furthermore, when the depth of enterprise knowledge is high, it further strengthens the non-linear relationship between innovation failure and breakthrough innovation.

The research results enrich the study of the failure predicament and breakthrough innovation of Chinese technology innovation enterprises, revealing effective paths for Chinese technology innovation enterprises to get rid of the passive situation of innovation failure, and providing theoretical support and practical reference for “breaking new ground and achieving breakthrough innovation”.

Organisational learning (OL) is a critical capability family firms (FFs) need in order to adapt to an increasingly turbulent environment. Given the uniqueness of FFs and their differentiated decision-making processes, this review addresses fragmentation in the literature and synthesises prior research outlining the development of OL in FFs.

A systematic literature review was conducted using four databases, and 53 pertinent papers on OL in FFs published from 1998 to 2023 were analysed using the theory, characteristics, context and methodology (TCCM) framework.

The last five years (2019–2023) show a marked increase in interest in OL in FFs, with a rise in the number of quantitative studies. The findings indicate that OL is mainly studied as a unidimensional construct, while it is a multidimensional capability. Strategic management and organisational behaviour theories are commonly employed, while theories specific to family business such as socioemotional wealth (SEW) and familiness are underrepresented. Most studies focus on FFs in the Northern Hemisphere, and few studies examine OL in FFs located in the Global South. The TCCM framework reveals the complexity and multi-layered nature of OL in FFs.

This is one of the first systematic reviews to synthesise research on OL in FFs. The proposed research agenda identifies fruitful areas for future investigations concentrating on the multidimensional nature of OL, family-related outcomes, as well as contextual and methodological research directions of interest to family business researchers.

Fierce competition in the crowdfunding market has resulted in high failure rates. Owing to their dedication and efforts, many founders have relaunched failed campaigns as a second attempt. Despite the need for a better understanding, the success of campaign relaunches has not been well-researched. To fill this research gap, this study first theorizes how founders’ learning may enhance their competencies and influence investors’ attribution of entrepreneurial failure. The study then empirically documents the extent and conditions under which such learning efforts impact campaign relaunch performance.

This study examines 5,798 Kickstarter-relaunched campaigns. The founders’ learning efforts are empirically captured by key changes in campaign design that deviate from past business practices. Word movers’ distances and perceptual hashing algorithms (pHash) are used separately to measure differences in campaign textual descriptions and pictorial designs.

Differences in textual descriptions and pictorial designs during campaign failure–relaunch are positively associated with campaign relaunch success. The impacts are further amplified when the previous failures are more severe.

This study is one of the first to examine the success of a campaign relaunch after an initial failure. This study contributes to a better understanding of founders’ learning in crowdfunding contexts and provides insights into the strategies founders can adopt to reap performance benefits.

This study aims to examine the underlying process through which learning organization culture positively influences knowledge sharing. It specifically explored the mediating role of social capital, underscoring its critical impact on enhancing both knowledge sharing and fostering learning organization culture.

To test the proposed hypotheses, structural equation modeling (SEM) analysis was conducted with a sample of 231 employees from a manufacturing firm in South Korea.

The results of this study indicate significant direct effects of learning organization culture on social capital. Also, social capital indicates a positive effect on knowledge sharing. Although learning organization culture had no direct effect on knowledge sharing, it indirectly affected learning organization culture and knowledge sharing by mediating social capital.

This study proposes that a learning organization culture will be interconnected with social capital and knowledge sharing. Organizations that can effectively harness the wealth of knowledge unlocked by social capital, and subsequently integrate this knowledge into their activities, are poised for competitive advantage.

First, this study places a special emphasis on the mediating role of social capital between learning organization culture and knowledge sharing. Despite extensive research exploring diverse knowledge-sharing factors (Wang and Noe, 2010), it is plausible that examining social capital as a mediator could offer insights for facilitating knowledge sharing through its structural, relational and cognitive dimensions. Second, while a plethora of literature examines knowledge sharing, this study also seeks to unravel the multifaceted pathways through which the learning organization culture influences knowledge sharing and how these processes could be optimized in organizations.

This study examines learner satisfaction and success as mechanisms through which online learning quality translates into learners’ continuous intentions of use by extending DeLone and McLean’s information system success model. It also examines the moderating effect of perceived supervisory support and learners’ self-regulation on online learning quality in Higher Education Institutions.

Survey data were obtained from 540 students in both private and public higher institutions of learning in Ghana. The Partial Least Squares – Structural Equations Modelling (PLS-SEM) technique was used to test the hypothesised relationships.

The results revealed that system quality emerged as the single most important variable in the DeLone and McLean model, that influences learner success and satisfaction. Further, learner satisfaction has a significant positive effect on learner attitudes, whilst self-regulation was found to moderate the relationship between online learning quality and learner success as well as learner satisfaction.

The study appears to be among the first to explore the inter-relationship among online learning environment quality and learner attitudes and moderating factors perceived supervisory support and self-regulation. The study highlights insightful practical implications for students, faculty and administrators of higher institutions.

Predicting student performance is crucial in educational settings to identify and support students who may need additional help or resources. Understanding and predicting student performance is essential for educators to provide targeted support and guidance to students. By analyzing various factors like attendance, study habits, grades, and participation, teachers can gain insights into each student’s academic progress. This information helps them tailor their teaching methods to meet the individual needs of students, ensuring a more personalized and effective learning experience. By identifying patterns and trends in student performance, educators can intervene early to address any challenges and help students acrhieve their full potential. However, the complexity of human behavior and learning patterns makes it difficult to accurately forecast how a student will perform. Additionally, the availability and quality of data can vary, impacting the accuracy of predictions. Despite these obstacles, continuous improvement in data collection methods and the development of more robust predictive models can help address these challenges and enhance the accuracy and effectiveness of student performance predictions. However, the scalability of the existing models to different educational settings and student populations can be a hurdle. Ensuring that the models are adaptable and effective across diverse environments is crucial for their widespread use and impact. To implement a student’s performance-based learning recommendation scheme for predicting the student’s capabilities and suggesting better materials like papers, books, videos, and hyperlinks according to their needs. It enhances the performance of higher education.

Thus, a predictive approach for student achievement is presented using deep learning. At the beginning, the data is accumulated from the standard database. Next, the collected data undergoes a stage where features are carefully selected using the Modified Red Deer Algorithm (MRDA). After that, the selected features are given to the Deep Ensemble Networks (DEnsNet), in which techniques such as Gated Recurrent Unit (GRU), Deep Conditional Random Field (DCRF), and Residual Long Short-Term Memory (Res-LSTM) are utilized for predicting the student performance. In this case, the parameters within the DEnsNet network are finely tuned by the MRDA algorithm. Finally, the results from the DEnsNet network are obtained using a superior method that delivers the final prediction outcome. Following that, the Adaptive Generative Adversarial Network (AGAN) is introduced for recommender systems, with these parameters optimally selected using the MRDA algorithm. Lastly, the method for predicting student performance is evaluated numerically and compared to traditional methods to demonstrate the effectiveness of the proposed approach.

The accuracy of the developed model is 7.66%, 9.91%, 5.3%, and 3.53% more than HHO-DEnsNet, ROA-DEnsNet, GTO-DEnsNet, and AOA-DEnsNet for dataset-1, and 7.18%, 7.54%, 5.43% and 3% enhanced than HHO-DEnsNet, ROA-DEnsNet, GTO-DEnsNet, and AOA-DEnsNet for dataset-2.

The developed model recommends the appropriate learning materials within a short period to improve student’s learning ability.

Drawing on the knowledge-based view, this study investigates how IT–business alignment influences business model design via organizational learning and examines the moderating role of data-driven culture in the relationship between IT–business alignment and business model design via organizational learning.

Using multi-respondent survey data collected from 597 Chinese firms, mediation and moderated mediation analyses were used to examine this study's hypotheses.

The mediation test results revealed organizational learning served as a mediator between IT–business alignment and two types of business model design (i.e. novelty- and efficiency-centered). In addition, data-driven culture strengthened the indirect effects of IT–business alignment on these two types of business model design via organizational learning.

This study extends current understandings of the relationship between IT–business alignment and business model design by revealing the mediating role of organizational learning and investigating its indirect effects under various degrees of data-driven culture. As such, it contributes to the literature on the business model and IT–business alignment and provides insights for managers seeking to achieve the expected business model design.

This bibliometric study aims to analyze publication trends, active countries, collaborations, influential citations and thematic evolution in learning analytics (LA) research focused on higher education (HE) during and after the COVID-19 lockdown period.

From the Scopus database, this bibliometric analysis extracts and evaluates 609 scholarly articles on LA in HE starting in 2019. The multidimensional process identifies the scope impacts, advancing the understanding of LA in HE. An analysis of co-citation data uncovers the key influences that have shaped the literature. This study uses the stimulus-organism-response (SOR) theory to suggest future research directions and organizational adaptations to new LA technologies and learner responses to LA-enabled personalized interventions.

Learning analytics are becoming important in the HE environment during and after the COVID-19 lockout. Institutions have used LA to collect socio-technical data from digital platforms, giving them important insights into learning processes and systems. The data gathered through LA has assisted in identifying areas for development, opening the path for improved student success and academic performance evaluation and helping students transition to the workforce.

The study’s concentration on the post-COVID-19 timeframe may lead to paying attention to potential pandemic developments. Nonetheless, the findings provide a thorough picture of LA’s contributions to HE and valuable ideas for future study initiatives. Future research with the SOR framework suggests areas for additional study to maximize LA’s potential in diverse HE situations.

This study adds to the growing corpus of knowledge on learning analytics in HE, especially in light of the COVID-19 lockdown and its aftermath. By using bibliometric analysis, the study provides a complete and evidence-based understanding of how LA has been used to address challenges related to HE. This study uses bibliometric analysis and SOR theory to appraise and map HE learning analytics research. The selected study themes can help scholars, educators and institutions shape their future efforts to improve teaching, learning and support mechanisms through learning analytics.

The global COVID-19 epidemic has posed significant challenges to the development of innovation and entrepreneurship education in Chinese and foreign universities, and the application of artificial intelligence generated content (AIGC) technology has presented both opportunities and challenges to its development. The purpose of this study is to summarize advanced experiences and models of new engineering innovation and entrepreneurship education development in Chinese and foreign universities, as well as to analyze the influencing factors. Taking the sustainable development goals (SDGs) into account, this study qualitatively proposes enhancement paths and improvement suggestions based on the application of AIGC technology, providing a reference for promoting the sustainable development (SD) of innovation and entrepreneurship education in Chinese universities.

By using the qualitative comparative analysis (QCA), this paper studies the interaction mechanism between the influencing factors of innovation and entrepreneurship in universities under the background of SDGs. This paper selects 12 representative universities with different cultures and strengths. Meanwhile, this paper analyzes the content of 2,535 publications on innovation and entrepreneurship education and summarizes seven influencing factors as comparison criteria. Then, this paper codes, summarizes and uses configuration to assess the primary factors influencing the development of innovation and entrepreneurship in colleges and universities at home and abroad.

On the quality of new engineering innovation and entrepreneurship education, comprehensive, diverse influencing factors and upgrading paths are obtained. Furthermore, this research proposes that the SD of innovation and entrepreneurship education in universities should make effective use of “AI plus education” and actively construct practical and teaching platforms. Meanwhile, the ChatGPT is being used to strengthen the innovation and entrepreneurship curricular system and talent training mode. The research also makes recommendations for improving teachers’ ability to acquire intelligent tools and promotes three-way teaching modalities of “teacher-AI-student” by taking into account the influence of various aspects.

This research uses the QCA research method, which analyzes not only influencing factors on the SD of innovation and entrepreneurship education but also explores the interaction mechanisms among factors. Furthermore, the research incorporates SDGs and AIGC technology application scenarios into the field of domestic innovation and entrepreneurship education, which will be helpful in SDGs of innovation and entrepreneurship education on both theoretical and practical levels.