Yue Suo, Jingyu Li, Yuanchun Shi and Peifeng Xiang
Smart spaces are open complex computing systems, consisting of a large variety of cooperative smart things. Central to building smart spaces is the support for sophisticated…
Abstract
Purpose
Smart spaces are open complex computing systems, consisting of a large variety of cooperative smart things. Central to building smart spaces is the support for sophisticated coordination among diverse smart things collaborating to accomplish specified tasks. Multi‐agent systems are often used as the software infrastructures to address the coordination issue in smart spaces. However, since agents in smart spaces are dynamic, resource‐bounded and have complicated service dependencies, current approaches to coordination in multi‐agent systems encounter new challenges when applied in smart spaces. The purpose of this paper is to address these issues.
Design/methodology/approach
The paper presents Baton, a service management system to explicitly resolve the particular issues stemming from smart spaces when coordinating agents. Baton is designed as a complement to coordination approaches in multi‐agent systems with a focus on mechanisms for service discovery, composition, request arbitration and dependency maintenance. Baton is now deployed in our own smart spaces to achieve better agent coordination.
Findings
The effectiveness and efficiency of Baton is validated by its practical use in the designed scenario and some evaluation experiments.
Research limitations/implications
An attempt at performing dynamic service composition in Baton is made by using semantic information in future work.
Originality/value
Baton, a service management system to explicitly resolve the particular issues stemming from smart spaces when coordinating agents is presented.
Details
Keywords
Ju Fan, Yuanchun Jiang, Yezheng Liu and Yonghang Zhou
Course recommendations are important for improving learner satisfaction and reducing dropout rates on massive open online course (MOOC) platforms. This study aims to propose an…
Abstract
Purpose
Course recommendations are important for improving learner satisfaction and reducing dropout rates on massive open online course (MOOC) platforms. This study aims to propose an interpretable method of analyzing students' learning behaviors and recommending MOOCs by integrating multiple data sources.
Design/methodology/approach
The study proposes a deep learning method of recommending MOOCs to students based on a multi-attention mechanism comprising learning records attention, word-level review attention, sentence-level review attention and course description attention. The proposed model is validated using real-world data consisting of the learning records of 6,628 students for 1,789 courses and 65,155 reviews.
Findings
The main contribution of this study is its exploration of multiple unstructured information using the proposed multi-attention network model. It provides an interpretable strategy for analyzing students' learning behaviors and conducting personalized MOOC recommendations.
Practical implications
The findings suggest that MOOC platforms must fully utilize the information implied in course reviews to extract personalized learning preferences.
Originality/value
This study is the first attempt to recommend MOOCs by exploring students' preferences in course reviews. The proposed multi-attention mechanism improves the interpretability of MOOC recommendations.
Details
Keywords
Seth Ampadu, Yuanchun Jiang, Samuel Adu Gyamfi, Emmanuel Debrah and Eric Amankwa
The purpose of this study is to examine the effect of perceived value of recommended product on consumer’s e-loyalty, based on the proposition of expectation confirmation theory…
Abstract
Purpose
The purpose of this study is to examine the effect of perceived value of recommended product on consumer’s e-loyalty, based on the proposition of expectation confirmation theory. Vendors’ reputation is tested as the mediator in the perceived value of recommended product and e-loyalty relationship, whereas shopping enjoyment is predicted as the moderator that conditions the perceived value of recommended product and e-loyalty relationship through vendors reputation.
Design/methodology/approach
Data were collected via an online survey platform and through a QR code. Partial least squares analysis, confirmatory factor analysis and structural equation modeling were used to verify the research proposed model.
Findings
The findings revealed that the perceived value of recommended product had a significant positive effect on E-loyalty; in addition, the perceived value of the recommended product and e-loyalty link was partly explained by e-shopper’s confidence in vendor reputation. Therefore, the study established that the direct and indirect relationship between the perceived value of the recommended product and e-loyalty was sensitive and profound to shopping enjoyment.
Originality/value
This study has established that the perceived value of a recommended product can result in consumer loyalty. This has successively provided the e-shop manager and other stakeholders with novel perspectives about why it is necessary to understand consumers’ pre- and postacquisition behavior before recommending certain products to the consumer.
Details
Keywords
Hua Liu, Weidong Zhu, Huiyue Dong and Yinglin Ke
This paper aims to propose a calibration model for kinematic parameters identification of serial robot to improve its positioning accuracy, which only requires position…
Abstract
Purpose
This paper aims to propose a calibration model for kinematic parameters identification of serial robot to improve its positioning accuracy, which only requires position measurement of the end-effector.
Design/methodology/approach
The proposed model is established based on local frame representation of the product of exponentials (local POE) formula, which integrates all kinematic errors into the twist coordinates errors; then they are identified with the tool frame’ position deviations simultaneously by an iterative least squares algorithm.
Findings
To verify the effectiveness of the proposed method, extensive simulations and calibration experiments have been conducted on a 4DOF SCARA robot and a 5DOF drilling machine, respectively. The results indicate that the proposed model outperforms the existing model in convergence, accuracy, robustness and efficiency; fewer measurements are needed to gain an acceptable identification result.
Practical implications
This calibration method has been applied to a variable-radius circumferential drilling machine. The machine’s positioning accuracy can be significantly improved from 11.153 initially to 0.301 mm, which is well in the tolerance (±0.5 mm) for fastener hole drilling in aircraft assembly.
Originality/value
An accurate and efficient kinematic calibration model has been proposed, which satisfies the completeness, continuity and minimality requirements. Due to generality, this model can be widely used for serial robot kinematic calibration with any combination of revolute and prismatic joints.