Yik Him Ho
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yik Him Ho has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Henry C. B. Chany
The Hong Kong Polytechnic University
6 shared publications - Yerkezhan Sartayeva
The Hong Kong Polytechnic University
2 shared publications Ada Pui-Ling Chan
Division of Business and Hospitality Management, College of Professional and Continuing Education, Hong Kong, SAR, China
1 shared publication- Adam Wong
School of Professional Education and Executive Development, The Hong Kong Polytechnic University, Hong Kong, China
1 shared publication Caiqi Zhang
Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China
1 shared publication- Joseph Chi Ho So
Hong Kong Community College, The Hong Kong Polytechnic University, China
1 shared publication
Latest Publications
- 22 September 2023
- Published by Elsevier in Computer Networks
- Vol. 237
A survey of indoor positioning systems based on a six-layer model
- 22 September 2023
- Published by Elsevier in Computer Networks
- Vol. 237
A survey of indoor positioning systems based on a six-layer model
- 4 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Learning Technologies
- Vol. 16 (5) , 790-803
Analytic Study for Predictor Development on Student Participation in Generic Competence Development Activities Based on Academic Performance
Generic competence (GC) development is an integral part of higher education to provide holistic education and enhance student career development. It also plays a critical role in complementing the curriculum. Many tertiary institutions provide various GC development activities (GCDA). Moreover, institutions strongly need to further understand student partici- pation, especially its relationship to student backgrounds, activity profiles, and academic results. With the fast advancement of educational technologies and data mining, data analytics (DA) in formal learning and online education has been widely explored. However, there has been little work on student behavior in GCDA. To fill this gap and to provide new contributions, we conduct a comprehensive study to investigate the interrelation- ship of GCDA participation and academic performance before and after higher education with significant and representative data (over 10,000 records) across three years. Hypotheses are formulated and validated, and the findings are triangulated with machine learning and DA. With supervised learning, the predictors of academic performance and GCDA participation are formulated, and the features to enhance predictions are analyzed. We develop predictors using novel approaches of genetic algorithm and Stacking in machine learning. The impacts of the breadth and depth of involvement is also studied. Results indicate that involvement in GCDA positively impacts student academic results. Our novel approaches give improvements in predicting student participation. Our holistic studies covering hypothesis validation, data analysis and machine learning provide valuable insights into GCDA development.
- 4 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Learning Technologies
- Vol. 16 (5) , 790-803
Analytic Study for Predictor Development on Student Participation in Generic Competence Development Activities Based on Academic Performance
Generic competence (GC) development is an integral part of higher education to provide holistic education and enhance student career development. It also plays a critical role in complementing the curriculum. Many tertiary institutions provide various GC development activities (GCDA). Moreover, institutions strongly need to further understand student partici- pation, especially its relationship to student backgrounds, activity profiles, and academic results. With the fast advancement of educational technologies and data mining, data analytics (DA) in formal learning and online education has been widely explored. However, there has been little work on student behavior in GCDA. To fill this gap and to provide new contributions, we conduct a comprehensive study to investigate the interrelation- ship of GCDA participation and academic performance before and after higher education with significant and representative data (over 10,000 records) across three years. Hypotheses are formulated and validated, and the findings are triangulated with machine learning and DA. With supervised learning, the predictors of academic performance and GCDA participation are formulated, and the features to enhance predictions are analyzed. We develop predictors using novel approaches of genetic algorithm and Stacking in machine learning. The impacts of the breadth and depth of involvement is also studied. Results indicate that involvement in GCDA positively impacts student academic results. Our novel approaches give improvements in predicting student participation. Our holistic studies covering hypothesis validation, data analysis and machine learning provide valuable insights into GCDA development.
- 22 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (14) , 12293-12307
Hybrid Learning for Mobile Ad-Hoc Distancing/Positioning Using Bluetooth Low Energy
With the advent of Bluetooth low-energy (BLE)-enabled smartphones, there has been considerable interest in investigating BLE-based distancing/positioning methods (e.g., for social distancing applications). In this article, we present a novel hybrid learning method to support mobile ad-hoc distancing (MAD)/positioning (MAP) using BLE-enabled smartphones. Compared to traditional BLE-based distancing/positioning methods, the hybrid learning method provides the following unique features and contributions. First, it combines unsupervised learning, supervised learning, and genetic algorithms (GAs) for enhancing distance estimation accuracy. Second, unsupervised learning is employed to identify three pseudo channels/clusters for enhanced RSSI data processing. Third, its underlying mechanism is based on a new pattern-inspired approach to enhance the machine learning process. Fourth, it provides a flagging mechanism to alert users if a predicted distance is accurate or not. Fifth, it provides a model aggregation scheme with an innovative 2-D GA to aggregate the distance estimation results of different machine learning models. As an application of hybrid learning for distance estimation, we also present a new MAP scenario with an iterative algorithm to estimate mobile positions in an ad-hoc environment. Experimental results show the effectiveness of the hybrid learning method. In particular, hybrid learning without flagging and with flagging outperforms the baseline by 57% and 65%, respectively, in terms of mean absolute error. By means of model aggregation, a further 4% improvement can be realized. The hybrid learning approach can also be applied to previous work to enhance distance estimation accuracy and provide valuable insights for further research.
- 22 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (14) , 12293-12307
Hybrid Learning for Mobile Ad-Hoc Distancing/Positioning Using Bluetooth Low Energy
With the advent of Bluetooth low-energy (BLE)-enabled smartphones, there has been considerable interest in investigating BLE-based distancing/positioning methods (e.g., for social distancing applications). In this article, we present a novel hybrid learning method to support mobile ad-hoc distancing (MAD)/positioning (MAP) using BLE-enabled smartphones. Compared to traditional BLE-based distancing/positioning methods, the hybrid learning method provides the following unique features and contributions. First, it combines unsupervised learning, supervised learning, and genetic algorithms (GAs) for enhancing distance estimation accuracy. Second, unsupervised learning is employed to identify three pseudo channels/clusters for enhanced RSSI data processing. Third, its underlying mechanism is based on a new pattern-inspired approach to enhance the machine learning process. Fourth, it provides a flagging mechanism to alert users if a predicted distance is accurate or not. Fifth, it provides a model aggregation scheme with an innovative 2-D GA to aggregate the distance estimation results of different machine learning models. As an application of hybrid learning for distance estimation, we also present a new MAP scenario with an iterative algorithm to estimate mobile positions in an ad-hoc environment. Experimental results show the effectiveness of the hybrid learning method. In particular, hybrid learning without flagging and with flagging outperforms the baseline by 57% and 65%, respectively, in terms of mean absolute error. By means of model aggregation, a further 4% improvement can be realized. The hybrid learning approach can also be applied to previous work to enhance distance estimation accuracy and provide valuable insights for further research.
- Open Access
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Mobile Intercloud System for Edge Cloud Computing
Recent years have seen considerable interest in mobile cloud computing and edge cloud computing. This paper presents a mobile Intercloud system for supporting mobile cloud computing in general and edge cloud computing in particular. In essence, a mobile user with a mobile terminal can set up a virtual mobile terminal with applications and data in a central/home cloud. The virtual mobile terminal can facilitate task and computation offloading and other functions. Moreover, when a mobile terminal joins an edge cloud, the virtual mobile terminal (including required applications and data) can be migrated to enhance system efficiency and the user experience (e.g., shorter access delays). An experimental prototype has been developed for evaluating certain basic object transfer functions. To support the application transfer function, we formulate both finite‐ and infinite‐horizon Markov decision models to determine decision policies (i.e., should an application be transferred to an edge cloud). The transfer decision depends on various factors, including transfer cost, duration associated with the edge cloud, usage probability, and usage cost in the central cloud and edge cloud. Based on the models, we obtain closed‐form solutions for the decision policies, which can be expressed in meaningful formulas to provide useful insights for edge cloud computing in general. To evaluate the mobile Intercloud system for edge cloud computing, we conducted extensive evaluations, including experimental evaluation for testing the basic functions and protocols, analytical evaluation for studying the analytical models, and simulation evaluation for analyzing performance in a multiuser and multicloud environment in particular. The experimental, simulation, and analytical results provide useful insights into the design and development of the mobile Intercloud system for edge cloud computing as well as decision policies for application transfer.
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Open AccessMobile Intercloud System for Edge Cloud Computing
Recent years have seen considerable interest in mobile cloud computing and edge cloud computing. This paper presents a mobile Intercloud system for supporting mobile cloud computing in general and edge cloud computing in particular. In essence, a mobile user with a mobile terminal can set up a virtual mobile terminal with applications and data in a central/home cloud. The virtual mobile terminal can facilitate task and computation offloading and other functions. Moreover, when a mobile terminal joins an edge cloud, the virtual mobile terminal (including required applications and data) can be migrated to enhance system efficiency and the user experience (e.g., shorter access delays). An experimental prototype has been developed for evaluating certain basic object transfer functions. To support the application transfer function, we formulate both finite‐ and infinite‐horizon Markov decision models to determine decision policies (i.e., should an application be transferred to an edge cloud). The transfer decision depends on various factors, including transfer cost, duration associated with the edge cloud, usage probability, and usage cost in the central cloud and edge cloud. Based on the models, we obtain closed‐form solutions for the decision policies, which can be expressed in meaningful formulas to provide useful insights for edge cloud computing in general. To evaluate the mobile Intercloud system for edge cloud computing, we conducted extensive evaluations, including experimental evaluation for testing the basic functions and protocols, analytical evaluation for studying the analytical models, and simulation evaluation for analyzing performance in a multiuser and multicloud environment in particular. The experimental, simulation, and analytical results provide useful insights into the design and development of the mobile Intercloud system for edge cloud computing as well as decision policies for application transfer.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
BluePrint: BLE Positioning Algorithm Based on NUFO Detection
The introduction of the Bluetooth 4.0 and Bluetooth Low Energy (BLE) standard greatly facilitates the development of Internet of Things (IoT) applications. Most of these applications require a positioning mechanism to detect the position of both people and objects. While BLE is a key enabling technology, it is relatively new as compared to Wi-Fi and RFID. Hence there is a need to conduct more studies on BLE-based positioning methods. In general, positioning methods based on signal propagation and fingerprint are commonly used in wireless networking. These methods have their own limitations in terms of practical use and ease of implementation. In this paper, we present an innovative BLE-based positioning methodology called BluePrint which makes use of a detection mechanism called NUFO (Near, Uncertain, Far and Out). It combines a simple fingerprint-like method with a rule-based algorithm to estimate positions. Experimental results show that Blueprint with NUFO detection can achieve good performance as compared to other methods. Furthermore, its implementation is simple and practical.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
BluePrint: BLE Positioning Algorithm Based on NUFO Detection
The introduction of the Bluetooth 4.0 and Bluetooth Low Energy (BLE) standard greatly facilitates the development of Internet of Things (IoT) applications. Most of these applications require a positioning mechanism to detect the position of both people and objects. While BLE is a key enabling technology, it is relatively new as compared to Wi-Fi and RFID. Hence there is a need to conduct more studies on BLE-based positioning methods. In general, positioning methods based on signal propagation and fingerprint are commonly used in wireless networking. These methods have their own limitations in terms of practical use and ease of implementation. In this paper, we present an innovative BLE-based positioning methodology called BluePrint which makes use of a detection mechanism called NUFO (Near, Uncertain, Far and Out). It combines a simple fingerprint-like method with a rule-based algorithm to estimate positions. Experimental results show that Blueprint with NUFO detection can achieve good performance as compared to other methods. Furthermore, its implementation is simple and practical.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Mobile Intercloud System and Objects Transfer Mechanism
In recent years, there has been considerable interest in studying intercloud with the aim of supporting interactions among different clouds, possibly managed by different service providers. The extension of intercloud to a mobile environment, called a "mobile intercloud system" is a relatively new research area. In this paper, we present a mobile intercloud system, which is developed based on the IEEE P2302 Intercloud architecture and inspired by the mobile Internet protocol. Basically a mobile terminal is associated with a home cloud in which a virtual mobile terminal can be set up together with the mobile applications and data. When a mobile terminal moves to a new area and joins a foreign cloud, certain mobile applications and data can be transferred to the foreign cloud. For data/files, we present a rule-based policy so that users can specify the rules for transferring data/files flexibly. A prototype has been developed to demonstrate the basic concept. For applications, we formulate a Markov decision process model to study how the applications should be transferred to minimize the overall cost. Analytical results are presented to provide valuable insights into the design of the mobile intercloud system.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Mobile Intercloud System and Objects Transfer Mechanism
In recent years, there has been considerable interest in studying intercloud with the aim of supporting interactions among different clouds, possibly managed by different service providers. The extension of intercloud to a mobile environment, called a "mobile intercloud system" is a relatively new research area. In this paper, we present a mobile intercloud system, which is developed based on the IEEE P2302 Intercloud architecture and inspired by the mobile Internet protocol. Basically a mobile terminal is associated with a home cloud in which a virtual mobile terminal can be set up together with the mobile applications and data. When a mobile terminal moves to a new area and joins a foreign cloud, certain mobile applications and data can be transferred to the foreign cloud. For data/files, we present a rule-based policy so that users can specify the rules for transferring data/files flexibly. A prototype has been developed to demonstrate the basic concept. For applications, we formulate a Markov decision process model to study how the applications should be transferred to minimize the overall cost. Analytical results are presented to provide valuable insights into the design of the mobile intercloud system.