Dr Hongmei (Mary) He (FHEA, SIEEE) is a Professor in Future Robotics, Engineering and Transport System in the School of Science, Engineering and Environment at University of Salford. She obtained her Ph.D. in Computer Science from Loughborough University, the UK in 2006, She once worked for the Motorola Design House in China as a leading embedded system engineer. Her research could briefly be divided into four themes: AI & Data Science, Cognitive Cybersecurity, Trustworthy Robots & Autonomous Systems, and Computing Theory & Optimisation.
Cyber–physical systems such as satellite telecommunications networks generate vast amounts of dat... more Cyber–physical systems such as satellite telecommunications networks generate vast amounts of data and currently, very crude data processing is used to extract salient information. Only a small subset of data is used reactively by operators for troubleshooting and finding problems. Sometimes, problematic events in the network may go undetected for weeks before they are reported. This becomes even more challenging as the size of the network grows due to the continuous proliferation of Internet of Things type devices. To overcome these challenges, this research proposes a knowledge-based cognitive architecture supported by machine learning algorithms for monitoring satellite network traffic. The architecture is capable of supporting and augmenting infrastructure engineers in finding and understanding the causes of faults in network through the fusion of the results of machine learning models and rules derived from human domain experience. The system is characterised by (1) the flexibi...
We propose several new heuristics for the twopage book crossing problem, which are based on recen... more We propose several new heuristics for the twopage book crossing problem, which are based on recent algorithms for the corresponding one-page problem. Especially, the neural network model for edge allocation is combined for the first time with various one-page algorithms. We investigate the performance of the new heuristics by testing them on various benchmark test suites. It is found out that the new heuristics outperform the previously known heuristics and produce good approximations of the planar crossing number for severalwell-known graph families. We conjecture that the optimal two-page drawing of a graph represents the planar drawing of the graph.
A wireless ad hoc sensor network consists of a number of sensors spreading across a geographical ... more A wireless ad hoc sensor network consists of a number of sensors spreading across a geographical area. The performance of the network suffers as the number of nodes grows, and a large sensor network quickly becomes difficult to manage. Thus, it is essential that the network be able to self-organize. Clustering is an efficient approach to simplify the network structure and to alleviate the scalability problem. One method to create clusters is to use weakly connected dominating sets (WCDSs). Finding the minimum WCDS in an arbitrary graph is an NP-complete problem. We propose a neural network model to find the minimum WCDS in a wireless sensor network. We present a directed convergence algorithm. The new algorithm outperforms the normal convergence algorithm both in efficiency and in the quality of solutions. Moreover, it is shown that the neural network is robust. We investigate the scalability of the neural network model by testing it on a range of sized graphs and on a range of transmission radii. Compared with Guha and Khuller's centralized algorithm, the proposed neural network with directed convergency achieves better results when the transmission radius is short, and equal performance when the transmission radius becomes larger. The parallel version of the neural network model takes time O(d), where d is the maximal degree in the graph corresponding to the sensor network, while the centralized algorithm takes O(n2). We also investigate the effect of the transmission radius on the size of WCDS. The results show that it is important to select a suitable transmission radius to make the network stable and to extend the lifespan of the network. The proposed model can be used on sink nodes in sensor networks, so that a sink node can inform the nodes to be a coordinator (clusterhead) in the WCDS obtained by the algorithm. Thus, the message overhead is O(M), where M is the size of the WCDS.
In aircraft industry, after labour and fuel costs, maintenance costs are the third largest expens... more In aircraft industry, after labour and fuel costs, maintenance costs are the third largest expense item for both regional and national carriers. By implementing CBM technologies not only the maintenance costs can be reduced, also it can provide more specific scheduled maintenance, onboard diagnostics and prognostics services. Maintenance department can be notified about the fault in advance and can arrange for components while aircraft is in mid-air. CBM technologies minimize the physical diagnostics costs and provide more realistic condition based maintenance (CBM). The aim of this project is to create and analyse network architecture for Condition Based Maintenance Systems. CBM consists of subsystems, sensors, model based reasoning systems for subsystem and system level managers, diagnostic and prognostics software for subsystems. In CBM systems, usually there is large amount of data (collected from sensors), which needs to be delivered to right places at the right time so communication paradigm is very essential design consideration which impacts many key properties such as scalability, reliability, availability, timeliness and cost of overall system. The OSA-CBM (Open System Architecture for Condition Based Maintenance) is an open standard that defines an open architecture for moving information in a condition-based maintenance system. Typically, companies developing condition-based maintenance systems must develop software and hardware components, in addition a framework for these components to integrate. OSA-CBM is a standard framework for implementing condition-based maintenance systems. It not only describes the six functional blocks of condition based maintenance systems but also the interfaces to establish communication among these blocks. OSA-CBM specifies the input and output between the CBM modules. In simple words, it describes the information that is moved and how to move it. OSA-CBM can be implemented using various available distributed middleware but it is not clear which implementation is more efficient. This paper presents an approach to design, implement and analysis of network architecture of CBM systems using OSACBM data model.
IEEE Transactions on Cognitive and Developmental Systems
The trustworthiness of robots and autonomous systems (RAS) has taken a prominent position on the ... more The trustworthiness of robots and autonomous systems (RAS) has taken a prominent position on the way towards full autonomy. This work is the first to systematically explore the key facets of human-centred AI for trustworthy RAS. We identified five key properties of a trustworthy RAS, i.e., RAS must be (i) safe in any uncertain and dynamic environment; (ii) secure, i.e., protect itself from cyber threats; (iii) healthy and fault-tolerant; (iv) trusted and easy to use to enable effective human-machine interaction (HMI); (v) compliant with the law and ethical expectations. While the applications of RAS have mainly focused on performance and productivity, not enough scientific attention has been paid to the risks posed by advanced AI in RAS. We analytically examine the challenges of implementing trustworthy RAS with respect to the five key properties and explore the role and roadmap of AI technologies in ensuring the trustworthiness of RAS in respect of safety, security, health, HMI, and ethics. A new acceptance model of RAS is provided as a framework for human-centric AI requirements and for implementing trustworthy RAS by design. This approach promotes human-level intelligence to augment human capabilities and focuses on contribution to humanity.
2019 International Conference on Computational Science and Computational Intelligence (CSCI)
A hierarchy of Linguistic Decision Trees (LDTs), called linguistic attribute hierarchy (LAH), can... more A hierarchy of Linguistic Decision Trees (LDTs), called linguistic attribute hierarchy (LAH), can provide a transparent information propagation and a hierarchical decision making process. In this paper, we quantified the effect of various factors on the diagnosis of Diabetes with the information gain of each attribute to the decision variable, and developed an LAH, where, the LDTs are constructed under the framework of the knowledge-based label semantics, referring to the knowledge of the diagnosis criteria of Diabetes, defined by the World Health Organisation. A genetic wrapper algorithm was developed to find the best LAH for improving the accuracy of Diabetes diagnosis. The optimal LAH for Diabetes diagnosis achieved the accuracy up to 92% on the benchmark database, Pima Indian Diabetes data. The accuracy is much better than that in the research literature.
The universe approximate theorem states that a shadow neural network (one hidden layer) can repre... more The universe approximate theorem states that a shadow neural network (one hidden layer) can represent any non-linear function. In this paper, we aim at examining how good a shadow neural network is for solving non-linear decision making problems. We proposed a performance driven incremental approach to searching the best shadow neural network for decision making, given a data set. The experimental results on the two benchmark data sets, Breast Cancer in Wisconsin and SMS Spams, demonstrate the correction of universe approximate theorem, and show that the number of hidden neurons, taking about the half of input number, is good enough to represent the function from data. It is shown that the performance driven BP learning is faster than the error-driven BP learning, and that the performance of the SNN obtained by the former is not worse than that of the SNN obtained by the latter. This indicates that when learning a neural network with the BP algorithm, the performance reaches a certa...
To identify the key factors and create the landscape of cybersecurity for embedded systems (CSES)... more To identify the key factors and create the landscape of cybersecurity for embedded systems (CSES), an analytical review of the existing research on CSES has been conducted. The common properties of embedded systems, such as mobility, small size, low cost, independence, and limited power consumption when compared to traditional computer systems, have caused many challenges in CSES. The conflict between cybersecurity requirements and the computing capabilities of embedded systems makes it critical to implement sophisticated security countermeasures against cyber-attacks in an embedded system with limited resources, without draining those resources. In this study, twelve factors influencing CSES have been identified: (1) the components; (2) the characteristics; (3) the implementation; (4) the technical domain; (5) the security requirements; (6) the security problems; (7) the connectivity protocols; (8) the attack surfaces; (9) the impact of the cyber-attacks; (10) the security challeng...
Genetic algorithms have been applied to solve the 2-page drawing problem successfully, but they w... more Genetic algorithms have been applied to solve the 2-page drawing problem successfully, but they work with one global population, so the search time and space are limited. Parallelization provides an attractive prospect in improving the efficiency and solution quality of genetic algorithms. One of the most popular tools for parallel computing is Message Passing Interface (MPI). In this paper, we present four island models of Parallel Genetic Algorithms with MPI: island models with linear, grid, random graph topologies, and island model with periodical synchronisation. We compare their efficiency and quality of solutions for the 2-page drawing problem on a variety of graphs.
Cyber–physical systems such as satellite telecommunications networks generate vast amounts of dat... more Cyber–physical systems such as satellite telecommunications networks generate vast amounts of data and currently, very crude data processing is used to extract salient information. Only a small subset of data is used reactively by operators for troubleshooting and finding problems. Sometimes, problematic events in the network may go undetected for weeks before they are reported. This becomes even more challenging as the size of the network grows due to the continuous proliferation of Internet of Things type devices. To overcome these challenges, this research proposes a knowledge-based cognitive architecture supported by machine learning algorithms for monitoring satellite network traffic. The architecture is capable of supporting and augmenting infrastructure engineers in finding and understanding the causes of faults in network through the fusion of the results of machine learning models and rules derived from human domain experience. The system is characterised by (1) the flexibi...
We propose several new heuristics for the twopage book crossing problem, which are based on recen... more We propose several new heuristics for the twopage book crossing problem, which are based on recent algorithms for the corresponding one-page problem. Especially, the neural network model for edge allocation is combined for the first time with various one-page algorithms. We investigate the performance of the new heuristics by testing them on various benchmark test suites. It is found out that the new heuristics outperform the previously known heuristics and produce good approximations of the planar crossing number for severalwell-known graph families. We conjecture that the optimal two-page drawing of a graph represents the planar drawing of the graph.
A wireless ad hoc sensor network consists of a number of sensors spreading across a geographical ... more A wireless ad hoc sensor network consists of a number of sensors spreading across a geographical area. The performance of the network suffers as the number of nodes grows, and a large sensor network quickly becomes difficult to manage. Thus, it is essential that the network be able to self-organize. Clustering is an efficient approach to simplify the network structure and to alleviate the scalability problem. One method to create clusters is to use weakly connected dominating sets (WCDSs). Finding the minimum WCDS in an arbitrary graph is an NP-complete problem. We propose a neural network model to find the minimum WCDS in a wireless sensor network. We present a directed convergence algorithm. The new algorithm outperforms the normal convergence algorithm both in efficiency and in the quality of solutions. Moreover, it is shown that the neural network is robust. We investigate the scalability of the neural network model by testing it on a range of sized graphs and on a range of transmission radii. Compared with Guha and Khuller's centralized algorithm, the proposed neural network with directed convergency achieves better results when the transmission radius is short, and equal performance when the transmission radius becomes larger. The parallel version of the neural network model takes time O(d), where d is the maximal degree in the graph corresponding to the sensor network, while the centralized algorithm takes O(n2). We also investigate the effect of the transmission radius on the size of WCDS. The results show that it is important to select a suitable transmission radius to make the network stable and to extend the lifespan of the network. The proposed model can be used on sink nodes in sensor networks, so that a sink node can inform the nodes to be a coordinator (clusterhead) in the WCDS obtained by the algorithm. Thus, the message overhead is O(M), where M is the size of the WCDS.
In aircraft industry, after labour and fuel costs, maintenance costs are the third largest expens... more In aircraft industry, after labour and fuel costs, maintenance costs are the third largest expense item for both regional and national carriers. By implementing CBM technologies not only the maintenance costs can be reduced, also it can provide more specific scheduled maintenance, onboard diagnostics and prognostics services. Maintenance department can be notified about the fault in advance and can arrange for components while aircraft is in mid-air. CBM technologies minimize the physical diagnostics costs and provide more realistic condition based maintenance (CBM). The aim of this project is to create and analyse network architecture for Condition Based Maintenance Systems. CBM consists of subsystems, sensors, model based reasoning systems for subsystem and system level managers, diagnostic and prognostics software for subsystems. In CBM systems, usually there is large amount of data (collected from sensors), which needs to be delivered to right places at the right time so communication paradigm is very essential design consideration which impacts many key properties such as scalability, reliability, availability, timeliness and cost of overall system. The OSA-CBM (Open System Architecture for Condition Based Maintenance) is an open standard that defines an open architecture for moving information in a condition-based maintenance system. Typically, companies developing condition-based maintenance systems must develop software and hardware components, in addition a framework for these components to integrate. OSA-CBM is a standard framework for implementing condition-based maintenance systems. It not only describes the six functional blocks of condition based maintenance systems but also the interfaces to establish communication among these blocks. OSA-CBM specifies the input and output between the CBM modules. In simple words, it describes the information that is moved and how to move it. OSA-CBM can be implemented using various available distributed middleware but it is not clear which implementation is more efficient. This paper presents an approach to design, implement and analysis of network architecture of CBM systems using OSACBM data model.
IEEE Transactions on Cognitive and Developmental Systems
The trustworthiness of robots and autonomous systems (RAS) has taken a prominent position on the ... more The trustworthiness of robots and autonomous systems (RAS) has taken a prominent position on the way towards full autonomy. This work is the first to systematically explore the key facets of human-centred AI for trustworthy RAS. We identified five key properties of a trustworthy RAS, i.e., RAS must be (i) safe in any uncertain and dynamic environment; (ii) secure, i.e., protect itself from cyber threats; (iii) healthy and fault-tolerant; (iv) trusted and easy to use to enable effective human-machine interaction (HMI); (v) compliant with the law and ethical expectations. While the applications of RAS have mainly focused on performance and productivity, not enough scientific attention has been paid to the risks posed by advanced AI in RAS. We analytically examine the challenges of implementing trustworthy RAS with respect to the five key properties and explore the role and roadmap of AI technologies in ensuring the trustworthiness of RAS in respect of safety, security, health, HMI, and ethics. A new acceptance model of RAS is provided as a framework for human-centric AI requirements and for implementing trustworthy RAS by design. This approach promotes human-level intelligence to augment human capabilities and focuses on contribution to humanity.
2019 International Conference on Computational Science and Computational Intelligence (CSCI)
A hierarchy of Linguistic Decision Trees (LDTs), called linguistic attribute hierarchy (LAH), can... more A hierarchy of Linguistic Decision Trees (LDTs), called linguistic attribute hierarchy (LAH), can provide a transparent information propagation and a hierarchical decision making process. In this paper, we quantified the effect of various factors on the diagnosis of Diabetes with the information gain of each attribute to the decision variable, and developed an LAH, where, the LDTs are constructed under the framework of the knowledge-based label semantics, referring to the knowledge of the diagnosis criteria of Diabetes, defined by the World Health Organisation. A genetic wrapper algorithm was developed to find the best LAH for improving the accuracy of Diabetes diagnosis. The optimal LAH for Diabetes diagnosis achieved the accuracy up to 92% on the benchmark database, Pima Indian Diabetes data. The accuracy is much better than that in the research literature.
The universe approximate theorem states that a shadow neural network (one hidden layer) can repre... more The universe approximate theorem states that a shadow neural network (one hidden layer) can represent any non-linear function. In this paper, we aim at examining how good a shadow neural network is for solving non-linear decision making problems. We proposed a performance driven incremental approach to searching the best shadow neural network for decision making, given a data set. The experimental results on the two benchmark data sets, Breast Cancer in Wisconsin and SMS Spams, demonstrate the correction of universe approximate theorem, and show that the number of hidden neurons, taking about the half of input number, is good enough to represent the function from data. It is shown that the performance driven BP learning is faster than the error-driven BP learning, and that the performance of the SNN obtained by the former is not worse than that of the SNN obtained by the latter. This indicates that when learning a neural network with the BP algorithm, the performance reaches a certa...
To identify the key factors and create the landscape of cybersecurity for embedded systems (CSES)... more To identify the key factors and create the landscape of cybersecurity for embedded systems (CSES), an analytical review of the existing research on CSES has been conducted. The common properties of embedded systems, such as mobility, small size, low cost, independence, and limited power consumption when compared to traditional computer systems, have caused many challenges in CSES. The conflict between cybersecurity requirements and the computing capabilities of embedded systems makes it critical to implement sophisticated security countermeasures against cyber-attacks in an embedded system with limited resources, without draining those resources. In this study, twelve factors influencing CSES have been identified: (1) the components; (2) the characteristics; (3) the implementation; (4) the technical domain; (5) the security requirements; (6) the security problems; (7) the connectivity protocols; (8) the attack surfaces; (9) the impact of the cyber-attacks; (10) the security challeng...
Genetic algorithms have been applied to solve the 2-page drawing problem successfully, but they w... more Genetic algorithms have been applied to solve the 2-page drawing problem successfully, but they work with one global population, so the search time and space are limited. Parallelization provides an attractive prospect in improving the efficiency and solution quality of genetic algorithms. One of the most popular tools for parallel computing is Message Passing Interface (MPI). In this paper, we present four island models of Parallel Genetic Algorithms with MPI: island models with linear, grid, random graph topologies, and island model with periodical synchronisation. We compare their efficiency and quality of solutions for the 2-page drawing problem on a variety of graphs.
Uploads
Papers by Hongmei He