This page has only limited features, please log in for full access.
MHealth is considered as an acceptable solution toward health-related challenges especially within maternal and neonatal health. This paper is a review of acceptable mHealth technologies and the impact on maternal and neonatal health. A focus is directed toward Sub-Saharan Africa where a review of mHealth technologies that work in the area is conducted. A randomized control trial utilizing text messages is reviewed to check on the reliability, and viability of the solution within the Kenyan context. Additional tools that are reviewed include open data kit, a data collection tool as well as Google Aggregate server, a data storage tool which are used to evaluate the viability of the ICT intervention. Key findings show that not only text messages are cost effective but also can be scaled for larger projects. A combination of text messages, open data kit, and Google aggregate provides for a feasible and reliable combination when running feasible control trials interventions. In conclusion, it is recommended that a customized developed system to be used instead of a commercial system especially when running large-size control trials which may require a more cost-effective solution.
Victoria Mukami; Richard Millham; Threethambal Puckree; Simon James Fong. Identifying the Most Feasible Technologies for mHealth Maternal Mortality Interventions in Sub-Saharan Africa. Proceedings of International Conference on Big Data, Machine Learning and Applications 2021, 173 -184.
AMA StyleVictoria Mukami, Richard Millham, Threethambal Puckree, Simon James Fong. Identifying the Most Feasible Technologies for mHealth Maternal Mortality Interventions in Sub-Saharan Africa. Proceedings of International Conference on Big Data, Machine Learning and Applications. 2021; ():173-184.
Chicago/Turabian StyleVictoria Mukami; Richard Millham; Threethambal Puckree; Simon James Fong. 2021. "Identifying the Most Feasible Technologies for mHealth Maternal Mortality Interventions in Sub-Saharan Africa." Proceedings of International Conference on Big Data, Machine Learning and Applications , no. : 173-184.
Remote sensing streams continuous data feed from the satellite to ground station for data analysis. Often the data analytics involves analyzing data in real-time, such as emergency control, surveillance of military operations or scenarios that change rapidly. Traditional data mining requires all the data to be available prior to inducing a model by supervised learning, for automatic image recognition or classification. Any new update on the data prompts the model to be built again by loading in all the previous and new data. Therefore, the training time will increase indefinitely making it unsuitable for real-time application in remote sensing. As a contribution to solving this problem, a new approach of data analytics for remote sensing for data stream mining is formulated and reported in this paper. Fresh data feed collected from afar is used to approximate an image recognition model without reloading the history, which helps eliminate the latency in building the model again and again. In the past, data stream mining has a drawback in approximating a classification model with a sufficiently high level of accuracy. This is due to the one-pass incremental learning mechanism inherently exists in the design of the data stream mining algorithm. In order to solve this problem, a novel streamlined sensor data processing method is proposed called evolutionary expand-and-contract instance-based learning algorithm (EEAC-IBL). The multivariate data stream is first expanded into many subspaces, and then the subspaces, which are corresponding to the characteristics of the features are selected and condensed into a significant feature subset. The selection operates stochastically instead of deterministically by evolutionary optimization, which approximates the best subgroup. Followed by data stream mining, the model learning for image recognition is done on the fly. This stochastic approximation method is fast and accurate, offering an alternative to the traditional machine learning method for image recognition application in remote sensing. Our experimental results show computing advantages over other classical approaches, with a mean accuracy improvement at 16.62%.
Shimin Hu; Simon Fong; Lili Yang; Shuang-Hua Yang; Nilanjan Dey; Richard Millham; Jinan Fiaidhi. Fast and Accurate Terrain Image Classification for ASTER Remote Sensing by Data Stream Mining and Evolutionary-EAC Instance-Learning-Based Algorithm. Remote Sensing 2021, 13, 1123 .
AMA StyleShimin Hu, Simon Fong, Lili Yang, Shuang-Hua Yang, Nilanjan Dey, Richard Millham, Jinan Fiaidhi. Fast and Accurate Terrain Image Classification for ASTER Remote Sensing by Data Stream Mining and Evolutionary-EAC Instance-Learning-Based Algorithm. Remote Sensing. 2021; 13 (6):1123.
Chicago/Turabian StyleShimin Hu; Simon Fong; Lili Yang; Shuang-Hua Yang; Nilanjan Dey; Richard Millham; Jinan Fiaidhi. 2021. "Fast and Accurate Terrain Image Classification for ASTER Remote Sensing by Data Stream Mining and Evolutionary-EAC Instance-Learning-Based Algorithm." Remote Sensing 13, no. 6: 1123.
In modern healthcare, sensing technologies such as IoT empower the quality of assisted living service by knowing what a resident is doing in real-time. Using extreme connectivity and cloud computing in a smart home, where a collection of sensors is installed, the sensors sample continuously from the movements of the resident as well as ambient data from the surrounding inside the house. Automatic human activity recognition of the resident's activities is one of the key components of assisted living in smart home. For monitoring in-home safety, the ability in recognizing abnormal activities such as accident, falling, acute disease attack (e.g. asthma, stroke, etc.), fainting, wobbling, is particularly important. The detection and machine learning process must be both accurate and fast, to cope with the real-time activity recognition. To this end, a novel streamlined sensor data processing method is proposed called Evolutionary Expand-and-Contract Instance-based Learning algorithm (EEAC-IBL). The multivariate data stream is first expanded into many subspaces, then the subspaces which are corresponding to the characteristics of the features are selected and condensed into a significant feature subset. The selection operates scholastically instead of deterministically by evolutionary optimization which approximates the best subgroup. Followed by data stream mining, the machine learning for activity recognition is done on the fly. This approach is unique and suitable for such extreme connectivity scenario where precise feature selection is not required, and the relative importance of each feature among the sensor data changes over time. This stochastic approximation method is fast and accurate, offering an alternative to traditional machine learning method for smart home activity recognition application. Our experimental results show computing advantages over other classical approaches.
Shimin Hu; Simon Fong; Wei Song; Kyungeun Cho; Richard C. Millham; Jinan Fiaidhi. Novel evolutionary-EAC instance-learning-based algorithm for fast data stream mining in assisted living with extreme connectivity. Computing 2021, 103, 1519 -1543.
AMA StyleShimin Hu, Simon Fong, Wei Song, Kyungeun Cho, Richard C. Millham, Jinan Fiaidhi. Novel evolutionary-EAC instance-learning-based algorithm for fast data stream mining in assisted living with extreme connectivity. Computing. 2021; 103 (7):1519-1543.
Chicago/Turabian StyleShimin Hu; Simon Fong; Wei Song; Kyungeun Cho; Richard C. Millham; Jinan Fiaidhi. 2021. "Novel evolutionary-EAC instance-learning-based algorithm for fast data stream mining in assisted living with extreme connectivity." Computing 103, no. 7: 1519-1543.
In this paper, we present a clustering model for energy optimization based on the nature-inspired behaviour of animals. This clustering model finds the optimal distance to send data packets from one location to another, either long or short distances, so as to maintain the lifetime of the sensor network. The challenge with sensor networks is how to balance the energy load, which can be achieved by selecting a sensor node with an adequate amount of energy from a cluster to compensate for those sensor nodes with limited amount of energy. Generally, the clustering technique is one of the approaches to solve this challenge because it optimizes energy to increase the lifetime of the sensor network. We focus on nodes with different energy makeup, and based on the number of nodes that send packets, and evaluated the network performance in terms of the stability period, network lifetime and network throughput. Two nature-inspired algorithms (that is, kestrel-based search algorithm and wolf search algorithm with minus step previous) were compared to evaluate which one is energy-efficient when used as a clustering algorithm. It was found that, the Kestrel-based Search Algorithm Distributed Energy Efficient Clustering (KSA-DEEC) model has the optimal network run time (in seconds) to send a higher number of packets to base station successfully. Consequently, The KSA-DEEC model has an optimal network lifetime performance as compared to the Wolf Search Algorithm with Minus Step Previous (WSAMP)-DEEC model. It also has the highest network throughput in the simulation that was performed while the WSAMP-DEEC model showed prospects of better performance in some of the cases.
Israel Edem Agbehadji; Richard C. Millham; Abdultaofeek Abayomi; Jason J. Jung; Simon James Fong; Samuel Ofori Frimpong. Clustering algorithm based on nature-inspired approach for energy optimization in heterogeneous wireless sensor network. Applied Soft Computing 2021, 104, 107171 .
AMA StyleIsrael Edem Agbehadji, Richard C. Millham, Abdultaofeek Abayomi, Jason J. Jung, Simon James Fong, Samuel Ofori Frimpong. Clustering algorithm based on nature-inspired approach for energy optimization in heterogeneous wireless sensor network. Applied Soft Computing. 2021; 104 ():107171.
Chicago/Turabian StyleIsrael Edem Agbehadji; Richard C. Millham; Abdultaofeek Abayomi; Jason J. Jung; Simon James Fong; Samuel Ofori Frimpong. 2021. "Clustering algorithm based on nature-inspired approach for energy optimization in heterogeneous wireless sensor network." Applied Soft Computing 104, no. : 107171.
Sustainable energy development consists of design, planning, and control optimization problems that are typically complex and computationally challenging for traditional optimization approaches. However, with developments in artificial intelligence, bio-inspired algorithms mimicking the concepts of biological evolution in nature and collective behaviors in societies of agents have recently become popular and shown potential success for these issues. Therefore, we investigate the latest research on bio-inspired approaches for smart energy management systems in smart homes, smart buildings, and smart grids in this paper. In particular, we give an overview of the well-known and emerging bio-inspired algorithms, including evolutionary-based and swarm-based optimization methods. Then, state-of-the-art studies using bio-inspired techniques for smart energy management systems are presented. Lastly, open challenges and future directions are also addressed to improve research in this field.
Tri-Hai Nguyen; Luong Nguyen; Jason Jung; Israel Agbehadji; Samuel Frimpong; Richard Millham. Bio-Inspired Approaches for Smart Energy Management: State of the Art and Challenges. Sustainability 2020, 12, 8495 .
AMA StyleTri-Hai Nguyen, Luong Nguyen, Jason Jung, Israel Agbehadji, Samuel Frimpong, Richard Millham. Bio-Inspired Approaches for Smart Energy Management: State of the Art and Challenges. Sustainability. 2020; 12 (20):8495.
Chicago/Turabian StyleTri-Hai Nguyen; Luong Nguyen; Jason Jung; Israel Agbehadji; Samuel Frimpong; Richard Millham. 2020. "Bio-Inspired Approaches for Smart Energy Management: State of the Art and Challenges." Sustainability 12, no. 20: 8495.
Technologies that can be used for location outdoors are readily available using Global Positioning Systems (GPS) whilst technologies used for indoor location still prove to be a challenge. Technologies such as Radio Frequency Identification (RFID), Bluetooth, and Wi-Fi, together with location algorithms that include optimization, still require further research for large-scale deployments. This study adopts Bluetooth Low Energy technology and uses the Received Signal strength Indicator (RSSI) from messages as a data source. We then analyse the RSSI from Low Power Nodes, their calculated mean, median and mode values as a basis for further use in an indoor real time location system. Fingerprint databases have been used extensively as a reference to determine location. However, due to the changing indoor environment these may become outdated very quickly. Therefore, this study proposes the use of a Link Quality Indicator as a reference point for further calculation of the location of an asset or a person. The Nordic System on Chip (SOC) is used as the low power node together with a series of Raspberry Pi gateways. Results show that the mean and mode can be used in combination to filter and smooth RSSI values. These calculated RSSI values can then be used and as inputs for an indoor location engine for location determination.
Jay Pancham; Richard Millham; Simon James Fong. Analysis of Bluetooth Low Energy RSSI Values for Use as a Real Time Link Quality Indicator for Indoor Location. Transactions on Petri Nets and Other Models of Concurrency XV 2020, 12254, 980 -991.
AMA StyleJay Pancham, Richard Millham, Simon James Fong. Analysis of Bluetooth Low Energy RSSI Values for Use as a Real Time Link Quality Indicator for Indoor Location. Transactions on Petri Nets and Other Models of Concurrency XV. 2020; 12254 ():980-991.
Chicago/Turabian StyleJay Pancham; Richard Millham; Simon James Fong. 2020. "Analysis of Bluetooth Low Energy RSSI Values for Use as a Real Time Link Quality Indicator for Indoor Location." Transactions on Petri Nets and Other Models of Concurrency XV 12254, no. : 980-991.
In this chapter, the concept of big data is defined based on the five characteristics namely velocity, volume, value, veracity, and variety. Once defined, the sequential phases of big data are denoted, namely data cleansing, data mining, and visualization. Each phase consists of several sub-phases or steps. These steps are briefly described. In order to manipulate data, a number of methods may be employed. In this chapter, we look at an approach for data imputation or the extrapolation of missing values in data. The concept of genetic algorithms along with its off-shoot, meta-heuristic algorithms, is presented. A specialized type of meta-heuristic algorithm, bio-inspired algorithms, is introduced with several example algorithms. An example, a bio-inspired algorithm, the kestrel, is introduced using the steps outlined for the development of a bio-inspired algorithm (Zang et al. 2010). This kestrel algorithm will be used as an approach for data imputation within the big data phases framework.
Richard Millham; Israel Edem Agbehadji; Hongji Yang. The Big Data Approach Using Bio-Inspired Algorithms: Data Imputation. Springer Tracts in Nature-Inspired Computing 2020, 1 -19.
AMA StyleRichard Millham, Israel Edem Agbehadji, Hongji Yang. The Big Data Approach Using Bio-Inspired Algorithms: Data Imputation. Springer Tracts in Nature-Inspired Computing. 2020; ():1-19.
Chicago/Turabian StyleRichard Millham; Israel Edem Agbehadji; Hongji Yang. 2020. "The Big Data Approach Using Bio-Inspired Algorithms: Data Imputation." Springer Tracts in Nature-Inspired Computing , no. : 1-19.
Data mining plays a critical role in uncovering hidden interesting patterns that can be exploited, through advantageous interpretation, for useful insight in the conduct of their industry. The prolific growth of data in business provides new opportunities in a wide range of domains from e-commerce to market intelligence. Big data provides a large, sometimes comprehensive view, of an organization’s functioning while thick data provides a more in-depth, ethnographical view of a tiny aspect of this operation. Data modelling may be denoted as a method to determine and evaluate the data needs required to support the business processes rooted within the information systems of an organization.
Richard Millham; Israel Edem Agbehadji; Emmanuel Freeman. Business Intelligence. Springer Tracts in Nature-Inspired Computing 2020, 207 -218.
AMA StyleRichard Millham, Israel Edem Agbehadji, Emmanuel Freeman. Business Intelligence. Springer Tracts in Nature-Inspired Computing. 2020; ():207-218.
Chicago/Turabian StyleRichard Millham; Israel Edem Agbehadji; Emmanuel Freeman. 2020. "Business Intelligence." Springer Tracts in Nature-Inspired Computing , no. : 207-218.
As the use of data mining with its application becomes more predominant in academe and in industry, there is a growing need to develop needed tools and rely on their outputs for meaningful information. As the various aspects of big data developed, different tools developed to assist with the utilisation of these aspects. Various types of users had different requirements for the same aspect of data mining. Furthermore, these tools began as tools for simple data mining tasks among software designed companies while eventually evolving into more specialised and niche roles within smaller business/groups. In this chapter, we will cover the various types of considerations that might form a customer base for a given tool. At the end, we will describe various tools in terms of the tasks that they perform and the user market that they are designed for.
Richard Millham. Big Data Tools for Tasks. Springer Tracts in Nature-Inspired Computing 2020, 219 -226.
AMA StyleRichard Millham. Big Data Tools for Tasks. Springer Tracts in Nature-Inspired Computing. 2020; ():219-226.
Chicago/Turabian StyleRichard Millham. 2020. "Big Data Tools for Tasks." Springer Tracts in Nature-Inspired Computing , no. : 219-226.
Data mining seeks to discover hidden relationship in data attributes for decision making. Mostly, search algorithms help to find hidden relationships between data attributes by counting the number of occurrence without focusing on the closeness of time dimension. In this chapter, we focus on how closeness preference model can be applied in discovering association rules instead of only using support and confidence value which are the traditional method of discovering association rules.
Richard Millham; Israel Edem Agbehadji; Hongji Yang. Extracting Association Rules: Meta-Heuristic and Closeness Preference Approach. Springer Tracts in Nature-Inspired Computing 2020, 81 -95.
AMA StyleRichard Millham, Israel Edem Agbehadji, Hongji Yang. Extracting Association Rules: Meta-Heuristic and Closeness Preference Approach. Springer Tracts in Nature-Inspired Computing. 2020; ():81-95.
Chicago/Turabian StyleRichard Millham; Israel Edem Agbehadji; Hongji Yang. 2020. "Extracting Association Rules: Meta-Heuristic and Closeness Preference Approach." Springer Tracts in Nature-Inspired Computing , no. : 81-95.
Feature selection helps with the selection of relevant features that are present in large number of features and ignores the remaining features that have little value on output feature set. Deep learning methods have been applied to select relevant features in the classification problem; however, the current approach (i.e., search strategies) to the learning of a parameter can either grow out of bound or shrink (they decay exponentially in the number of layers) at each time step (iteration) with the subsequent effect of inaccurate classification of features. To address this challenge of the current search strategies, we proposes an approach to the learning of a parameter for the classification problem based on the behavior of birds (i.e., kestrel bird). The proposed approach, bio-inspired approach, is modeled as a search algorithm which is then integrated with deep learning method. The integration enables learning of optimum parameter for feature selection in a classification problem. A benchmark dataset (i.e., bioinformatics dataset with continuous data attributes) from the Arizona State University was chosen because of its high dimensionality and its continuous data attribute nature. This dataset was used to test the proposed algorithm. The algorithm proposed was evaluated against comparative bio-inspired algorithms namely PSO, ACO, WSA-MP and BAT. The findings indicate that KSA produces minimum learning rate in five datasets out of nine datasets. While on the classification accuracy, KSA produces the highest accuracy of classification in four out of nine dataset. In terms of comparison of classification accuracy using “Wilcoxon signed-rank test,” the finding indicates that “there is no statistically significant differences between the comparative algorithm and the proposed algorithm.” This indicates that KSA could be used as an alternative approach to feature selection for a classification problem.
Richard Millham; Israel Edem Agbehadji; Hongji Yang. Parameter Tuning onto Recurrent Neural Network and Long Short-Term Memory (RNN-LSTM) Network for Feature Selection in Classification of High-Dimensional Bioinformatics Datasets. Springer Tracts in Nature-Inspired Computing 2020, 21 -42.
AMA StyleRichard Millham, Israel Edem Agbehadji, Hongji Yang. Parameter Tuning onto Recurrent Neural Network and Long Short-Term Memory (RNN-LSTM) Network for Feature Selection in Classification of High-Dimensional Bioinformatics Datasets. Springer Tracts in Nature-Inspired Computing. 2020; ():21-42.
Chicago/Turabian StyleRichard Millham; Israel Edem Agbehadji; Hongji Yang. 2020. "Parameter Tuning onto Recurrent Neural Network and Long Short-Term Memory (RNN-LSTM) Network for Feature Selection in Classification of High-Dimensional Bioinformatics Datasets." Springer Tracts in Nature-Inspired Computing , no. : 21-42.
The purpose of this chapter is to examine the role of various fog computing models, particularly in managing the three main characteristics of big data (volume, velocity, and variety) produced within the Internet of Things. Fog computing is shown to be highly advantageous in areas such as smart city and healthcare monitoring. Given its architecture, the fog computing model has significant energy savings over its traditional cloud computing model. Different algorithms, including bio-inspired algorithms, are presented that have been used for distribution of architectural components, such as sensors and nodes, for optimal energy efficiency, load scheduling, quality of services, and resources. At the end, a fog computing framework is proposed that is able to manage both the essential characteristics (velocity, variety, volume) and the quality of use characteristics (veracity, value) of big data. The “quality of use” dimensions of this data could be assessed through the use of a set of metrics along with expert knowledge that determines “high value” data.
Richard Millham; Israel Edem Agbehadji; Samuel Ofori Frimpong. The Paradigm of Fog Computing with Bio-inspired Search Methods and the “5Vs” of Big Data. Springer Tracts in Nature-Inspired Computing 2020, 145 -167.
AMA StyleRichard Millham, Israel Edem Agbehadji, Samuel Ofori Frimpong. The Paradigm of Fog Computing with Bio-inspired Search Methods and the “5Vs” of Big Data. Springer Tracts in Nature-Inspired Computing. 2020; ():145-167.
Chicago/Turabian StyleRichard Millham; Israel Edem Agbehadji; Samuel Ofori Frimpong. 2020. "The Paradigm of Fog Computing with Bio-inspired Search Methods and the “5Vs” of Big Data." Springer Tracts in Nature-Inspired Computing , no. : 145-167.
In this chapter, we first look at patterns with their relevance of discovery to business. We then do a survey and evaluation, in terms of advantages and disadvantages, of different mining algorithms that are suited for both traditional and big data sources. These algorithms include those designed for both sequential and closed sequential pattern mining for both the sequential and parallel processing environments.
Richard Millham; Israel Edem Agbehadji; Hongji Yang. Pattern Mining Algorithms. Springer Tracts in Nature-Inspired Computing 2020, 67 -80.
AMA StyleRichard Millham, Israel Edem Agbehadji, Hongji Yang. Pattern Mining Algorithms. Springer Tracts in Nature-Inspired Computing. 2020; ():67-80.
Chicago/Turabian StyleRichard Millham; Israel Edem Agbehadji; Hongji Yang. 2020. "Pattern Mining Algorithms." Springer Tracts in Nature-Inspired Computing , no. : 67-80.
The emergence of the 2019 novel coronavirus (COVID-19) which was declared a pandemic has spread to 210 countries worldwide. It has had a significant impact on health systems and economic, educational and social facets of contemporary society. As the rate of transmission increases, various collaborative approaches among stakeholders to develop innovative means of screening, detecting and diagnosing COVID-19’s cases among human beings at a commensurate rate have evolved. Further, the utility of computing models associated with the fourth industrial revolution technologies in achieving the desired feat has been highlighted. However, there is a gap in terms of the accuracy of detection and prediction of COVID-19 cases and tracing contacts of infected persons. This paper presents a review of computing models that can be adopted to enhance the performance of detecting and predicting the COVID-19 pandemic cases. We focus on big data, artificial intelligence (AI) and nature-inspired computing (NIC) models that can be adopted in the current pandemic. The review suggested that artificial intelligence models have been used for the case detection of COVID-19. Similarly, big data platforms have also been applied for tracing contacts. However, the nature-inspired computing (NIC) models that have demonstrated good performance in feature selection of medical issues are yet to be explored for case detection and tracing of contacts in the current COVID-19 pandemic. This study holds salient implications for practitioners and researchers alike as it elucidates the potentials of NIC in the accurate detection of pandemic cases and optimized contact tracing.
Israel Edem Agbehadji; Bankole Osita Awuzie; Alfred Beati Ngowi; Richard C. Millham. Review of Big Data Analytics, Artificial Intelligence and Nature-Inspired Computing Models towards Accurate Detection of COVID-19 Pandemic Cases and Contact Tracing. International Journal of Environmental Research and Public Health 2020, 17, 5330 .
AMA StyleIsrael Edem Agbehadji, Bankole Osita Awuzie, Alfred Beati Ngowi, Richard C. Millham. Review of Big Data Analytics, Artificial Intelligence and Nature-Inspired Computing Models towards Accurate Detection of COVID-19 Pandemic Cases and Contact Tracing. International Journal of Environmental Research and Public Health. 2020; 17 (15):5330.
Chicago/Turabian StyleIsrael Edem Agbehadji; Bankole Osita Awuzie; Alfred Beati Ngowi; Richard C. Millham. 2020. "Review of Big Data Analytics, Artificial Intelligence and Nature-Inspired Computing Models towards Accurate Detection of COVID-19 Pandemic Cases and Contact Tracing." International Journal of Environmental Research and Public Health 17, no. 15: 5330.
Clustering technique is one of the approach to optimize energy consumption, balance load and increase lifetime of networks in wireless sensor network (WSN). In this paper, a novel multi-stage clustering algorithm is proposed for heterogeneous energy environment. The proposed multi-stage approach combines the behaviour of a bird and the distributed energy efficient model. The behaviour of the bird is expressed in the form of mathematical expression and then translated into an algorithm. The algorithm is then combined with the distributed energy efficient model to ensure efficient energy optimization. The proposed multi-stage clustering algorithm (referred to as DEEC-KSA) is evaluated through simulation and compared with benchmarked clustering algorithms. The result of simulation showed that the performance of DEEC-KSA is efficient among the comparative clustering algorithms for energy optimization in terms of stability period, network lifetime and network throughput. Additionally, the proposed DEEC-KSA has the optimal network running time (in seconds) to send higher number of packets to base station successfully.
Israel Edem Agbehadji; Richard C. Millham; Simon James Fong; Jason J. Jung; Nam Bui; Abdultaofeek Abayomi. Multi-stage Clustering Algorithm for Energy Optimization in Wireless Sensor Networks. Communications in Computer and Information Science 2019, 223 -238.
AMA StyleIsrael Edem Agbehadji, Richard C. Millham, Simon James Fong, Jason J. Jung, Nam Bui, Abdultaofeek Abayomi. Multi-stage Clustering Algorithm for Energy Optimization in Wireless Sensor Networks. Communications in Computer and Information Science. 2019; ():223-238.
Chicago/Turabian StyleIsrael Edem Agbehadji; Richard C. Millham; Simon James Fong; Jason J. Jung; Nam Bui; Abdultaofeek Abayomi. 2019. "Multi-stage Clustering Algorithm for Energy Optimization in Wireless Sensor Networks." Communications in Computer and Information Science , no. : 223-238.
Nature serves as a source of motivation for the development of new approaches to solve real life problems such as minimizing the computation time on visualization of frequently changed patterns from datasets. An approach adopted is the use of evolutionary algorithm based on swarm intelligence. This evolutionary algorithm is a computational approach that is based on the characteristics of dung beetles in moving dung with limited computational power. The contribution of this paper is the mathematical formulation of the unique characteristics of dung beetles (that is, path integration with replusion and attraction of trace, dance during orientation and ball rolling on straight line) in creating imaginary homes after displacement of its food (dung) source. The mathematical formulation is translated into an algorithmic structure that search for the best possible path and display patterns using simple two dimensional view. The computational time and optimal value are the techniques to select the best visualization algorithm (between the proposed dung beetle algorithm and comparative algorithms –that is Bee and ACO). The analysis shows that dung beetle algorithm has mean computational time of 0.510, Bee has 2.189 and ACO for data visualization has 0.978. While, the mean optimal value for bung beetle is 0.000117, Bee algorithm is 2.46E−08 and ACO for data visualization is 6.73E−13. The results indicates that dung beetle algorithm uses minimum computation time for data visualization.
Israel Edem Agbehadji; Richard Millham; Surendra Thakur; Hongji Yang; Hillar Addo. Visualization of Frequently Changed Patterns Based on the Behaviour of Dung Beetles. Communications in Computer and Information Science 2018, 230 -245.
AMA StyleIsrael Edem Agbehadji, Richard Millham, Surendra Thakur, Hongji Yang, Hillar Addo. Visualization of Frequently Changed Patterns Based on the Behaviour of Dung Beetles. Communications in Computer and Information Science. 2018; ():230-245.
Chicago/Turabian StyleIsrael Edem Agbehadji; Richard Millham; Surendra Thakur; Hongji Yang; Hillar Addo. 2018. "Visualization of Frequently Changed Patterns Based on the Behaviour of Dung Beetles." Communications in Computer and Information Science , no. : 230-245.
Feed-forward neural networks are efficient at solving various types of problems. However, finding efficient training algorithms for feed-forward neural networks is challenging. The dynamic group optimisation (DGO) algorithm is a recently proposed half-swarm half-evolutionary algorithm, which exhibits a rapid convergence rate and good performance in searching and avoiding local optima. In this paper, we propose a new hybrid algorithm, FNNDGO that integrates the DGO algorithm into a feed-forward neural network. DGO plays an optimisation role in training the neural network, by tuning parameters to their optimal values and configuring the structure of feed-forward neural networks. The performance of the proposed algorithm was determined by comparing its performance with those of other training methods in solving two types of problems. The experimental results show that our proposed algorithm exhibits promising performance for solving real-world problems.
Rui Tang; Simon Fong; Suash Deb; Athanasios V. Vasilakos; Richard C Millham. Dynamic group optimisation algorithm for training feed-forward neural networks. Neurocomputing 2018, 314, 1 -19.
AMA StyleRui Tang, Simon Fong, Suash Deb, Athanasios V. Vasilakos, Richard C Millham. Dynamic group optimisation algorithm for training feed-forward neural networks. Neurocomputing. 2018; 314 ():1-19.
Chicago/Turabian StyleRui Tang; Simon Fong; Suash Deb; Athanasios V. Vasilakos; Richard C Millham. 2018. "Dynamic group optimisation algorithm for training feed-forward neural networks." Neurocomputing 314, no. : 1-19.
Israel Edem Agbehadji; Richard Millham; Simon James Fong; Hongji Yang. Kestrel-based Search Algorithm (KSA) and Long Short Term Memory (LSTM) Network for feature selection in classification of high-dimensional bioinformatics datasets. Proceedings of the 2018 Federated Conference on Computer Science and Information Systems 2018, 15, 15 -20.
AMA StyleIsrael Edem Agbehadji, Richard Millham, Simon James Fong, Hongji Yang. Kestrel-based Search Algorithm (KSA) and Long Short Term Memory (LSTM) Network for feature selection in classification of high-dimensional bioinformatics datasets. Proceedings of the 2018 Federated Conference on Computer Science and Information Systems. 2018; 15 ():15-20.
Chicago/Turabian StyleIsrael Edem Agbehadji; Richard Millham; Simon James Fong; Hongji Yang. 2018. "Kestrel-based Search Algorithm (KSA) and Long Short Term Memory (LSTM) Network for feature selection in classification of high-dimensional bioinformatics datasets." Proceedings of the 2018 Federated Conference on Computer Science and Information Systems 15, no. : 15-20.
Duplicate detection is a process of identifying a pair of words that refers to the same real-word object. Generally, words consist of letters that have a syntax representation. In most cases, words, such as names, are incorrectly spelt during data entry and that creates duplicate data and if it is unresolved could lead to inconsistency of data. Fundamental algorithms that are applied in the design of duplicate detection systems includes Smith-Waterman and Jaro-Winkler algorithms. The study compares and analyses the application of Smith-Waterman algorithm and Jaro-Winkler algorithm to find duplicate words in large dataset such as health dataset. The basis for comparison is to find how accurate these algorithms are in detecting duplicate words in large health dataset. The contribution of this paper is the use of transitive and symmetry property on both Smith-Waterman and Jaro-Winkler algorithm when large dataset is involved in the duplicate detection processes.
Israel Edem Agbehadji; Hongji Yang; Simon Fong; Richard Millham. The Comparative Analysis of Smith-Waterman Algorithm with Jaro-Winkler Algorithm for the Detection of Duplicate Health Related Records. 2018 International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD) 2018, 1 -10.
AMA StyleIsrael Edem Agbehadji, Hongji Yang, Simon Fong, Richard Millham. The Comparative Analysis of Smith-Waterman Algorithm with Jaro-Winkler Algorithm for the Detection of Duplicate Health Related Records. 2018 International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD). 2018; ():1-10.
Chicago/Turabian StyleIsrael Edem Agbehadji; Hongji Yang; Simon Fong; Richard Millham. 2018. "The Comparative Analysis of Smith-Waterman Algorithm with Jaro-Winkler Algorithm for the Detection of Duplicate Health Related Records." 2018 International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD) , no. : 1-10.
Indoor Real Time Location Systems (RTLS) research identifies Bluetooth Low Energy as one of the technologies that promise an acceptable response to the requirements of the Healthcare environment. A scalable dynamic model for sensor detection, which uses the latest developments of Bluetooth Low Energy, is designed to extend its range coverage. This design extends on our previous papers which tested the range and signal strength through multiple types of obstructions. The model is based on the scenarios and use cases identified for future use in RTLS within the Health care sector. The Unified Modelling Language (UML) is used to present the models and inspections and walkthroughs are used to validate and verify them. This model will be implemented using Bluetooth Low Energy devices for patients and assets with in the Health care sector.
Jay Pancham; Richard Millham; Simon James Fong. A Scalable Bluetooth Low Energy Design Model for Sensor Detection for an Indoor Real Time Location System. Transactions on Petri Nets and Other Models of Concurrency XV 2018, 317 -330.
AMA StyleJay Pancham, Richard Millham, Simon James Fong. A Scalable Bluetooth Low Energy Design Model for Sensor Detection for an Indoor Real Time Location System. Transactions on Petri Nets and Other Models of Concurrency XV. 2018; ():317-330.
Chicago/Turabian StyleJay Pancham; Richard Millham; Simon James Fong. 2018. "A Scalable Bluetooth Low Energy Design Model for Sensor Detection for an Indoor Real Time Location System." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 317-330.