Kwok Tai Chui

The Generic Design of a High-Traffic Advanced Metering Infrastructure Using ZigBee

A multi-interface ZigBee building area network (MIZBAN) for a high-traffic advanced metering infrastructure (AMI) for high-rise buildings was developed. This supports meter management functions such as Demand Response for smart grid applications. To cater for the high-traffic communication in these building area networks (BANs), a multi-interface management framework was defined and designed to coordinate the operation between multiple interfaces based on a newly defined tree-based mesh (T-Mesh) ZigBee topology, which supports both mesh and tree routing in a single network. To evaluate MIZBAN, an experiment was set up in a five-floor building. Based on the measured data, simulations were performed to extend the analysis to a 23-floor building. These revealed that MIZBAN yields an improvement in application-layer latency of the backbone and the floor network by 75% and 67%, respectively. This paper provides the design engineer with seven recommendations for a generic MIZBAN design, which will fulfill the requirement for demand response by the U.S. government, i.e. a latency of less than 0.25 s.

The design of dual radio ZigBee homecare gateway for remote patient monitoring

A Dual Radio ZigBee Homecare Gateway (DRZHG) has been proposed and implemented to support remote patient monitoring. The novelty of DR-ZHG is two-fold. Firstly, it increases the transmission data rate of ZigBee. The Dual Radio ZigBee design furnishes low latency and highly accurate telehealth service at home. Secondly, the zero-configuration design of the DR-ZHG offers the most user friendly telehealth service to elderly people and long-terms patients. Analysis reveals that, for streaming data devices, the network depth should be confined to three (3) in a ZigBee tree network. As for polling data devices, it is analyzed that nine (9) sensors can be supported in a single hop communication. To align with the maximum hop count of three (3) for streaming devices, seven (7) polling devices can be accommodated. In summary, the developed DR-ZHG supports seven (7) polling service sensors and one (1) streaming service senor. Such a gateway meets the general latency standard of 2s for telemedicine services as stipulated by U.S. NIST.

Cardiovascular diseases identification using electrocardiogram health identifier based on multiple criteria decision making

Binary classifier (BC) and multi-class classifier (MCC) are designed and analyzed.A scheme namely MCC-BC will pave the way for speedy and accurate ECGHI.A confidence index is newly proposed to evaluate the performance of ECGHI.MCDM using AHP has been developed to evaluate the optimal hyperplanes of ECGHI. Cardiovascular diseases can wreak havoc on human beings and lead to 30% of global death annually. The World Health Organization has always highlighted that there is a severe shortage of medical personnel, especially cardiologists, in most of the countries. In this paper, an electrocardiogram health identifier (ECGHI) has been proposed and developed for swift identification of heart diseases. The ECGHI has been applied to four most common types of cardiovascular diseases, namely Myocardial Infarction, Dysrhythmia, Bundle Branch Block and Heart Failure since these four types of cardiovascular diseases contribute to 25% of the overall population suffering from heart diseases. In the investigation of ECGHI, the binary classifier (BC) and multi-class classifier (MCC) are designed and analyzed. The MCC features a multi-class support vector machine (SVM) to diagnose the exact type of cardiovascular disease. The BC features a two-class SVM to identify healthiness of heart accurately. In this paper, the following indicators have been investigated, namely the overall accuracy, specificity, sensitivity, the dimensionality of feature vector, the total training and testing time of ECGHI and a newly defined confidence index. These six criteria form the basis to derive an analytic hierarchy process (AHP) to facilitate the multiple criteria decision making (MCDM) for the optimal evaluation of hyperplanes. Four kernels have been analyzed from which both the BC and MCC are evaluated and analyzed. The optimized ECGHI using BC yields an AHP Performance Score of 0.079 with score components (overall accuracy, specificity, sensitivity, average confidence index, dimensionality, total time for training and testing time) of 0.982, 0.978, 0.986, 0.608, 6, and 5.77s respectively. Likewise, the optimized ECGHI using MCC yields an AHP Performance Score of 0.093 with score components of 0.882, 0.89, 0.874, 0.504, 9, and 7.32s respectively. The BC is employed as a supplement of the MCC to achieve a further improvement in all six criteria. Such a novel process of identification and detection with high accuracy is referred as the MCC-BC scheme. The developed ECGHI (MCC) may identify the FOUR most common and important cardiovascular diseases simultaneously (with BC supplementing the MCC to achieve a high accuracy). Such simultaneous identification of cardiovascular diseases is the first of its kind in this research area, so no comparison can be made. The MCC-BC scheme will pave the way for speedy and accurate identification and detection of heart disease. The instant response of the ECGHI minimizes the probability of death from Myocardial Infarction, Bundle Branch Block, Dysrhythmia, and Heart Failure.

Interference-Mitigated ZigBee-Based Advanced Metering Infrastructure

An interference-mitigated ZigBee-based advanced metering infrastructure (AMI) solution, namely IMM2ZM, has been developed for high-traffics smart metering (SM). The IMM2ZM incorporates multiradios multichannels network architecture and features an interference mitigation design by using multiobjective optimization. To evaluate the performance of the network due to interference, the channel-swapping time (Tcs) has been investigated. Analysis shows that when the sensitivity (PRχ) is less than -12 dBm, Tcs increases tremendously. Evaluation shows that there are significant improvements in the performance of the application-layer transmission rate (σ) and the average delay (D). The improvement figures are σ > ~300% and D > 70% in a 10-floor building, σ > ~280 % and D > 65% in a 20-floor building, and σ > ~270% and D > 56% in a 30-floor building. Further analysis reveals that IMM2ZM results in typically less than 0.43 s delay for a 30-floor building under interference. This performance fulfills the latency requirement of less than 0.5 s for SMs in the USA (Magazine of Department of Energy Communications, USA, 2010). The IMM2ZM provides a high-traffics interference-mitigated ZigBee AMI solution.

A High Fuel Consumption Efficiency Management Scheme for PHEVs Using an Adaptive Genetic Algorithm

A high fuel efficiency management scheme for plug-in hybrid electric vehicles (PHEVs) has been developed. In order to achieve fuel consumption reduction, an adaptive genetic algorithm scheme has been designed to adaptively manage the energy resource usage. The objective function of the genetic algorithm is implemented by designing a fuzzy logic controller which closely monitors and resembles the driving conditions and environment of PHEVs, thus trading off between petrol versus electricity for optimal driving efficiency. Comparison between calculated results and publicized data shows that the achieved efficiency of the fuzzified genetic algorithm is better by 10% than existing schemes. The developed scheme, if fully adopted, would help reduce over 600 tons of CO2 emissions worldwide every day.

An Accurate ECG-Based Transportation Safety Drowsiness Detection Scheme

Many traffic injuries and deaths are caused by the drowsiness of drivers during driving. Existing drowsiness detection schemes are not accurate due to various reasons. To resolve this problem, an accurate driver drowsiness classifier (DDC) has been developed using an electrocardiogram genetic algorithm-based support vector machine (ECG GA-SVM). In existing studies, a cross correlation kernel and a convolution kernel have both been applied for performing the classification. The DDC is designed by a Mercer kernel KDDC formed by commuting the cross correlation kernel Kxcorr,ij and the convolution kernel Kconv,ij. Kxcorr,ij, and captures the symmetric information among ECG signals from different classes, while Kconv,ij captures the antisymmetric information among ECG signals from the same class. The final KDDC (a precomputed kernel) is obtained by a genetic mutation using a multiobjective genetic algorithm. This renders an optimal KDDC that confidently serves as the full descriptor of the drowsiness. The performance of KDDC is compared with the most prevailing kernels. The obtained DDC yields an overall accuracy of 97.01%, sensitivity of 97.16%, and specificity of 96.86%. The analysis reveals that the accuracy of KDDC is better than those of both Kxcorr,ij and Kconv,ij by more than 11%, and typical kernels including linear, quadratic, third order polynomial, and Gaussian radial basis function by 17-63%, respectively. Comparing with related works using the image-based method and the biometric signal-based method, KDDC improves the accuracy by 48.4-87.2%. Testing results showed that KDDC has a less than 1% deviation from simulated results. Also, the average delay of DDC was bounded by 0.55 ms. This renders the real time implementation. Thus, the developed ECG GA-SVM provides an accurate and instantaneous warning to the drivers before they fall into sleep. As a result this ensures the public transport safety.

Electrocardiogram based classifier for driver drowsiness detection

Driver drowsiness may cause traffic injuries and death. In literature, various methods, for instance, image-based, vehicle-based, and biometric-signals-based, have been proposed for driver drowsiness detection. In this paper, a new approach using Electrocardiogram is discussed. Performance evaluation is carried out for the driver drowsiness classifier. The developed classifier yields overall accuracy, sensitivity, and specificity of 76.93%, 77.36%, and 76.5% respectively. Results have revealed that the performance of proposed classifier is better than traditional methods.

Energy management of hybrid vehicles using artificial intelligence

High depletion of diesel and petroleum gas in vehicles has wreaked havoc on environment and human beings. In the light of better fuel economy and lower pollution, more people will adopt hybrid electric vehicles. To improve the energy efficiency of fuel-cell based hybrid electric vehicles and thus improving the performance of fuel reduction, a feasibility study of optimization of energy efficiency has been discussed using fuzzy logic controller. On the other hand, energy has precedence to be generated by battery over fuel as battery produces less pollutants and carbon dioxide. Based on various percentage battery capacity and fuel tank capacity, thirty two (9) scenarios have been investigated. The average reduction of fuel consumption by fuzzy logic controller is 21.1% with 464 tons carbon dioxide reduction and 3.3 million Hong Kong dollars saving provided one million of hybrid electric vehicles travel for 28 kilometers. This can relieve the greenhouse effect and increase the popularity of people from replacing conventional vehicles with hybrid electric vehicles.

Non-Convex Sparse and Low-Rank Based Robust Subspace Segmentation for Data Mining

Parsimony, including sparsity and low-rank, has shown great importance for data mining in social networks, particularly in tasks such as segmentation and recognition. Traditionally, such modeling approaches rely on an iterative algorithm that minimizes an objective function with convex l1-norm or nuclear norm constraints. However, the obtained results by convex optimization are usually suboptimal to solutions of original sparse or low-rank problems. In this paper, a novel robust subspace segmentation algorithm has been proposed by integrating lp-norm and Schatten p-norm constraints. Our so-obtained affinity graph can better capture local geometrical structure and the global information of the data. As a consequence, our algorithm is more generative, discriminative and robust. An efficient linearized alternating direction method is derived to realize our model. Extensive segmentation experiments are conducted on public datasets. The proposed algorithm is revealed to be more effective and robust compared to five existing algorithms.

Nonlinear switching control for suppressing the spread of avian influenza

This paper proposes a novel method of killing birds and applying vaccines for suppressing the spread of avian influenza via a nonlinear switching control approach. The switching strategy is based on the population of the susceptible birds and the population of the susceptible humans. There are four switching cases. For the first three switching cases, the elimination control force and the quarantine control force are equal to either zero or one. For the last switching case, they are equal to one minus a scalar divided by the population of the susceptible birds and one minus another scalar divided by the population of the susceptible humans, respectively. The system state vectors of the avian influenza model are guaranteed to reach the desirable equilibrium point. Also, the positivity requirements on the system states as well as the constraints on both the lower bounds and the upper bounds of both the elimination control force and the quarantine control force are guaranteed to be satisfied. Computer numerical simulation results show that the proposed control strategy is very effective and efficient.