Find Research Output

Research Output
  • All
  • Scholar Profiles
  • Research Units
  • Research Output
Department Publication Year Content Type Data Sources


1.On the theoretical distribution of the wind farm power when there is a correlation between wind speed and wind turbine availability

Author:Kan, C;Devrim, Y;Eryilmaz, S


Abstract:It is important to elicit information about the potential power output of a wind turbine and a wind farm consisting of specified number of wind turbines before installation of the turbines. Such information can be used to estimate the potential power output of the wind farm which will be built in a specific region. The output power of a wind turbine is affected by two factors: wind speed and turbine availability. As shown in the literature, the correlation between wind speed and wind turbine availability has an impact on the output of a wind farm. Thus, the probability distribution of the power produced by the farm depending on the wind speed distribution and turbine availability can be effectively used for planning and risk management. In this paper, the theoretical distribution of the wind farm power is derived by considering the dependence between turbine availability and the wind speed. The theoretical results are illustrated for real wind turbine reliability and wind speed data.

2.Brain Storm Optimization Algorithm for Multi-objective Optimization Problems

Author:Xue, JQ;Wu, YL;Shi, YH;Cheng, S


Abstract:In this paper, a novel multi-objective optimization algorithm based on the brainstorming process is proposed(MOBSO). In addition to the operations used in the traditional multi-objective optimization algorithm, a clustering strategy is adopted in the objective space. Two typical mutation operators, Gaussian mutation and Cauchy mutation, are utilized in the generation process independently and their performances are compared. A group of multi-objective problems with different characteristics were tested to validate the effectiveness of the proposed algorithm. Experimental results show that MOBSO is a very promising algorithm for solving multi-objective optimization problems.

3.Infrared motion detection and electromyographic gesture recognition for navigating 3D environments

Author:Chen, KY;Liang, HN;Yue, Y;Craig, P


Abstract:This research explores the suitability and effectiveness of two relatively new types of input device for navigating 3D virtual environments. These are infrared motion detection, like the Leap Motion tracker, and electromyographic gesture recognition, like the Myo Armband. Despite the introduction of a variety of new input devices intended to provide a more natural interaction experience, navigation within 3D virtual environments is still normally done on more traditional control devices such as game controllers or the keyboard-mouse combination. This study investigates the potential of new devices to support navigation in 3D environments through an experiment conducted with 27 participants using three different types of input devices to play a ball-balancing maze-like game. The input devices tested are a standard game controller, a Leap Motion tracker for infrared motion detection, and the Myo Armband for electromyographic gesture recognition. Results demonstrated the real potential of both types of device to support navigation interaction within 3D environments.

4.Anomaly detection of rolling elements using fuzzy entropy and similarity measures

Author:Wong, M.L.D. ; Lee, S.H. ; Nandi, A.K.

Source:Institution of Mechanical Engineers - 10th International Conference on Vibrations in Rotating Machinery,2012,Vol.

Abstract:The ability of detecting faults in rotating elements is highly desired in machine condition monitoring application (MCM). On many MCM platforms, discriminating attributes based on time and/or frequency domain of the acquired vibration data are used to classify the element under monitoring into normal and abnormal conditions. However, having such diagnostic ability is still insufficient in our global goal towards predictive maintenance. To achieve true predictive maintenance, the development tool must be able to provide a certain level of real time computation capability. In this paper, the authors propose a novel method based on fuzzy entropy and similarity measure for monitoring the health conditions of ball bearings on-line. The practicalities of the effectiveness and speed of the method are verified empirically, and results are presented towards the end of this paper. © The author(s) and/or their employer(s), 2012.

5.On the constructing mechanism and strategy of HeXie society from the perspective of social governance

Author:Xi Youmin;Zhang Xiaojun

Source:Systems Engineering-Theory & Practice,2013,Vol.33

Abstract:With regard to the challenge of social contradictions and the plan to construct HeXie society, this paper analyzed reasons of the contradictions and proposed three mechanisms to realize HeXie society from the perspective of social governance. We argued that soft legal system, incomplete market, and weakened network mechanisms are main factors that bring about the current unstable social events. Based on the analysis of the essence of HeXie society, we explored the way to construct HeXie society by combining hierarchy, market and network mechanisms, and reforming current political system to build positive environment for the interaction among these mechanisms. The paper also discussed the task and strategy of constructing HeXie society under the framework of HeXie management theory.

6.Segregated Lightweight Dynamic Rate (SLDR) control scheme for efficient internet communications

Author:Ting,T. O.;Ting,H. C.;Lee,Sanghyuk

Source:Lecture Notes in Electrical Engineering,2013,Vol.235 LNEE

Abstract:This paper proposes an effective Segregated Lightweight Dynamic Rate Control Scheme (SLDRCS) over the internet. Based on the feedback analysis of the current approaches, we found that the indicator of the congestion is only the queue length. It only captures a partial indicator of delay and loss in feedback mechanism. This may result in an ineffective way in controlling the network when congestion control occurs. Therefore, we suggest multiple congestion indicators to adapt inside this scheme to fully control the average delay and loss from bidirectional of sender to receiver. The behavior of next event packet being control using discrete event simulation tool with First Come First Serve (FCFS) scheduling policy and we code this algorithm into C programming language. Through the simulation results, our Segregated Lightweight Dynamic Rate Control Scheme (SLDRCS) guaranteed high improvement in packet drop and average delay under various congestion level and traffic load conditions compare with the current approach. © 2013 Springer Science+Business Media Dordrecht.

7.Attributes and Action Recognition Based on Convolutional Neural Networks and Spatial Pyramid VLAD Encoding

Author:Yan, SY;Smith, JS;Zhang, BL


Abstract:Determination of human attributes and recognition of actions in still images are two related and challenging tasks in computer vision, which often appear in fine-grained domains where the distinctions between the different categories are very small. Deep Convolutional Neural Network (CNN) models have demonstrated their remarkable representational learning capability through various examples. However, the successes are very limited for attributes and action recognition as the potential of CNNs to acquire both of the global and local information of an image remains largely unexplored. This paper proposes to tackle the problem with an encoding of a spatial pyramid Vector of Locally Aggregated Descriptors (VLAD) on top of CNN features. With region proposals generated by Edgeboxes, a compact and efficient representation of an image is thus produced for subsequent prediction of attributes and classification of actions. The proposed scheme is validated with competitive results on two benchmark datasets: 90.4%% mean Average Precision (mAP) on the Berkeley Attributes of People dataset and 88.5%% mAP on the Stanford 40 action dataset.

8.Coupling of the Crank–Nicolson scheme and localized meshless technique for viscoelastic wave model in fluid flow

Author:Nikan, O. ; Avazzadeh, Z.

Source:Journal of Computational and Applied Mathematics,2021,Vol.398

Abstract:This paper proposes an efficient localized meshless technique for approximating the viscoelastic wave model. This model is a significant methodology to explain wave propagation in solids modeled with a wide collection of viscoelastic laws. In the first method, a difference scheme with the second-order accuracy is implemented to obtain a semi-discrete scheme. Then, a localized radial basis function partition of unity scheme is adopted to get a full-discrete scheme. This localization technique consists of decomposing the initial domain into several sub-domains and constructing a local radial basis function approximation over every sub-domain. A well-conditioned resulting linear system and a low computational burden are the main merits of this technique compared to global collocation methods. Further, the stability and convergence analysis of the temporal discretization scheme are deduced using discrete energy method. Numerical results are shown to validate the accuracy and effectiveness of the proposed method. © 2021

9.Analysis of liquid feedstock behavior in high velocity suspension flame spraying for the development of nanostructured coatings

Author:Gozali, Ebrahim ; Kamnis, Spyros ; Gu, Sai

Source:Proceedings of the International Thermal Spray Conference,2013,Vol.

Abstract:Over the last decade the interest in thick nano-structured layers has been increasingly growing. Several new applications, including nanostructured thermoelectric coatings, thermally sprayed photovoltaic systems and solid oxide fuel cells, require reduction of micro-cracking, resistance to thermal shock and/or controlled porosity. The high velocity suspension flame spray (HVSFS) is a promising method to prepare advanced materials from nano-sized particles with unique properties. However, compared to the conventional thermal spray, HVSFS is by far more complex and difficult to control because the liquid feedstock phase undergoes aerodynamic break up and vaporization. The effects of suspension droplet size, injection velocity and mass flow rate were parametrically studied and the results were compared for axial, transverse and external injection. The numerical simulation consists of modeling aerodynamic droplet break-up and evaporation, heat and mass transfer between liquid droplets and gas phase.

10.Modeling and Verification of NCL Circuits Using PAT

Author:Ma, JM;Man, KL;Lim, EG;Zhang, N;Lei, CU;Guan, SU;Jeong, TT;Seon, JK

Source:CEIS 2011,2011,Vol.15

Abstract:NULL Conventional Logic (NCL) is a Delay-Insensitive (DI) clockless paradigm and is suitable for implementing asynchronous circuits. Efficient methods of analysis are required to specify and verify such DI systems. Based on Delay Insensitive sequential Process (DISP) specification, this paper demonstrates the application of formal methods by applying Process Analysis Toolkit (PAT) to model and verify the behavior of NCL circuits. A few useful constructs are successfully modeled and verified by using PAT. The flexibility and simplicity of the coding, simulation and verification shows that PAT is effective and applicable for NCL circuit design and verification. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of [CEIS 2011]

11.High Efficiency WPT System for Electric Vehicles with LCL-S and SS compensation

Author:Li, Y;Zhu, YH;Liu, W;Zhu, YS;Pei, Y;Wen, HQ;Zhao, C


Abstract:a wireless power transmission (WPT) prototype for EV with constant current charging and constant voltage charging characteristics is built up to systematically analyze LCL-S and SS compensation topology. The transmission efficiencies have been improved tremendously to 94.02%% for SS compensation and 87.3%% for LCL-S compensation when the coil distance is 15cm. The output powers at different resistance levels are discussed and compared.

12.Named Entity Recognition Using BERT BiLSTM CRF for Chinese Electronic Health Records

Author:Dai, Zhenjin ; Wang, Xutao ; Ni, Pin ; Li, Yuming ; Li, Gangmin ; Bai, Xuming

Source:Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019,2019,Vol.

Abstract:As the generation and accumulation of massive electronic health records (EHR), how to effectively extract the valuable medical information from EHR has been a popular research topic. During the medical information extraction, named entity recognition (NER) is an essential natural language processing (NLP) task. This paper presents our efforts using neural network approaches for this task. Based on the Chinese EHR offered by CCKS 2019 and the Second Affiliated Hospital of Soochow University (SAHSU), several neural models for NER, including BiLSTM, have been compared, along with two pre-trained language models, word2vec and BERT. We have found that the BERT-BiLSTM-CRF model can achieve approximately 75%% F1 score, which outperformed all other models during the tests. © 2019 IEEE.

13.Study Frequency Characteristics of Ground By Using Four Electrode Method

Author:Nayel, M


Abstract:This paper studies the effect of frequencies and penetration depth on ground impedance, resisitivity and permittivity. The effect of injected a step like current in the four electrode method for ground resistivity and permittivity measurements are investigated. The ground impedance is obtained from measured voltage and current wave forms. A balance transformer is used to inject a step current in outer electrode and sink the same current from the other outer electrode. Calculation models had been proposed to explain physically the effects of frequency and penetration depth on four electrodes method measurements.

14.Designing an Optimized Water Quality Monitoring Network with Reserved Monitoring Locations

Author:Zhu, XH;Yue, Y;Wong, PWH;Zhang, YX;Ding, H


Abstract:The optimized design of water quality monitoring networks can not only minimize the pollution detection time and maximize the detection probability for river systems but also reduce redundant monitoring locations. In addition, it can save investments and costs for building and operating monitoring systems as well as satisfy management requirements. This paper aims to use the beneficial features of multi-objective discrete particle swarm optimization (MODPSO) to optimize the design of water quality monitoring networks. Four optimization objectives: minimum pollution detection time, maximum pollution detection probability, maximum centrality of monitoring locations and reservation of particular monitoring locations, are proposed. To guide the convergence process and keep reserved monitoring locations in the Pareto frontier, we use a binary matrix to denote reserved monitoring locations and develop a new particle initialization procedure as well as discrete functions for updating particle's velocity and position. The storm water management model (SWMM) is used to model a hypothetical river network which was studied in the literature for comparative analysis of our work. We define three pollution detection thresholds and simulate pollution events respectively to obtain all the pollution detection time for all the potential monitoring locations when a pollution event occurs randomly at any potential monitoring locations. Compared to the results of an enumeration search method, we confirm that our algorithm could obtain the Pareto frontier of optimized monitoring network design, and the reserved monitoring locations are included to satisfy the management requirements. This paper makes fundamental advancements of MODPSO and enables it to optimize the design of water quality monitoring networks with reserved monitoring locations.

15.Driving posture recognition by convolutional neural networks

Author:Yan, C;Coenen, F;Zhang, BL

Source:IET COMPUTER VISION,2016,Vol.10

Abstract:Driver fatigue and inattention have long been recognised as the main contributing factors in traffic accidents. This study presents a novel system which applies convolutional neural network (CNN) to automatically learn and predict pre-defined driving postures. The main idea is to monitor driver hand position with discriminative information extracted to predict safe/unsafe driving posture. In comparison to previous approaches, CNNs can automatically learn discriminative features directly from raw images. In the authors' works, a CNNmodel was first pre-trained by an unsupervised feature learning method called sparse filtering, and subsequently fine-tuned with classification. The approach was verified using the Southeast University driving posture dataset, which comprised of video clips covering four driving postures, including normal driving, responding to a cell phone call, eating, and smoking. Compared with other popular approaches with different image descriptors and classification methods, the authors' scheme achieves the best performance with an overall accuracy of 99.78%%. To evaluate the effectiveness and generalisation performance in more realistic conditions, the method was further tested using other two specially designed datasets which takes into account of the poor illuminations and different road conditions, achieving an overall accuracy of 99.3 and 95.77%%, respectively.

16.Research investigations on the use or non-use of hearing aids in the smart cities

Author:Chang, V;Wang, YY;Wills, G


Abstract:This study aims to explore factors influencing behavioral intention to adopt hearing aids among old adults in smart cities. It argues that trust is a moderator to influence the relationship between attitude, subjective norm and individual's behavioral intention in smart cities. This study tests hypotheses using a sample of 103 respondents from six smart cities in China. The results reveal that attitude is main factor influencing individual's behavioral intention. Subjective norm and trust are both not statistically significant at the 95%% confidence interval in the model of multiple-regression. Interestingly, it finds that trust moderates the relationship between subjective norm and individual's behavioral intention. It means that the audiologists' advice can positively affect person's behavioral intention in smart cities. The findings imply that the Theory of Reasoned Action can be partially used to explain the person's behavioral intention in Chinese context. This study contributes to encourage old people to use smart hospitals to consult audiologists about hearing loss and hearing aids rehabilitation. Hence, hearing aids can improve their quality of life (QoL), which can be reflected by the improved standard of living, better access to treatments and also the positive sentiment about their life, including comfort, friendship, happiness and a closer connection to the society.

17.Particle swarm Optimized Density-based Clustering and Classification: Supervised and unsupervised learning approaches

Author:Guan, C;Yuen, KKF;Coenen, F


Abstract:Two pattern recognition technologies in the field of machine learning, clustering and classification, have been applied in many domains. Density-based clustering is an essential clustering algorithm. The best known density-based clustering method is Density-Based Spatial Clustering of Applications with Noise (DBSCAN), which can find arbitrary shaped clusters in datasets. DBSCAN has three drawbacks: firstly, the parameters for DBSCAN are hard to set; secondly, the number of clusters cannot be controlled by the users; and thirdly, DBSCAN cannot directly be used as a classifier. In this paper a novel Particle swarm Optimized Density-based Clustering and Classification (PODCC) is proposed, designed to offset the drawbacks of DBSCAN. Particle Swarm Optimization (PSO), a widely used Evolutionary and Swarm Algorithm (ESA), has been applied in optimization problems in different research domains including data analytics. In PODCC, a variant of PSO, SPSO-2011, is used to search the parameter space so as to identify the best parameters for density-based clustering and classification. PODCC can function in terms of both Supervised and Unsupervised Learnings by applying the appropriate fitness functions proposed in this paper. With the proposed fitness function, users can set the number of clusters as input for PODCC. The proposed method was evaluated by testing ten synthetic datasets and ten benchmarking datasets selected from various open sources. The experimental results indicate that the proposed PODCC can perform better than some established methods, especially with respect to imbalanced datasets.

18.Au-Free AlGaN/GaN MIS-HEMTs With Embedded Current Sensing Structure for Power Switching Applications

Author:Sun, RZ;Liang, YC;Yeo, YC;Zhao, CZ


Abstract:AlGaN/GaN metal-insulator-semiconductor high electron mobility transistors (MIS-HEMTs) have become a promising candidate for use in efficient power conversion applications. In order to realize converter circuit control function and overcurrent protection of device itself, we have designed, fabricated, and experimentally measured the Au-free AlGaN/GaN MIS-HEMTs with embedded current sensing structure. A floating ohmic current sensing electrode is inserted between source and gate electrode of which the sensing voltage signal can represent the drain current. We have achieved stable current sensing ratios at various operating conditions including quasi-static, transient state, and under high temperature. The proposed structure is highly useful in monolithic power integrated circuit on CMOS-compatible AlGaN/GaN technologies.

19.Zero-Shot Learning via Attribute Regression and Class Prototype Rectification

Author:Luo, CZ;Li, ZT;Huang, KZ;Feng, JS;Wang, M


Abstract:Zero-shot learning (ZSL) aims at classifying examples for unseen classes (with no training examples) given some other seen classes (with training examples). Most existing approaches exploit intermedia-level information (e.g., attributes) to transfer knowledge from seen classes to unseen classes. A common practice is to first learn projections from samples to attributes on seen classes via a regression method, and then apply such projections to unseen classes directly. However, it turns out that such a manner of learning strategy easily causes projection domain shift problem and hubness problem, which hinder the performance of ZSL task. In this paper, we also formulate ZSL as an attribute regression problem. However, different from general regression-based solutions, the proposed approach is novel in three aspects. First, a class prototype rectification method is proposed to connect the unseen classes to the seen classes. Here, a class prototype refers to a vector representation of a class, and it is also known as a class center, class signature, or class exemplar. Second, an alternating learning scheme is proposed for jointly performing attribute regression and rectifying the class prototypes. Finally, a new objective function which takes into consideration both the attribute regression accuracy and the class prototype discrimination is proposed. By introducing such a solution, domain shift problem and hubness problem can be mitigated. Experimental results on three public datasets (i.e., CUB200-2011, SUN Attribute, and aPaY) well demonstrate the effectiveness of our approach.

20.Exploring the potential of red mud and beechwood co-processing for the upgrading of fast pyrolysis vapours

Author:Gupta, J;Papadikis, K;Kozhevnikov, IV;Konysheva, EY


Abstract:Red mud, a by-product of the Bayer process in the aluminium industry, is co-processed with beechwood for the in-situ upgrading of fast pyrolysis vapour products. It is revealed that the co-processing of beechwood with thermally pre-treated red mud enhanced the vapour upgrading effect. Individual oxides (alpha-Al2O3, Fe2O3, SiO2, and TiO2), which are the main constituents of red mud were also tested for the identification of their individual impact on the upgrading process. A biomass/catalyst weight ratio of 1:4 showed the strongest effect on the product distribution. Red mud was found to reduce the yield of phenolic compounds and promote the formation of cellulose- and hemicellulose-derived furfurals and hemicellulose-derived acetic acid, which can be used for the production of a broad range of chemicals and liquid transportation fuels. alpha-Al2O3 and Fe2O3 reduced the relative yield of phenols as well, whereas the formation of furfurals was promoted by Fe2O3 and TiO2. SiO2 showed negligible effect on fast pyrolysis vapours. The impact of catalysts on the product distribution is discussed for phenols, furfurals, and acids, for which the strongest effects were observed.
Total 1,740 results found
Copyright 2006-2020 © Xi'an Jiaotong-Liverpool University 苏ICP备07016150号-1 京公网安备 11010102002019号