Showing papers presented at "International Conference on Control, Automation, Robotics and Vision in 2004"

Extreme learning machine: RBF network case

Abstract: A new learning algorithm called extreme learning machine (ELM) has recently been proposed for single-hidden layer feedforward neural networks (SLFNs) to easily achieve good generalization performance at extremely fast learning speed. ELM randomly chooses the input weights and analytically determines the output weights of SLFNs. This paper shows that ELM can be extended to radial basis function (RBF) network case, which allows the centers and impact widths of RBF kernels to be randomly generated and the output weights to be simply analytically calculated instead of iteratively tuned. Interestingly, the experimental results show that the ELM algorithm for RBF networks can complete learning at extremely fast speed and produce generalization performance very close to that of SVM in many artificial and real benchmarking function approximation and classification problems. Since ELM does not require validation and human-intervened parameters for given network architectures, ELM can be easily used.

A globally convergent numerical algorithm for computing the centre of mass on compact Lie groups

Abstract: Motivated by applications in fuzzy control, robotics and vision, this paper considers the problem of computing the centre of mass (precisely, the Karcher mean) of a set of points defined on a compact Lie group, such as the special orthogonal group consisting of all orthogonal matrices with unit determinant. An iterative algorithm, whose derivation is based on the geometry of the problem, is proposed. It is proved to be globally convergent. Interestingly, the proof starts by showing the algorithm is actually a Riemannian gradient descent algorithm with fixed step size.

Fault detection of networked control systems with network-induced delay

Abstract: Problems related to the fault detection of networked control systems are studied. The influence of network-induced delay on conventional observer based fault detection systems designed without considering it is first evaluated, then a parity relation based fault detection system robust to that kind of delay is proposed and studied.

Machine learning techniques for ontology-based leaf classification

Abstract: Leaf classification, indexing as well as retrieval is an important part of a computerized plant identification system In this paper, an integrated approach for an ontology-based leaf classification system is proposed, wherein machine learning techniques play a crucial role for the automatization of the system For the leaf contour classification, a scaled CCD code system is proposed to categorize the basic shape and margin type of a leaf by using the similar taxonomy principle adopted by the botanists Then a trained neural network is employed to recognize the detailed tooth patterns The measurement on an unlobed leaf is also conducted automatically according to the method used in botany For the leaf vein recognition, the vein texture is extracted by employing an efficient combined thresholding and neural network approach so as to obtain more vein details of a leaf Compared with the past studies, the proposed method integrates low-level features of an image and the specific knowledge in the domain (ontology) of botany, and therefore provides a more practical system for users to comprehend and handle Primary experiments have shown promising results and proven the feasibility of the proposed system

Wireless sensor network for machine condition based maintenance

Abstract: A new application architecture is designed for continuous, real-time, distributed wireless sensor networks. We develop a wireless sensor network for machinery condition-based maintenance (CBM) using commercially available products, including a hardware platform, networking architecture, and medium access communication protocol. We implement a single-hop sensor network to facilitate real-time monitoring and extensive data processing for machine monitoring. A LabVIEW graphical user interface is described that allows for signal processing, including FFT, various moments, and kurtosis. A wireless CBM sensor network implementation on a heating and air conditioning plant is presented as a case study.

Current trends in steganalysis: a critical survey

Abstract: This paper presents a critical analysis of some of the current steganalysis methodologies. The pros and cons of these methods are discussed from statistical and usability perspectives. It is concluded that no single strategy works best. Depending on the amount of statistical information available at hand, a proper choice has to be made.

Military robots - a glimpse from today and tomorrow

Abstract: The military forces always tried to use new gadgets and weapons for reducing the risk of their casualties and to defeat their enemies. With the development of sophisticated technology, it mostly relies on the high tech weapons or machinery being used. Robotics is one of the hot fields of modern age in which the nations are concentrating upon for military purposes in the state of war and peace. They have been in use for some time for demining and rescue operations but now they are under research for combat or spy missions. Today's modern military forces are using different kinds of robots for different applications ranging from mine detection, surveillance, logistics and rescue operations. In the future they will be used for reconnaissance and surveillance, logistics and support, communications infrastructure, forward-deployed offensive operations, and as tactical decoys to conceal maneuver by manned assets. In order to make robots for the unpredicted cluttered environment of the battlefield, research on different aspects of robots is under investigation in laboratories to be able to do its job autonomously, as efficiently as a human operated machine can do. Latest techniques are being investigated to have advanced and intelligent robots for different operations. This paper presents different kinds of robotic technologies being used in all the three main forces, Navy, Army and Air. Some of the robots discussed are also being used in the wars of Afghanistan and Iraq, also, the robots that are under investigation in laboratories for future military operations. These robots are under investigation for autonomous and cooperative environment. We focus our attention on the uses of robots in war and peace as well as their impact on society.

Study of migration topology in island model parallel hybrid-GA for large scale quadratic assignment problems

Abstract: This paper extends our previous work on the island model parallel hybrid-genetic algorithm (PHGA) for large scale quadratic assignment problems (QAPs). Some issues on the control parameters of the migration process and how they affect the quality of the solutions and the efficiency of algorithm deserve further evaluative study. In this paper, we investigate the effect of migration topology on the performance of the PHGA. Two topologies, one-way ring topology and random topology, are studied and analyzed. The empirical results show that the PHGA with ring topology is better able to achieve an appropriate tradeoff between exploration and exploitation and hence more helpful to improve the performance of PHGA for solving large scale QAPs.

SLAM using natural features in an underwater environment

Abstract: This paper presents techniques developed to apply the simultaneous localisation and mapping (SLAM) algorithm to an unmanned underwater vehicle operating in an unstructured, natural environment. It is shown that information from on-board sonar and vision sensors can be fused to select and track regions of the environment that may be used as features to estimate the vehicle's motion. Results including vehicle pose estimates and resulting environment models are shown for data acquired at the Great Barrier Reef in Australia.

Universal communication architecture for high-dynamic robot systems using QNX

Abstract: In this paper a new flexible communication architecture for high dynamic robot applications is presented. The motivation for the development is founded on the special requirements imposed by PKMs (parallel kinematic machines). PKMs obtain a different kinematic structure compared to their serial counterparts based on closed kinematic chains. This structural feature leads to a number of favorable properties as high structural stiffness, high accuracy and low moved masses resulting in high payload to robot mass ratio. This paper also introduces the structure and application of a new communication architecture matching with the needs of high-dynamic parallel robot systems.

Self-trained automated parking system

Abstract: This paper presents part of the research work carried out at the Centre for Computational Intelligence at NTU to develop novel technologies for the routing, navigation, and control of intelligent cars. One objective is to endow the cars with the ability to autonomously drive on various types of roads and realize manoeuvres such as reverse and parallel parking, three-point turns, etc. Our approach is to design a self-training system that makes use of human expertise to automatically derive a working car control system. A new neuro-fuzzy architecture known as the GenSoYager fuzzy neural network has been realized and integrated with our car-driving simulator for training and testing purposes. The GenSoYagerFNN has proven so far superior to other trained networks in detecting parking slots and accomplishing reverse parking manoeuvres. The approach described has also been validated using a microprocessor controlled model car.

Features extraction for structured light image of welding seam with arc and splash disturbance

Abstract: A method of image process and features extraction for structured light image of welding seam with arc and splash disturbance is proposed. The seam area is detected by search with large step. The adaptive thresholds of image enhancement are determined in the frequency domain of the gray image. Then, the target image is pre-processed using image enhancement and binarization. After thinning the seam with its both edges, main characteristic line is obtained using Hotelling transform and Hough transform. Finally, the feature points in the seam are found according to its second derivative. Experimental results show its effectiveness, good performance in real time and adaptability to different seams.

Nonlinear phase portrait modeling of fingerprint orientation

Abstract: Fingerprint orientation is crucial for automatic fingerprint identification. However, recovery of orientation is still difficult especially in noisy region. A way to aid recovery of the orientation is to provide an orientation model. In this paper, an orientation model for the entire fingerprint orientation using high order phase portrait is suggested. Proper analysis of the orientation pattern at the singular point regions is provided. Then a low-order phase portrait near each of the singular point is added as constraint to the high-order phase portrait to provide accurate orientation modeling for the entire fingerprint image. The main advantage of the proposed approach is that the nonlinear model itself is able to model all type of fingerprint orientations completely. Experiments and visual analysis show the effectiveness of the proposed model.

Digital watermarking based on frequency random position insertion

Abstract: In this paper, we propose a novel digital watermarking to hide a trademark into a host-image such that an unintended observer will not be aware of the watermarking. By inserting the watermarking information into the random positioning location of a DCT image, the image capability against median filtering can be greatly improved. Experimental results demonstrate that the resulting proposed digital watermarking scheme has a higher peak signal-to-noise ratio and the visual quality of the digital watermarked image is indistinguishable from the original unmarked image.

Feature fusion method based on canonical correlation analysis and handwritten character recognition

Abstract: A new feature extraction method, based on feature fusion, according to the idea of canonical correlation analysis (CCA), is proposed in this paper. A framework of CCA used in pattern recognition is described. The overall process comprises: extracting two groups of feature vectors with the same pattern; establishing the correlation criterion function between the two groups of feature vectors, and extract their canonical correlation features in order to form effective discriminant vectors for recognition. The inherent essence of this method used in recognition is theoretically analyzed. This method uses correlation features between two groups of feature vectors as effective discriminant information, so it not only is suitable for information fusion, but also eliminates redundant information within features, a new way for classification is proposed. Experimental results of our method applying on Concordia University CENPARMI handwritten numeral database has shown that our recognition rate is higher than that of the algorithm adopting single feature or the existing fusion algorithm.

Finite time stabilization for a class of nonlinear systems

Abstract: In this paper, global finite-time stabilization problem for a large class of nonlinear control systems in the p normal form is considered. An iterative design approach is given based on Lyapunov function and homogeneity. The finite-time stabilizing control laws are constructed in the form of continuous but non-smooth time-invariant feedback.

A fast video encryption scheme based-on chaos

Abstract: Video encryption is a suitable method to protect video data. There are some disadvantages in the algorithms proposed before. In this paper, we propose a novel fast MPEG video encryption algorithm, which encrypts run length codes with chaotic run-length encryption algorithm (CREA), encrypts the signs of motion vectors with security-enhanced chaotic stream cipher (SECSC) and distributes keys with chaotic key distributor (CKD) at the same time. Its security, compression ratio and computational complexity are analyzed in details. Experimental results show that, the algorithm has less effect on compression ratio than the algorithms confusing DCT coefficients do, does not change file format, and is of low cost. Thus, it is suitable for secure video encoding with real-time requirement.

Radar emitter signal recognition based on support vector machines

Abstract: Radar emitter signal recognition plays an important role in electronic intelligence systems and electronic support measure systems. To heighten accurate recognition rate of radar emitter signals, this paper proposes a hierarchical classifier structure to recognize radar emitter signals. The proposed structure combines resemblance coefficient classifier, support vector machines with binary tree architecture and linear classifier based on Mahalanobis distance. Experimental results of recognizing multiple radar emitter signals show that the introduced classifier is simpler, consumes smaller training time and achieves higher accurate recognition rate and greater efficiency, in comparison with one-versus-rest support vector machines, one-versus-one support vector machines and binary-tree support vector machines.

Stability of networked control systems: analysis of packet dropping

Abstract: In this paper, we derive a necessary and sufficient condition for stability of networked control systems (NCSs) in the mean square sense and introduce the packet dropping margin to determine the robustness of the system with respect to packet dropping. By analyzing the relationship between the packet dropping probability and stability robustness, it is shown that a controller designed by a robust pole assignment approach makes the system less sensitive to packet dropping.

Tilted plane Feldkamp type reconstruction algorithm for spiral cone-beam CT

Abstract: An approximation image reconstruction method for spiral cone-beam computed tomography (CT), called tilted plane Feldkamp type reconstruction algorithm (TPFR), is presented in this paper, which extends the Feldkamp cone-beam reconstruction algorithm to overcome its inaccuracy problem caused by large cone-angle. This is done by tilting the reconstructing planes to minimize the cone angle and optimally fit the spiral segment of the source. After reconstruction of the tilted plane images, a subsequent interpolation step reforms the tilted plane images to plane images perpendicular to the z-axis. Simulations of Shepp-Logan phantom can show that the image reconstruction performance of the proposed TPFR algorithm is superior to that of the conventional Feldkamp type reconstruction algorithm.

Fault diagnosis for boilers in thermal power plant by data mining

Abstract: A new approach to diagnose faults of boilers in thermal power plants is proposed and a hybrid-intelligence data-mining framework is developed to extract hidden diagnosis information from supervisory control and data acquisition (SCADA) system. The hard core of this framework is a data mining algorithm based on rough set theory. The decision table mining from SCADA system is expressed directly by variables in its database, it is easy for engineers to understand and apply. This makes it possible to eliminate additional test or experiments for fault diagnosis which are usually expensive and involve some risks to boilers. This approach is tested in a thermal power plant; the decision accuracy is varied from 91.6 percent to 96.7 percent in different months.

Intelligent data mining and personalisation for customer relationship management

Abstract: Customer relationship management (CRM) initiatives have gained much attention in recent years. With the aid of data mining technology, businesses can formulate specific strategies for different customer bases more precisely. Additionally, personalisation is another important issue in CRM - especially when a company has a huge product range. This paper presents a case model and investigates the use of computational intelligent techniques for CRM. These techniques allow the complex functions of relating customer behaviour to internal business processes to be learned more easily and the industry expertise and experience from business managers to be integrated into the modelling framework directly. Hence, they can be used in the CRM framework to enhance the creation of targeted strategies for specific customer bases.

Comparison of the support vector machine and relevant vector machine in regression and classification problems

Abstract: In this paper, we introduce the relevant vector machine (RVM) from Michael Tipping. The formulation of the RVM in regression and classification is reviewed. Then we analyze why the RVM can reach a sparse solution. In the experiment, we use the real application data to compare the performance of SVM and RVM. The advantages and disadvantage of the SVM and RVM is analyzed based on the experimental results. Some suggestion for the RVM is presented in the discussion section.

Robust pole assignment via P-D feedback in a class of second-order dynamic systems

Abstract: The design of robust pole assignment via proportional-plus-derivative (P-D) feedback is investigated for a class of second-order dynamic systems. Based on P-D feedback parametric eigenstructure assignment for second-order dynamic systems, parametric expressions of the closed-loop eigenvalue sensitivities to the perturbed elements in the open-loop system matrices are derived and an effective algorithm for robust pole assignment in second-order dynamic systems via P-D feedback is proposed. This method utilizes directly the system data of the original second-order dynamic system, and thus is convenient to use in applications. A three lumped mass-spring dashpot system example shows the effect of this proposed algorithm.

Stereo-based human detection for mobile service robots

Abstract: Without knowledge of background or motion feature, detecting humans from a 2D image is still a tough task. In this paper, a novel stereo-based method to detect human objects for mobile service robots is proposed. Human objects are detected from the stereo spatial space through three distinct steps: (i) human oriented scale-adaptive filtering to aggregate and enhance the evidence of human presence, (ii) human like object segmentation, and (iii) human object identification based on the matching of a deformable head shoulder template to the evidence from both stereo and edge information. Systematic evaluation of the experimental results show that the high accuracy rates for human detection have been achieved with fewer constraints on the human operator, robot and the environment which they are in.

Application of coefficient diagram method for rotational inverted pendulum control

Abstract: In this paper, a design of the augmented state feedback controller by using the concept of coefficient diagram method (CDM) for a servo type of the rotational inverted pendulum system is presented. An integrator is augmented to the system due to the responses exhibiting steady-state error. In order to apply the CDM method, the augmented system must be firstly linearized and converted into controllable canonical form by a transform matrix. Then a feedback gain matrix in sense of CDM can be obtained. One can observe that the design procedure of the proposed controller is easy compared to other methods. The experimental results are shown in order to verify the effectiveness of the controller.

Synchronization of chaotic systems via learning control

Abstract: In this paper, a learning control approach is applied to the synchronization of two uncertain chaotic systems, which contain both, time varying and time invariant parametric uncertainties. The new learning approach also deals with unknown time varying parameters having distinct periods in the master and slave systems. Using the Lyapunov-Krasovskii functional and incorporating periodic parametric learning mechanism, the global stability and asymptotic synchronization between the master and the slave systems are obtained. Simulations on representative classes of chaotic systems show the effectiveness of the method.

Effective video text detection using line features

Abstract: Text superimposed on video frames provides synoptic or supplemental information on video semantics. In this paper, we propose a novel method to detect superimposed text effectively. First, we detect edges by an improved Canny edge detector. Then, a line-feature vector graph is generated based on the edge map and the stroke information is extracted. Finally text regions are generated and filtered according to line features. Experimental results show that, without much increasing the computational cost, our proposed method could suppress the false alarms notably. Furthermore, our method can be easily customized to applications with different tradeoffs in recall and precision.

Research on dynamic zoning of elevator traffic based on artificial immune algorithm

Abstract: As the abbreviation for artificial immune system, AIS is an artificial intelligence approach newly put forward, which has been widely applied to many fields such as data analysis, multimodal function optimization, computer security, error detection, etc. Based on AIS, a novel approach was proposed for elevator traffic dynamic zoning with contiguous floors during the peak traffic. In this paper, the basic theory of AIS was firstly described, then the dynamic zoning model of elevator traffic was outlined in detail, and the artificial immune algorithm (AIA) was designed for the dynamic zoning model. Comparison was drawn among the dynamic zoning based on AIA, static zoning and non-zoning. The simulation results demonstrated the feasibility of the approach proposed in this paper. Due to its fast convergence, AIA is utilized to quickly search the optimal or suboptimal zoning of elevator traffic, so it is adaptive to variable traffic demands.

Adaptive time-varying sliding mode control for hydraulic servo system

Abstract: This paper studies the position control of an electro-hydraulic servo system. Because the dynamics of the system are highly nonlinear and have large extent of model uncertainties including big changes in load and hydraulic parameters, which are unmatched, a time-varying sliding mode control approach combined with adaptive control is proposed based on Lyapunov analysis. The time-varying sliding mode control avoids the reaching phase of conventional sliding mode control, thus the control method proposed can be robust all the time. Adaptive control is used to identify the system parameters to overcome the influence of the uncertain parameters and disturbances. Simulation results indicate that the control approach has nice global robustness and improves position tracking accuracy considerably.