Lâm Bùi - Academia.edu (original) (raw)

Papers by Lâm Bùi

Các công trình nghiên cứu, phát triển và ứng dụng Công nghệ Thông tin và Truyền thông

Time series forecasting is paid a considerable attention of the researchers. At present, in the f... more Time series forecasting is paid a considerable attention of the researchers. At present, in the field of machine learning, there are a lot of studies using artificial neural networks to construct the model of time series forecast in general, and foreign currency exchange rates forecast, in particular. However, determining the number of members of an ensemble is still debatable. This paper proposes the way of constructing a model and designing a multi-objective evolutionary algorithm in training neural networks ensembles in order to increase the diversity of the population. Two objectives of the selected model include: Mean Sum of Squared Errors - MSE and Diversity. We experimented the model on four data sets and compared three methods (single-objective, multi- objective and ensembles). The experimental results showed that the proposed model produced better in investigated cases.

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010

In home service robot applications, robots often deal with textured objects. The variation of sur... more In home service robot applications, robots often deal with textured objects. The variation of surface's reflectivity may decrease the accuracy of depth measurement of structured light 3D camera. In this paper, we propose a new method to correct the boundary of structured light pattern in order to increase the accuracy of depth measurement. The algorithm first estimates the reflection index of the surface. The light stripe is deconvoluted to remove the smooth effect of the camera lens. Finally, the edge is normalised by the reflection index, and the boundary is estimated from the intersection between the corrected versions of the edge and its inverse. The experimental results show that with the proposed boundary estimator, there are significant improvements in term of surface smoothness of textured objects.

2012 IEEE International Conference on Robotics and Automation, 2012

In this paper, we present a new method for decoding pixel correspondences in structured light bas... more In this paper, we present a new method for decoding pixel correspondences in structured light based 3D reconstruction, refer to here as Ray-Tracing codec. The key idea of Ray-Tracing codec is to correctly define the region boundaries in real number, for each layer of the Hierarchical Orthogonal Code (HOC) based on an accurate boundary estimator, and to inherit the correct region boundaries between layers sharing common boundaries. Furthermore, each region in lower layer is traced back to the upper layer for the correct correspondence between regions. This is an improvement over existing HOC decoding algorithms as the wrong decoded pixel correspondences can be greatly reduced. The experimental results have shown that the proposed Ray-Tracing codec significantly enhances the robustness and precision in depth imaging, compare with HOC and other well-known conventional approach. The proposed approach opens a greater feasibility of applying structured light based depth imaging to a 3D modeling of cluttered workspace for home service robots.

Journal of the Optical Society of America A, 2011

Depth recovery based on structured light using stripe patterns, especially for a region-based cod... more Depth recovery based on structured light using stripe patterns, especially for a region-based codec, demands accurate estimation of the true boundary of a light pattern captured on a camera image. This is because the accuracy of the estimated boundary has a direct impact on the accuracy of the depth recovery. However, recovering the true boundary of a light pattern is considered difficult due to the deformation incurred primarily by the textureinduced variation of the light reflectance at surface locales. Especially for heavily textured surfaces, the deformation of pattern boundaries becomes rather severe. We present here a novel (to the best of our knowledge) method to estimate the true boundaries of a light pattern that are severely deformed due to the heavy textures involved. First, a general formula that models the deformation of the projected light pattern at the imaging end is presented, taking into account not only the light reflectance variation but also the blurring along the optical passages. The local reflectance indices are then estimated by applying the model to two specially chosen reference projections, all-bright and all-dark. The estimated reflectance indices are to transform the edge-deformed, captured pattern signal into the edge-corrected, canonical pattern signal. A canonical pattern implies the virtual pattern that would have resulted if there were neither the reflectance variation nor the blurring in imaging optics. Finally, we estimate the boundaries of a light pattern by intersecting the canonical form of a light pattern with that of its inverse pattern. The experimental results show that the proposed method results in significant improvements in the accuracy of the estimated boundaries under various adverse conditions.

Applied Optics, 2013

This paper presents a new method of structured light-based 3D reconstruction, referred to here as... more This paper presents a new method of structured light-based 3D reconstruction, referred to here as Boundary Inheritance Codec, that provides high accuracy and low noise in projector-camera correspondence. The proposed method features (1) real-boundary recovery: the exact locations of region boundaries, defined by a coded pattern, are identified in terms of their real coordinates on the image plane. To this end, a radiance independent recovery of accurate boundaries and a disambiguation of true and false boundaries are presented. (2) Boundary inheritance: the consistency among the same boundaries of different layers in pattern hierarchy is exploited to further enhance the accuracy of region correspondence and boundary estimation. Extensive experimentations are carried out to verify the performance of the proposed Boundary Inheritance Codec, especially, in comparison with a number of well-known methods currently available, including Gray-code (GC) plus line/phase shift (LS/PS). The results indicate that the proposed method of recovering real boundaries with boundary inheritance is superior in accuracy and robustness to Gray-code inverse (GCI), GC LS∕PS. For instance, the error standard deviation and the percentile of outliers of the proposed method were 0.152 mm and 0.089%, respectively, while those of GCI were 0.312 mm and 3.937%, respectively, and those of GC LS∕PS were 0.280∕0.321 mm and 0.159∕7.074%, respectively.

In this study, two samples of Irrawaddy dolphins (Orcaella brevirostris Gray, 1866) in Kien Giang... more In this study, two samples of Irrawaddy dolphins (Orcaella brevirostris Gray, 1866) in Kien Giang waters, Vietnam were collected. The phylogenetic tree showed that Irrawaddy dolphins in Vietnam had a close genetic relationship to Irrawaddy dolphins in Indonesia and Laos which have been registered in the Gene Bank. This is the latest research in Vietnam about determining the mitochondrial cytochrome b gene sequence and the hereditary relationship of Irrawaddy dolphin (Orcaella brevirostris Gray, 1866) in Kien Giang waters. This results contributed to the conservative research and development of this valuable and rare marine mammal species.

대한기계학회 춘추학술대회, May 1, 2013

In this paper, a new hybrid algorithm based on exploration power of a new improvement self-adapti... more In this paper, a new hybrid algorithm based on exploration power of a new improvement self-adaptive strategy for controlling parameters in DE (differential evolution) algorithm and exploitation capability of Nelder-Mead simplex method is presented (HISADE-NMS). The DE has been used in many practical cases and has demonstrated good convergence properties. It has only a few control parameters as number of particles (NP), scaling factor (F) and crossover control (CR), which are kept fixed throughout the entire evolutionary process. However, these control parameters are very sensitive to the setting of the control parameters based on their experiments. The value of control parameters depends on the characteristics of each objective function, therefore, we have to tune their value in each problem that mean it will take too long time to perform. In the new manner, we present a new version of the DE algorithm for obtaining self-adaptive control parameter settings. Some modifications are imposed on DE to improve its capability and efficiency while being hybridized with Nelder-Mead simplex method. To valid the robustness of new hybrid algorithm, we apply it to solve some examples of structural optimization constraints.

Communications in computer and information science, 2012

In recent decades, new optimization algorithms have attracted much attention from researchers in ... more In recent decades, new optimization algorithms have attracted much attention from researchers in both gradientand evolution-based optimal methods. Many strategy techniques are employed to enhance the effectiveness of optimal methods. One of the newest techniques is opposition-based learning (OBL), which shows more power in enhancing various optimization methods. This research presents a new edition of the Differential Evolution (DE) algorithm in which the OBL technique is applied to investigate the opposite point of each candidate of selfadaptive control parameters. In comparison with conventional optimal methods, the proposed method is used to solve benchmark-test optimal problems and applied to real optimizations. Simulation results show the effectiveness and improvement compared with some reference methodologies in terms of the convergence speed and stability of optimal results.

In this paper, the authors propose an ensemble multi-objective particle swarm optimisation approa... more In this paper, the authors propose an ensemble multi-objective particle swarm optimisation approach (named EMPSO) for forecasting the currency exchange rate chain. The proposed algorithm consists of two main phases. The first phase uses a multi-objective particle swarm optimisation algorithm to find a set of the best optimal particles (named leaders). The second phase then uses these leaders to jointly calculate the final results by using the soft voting ensemble method. The two objective functions used here are predictive error and particle diversity. The empirical data used in this study are six different sets of currency exchange rates. Through comparison results with other evolutionary algorithms and other multi-objective PSO algorithms, the proposed algorithm shows that it can achieve better as well as more stability results on experimental data sets.

International journal of mechanical engineering and robotics research, 2021

The objective of this paper is to develop an efficient Wall-Climbing Robot (WCR) which can move o... more The objective of this paper is to develop an efficient Wall-Climbing Robot (WCR) which can move on the wall for cleaning purposes. The biggest problem with this type of robot that the researchers encounter is how to keep the robot moving steadily on the wall. This study proposed a new mechanical design of the Wall-Climbing robot using the Vacuum principle and wireless control technology for flexible movement on the wall. In which, the Minimum Required Adhesion Force (FMRA) is calculated to be balanced with gravity and its torque. Moreover, a Wireless Control System (WCS) is designed to drive the Robot remotely.

The guidance of a large swarm is a challenging control problem. Shepherding offers one approach t... more The guidance of a large swarm is a challenging control problem. Shepherding offers one approach to guide a large swarm using a few shepherding agents (sheepdogs). While noise is an inherent characteristic in many real-world problems, the impact of noise on shepherding is not a wellstudied problem. We study two forms of noise. First, we evaluate noise in the sensorial information received by the shepherd about the location of sheep. Second, we evaluate noise in the ability of the sheepdog to influence sheep due to disturbance forces occurring during actuation. We study both types of noise in this paper, and investigate the performance of Strömbom's approach under these actuation and perception noises. To ensure that the parameterisation of the algorithm creates a stable performance, we need to run a large number of simulations, while increasing the number of random episodes until stability is achieved. We then systematically study the impact of sensorial and actuation noise on performance. Strömbom's approach is found to be more sensitive to actuation noise than perception noise. This implies that it is more important for the shepherding agent to influence the sheep more accurately by reducing actuation noise than attempting to reduce noise in its sensors. Moreover, different levels of noise required different parameterisation for the shepherding agent, where the threshold needed by an agent to decide whether or not to collect astray sheep is different for different noise levels.

Journal of Advanced Transportation, Oct 25, 2020

is paper introduces a model-driven control realization, which is based on the systems engineering... more is paper introduces a model-driven control realization, which is based on the systems engineering concepts of the model-driven architecture (MDA)/model-based systems engineering (MBSE) approach combined with the real-time UML/SysML, extended/ unscented Kalman filter (EKF/UKF) algorithms, and hybrid automata, in order to conveniently deploy controllers of autonomous underwater vehicles (AUVs). is model also creates a real-time communication pattern, which can permit the designed components to be customizable and reusable in new application developments of different AUV types. e paper brings out stepwise adapted AUV dynamics for control that are then combined with the specialization of MDA/MBSE features as follows: the computation independent model (CIM) is defined by the specification of the use-case model together with hybrid automata to gather the requirement analysis for control; the platform-independent model (PIM) is then designed by specializing the real-time UML/SysML's features including main control capsules that depict structures and behaviors of controllers in detail; and the detailed PIM is subsequently converted into the platform-specific model (PSM) by object-oriented platforms to rapidly implement the AUV controller. Based on this proposed model, a horizontal planar trajectory-tracking controller was deployed and tested that permits a miniature AUV possessing a torpedo shape to reach and follow the desired horizontal planar trajectory.

Natural computing series, 2008

In this chapter, we discuss the use of multiobjective evolutionary algorithms (MOEAs) for solving... more In this chapter, we discuss the use of multiobjective evolutionary algorithms (MOEAs) for solving single-objective optimization problems in dynamic environments. Specifically, we investigate the consideration of a second (artificial) objective, with the aim of maintaining ...

Journal of physics, May 1, 2022

IntechOpen eBooks, Mar 31, 2021

In this study, the Self-adaptive strategy algorithm for controlling parameters in Differential Ev... more In this study, the Self-adaptive strategy algorithm for controlling parameters in Differential Evolution algorithm (ISADE) improved from the Differential Evolution (DE) algorithm, as well as the upgraded version of the algorithms has been applied to solve the Inverse Kinetics (IK) problem for the redundant robot with 7 Degree of Freedom (DoF). The results were compared with 4 other algorithms of DE and Particle Swarm Optimization (PSO) as well as Pro-DE and Pro-PSO algorithms. These algorithms are tested in three different Scenarios for the motion trajectory of the end effector of in the workspace. In the first scenario, the IK results for a single point were obtained. 100 points randomly generated in the robot's workspace was input parameters for Scenario 2, while Scenario 3 used 100 points located on a spline in the robot workspace. The algorithms were compared with each other based on the following criteria: execution time, endpoint distance error, number of generations required and especially quality of the joints' variable found. The comparison results showed 2 main points: firstly, the ISADE algorithm gave much better results than the other DE and PSO algorithms based on the criteria of execution time, endpoint accuracy and generation number required. The second point is that when applying Pro-ISADE, Pro-DE and Pro-PSO algorithms, in addition to the ability to significantly improve the above parameters compared to the ISADE, DE and PSO algorithms, it also ensures the quality of solved joints' values.

Journal of Advanced Mechanical Design Systems and Manufacturing, 2019

Applied sciences, Apr 13, 2020

Laser interferometers can achieve a nanometer-order uncertainty of measurements when their freque... more Laser interferometers can achieve a nanometer-order uncertainty of measurements when their frequencies are locked to the reference frequencies of the atom or molecule transitions. There are three types of displacement-measuring interferometers: homodyne, heterodyne, and frequency modulation (FM) interferometers. Among these types of interferometer, the FM interferometer has many advantageous features. The interference signal is a series of time-dependent harmonics of modulation frequency, so the phase shift can be detected accurately using the synchronous detection method. Moreover, the FM interferometer is the most suitable for combination with a frequency-locked laser because both require frequency modulation. In previous research, low modulation frequencies at some tens of kHz have been used to lock the frequency of laser diodes (LDs). The low modulation frequency for the laser source means that the maximum measurement speed of the FM interferometers is limited. This paper proposes a novel contribution regarding the application of a high-frequency modulation for an LD to improve both the frequency stability of the laser source and the measurement speed of the FM interferometer. The frequency of the LD was locked to an I 2 hyperfine component at 1 MHz modulation frequency. A high bandwidth lock-in amplifier was utilized to detect the saturated absorption signals of the I 2 hyperfine structure and induce the signal to lock the frequency of the LD. The locked LD was then used for an FM displacement measuring interferometer. Moreover, a suitable modulation amplitude that affected the signal-to-noise ratio of both the I 2 absorption signal and the harmonic intensity of the interference signal was determined. In order to verify the measurement resolution of the proposed interferometer, the displacement induced by a piezo electric actuator was concurrently measured by the interferometer and a capacitive sensor. The difference of the displacement results was less than 20 nm. To evaluate the measurement speed, the interferometer was used to measure the axial error of a high-speed spindle at 500 rpm. The main conclusion of this study is that a stable displacement interferometer with high accuracy and a high measurement speed can be achieved using an LD frequency locked to an I 2 hyperfine transition at a high modulation frequency.

In this research, Particle Swarm Optimization (PSO) algorithm has been applied to solve the Inver... more In this research, Particle Swarm Optimization (PSO) algorithm has been applied to solve the Inverse Kinematic (IK) problem for redundant serial manipulator robots. The new point of the study is to consider the continuity of the joints' variable. By noting this problem, the process of solving the Inverse Kinematic problem for the robots by the optimal algorithm has been significantly improved in terms of accuracy, execution time, and standard deviation (STD) as well as the number of iterations needed. The algorithm has been applied to solve the Inverse Kinematic problem on the 5-Degree of Freedom 5R robot model. The results show that just using the PSO algorithm with the above search domain limit has improved the quality of IK process.