Browsing by Author "Lin, Sheng-Fuu"

Now showing 1 - 20 of 40

A New Method for Three-dimensional Measurement with Two Horizontally-aligned Omni-directional Cameras
(2014)
Lin, Sheng-Fuu
;
Ke, Jau-Chi
;
Liu, Hsin-Yi
;
Liao, Jiao-Rou
;
電機工程學系
In this paper, a new method for three-dimensional measurement with two horizontally-aligned omni-directional cameras is proposed. Some omni-camera stereo vision systems calculate three-dimensional information which always considers either azimuth angles or elevation angles causing inaccuracy easily. The proposed method takes into account both azimuth angles and elevation angles in order to reduce errors. Besides, the range of interest (ROI) is 3 to 8 meters around cameras in the system. The proposed method has better perfonnance than the vertically- or horizontally-aligned in the 3D measurement.
A Novel Self-Constructing Evolution Algorithm for TSK-type Fuzzy Model Design
(2010)
Lin, Sheng-Fuu
;
Chang, Jyun-Wei
;
Cheng, Yi-Chang
;
Hsu, Yung-Chi
;
電機工程學系
In this paper, a novel self-constructing evolution algorithm (SCEA) for TSK-type fuzzy model (TFM) design is proposed. The proposed SCEA method is different from the traditional genetic algorithms (GA). A chromosome of the population in GA represents a full solution and only one population presents all solutions. Our method applies a population to evaluate a partial solution locally, and several populations to construct the full solution. Thus, a chromosome represents only partial solution. The proposed SCEA uses the self-constructing learning algorithm to construct the TFM automatically that is based on the input data to decide the input partition. And we also adopted the sequence search-based dynamic evolution (SSDE) method to perform parameter learning. Simulation results have shown that the proposed SCEA method obtains better performance than some existing models.
A self-organization mining based hybrid evolution learning for TSK-type fuzzy model design
(2012-03-01)
Lin, Sheng-Fuu
;
Chang, Jyun-Wei
;
Hsu, Yung-Chi
;
電機工程學系
;
Department of Electrical and Computer Engineering
In this paper, a self-organization mining based hybrid evolution (SOME) learning algorithm for designing a TSK-type fuzzy model (TFM) is proposed. In the proposed SOME, group-based symbiotic evolution (GSE) is adopted in which each group in the GSE represents a collection of only one fuzzy rule. The proposed SOME consists of structure learning and parameter learning. In structure learning, the proposed SOME uses a two-step self-organization algorithm to decide the suitable number of rules in a TFM. In parameter learning, the proposed SOME uses the data mining based selection strategy and data mining based crossover strategy to decide groups and parental groups by the data mining algorithm that called frequent pattern growth. Illustrative examples were conducted to verify the performance and applicability of the proposed SOME method.
A self-powered current monitoring module with ZigBee communication for industrial applications
(2015-04-01)
Cheng, Shih-Hsien
;
Lin, Sheng-Fuu
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This study presents a module integrated with ZigBee communication but without an external power supply and battery to monitor the current consumption of industrial machines. In the module, power is collected from the magnetic field around an electric current in a conductor that is connected to the machine. The collected power is then supplied to the current-measuring and ZigBee communication devices. The information provided by the module supports energy management systems and is the basis for the replacement of old equipment at the appropriate time, thus resulting in increasingly efficient energy usage. Experimental tests, including an energy-harvesting test, a full-function test, and a third party report, verify the performance of the proposed system. Test results show that full function is supported from 10 to 60A and that accuracy is better than 3%.
Accuracy enhanced thermal face recognition
(2013-11-01)
Lin, Chun-Fu
;
Lin, Sheng-Fuu
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Human face recognition has been generally researched for the last three decades. Face recognition with thermal image has begun to attract significant attention gradually since illumination of environment would not affect the recognition performance. However, the recognition performance of traditional thermal face recognizer is still insufficient in practical application. This study presents a novel thermal face recognizer employing not only thermal features but also critical facial geometric features which would not be influenced by hair style to improve the recognition performance. A three-layer back-propagation feed-forward neural network is applied as the classifier. Traditional thermal face recognizers only use the indirect information of the topography of blood vessels like thermogram as features. To overcome this limitation, the proposed thermal face recognizer can use not only the indirect information but also the direct information of the topography of blood vessels which is unique for every human. Moreover, the recognition performance of the proposed thermal features would not decrease even if the hair of frontal bone varies, the eye blinks or the nose breathes. Experimental results show that the proposed features are significantly more effective than traditional thermal features and the recognition performance of thermal face recognizer is improved. (C) 2013 Elsevier B.V. All rights reserved.
Accurate and rapid alignment of laser scanned 3D surface using TSK-type neural-fuzzy network-based coarse-to-fine strategy
(2012-10-01)
Chang, Jyun-Wei
;
Lin, Sheng-Fuu
;
Hsu, Chi-Yao
;
電機工程學系
;
Department of Electrical and Computer Engineering
Aligning a laser scanned three-dimensional (3D) surface is considered a critical step in object recognition, shape analysis, and automatic visual inspection. Two major concerns for the alignment task are execution time and alignment accuracy. Recently, neural network-based methods have become very popular due to their high efficiency. However, such methods experience difficulty in reaching high accuracy because the use of principal component analysis (PCA) to perform coarse alignment causes a large alignment error. Thus, a TSK-type neural-fuzzy network (TNFN)-based coarse-to-fine 3D surface alignment scheme is proposed in the current paper. Compared with traditional neural network-based approaches, the proposed method provides a coarse-to-fine alignment approach to ensure the accurate pose estimated by TNFN in the coarse phase, as well the high alignment speed provided by TNFN-based surface modeling in the fine phase. Experimental results demonstrate the superior performance of the proposed 3D surface alignment system over existing systems. (C) 2012 Elsevier Ltd. All rights reserved.
AN EFFICIENT 3D MODEL RETRIEVAL BASED ON PRINCIPAL AXES ANALYSIS AND FEATURE INTEGRATION
(2011-06-01)
Lin, Sheng-Fuu
;
Wu, Chin-Chia
;
Hsu, Chi-Yao
;
Hsu, Dou-Chih
;
電機工程學系
Three-dimensional (3D) model retrieval has gathered great importance in recent years, since the number of available 3D models on the Internet has drastically increased. Many content-based 3D model retrieval approaches have been proposed. Among these methods, visual similarity-based methods have shown higher retrieval accuracy. However, because these methods capture enormous shape features from different viewpoints or locations, a large amount of calculation and comparison is necessary. Furthermore, there is a trade-off between retrieval accuracy and speed. In this paper, a 3D model retrieval method constituting Continuous Principal Component Analysis (CPCA), Fourier descriptors, and Zernike moments is proposed. CPCA is applied to extract significant shape features based on projecting the model along the principal axes. Then, Fourier descriptors and Zernike moments are used to provide shape descriptors with rotation invariants. In addition, a feature integration process combines them. A strategy of similarity measure is proposed to solve the axes switching problem. To conclude, the experimental results show that the approach outperforms SECTORS(2) and D2,(18) and has slightly better retrieval results than Light Field Descriptor (LFD)(6) and spin-image signatures.(3) Moreover, the approach is more efficient and the storage size is much less.
Applying Two-Stage Differential Evolution for Energy Saving in Optimal Chiller Loading
(2019-02-02)
Lin, Chang-Ming
;
Wu, Chun-Yin
;
Tseng, Ko-Ying
;
Ku, Chih-Chiang
;
Lin, Sheng-Fuu
In Taiwan, over 45% of the energy in common buildings is used for the air-conditioning system. In particular, the chiller plant consumes about 70% of the energy in air-conditioning system. The electric energy consumption of air-condition system in a clean room of semiconductor factory is about 5-10 times of that in a common building. Consequently, the optimal chiller loading in energy saving of building is a vital issue. This paper develops a new algorithm to solve optimal chiller loading (OCL) problems. The proposed two-stage differential evolution algorithm integrated the advantages of exploration (global search) in the modified binary differential evolution (MBDE) algorithm and exploitation (local search) in the real-valued differential evolution (DE) algorithm for finding the optimal solution of OCL problems. In order to show the performance of the proposed algorithm, comparison with other optimization methods has been done and analyzed. The result shows that the proposed algorithm can obtain similar or better solution in comparison to previous studies. It is a promising approach for the OCL problem.
Automatic Counting Cancer Cell Colonies using Fuzzy Inference System
(2011-03-01)
Lin, Sheng-Fuu
;
Chen, Hsien-Tse
;
Lin, Yi-Hsien
;
電機工程學系
;
Department of Electrical and Computer Engineering
This paper examines the efficacy of liver cancer treatment using HA22T cancer cells specific to the Taiwanese population. The Clonogenic Assay is the current standard method for detecting liver cancer. This paper uses image processing technology and a fuzzy inference system to identify in-vitro colonies of cancer cells. A scanner was first used to capture an image of the culture dish. This image was then analyzed using image processing techniques and the Hough transform to establish the relative position of the dish. Image segmentation was accomplished by image differencing, while feature extraction was based on the features specific to the image. Decision-making was then carried out using a fuzzy inference system to calculate the number of colonies within the image. In summary, this paper proposes a fuzzy cancer cell colony identification system based on a fuzzy inference system (FIS) that successfully identifies cancer cell colonies that are indiscernible to the naked eye.
AUTOMATIC IDENTIFYING LARYNGOPHARYNGEAL REFLUX USING ARTIFICIAL NEURAL NETWORK
(2012-02-01)
Lin, Sheng-Fuu
;
Chen, Hsien-Tse
;
Tsai, Tung-Lung
;
電機工程學系
;
Department of Electrical and Computer Engineering
Laryngopharyngeal Reflux mostly leads to burns of the pharynx and larynx by reflux from gastric acid and also leads to different degrees of burns in the esophagus and the stomach. This paper aims to develop a technique for analyzing pharyngeal and laryngeal images. With techniques of digital image processing, this paper can choose the suitable images from burns of the pharynx and larynx to obtain the feature zones of burns of the pharynx and larynx. Artificial neural network helps physicians to develop the diagnostic standard about the burns severity of Laryngopharyngeal Reflux. This paper divides the types of the complications into three degrees and compares with other ways (Hanson et al.(5) and Ilgner et al.(6)). The results can be the technical assistance in helping physicians to diagnose the severity of Laryngopharyngeal Reflux and to make a more precise diagnosis.
Data mining-based hierarchical cooperative coevolutionary algorithm for TSK-type neuro-fuzzy networks design
(2013-08-01)
Hsu, Chi-Yao
;
Lin, Sheng-Fuu
;
Chang, Jyun-Wei
;
電機工程學系
;
Department of Electrical and Computer Engineering
This study proposes a data mining-based hierarchical cooperative coevolutionary algorithm (DMHCCA) for TSK-type neuro-fuzzy networks design. The proposed DMHCCA consists of two-level evolutions: the neuro-level evolution (NULE) and the network-level evolution (NWLE). In NULE, a data mining-based evolutionary learning algorithm is utilized to evolve neurons. The good combinations of neurons evolved in NULE are reserved for being the initial populations of NWLE. In NWLE, the initial population are mated and mutated to produce new structure of networks. Similar to NULE, the good neurons of evolved network in NWLE are inserted into the NULE. Thus, by interactive two-level evolutions, the neurons and structure of network can be evolved locally and globally, respectively. Simulation results using DMHCCA are reported and compared with other existing models. Application of DMHCCA to a three-dimensional (3D) surface alignment task is also described, and experimental results are presented better performance than other alignment systems.
Efficient face detection method with eye region judgment
(2013)
Lin, Chun-Fu
;
Lin, Sheng-Fuu
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Real-time face detection technology can be applied in many industrial or commercial products. Many face detection applications use the traditional Adaboost face detection system which is proposed by Viola and Jones in 2004. Viola and Jones used the Adaboost training algorithm and the Haar-like features in their proposed traditional Adaboost face detection system, which has a high detection rate but long training time. Many studies have attempted to reduce the training time and retain the high detection rate of the traditional Adaboost face detection system. However, the detection rate of the Adaboost-based face detection system cannot compete with the traditional Adaboost face detection system when the training time is reduced significantly. This study proposes the judging existence of eye region (JEER) method to enhance the detection rate of the previous Adaboost-based face detection systems. The eyes are more salient and representative features than the other facial parts such as the mouth or ears, especially when mask is worn on the human face. Therefore, the proposed face detection system with the JEER method achieves higher detection rate than the Adaboost-based face detection systems. Although the JEER computation results in a slightly longer training time, the training time of the proposed face detection system is still much shorter than the traditional Adaboost face detection system owing to the efficient JEER computation. The experimental results obtained using the gray FERET and CMU databases show that the proposed face detection system is effective in detection and efficient in training.
Estimation of the pedestrians on a crosswalk
(2006)
Lin, Sheng-Fuu
;
Lin, Chi-De
;
電控工程研究所
;
Institute of Electrical and Control Engineering
The estimation of the pedestrians on a crosswalk is a challenging job due to the occluded pedestrians and its complicated background. Here, an efficient method to estimate approximately the number of pedestrians on a crosswalk is presented. Foregrounds are extracted from an incoming image by using the constructed background, and then elaborately processing to remove unwanted pixels. With the aid of perspective transformation, the relation between the number of remaining foreground pixels and the number of pedestrians can be linearized, thus the estimation can be done. Instead of segmenting each pedestrian in the scene, our system counts foreground pixels, so it demands low computational power. Furthermore, this system doesn't need to be trained. The experimental results show that it works well in different scenes.
Fuzzy Adaptive Cubature Kalman Filter for Integrated Navigation Systems
(2016-08-01)
Tseng, Chien-Hao
;
Lin, Sheng-Fuu
;
Jwo, Dah-Jing
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This paper presents a sensor fusion method based on the combination of cubature Kalman filter (CKF) and fuzzy logic adaptive system (FLAS) for the integrated navigation systems, such as the GPS/INS (Global Positioning System/inertial navigation system) integration. The third-degree spherical-radial cubature rule applied in the CKF has been employed to avoid the numerically instability in the system model. In processing navigation integration, the performance of nonlinear filter based estimation of the position and velocity states may severely degrade caused by modeling errors due to dynamics uncertainties of the vehicle. In order to resolve the shortcoming for selecting the process noise covariance through personal experience or numerical simulation, a scheme called the fuzzy adaptive cubature Kalman filter (FACKF) is presented by introducing the FLAS to adjust the weighting factor of the process noise covariance matrix. The FLAS is incorporated into the CKF framework as a mechanism for timely implementing the tuning of process noise covariance matrix based on the information of degree of divergence (DOD) parameter. The proposed FACKF algorithm shows promising accuracy improvement as compared to the extended Kalman filter (EKF), unscented Kalman filter (UKF), and CKF approaches.
Heating, Ventilation, and Air Conditioning System Optimization Control Strategy Involving Fan Coil Unit Temperature Control
(2019-06-01)
Lin, Chang-Ming
;
Liu, Hsin-Yu
;
Tseng, Ko-Ying
;
Lin, Sheng-Fuu
;
電控工程研究所
The objective of this study was to develop a heating, ventilation, and air conditioning (HVAC) system optimization control strategy involving fan coil unit (FCU) temperature control for energy conservation in chilled water systems to enhance the operating efficiency of HVAC systems. The proposed control strategy involves three techniques, which are described as follows. The first technique is an algorithm for dynamic FCU temperature setting, which enables the FCU temperature to be set in accordance with changes in the outdoor temperature to satisfy the indoor thermal comfort for occupants. The second technique is an approach for determining the indoor cold air demand, which collects the set FCU temperature and converts it to the refrigeration ton required for the chilled water system; this serves as the control target for ensuring optimal HVAC operation. The third technique is a genetic algorithm for calculating the minimum energy consumption for an HVAC system. The genetic algorithm determines the pump operating frequency associated with minimum energy consumption per refrigeration ton to control energy conservation. To demonstrate the effectiveness of the proposed HVAC system optimization control strategy combining FCU temperature control, this study conducted a field experiment. The results revealed that the proposed strategy enabled an HVAC system to achieve 39.71% energy conservation compared with an HVAC system operating at full load.
LMI-based robust sliding control for mismatched uncertain nonlinear systems using fuzzy models
(2012-11-10)
Liu, Sung-Chieh
;
Lin, Sheng-Fuu
;
電機工程學系
;
Department of Electrical and Computer Engineering
We propose a robust sliding control design method for uncertain TakagiSugeno fuzzy models. The uncertain fuzzy systems under consideration have mismatched parameter uncertainties in the state matrix and external disturbances. We make the first attempt to relax the restrictive assumption that each nominal local system model shares the same input channel, which is required in the traditional VSS-based fuzzy control design methods. We derive the existence conditions of linear sliding surfaces guaranteeing the asymptotic stability in terms of constrained LMIs. We present an LMI characterization of such sliding surfaces. Also, an LMI-based algorithm is given to design the switching feedback control term so that a stable sliding motion is induced in finite time. Finally, we give two simulation results to show the effectiveness of the proposed method. Copyright (c) 2011 John Wiley & Sons, Ltd.
Moving Object Detection from a Moving Stereo Camera via Depth Information and Visual Odometry
(2018-01-01)
Lin, Sheng-Fuu
;
Huang, Sheng-Huei
;
電控工程研究所
;
Institute of Electrical and Control Engineering
It is important for driving safety to know whether surrounding objects are moving or static. Most existing methods use pre-trained object detectors to detect vehicles and humans before determine whether they are moving or not. However, there are not only these two type objects on the real road. This study presents a system using depth information and visual odometry to detect moving object. It also adopts an adaptive thresholding method to enhance performance on detection. The proposed system can accurately detect moving objects according to the experimental results.
Multi groups cooperation based symbiotic evolution for TSK-type neuro-fuzzy systems design
(2010-07-01)
Hsu, Yung-Chi
;
Lin, Sheng-Fuu
;
Cheng, Yi-Chang
;
電控工程研究所
;
Institute of Electrical and Control Engineering
In this paper, a TSK-type neuro-fuzzy system with multi groups cooperation based symbiotic evolution method (TNFS-MGCSE) is proposed. The TNFS-MGCSE is developed from symbiotic evolution. The symbiotic evolution is different from traditional GAs (genetic algorithms) that each chromosome in symbiotic evolution represents a rule of fuzzy model. The MGCSE is different from the traditional symbiotic evolution; with a population in MGCSE is divided into several groups. Each group formed by a set of chromosomes represents a fuzzy rule and cooperate with other groups to generate the better chromosomes by using the proposed cooperation based crossover strategy (CCS). In this paper, the proposed TNFS-MGCSE is used to evaluate by numerical examples (Mackey-Glass chaotic time series and sunspot number forecasting). The performance of the TNFS-MGCSE achieves excellently with other existing models in the simulations. (C) 2010 Elsevier Ltd. All rights reserved.
Optimal Chiller Loading Using Modified Artificial Bee Colony Algorithm
(2020-01-01)
Lin, Chang-Ming
;
Tseng, Ko-Ying
;
Lin, Sheng-Fuu
;
電控工程研究所
;
Institute of Electrical and Control Engineering
In Taipei, over 45% of the energy used in buildings is for air-conditioning systems. In particular, multiple chiller systems consume about 70% of the energy in an air-conditioning system. Consequently, optimal chiller loading (OCL) or energy saving of a building is a vital issue. In this paper, we report a newly developed heuristic algorithm to solve OCL problems. A digital flow meter and a digital meter are installed to calculate the energy efficiency of a chiller. The exploration and exploitation of chiller loading can be efficiently improved without increasing the number of iterations by adopting the proposed modified artificial bee colony (MABC) algorithm. To demonstrate the performance of the proposed algorithm, it has been analyzed in comparison with other optimization methods. The result shows that the proposed algorithm can obtain a similar or better solution than previous algorithms. Therefore, it is a promising approach for solving the OCL problem.
Pedestrians and Vehicles Recognition Based on Image Recognition and Laser Distance Detection
(2016-01-01)
Lin, Sheng-Fuu
;
Lee, Chung-Han
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
Nowadays, most vehicles are equipped with the display device and dashboard camera. The former provides drivers with a variety of road information such as the reverse image and satellite navigation, the latter ensures the interests of the driver when the accidents happened. A laser range finder and a webcam are used in the proposed system. This system can provide drivers with driving safety information on the display device. A laser range finder which cuts up objects around the car through the breakpoint detection is involved with the distance and azimuth angle information of the surrounding environment. Also, Haar detection is used to extract the related features of the pedestrians and vehicles for image recognition system. It will be more accurate to recognize the pedestrians and vehicles on the road, if both image recognition system and information of laser distance are combined together. The proposed system can accurately recognize the pedestrians and vehicles according to the experimental results.