Browsing by Author "Li, Dong-Lin"

Now showing 1 - 14 of 14

A Comparative Study of Machine Learning Techniques for Credit Card Fraud Detection Based on Time Variance
(2018-01-01)
Rajora, Shantanu
;
Li, Dong-Lin
;
Jha, Chandan
;
Bharill, Neha
;
Patel, Om Prakash
This paper proposes a comparative performance of ten different machine learning algorithms, done on a credit card fraud detection application. The machine learning methods have been classified into two groups namely classification algorithms and ensemble learning group. Each group is comprised of five different algorithms. Besides, the 'Time' feature is introduced in the data set and performances of the algorithms are studied with and without the 'Time' feature. Two algorithms of the ensemble learning group have been found to perform better when the used dataset does not include the 'Time' feature. However, for the classification algorithms group, three classifiers are found to show better predictive accuracies when all attributes are included in the used dataset. The rest of the machine learning models have approximate similar scores between these datasets.
A Generalized Enhanced Quantum Fuzzy Approach for Efficient Data Clustering
(2019-01-01)
Bharill, Neha
;
Patel, Om Prakash
;
Tiwari, Aruna
;
Mu, Lifeng
;
Li, Dong-Lin
Data clustering is a challenging task to gain insights into data in various fields. In this paper, an Enhanced Quantum-Inspired Evolutionary Fuzzy C-Means (EQIE-FCM) algorithm is proposed for data clustering. In the EQIE-FCM, quantum computing concept is utilized in combination with the FCM algorithm to improve the clustering process by evolving the clustering parameters. The improvement in the clustering process leads to improvement in the quality of clustering results. To validate the quality of clustering results achieved by the proposed EQIE-FCM approach, its performance is compared with the other quantum-based fuzzy clustering approaches and also with other evolutionary clustering approaches. To evaluate the performance of these approaches, extensive experiments are being carried out on various benchmark datasets and on the protein database that comprises of four superfamilies. The results indicate that the proposed EQIE-FCM approach finds the optimal value of fitness function and the fuzzifier parameter for the reported datasets. In addition to this, the proposed EQIE-FCM approach also finds the optimal number of clusters and more accurate location of initial cluster centers for these benchmark datasets. Thus, it can be regarded as a more efficient approach for data clustering.
A Light Deep Learning Based Method for Bank Serial Number Recognition
(2018-01-01)
Umam, Ardian
;
Chuang, Jen-Hui
;
Li, Dong-Lin
;
資訊工程學系
;
電機工程學系
A full stage bank serial number (SN) recognition system is proposed in this paper. We introduce Block-wise Prediction Networks (BPN) to treat the localization of an SN as block-wise binary classification, which can be considered as a coarse version of dense/pixel-wise prediction used in semantic segmentation. The benefits include short execution time, which is equal to 85.22 ms in CPU, and the use of global features instead of local features to improve the segmentation. Our system then separates the localized Region of Interest (Rol) into individual characters, and feeds them into softmax CNN classifier. Experimental results show that the proposed method can achieve 99.92% and 99.24% accuracy for character and SN of Renminbi (RMB), respectively, tested with 2,368 two sides images of 1,184 RMB bills.
A METHOD TO ENHANCE THE DEEP LEARNING IN AN AERIAL IMAGE
(2017-01-01)
Chou, Kuang-Pen
;
Li, Dong-Lin
;
Lin, Wen-Chieh
;
Prasad, Mukesh
;
Lin, Chin-Teng
In this paper, we propose a kind of pre-processing method which can be applied to the depth learning method for the characteristics of aerial image. This method combines the color and spatial information to do the quick background filtering. In addition to increase execution speed, but also to reduce the rate of false positives
Automatic Age Estimation System for Face Images Regular Paper
(2012-11-28)
Lin, Chin-Teng
;
Li, Dong-Lin
;
Lai, Jian-Hao
;
Han, Ming-Feng
;
Chang, Jyh-Yeong
Humans are the most important tracking objects in surveillance systems. However, human tracking is not enough to provide the required information for personalized recognition. In this paper, we present a novel and reliable framework for automatic age estimation based on computer vision. It exploits global face features based on the combination of Gabor wavelets and orthogonal locality preserving projections. In addition, the proposed system can extract face aging features automatically in real-time. This means that the proposed system has more potential in applications compared to other semi-automatic systems. The results obtained from this novel approach could provide clearer insight for operators in the field of age estimation to develop real-world applications.
DEEP LEARNING-BASED OBSTACLE DETECTION AND DEPTH ESTIMATION
(2019-01-01)
Hsieh, Yi-Yu
;
Lin, Wei-Yu
;
Li, Dong-Lin
;
Chuang, Jen-Hui
;
資訊工程學系
This paper proposed a modified YOLOv3 which has an extra object depth prediction module for obstacle detection and avoidance. We use a pre-processed KITTI dataset to train the proposed, unified model for (i) object detection and (ii) depth prediction and use the AirSim flight simulator to generate synthetic aerial images to verify that our model can be applied in different data domains. Experimental results show that the proposed model compares favorably with other depth map prediction methods in terms of accuracy in the prediction of object depth for pre-processed KITTI dataset, while the unified approach can actually improve both (i) and (ii) at the same time.
Face recognition using nonparametric-weighted Fisherfaces
(2012)
Li, Dong-Lin
;
Prasad, Mukesh
;
Hsu, Sheng-Chih
;
Hong, Chao-Ting
;
Lin, Chin-Teng
This study presents an appearance-based face recognition scheme called the nonparametric-weighted Fisherfaces (NW-Fisherfaces). Pixels in a facial image are considered as coordinates in a high-dimensional space and are transformed into a face subspace for analysis by using nonparametric-weighted feature extraction (NWFE). According to previous studies of hyperspectral image classification, NWFE is a powerful tool for extracting hyperspectral image features. The Fisherfaces method maximizes the ratio of between-class scatter to that of within-class scatter. In this study, the proposed NW-Fisherfaces weighted the between-class scatter to emphasize the boundary structure of the transformed face subspace and, therefore, enhances the separability for different persons' face. The proposed NW-Fisherfaces was compared with Orthogonal Laplacianfaces, Eigenfaces, Fisherfaces, direct linear discriminant analysis, and null space linear discriminant analysis methods for tests on five facial databases. Experimental results showed that the proposed approach outperforms other feature extraction methods for most databases.
Nonlinear System Control Using Functional-Link-Based Neuro-Fuzzy Network Model Embedded with Modified Particle Swarm Optimizer
(2012-03-01)
Su, Miin-Tsair
;
Lin, Chin-Teng
;
Hsu, Sheng-Chih
;
Li, Dong-Lin
;
Lin, Cheng-Jian
This study presents an evolutionary neural fuzzy system (NFS) for nonlinear system control. The proposed NFS model uses functional link neural networks (FLNNs) as the consequent part of the fuzzy rules. This study uses orthogonal polynomials and linearly independent functions in a functional expansion of the functional link neural networks. A learning algorithm, which consists of structure learning and parameter learning, is presented. The structure learning depends on the entropy measure to determine the number of fuzzy rules. The parameter learning, based on the particle swarm optimization (PSO) algorithm, can adjust the shape of the membership function and the corresponding weighting of the FLNN. The distance-based mutation operator, which strongly encourages a global search giving the particles more chance of converging to the global optimum, is introduced. The simulation results have shown the proposed method can improve the searching ability and is very suitable for the nonlinear system control applications.
Reduced graphene oxide based bimetallic Ni/Fe nanohybrids for rapid dechlorination of trichloroethylene
(2016-08-20)
Sahu, Rama
;
Li, Dong-Lin
;
Doong, Ruey-An
;
環境工程研究所
;
Institute of Environmental Engineering
Robust Feature-Based Automated Multi-View Human Action Recognition System
(2018-01-01)
Chou, Kuang-Pen
;
Prasad, Mukesh
;
Wu, Di
;
Sharma, Nabin
;
Li, Dong-Lin
Automated human action recognition has the potential to play an important role in public security, for example, in relation to the multiview surveillance videos taken in public places, such as train stations or airports. This paper compares three practical, reliable, and generic systems for multiview video-based human action recognition, namely, the nearest neighbor classifier, Gaussian mixture model classifier, and the nearest mean classifier. To describe the different actions performed in different views, view-invariant features are proposed to address multiview action recognition. These features are obtained by extracting the holistic features from different temporal scales which are modeled as points of interest which represent the global spatial-temporal distribution. Experiments and cross-data testing are conducted on the KTH, WEIZMANN, and MuHAVi datasets. The system does not need to be retrained when scenarios are changed which means the trained database can be applied in a wide variety of environments, such as view angle or background changes. The experiment results show that the proposed approach outperforms the existing methods on the KTH and WEIZMANN datasets.
Self-Adjusting Feature Maps Network
(2011)
Lin, Chin-Teng
;
Li, Dong-Lin
;
Chang, Jyh-Yeong
;
電控工程研究所
;
Institute of Electrical and Control Engineering
In this paper, we propose a novel artificial neural network, called self-adjusting feature map (SAM), and its unsupervised learning algorithm with self-adjusting mechanism. After the training of SAM network, we will obtain a map composed of a set of representative connected neurons. The trained network structure of representative connected neurons not only displays the spatial relation of the input data distribution but also quantizes the data well. SAM can automatically isolate a set of connected neurons, in which the number of the set may indicate the number of clusters to be used. The idea of self-adjusting mechanism is based on combining of mathematical statistics and neurological advance and retreat of waste. For each representative neuron, there are three periods, growth. adaptation and decline, in its training process. The network of representative neurons will first create the necessary neurons according to the local density of the input data in the growth period. Then it will adjust neighborhood neuron pair's connected/disconnected topology constantly according to the statistics of input feature data in the adaptation period. Lastly the unnecessary neurons of the network will be merged or deleted in the decline period. In this study. we exploit SAM to handle some peculiar cases that cannot be well dealt with by classical unsupervised learning networks such as self-organizing feature map (SOM) network. Furthermore, we also take several real world cases to exhibit the remarkable characteristics of SAM.
Self-adjusting feature maps network and its applications
(2016-09-26)
Li, Dong-Lin
;
Prasad, Mukesh
;
Lin, Chin-Teng
;
Chang, Jyh-Yeong
;
資訊工程學系
This paper, proposes a novel artificial neural network, called self-adjusting feature map (SAM), and develop its unsupervised learning ability with self-adjusting mechanism. The trained network structure of representative connected neurons not only displays the spatial relation of the input data distribution but also quantizes the data well. The SAM can automatically isolate a set of connected neurons, in which, the used number of the sets may indicate the number of clusters. The idea of self-adjusting mechanism is based on combining of mathematical statistics and neurological advantages and retreat of waste. In the training process,, for each representative neuron has are three phases, growth, adaptation and decline. The network of representative neurons, first create the necessary neurons according to the local density of the input data in the growth phase. In the adaption phase, it adjusts neighborhood neuron pair\'s connected/disconnected topology constantly according to the statistics of input feature data. Finally, the unnecessary neurons of the network are merged or remove in the decline phase. In this paper, we exploit the SAM to handle some peculiar cases that cannot be handled easily by classical unsupervised learning networks such as self-organizing map (SOM) network. The remarkable characteristics of the SAM can be seen on various real world cases in the experimental results. (C) 2016 Elsevier B.V. All rights reserved.
Soft-Boosted Self-Constructing Neural Fuzzy Inference Network
(2017-03)
Prasad, Mukesh
;
Lin, Chin-Teng
;
Li, Dong-Lin
;
Hong, Chao-Tien
;
Ding, Wei-Ping
This correspondence paper proposes an improved version of the self-constructing neural fuzzy inference network (SONFIN), called soft-boosted SONFIN (SB-SONFIN). The design softly boosts the learning process of the SONFIN in order to decrease the error rate and enhance the learning speed. The SB-SONFIN boosts the learning power of the SONFIN by taking into account the numbers of fuzzy rules and initial weights which are two important parameters of the SONFIN, SB-SONFIN advances the learning process by: 1) initializing the weights with the width of the fuzzy sets rather than just with random values and 2) improving the parameter learning rates with the number of learned fuzzy rules. The effectiveness of the proposed soft boosting scheme is validated on several real world and benchmark datasets. The experimental results show that the SB-SONFIN possesses the capability to outperform other known methods on various datasets.
Unveiling the hydrodechlorination of trichloroethylene by reduced graphene oxide supported bimetallic Fe/Ni nanoparticles
(2018-02-15)
Sahu, Rama Shanker
;
Li, Dong-Lin
;
Doong, Ruey-an
;
環境工程研究所
;
Institute of Environmental Engineering
Reduced graphene oxide (rGO) is a promising support for electrochemical and environmental applications. However, the role of rGO in dechlorination of chlorinated hydrocarbon by zerovalent iron-based nanoparticles remains unclear. Herein, the rGO-supported bimetallic Fe/Ni nanocomposites were fabricated by chemical reduction method and the microstructures as well as the electrochemical properties of rGO/Fe/Ni, were investigated to elucidate the dechlorination behaviors of trichloroethylene (TCE) under various environmental conditions. Results show that the 10-60 nm Fe/Ni nanoparticles with average particle size of 32 nm are homogeneously dispersed onto the rGO surface. The rGO/Fe/Ni exhibits excellent dechlorination efficiency and rate of TCE is 2.4 times higher than that of free Fe/Ni nanoparticles. Cyclic voltammetric curves and electrochemical impedance spectra indicate that the superior dechlorination activity is attributed to the strong interaction between Fe/Ni and rGO, low internal resistance and rapid diffusion rate of electrons and ions. In addition, the capacitive behavior of rGO can store and transfer 2.7-3.4 electrons produced from Fe-0 to the adsorbed TCE more readily, and then converts TCE to non-toxic ethane via hydrodechlorination in the presence of Ni nanoparticles. The rGO/Fe/Ni can be recycled for at least 8 times to effective dechlorinate TCE. Moreover, the reaction rate of TCE dechlorination can be enhanced 1.26-1.49 times when 5-10 mg L-1 humic acid are added. Results obtained in this study have clearly unveiled the role of rGO in hydrodechlorination of TCE and can provide a new insight into the development of rGO-supported bimetallic Fe/Ni nanoparticles for the enhanced removal of chlorinated pollutants in water and wastewater treatment.