• Journal of Information Processing Systems
• /
• v.11 no.4
• /
• pp.643-654
• /
• 2015

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we propose using the combination of Affine Scale Invariant Feature Transform (SIFT) and Probabilistic Similarity for face recognition under a large viewpoint change. Affine SIFT is an extension of SIFT algorithm to detect affine invariant local descriptors. Affine SIFT generates a series of different viewpoints using affine transformation. In this way, it allows for a viewpoint difference between the gallery face and probe face. However, the human face is not planar as it contains significant 3D depth. Affine SIFT does not work well for significant change in pose. To complement this, we combined it with probabilistic similarity, which gets the log likelihood between the probe and gallery face based on sum of squared difference (SSD) distribution in an offline learning process. Our experiment results show that our framework achieves impressive better recognition accuracy than other algorithms compared on the FERET database.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.1
• /
• pp.108-117
• /
• 1996

In this paper, we propose a new type of recurrent neural network architecture in which each output unit is connected with itself and fully-connected with other output units and all hidden units. The proposed recurrent network differs from Jordan's and Elman's recurrent networks in view of functions and architectures because it was originally extended from the multilayer feedforward neural network for improving the discrimination and generalization power. We also prove the convergence property of learning algorithm of the proposed recurrent neural network and analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeral database of Concordia University of Canada. Experimental results confirmed that the proposed recurrent neural network improves the discrimination and generalization power in recognizing spatial patterns.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1480-1491
• /
• 2015

In new deregulated electricity market, short-term price forecasting is key information for all market players. A better forecast of market-clearing price (MCP) helps market participants to strategically set up their bidding strategies for energy markets in the short-term. This paper presents a new prediction strategy to improve the need for more accurate short-term price forecasting tool at spot market using an artificial neural networks (ANNs). To build the forecasting ANN model, a three-layered feedforward neural network trained by the improved Levenberg-marquardt (LM) algorithm is used to forecast the locational marginal prices (LMPs). To accurately predict LMPs, actual power generation and load are considered as the input sets, and then the difference is used to predict price differences in the spot market. The proposed ANN model generalizes the relationship between the LMP in each area and the unconstrained MCP during the same period of time. The LMP calculation is iterated so that the capacity between the areas is maximized and the mechanism itself helps to relieve grid congestion. The addition of flow between the areas gives the LMPs a new equilibrium point, which is balanced when taking the transfer capacity into account, LMP forecasting is then possible. The proposed forecasting strategy is tested on the spot market of the Nord Pool. The validity, the efficiency, and effectiveness of the proposed approach are shown by comparing with time-series models

• Journal of Information Technology Applications and Management
• /
• v.15 no.1
• /
• pp.261-270
• /
• 2008

Wireless Mesh Networks (WMNs) have emerged as one of the new hot topics in wireless communications. WMNs have been suggested for use in situations in which some or all of the users are mobile or are located in inaccessible environments. Unconstrained transmission in a WMN may lead to the time overlap of two or more packet receptions, called collisions or interferences, resulting in damaged useless packets at the destination. There are two types of collisions; primary collision, due to the transmission of the stations which can hear each other, and hidden terminal collision, when stations outside the hearing range of each other transmit to the same receiving stations. For a WMN, direct collisions can be minimized by short propagation and carrier sense times. Thus, in this paper we only consider hidden terminal collision while neglecting direct collisions. To reduce or eliminate hidden terminal collision, code division multiple access (CDMA) protocols have been introduced. The collision-free property is guaranteed by the use of spread spectrum communication techniques and the proper assignment of orthogonal codes. Such codes share the fixed channel capacity allocated to the network in the design stage. Thus, it is very important to minimize the number of codes while achieving a proper transmission quality level in CDMA WMNs. In this paper, an efficient heuristic code assignment algorithm for eliminating hidden terminal collision in CDMA WMNs with general topology.

• ETRI Journal
• /
• v.39 no.5
• /
• pp.621-631
• /
• 2017

Abnormal samples are usually difficult to obtain in production systems, resulting in imbalanced training sample sets. Namely, the number of positive samples is far less than the number of negative samples. Traditional Support Vector Machine (SVM)-based anomaly detection algorithms perform poorly for highly imbalanced datasets: the learned classification hyperplane skews toward the positive samples, resulting in a high false-negative rate. This article proposes a new imbalanced SVM (termed ImSVM)-based anomaly detection algorithm, which assigns a different weight for each positive support vector in the decision function. ImSVM adjusts the learned classification hyperplane to make the decision function achieve a maximum GMean measure value on the dataset. The above problem is converted into an unconstrained optimization problem to search the optimal weight vector. Experiments are carried out on both Cloud datasets and Knowledge Discovery and Data Mining datasets to evaluate ImSVM. Highly imbalanced training sample sets are constructed. The experimental results show that ImSVM outperforms over-sampling techniques and several existing imbalanced SVM-based techniques.

• Nuclear Engineering and Technology
• /
• v.51 no.3
• /
• pp.807-817
• /
• 2019

Airborne Gamma Ray Spectrometry (AGRS) with its important applications such as gathering radiation information of ground surface, geochemistry measuring of the abundance of Potassium, Thorium and Uranium in outer earth layer, environmental and nuclear site surveillance has a key role in the field of nuclear science and human life. The Broyden-Fletcher-Goldfarb-Shanno (BFGS), with its advanced numerical unconstrained nonlinear optimization in collaboration with Artificial Neural Networks (ANNs) provides a noteworthy opportunity for modern AGRS. In this study a new AGRS system empowered by ANN-BFGS has been proposed and evaluated on available empirical AGRS data. To that effect different architectures of adaptive ANN-BFGS were implemented for a sort of published experimental AGRS outputs. The selected approach among of various training methods, with its low iteration cost and nondiagonal scaling allocation is a new powerful algorithm for AGRS data due to its inherent stochastic properties. Experiments were performed by different architectures and trainings, the selected scheme achieved the smallest number of epochs, the minimum Mean Square Error (MSE) and the maximum performance in compare with different types of optimization strategies and algorithms. The proposed method is capable to be implemented on a cost effective and minimum electronic equipment to present its real-time process, which will let it to be used on board a light Unmanned Aerial Vehicle (UAV). The advanced adaptation properties and models of neural network, the training of stochastic process and its implementation on DSP outstands an affordable, reliable and low cost AGRS design. The main outcome of the study shows this method increases the quality of curvature information of AGRS data while cost of the algorithm is reduced in each iteration so the proposed ANN-BFGS is a trustworthy appropriate model for Gamma-ray data reconstruction and analysis based on advanced novel artificial intelligence systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.4
• /
• pp.1-12
• /
• 2016

The Harmony Search Algorithm (HSA) is one of the recently developed metaheuristic optimization algorithms. Since the development of HSA, it has been applied by many researchers from various fields. The increasing complexity of problems has created enormous challenges for the current technique, and improved techniques of optimization algorithms are required. In this study, to improve the HSA in terms of a structural setting, a new HSA that has structural characteristics, called the Multi-layered Harmony Search Algorithm (MLHSA) was proposed. In this new method, the structural characteristics were added to HSA to improve the exploration and exploitation capability. In addition, the MLHSA was applied to optimization problems, including unconstrained benchmark functions and water distribution system pipe diameter design problems to verify the efficiency and applicability of the proposed algorithm. The results revealed the strength of MLHSA and its competitiveness.

• Journal of Mechanical Science and Technology
• /
• v.16 no.8
• /
• pp.1072-1078
• /
• 2002

The constrained motion requires the determination of constraint force acting on unconstrained systems for satisfying given constraints. Most of the methods to decide the force depend on numerical approaches such that the Lagrange multiplier method, and the other methods need vector analysis or complicated intermediate process. In 1992, Udwadia and Kalaba presented the generalized inverse method to describe the constrained motion as well as to calculate the constraint force. The generalized inverse method has the advantages which do not require any linearization process for the control of nonlinear systems and can explicitly describe the motion of holonomically and/or nongolonomically constrained systems. In this paper, an explicit equation to describe the constrained motion is derived by minimizing the performance index, which is a function of constraint force vector, with respect to the constraint force. At this time, it is shown that the positive-definite weighting matrix in the performance index must be the inverse of mass matrix on the basis of the Gauss's principle and the derived differential equation coincides with the generalized inverse method. The effectiveness of this method is illustrated by means of two numerical applications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.2
• /
• pp.742-762
• /
• 2015

In this study, we propose a distance metric learning approach called discriminant metric learning (DML) for face verification, which addresses a binary-class problem for classifying whether or not two input images are of the same subject. The critical issue for solving this problem is determining the method to be used for measuring the distance between two images. Among various methods, the large margin nearest neighbor (LMNN) method is a state-of-the-art algorithm. However, to compensate the LMNN's entangled data distribution due to high levels of appearance variations in unconstrained environments, DML's goal is to penalize violations of the negative pair distance relationship, i.e., the images with different labels, while being integrated with LMNN to model the distance relation between positive pairs, i.e., the images with the same label. The likelihoods of the input images, estimated using DML and LMNN metrics, are then weighted and combined for further analysis. Additionally, rather than using the k-nearest neighbor (k-NN) classification mechanism, we propose a verification mechanism that measures the correlation of the class label distribution of neighbors to reduce the false negative rate of positive pairs. From the experimental results, we see that DML can modify the relation of negative pairs in the original LMNN space and compensate for LMNN's performance on faces with large variances, such as pose and expression.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2534-2553
• /
• 2018

Source routing is the routing scheme that arranges the whole path from source to target at the origin node that may suit the requirements from the upper layer applications' perspective. The centralized control in SDN (Software-Defined Networking) networks enables the awareness of the global topology at the controller. Therefore, augmented source routing schemes can be designed to achieve various purposes. This paper proposes a source routing scheme that conducts the top-K QoS-aware paths discovery in SDN. First, the novel non-invasive QoS over LLDP scheme is designed to collect QoS information based on LLDP in a piggyback fashion. Then, variations of the KSP (K Shortest Paths) algorithm are derived to find the unconstrained/constrained top-K ranked paths with regard to individual/overall path costs, reflecting the Quality of Service. The experiment results show that the proposed scheme can efficiently collect the QoS information and find the top-K paths. Also, the performance of our scheme is applicable in QoS-sensitive application scenarios compared with previous works.