• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.6
• /
• pp.345-359
• /
• 2011

In high performance embedded systems, the use of multiple on-chip memories is an essential architectural feature for exploiting inherent parallelism in multimedia applications. This feature allows multiple data accesses to be executed in parallel. However, it remains difficult to effectively exploit of multiple on-chip memories. The successful use of this architecture strongly depends on how to efficiently detect and exploit memory parallelism in target applications. In this paper, we propose a technique based on a linear array access descriptor [1], which is generated from profiled data, to detect and exploit memory parallelism. The proposed technique tackles an array reorganization problem to maximize memory parallelism in multimedia applications. We present preliminary experiments applying the proposed technique onto a representative coarse grained reconfigurable array processor (CGRA) with multimedia kernel codes. Our experimental results demonstrate that our technique optimizes data placement by putting independent data on separate storage. The results exhibit 9.8% higher performance on average compared to the existing method.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.40-48
• /
• 2023

Speech Emotions recognition has become the active research theme in speech processing and in applications based on human-machine interaction. In this work, our system is a two-stage approach, namely feature extraction and classification engine. Firstly, two sets of feature are investigated which are: the first one is extracting only 13 Mel-frequency Cepstral Coefficient (MFCC) from emotional speech samples and the second one is applying features fusions between the three features: Zero Crossing Rate (ZCR), Teager Energy Operator (TEO), and Harmonic to Noise Rate (HNR) and MFCC features. Secondly, we use two types of classification techniques which are: the Support Vector Machines (SVM) and the k-Nearest Neighbor (k-NN) to show the performance between them. Besides that, we investigate the importance of the recent advances in machine learning including the deep kernel learning. A large set of experiments are conducted on Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of our experiments showed given good accuracy compared with the previous studies.

• Information Systems Review
• /
• v.16 no.3
• /
• pp.161-177
• /
• 2014

Corporate credit rating assessment consists of complicated processes in which various factors describing a company are taken into consideration. Such assessment is known to be very expensive since domain experts should be employed to assess the ratings. As a result, the data-driven corporate credit rating prediction using statistical and artificial intelligence (AI) techniques has received considerable attention from researchers and practitioners. In particular, statistical methods such as multiple discriminant analysis (MDA) and multinomial logistic regression analysis (MLOGIT), and AI methods including case-based reasoning (CBR), artificial neural network (ANN), and multiclass support vector machine (MSVM) have been applied to corporate credit rating.2) Among them, MSVM has recently become popular because of its robustness and high prediction accuracy. In this study, we propose a novel optimized MSVM model, and appy it to corporate credit rating prediction in order to enhance the accuracy. Our model, named 'GAMSVM (Genetic Algorithm-optimized Multiclass Support Vector Machine),' is designed to simultaneously optimize the kernel parameters and the feature subset selection. Prior studies like Lorena and de Carvalho (2008), and Chatterjee (2013) show that proper kernel parameters may improve the performance of MSVMs. Also, the results from the studies such as Shieh and Yang (2008) and Chatterjee (2013) imply that appropriate feature selection may lead to higher prediction accuracy. Based on these prior studies, we propose to apply GAMSVM to corporate credit rating prediction. As a tool for optimizing the kernel parameters and the feature subset selection, we suggest genetic algorithm (GA). GA is known as an efficient and effective search method that attempts to simulate the biological evolution phenomenon. By applying genetic operations such as selection, crossover, and mutation, it is designed to gradually improve the search results. Especially, mutation operator prevents GA from falling into the local optima, thus we can find the globally optimal or near-optimal solution using it. GA has popularly been applied to search optimal parameters or feature subset selections of AI techniques including MSVM. With these reasons, we also adopt GA as an optimization tool. To empirically validate the usefulness of GAMSVM, we applied it to a real-world case of credit rating in Korea. Our application is in bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. The experimental dataset was collected from a large credit rating company in South Korea. It contained 39 financial ratios of 1,295 companies in the manufacturing industry, and their credit ratings. Using various statistical methods including the one-way ANOVA and the stepwise MDA, we selected 14 financial ratios as the candidate independent variables. The dependent variable, i.e. credit rating, was labeled as four classes: 1(A1); 2(A2); 3(A3); 4(B and C). 80 percent of total data for each class was used for training, and remaining 20 percent was used for validation. And, to overcome small sample size, we applied five-fold cross validation to our dataset. In order to examine the competitiveness of the proposed model, we also experimented several comparative models including MDA, MLOGIT, CBR, ANN and MSVM. In case of MSVM, we adopted One-Against-One (OAO) and DAGSVM (Directed Acyclic Graph SVM) approaches because they are known to be the most accurate approaches among various MSVM approaches. GAMSVM was implemented using LIBSVM-an open-source software, and Evolver 5.5-a commercial software enables GA. Other comparative models were experimented using various statistical and AI packages such as SPSS for Windows, Neuroshell, and Microsoft Excel VBA (Visual Basic for Applications). Experimental results showed that the proposed model-GAMSVM-outperformed all the competitive models. In addition, the model was found to use less independent variables, but to show higher accuracy. In our experiments, five variables such as X7 (total debt), X9 (sales per employee), X13 (years after founded), X15 (accumulated earning to total asset), and X39 (the index related to the cash flows from operating activity) were found to be the most important factors in predicting the corporate credit ratings. However, the values of the finally selected kernel parameters were found to be almost same among the data subsets. To examine whether the predictive performance of GAMSVM was significantly greater than those of other models, we used the McNemar test. As a result, we found that GAMSVM was better than MDA, MLOGIT, CBR, and ANN at the 1% significance level, and better than OAO and DAGSVM at the 5% significance level.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.2
• /
• pp.119-127
• /
• 2004

Butterfly valves are popularly used in service in the industrial and water works pipeline systems with large diameter because of its lightweight, simple structure and the rapidity of its manipulation. Sometimes cavitation can occur. resulting in noise, vibration and rapid deterioration of the valve trim, and do not allow further operation. Thus, the monitoring of cavitation is of economic interest and is very importance in industry. This paper proposes a condition monitoring scheme using statistical feature evaluation and support vector machine (SVM) to detect the cavitation conditions of butterfly valve which used as a flow control valve at the pumping stations. The stationary features of vibration signals are extracted from statistical moments. The SVMs are trained, and then classify normal and cavitation conditions of control valves. The SVMs with the reorganized feature vectors can distinguish the class of the untrained and untested data. The classification validity of this method is examined by various signals that are acquired from butterfly valves in the pumping stations and compared the classification success rate with those of self-organizing feature map neural network.

• Advances in robotics research
• /
• v.2 no.1
• /
• pp.33-44
• /
• 2018

This paper presents a novel feature detection algorithm called depth-hybrid speeded-up robust features (DH-SURF) augmented by depth information in the speeded-up robust features (SURF) algorithm. In the keypoint detection part of classical SURF, the standard deviation of the Gaussian kernel is varied for its scale-invariance property, resulting in increased computational complexity. We propose a keypoint detection method with less variation of the standard deviation by using depth data from a red-green-blue depth (RGB-D) sensor. Our approach maintains a scale-invariance property while reducing computation time. An RGB-D simultaneous localization and mapping (SLAM) system uses a feature extraction method and depth data concurrently; thus, the system is well-suited for showing the performance of the DH-SURF method. DH-SURF was implemented on a central processing unit (CPU) and a graphics processing unit (GPU), respectively, and was validated through the real-time RGB-D SLAM.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.4
• /
• pp.19-26
• /
• 2013

Pseudo sample neural network (PSNN) is a variant of traditional neural network using pseudo samples to mitigate the local-optima-convergence problem when the size of training samples is small. PSNN can take advantage of the smoothed solution space through the use of pseudo samples. PSNN has a focus on the quantity problem in training, whereas, methods stressing the quality of training samples is presented in this paper to improve further the performance of PSNN. It is evident that typical samples and highly correlated features help in training. In this paper, therefore, kernel density estimation is used to select typical samples and correlation factor is introduced to select features, which can improve the performance of PSNN. Debris flow data set is used to demonstrate the usefulness of the proposed methods.

• Journal of Internet Computing and Services
• /
• v.6 no.3
• /
• pp.159-170
• /
• 2005

OC-SVM(One Class Support Vector Machine) avoids solving a full density estimation problem, and instead focuses on a simpler task, estimating quantiles of a data distribution, i.e. its support. OC-SVM seeks to estimate regions where most of data resides and represents the regions as a function of the support vectors, Although OC-SVM is powerful method for data description, it is difficult to incorporate human subjective importance into its estimation process, In order to integrate the importance of each point into the OC-SVM process, we propose a fuzzy version of OC-SVM. In FOC-SVM (Fuzzy One-Class Support Vector Machine), we do not equally treat data points and instead weight data points according to the importance measure of the corresponding objects. That is, we scale the kernel feature vector according to the importance measure of the object so that a kernel feature vector of a less important object should contribute less to the detection process of OC-SVM. We demonstrate the performance of our algorithm on several synthesized data sets, Experimental results showed the promising results.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.266-274
• /
• 2003

This paper considers an incremental support vector learning for the abnormality detection problems. One of the most well-known support vector learning methods for abnormality detection is the so-called SVDD(support vector data description), which seeks the strategy of utilizing balls defined on the kernel feature space in order to distinguish a set of normal data from all other possible abnormal objects. The major concern of this paper is to modify the SVDD into the direction of utilizing the relation between the optimal solution and incrementally given training data. After a thorough review about the original SVDD method, this paper establishes an incremental method for finding the optimal solution based on certain observations on the Lagrange dual problems. The applicability of the presented incremental method is illustrated via a design example.

• Journal of Energy Engineering
• /
• v.23 no.4
• /
• pp.263-271
• /
• 2014

Corrective thermal performance analysis is required for thermal power plants to determine performance status of turbine cycle. We developed classification method for main feed water flow to make precise correction for performance analysis based on ASME (American Society of Mechanical Engineers) PTC (Performance Test Code). The classification is based on feature identification of status of main water flow. Also we developed predictive algorithms for corrected main feed-water through Support Vector Machine (SVM) Model for each classified feature area. The results was compared to estimations using Neural Network(NN) and Kernel Regression(KR). The feature classification and predictive model of main feed-water flow provides more practical methods for corrective thermal performance analysis of turbine cycle.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.2
• /
• pp.91-100
• /
• 2023

The existing indoor localization method using Wi-Fi fingerprinting has a high collection cost and relatively low accuracy, thus requiring integrated correction of convergence with other technologies. This paper proposes a new method that significantly reduces collection costs compared to existing methods using Wi-Fi fingerprinting. Furthermore, it does not require labeling of data at collection and can estimate pedestrian travel paths even in large indoor spaces. The proposed pedestrian movement path estimation process is as follows. Data collection is accomplished by setting up a feature area near an indoor space intersection, moving through the set feature areas, and then collecting data without labels. The collected data are processed using Kernel Linear Discriminant Analysis (KLDA) and the valley point of the Euclidean distance value between two data is obtained within the feature space of the data. We build learning data by labeling data corresponding to valley points and some nearby data by feature area numbers, and labeling data between valley points and other valley points as path data between each corresponding feature area. Finally, for testing, data are collected randomly through indoor space, KLDA is applied as previous data to build test data, the K-Nearest Neighbor (K-NN) algorithm is applied, and the path of movement of test data is estimated by applying a correction algorithm to estimate only routes that can be reached from the most recently estimated location. The estimation results verified the accuracy by comparing the true paths in indoor space with those estimated by the proposed method and achieved approximately 90.8% and 81.4% accuracy in two experimental spaces, respectively.