• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Journal of Information Technology Applications and Management
• /
• v.17 no.1
• /
• pp.141-155
• /
• 2010

We develop an intelligent information system in a multilayer electronic supply chain network. Using the internet for supply chain management (SCM) is a key interest for contemporary managers and researchers. It has been realized that the internet can facilitate SCM by making real time information available and enabling collaboration between trading partners. Here, we propose a multi-agent system to analyze the performance of the elements of a supply network based on the attributes of the information flow. Each layer consists of elements which are differentiated by their performance throughout the supply network. The proposed agents measure and record the performance flow of elements considering their web interactions for a dynamic route selection. A dynamic programming approach is applied to determine the optimal route for a customer in the end-user layer.

• International Journal of Precision Engineering and Manufacturing
• /
• v.7 no.3
• /
• pp.66-71
• /
• 2006

Some wheelchair users with neuromuscular disorders experience involuntary extensor thrusts, which may cause injuries via impact with the wheelchair, cause the user to slide out of the wheelchair seat, and damage the wheelchair. Knowledge of the human-generated forces during an extensor thrust is of great importance in devising safer, more comfortable wheelchairs. This paper presents an efficient method for identifying human-generated forces during an extensor thrust. We used an inverse dynamic approach with a three-link human body model and a system for measuring human body motion. We developed an experimental system that determines the angular motion of each human body segment and the force at the footrest, which was used to overcome the mathematical indeterminacy of the problem. The proposed method was validated experimentally, illustrating the force-identification process during an extensor thrust.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.2
• /
• pp.156-164
• /
• 2004

The unmanned tandem helicopter, which is a MIMO nonlinear system with complexity and inherent instability, exists in unstable zero dynamics. In this paper, approximate linearization is presented to design the controller for output tracking of an unmanned tandem helicopter based on the dynamic augment method, and the simulation results are encouraging.

• Journal of KSNVE
• /
• v.9 no.6
• /
• pp.1227-1233
• /
• 1999

Modern technology depends on the reliability of extremely high technology equipments. In the production of semiconductor wafer, optical and electron microscopes, ion-beam, laser device must maintain their alignments within a nanometer. This equipment requires a vibration free environment to provide its proper function. Especially, lithography and inspection devices, which have sub-nanometer class high accuracy and resolution, have come to necessity for producing more improved giga and tera class semiconductor wafers. This high technology equipments require very strict environmental vibration standard, vibration criteria, in proportion to the accuracy of the manufacturing, inspecting devices. This paper deals with the structural dynamic design in high class semiconductor factory in order to be satisfied more strict vibration criteria for high sensitive equipment.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2005.07a
• /
• pp.539-542
• /
• 2005

We report how to establish the dynamic index for production control in a pilot fabrication over versatile and diverse production environments. We used dynamic index provided by a simulation model to monitor production performance. When production control is abnormal, the information system prompts administrators to classify these abnormal situations. In addition, the trend over the operation index is continuously reviewed in short-term and long-term. This simulation model is handy at setting goal for a versatile and diverse pilot production fab.

• Structural Engineering and Mechanics
• /
• v.13 no.2
• /
• pp.211-230
• /
• 2002

The objective of this study is to investigate the dynamic behavior of elastic beams subjected to moving loads. Although analytical methods are available, they have limitations with respect to complicated structures. The use of computer technology in recent years is an effective way to solve the problem; thus using the latest technology this study establishes a finite-element solution procedure to investigate dynamic behaviors of a typical elastic beam having a set of constant geometric properties and various span lengths. Both the dead load of the beam and traffic load are applied in which the traffic load is considered a concentrated moving force with various traveling passage speeds on the beam. Dynamic behaviors including deflection, shear, and bending moment due to moving loads are obtained by both analytical and finite element methods; for simple structures, they have an excellent agreement. The numerical results show that based on analytical methods the fundamental mode is good enough to estimate the dynamic deflection along the beam, but is not sufficient to simulate the total response of the shear force or the bending moment. The linear dynamic behavior of the elastic beams subjected to multiple exciting loads can easily be found by linear superposition, and the geometric nonlinear results caused by large deformation and axial force of the beam are always underestimated with only a few exceptions which are indicated. In order to make the results useful, they have been nondimensionalized and presented in graphical form.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.2060-2073
• /
• 2022

Cloud Computing permits users to access vast amounts of services of computing power in a virtualized environment. Providing secure services is essential. There are several problems to real-world optimization that are dynamic which means they tend to change over time. For these types of issues, the goal is not always to identify one optimum but to keep continuously adapting to the solution according to the change in the environment. The problem of scheduling in Cloud where new tasks keep coming over time is unique in terms of dynamic optimization problems. Until now, there has been a large majority of research made on the application of various Evolutionary Algorithms (EAs) to address the issues of dynamic optimization, with the focus on the maintenance of population diversity to ensure the flexibility for adapting to the changes in the environment. Generally, trust refers to the confidence or assurance in a set of entities that assure the security of data. In this work, a dynamic optimization technique is proposed to find an optimal trust weights in cloud during scheduling.

• International Journal of Highway Engineering
• /
• v.16 no.3
• /
• pp.43-50
• /
• 2014

PURPOSES : The dynamic modulus can be determined by applying the various theories from the Impact Resonance Testing(IRT) Method. The objective of this paper is to determine the best theory to produce the dynamic modulus that has the lowest error as the dynamic modulus data obtained from these theories(Complex Wave equation Resonance Method related to either the transmissibility loss or not, Dynamic Stiffness Resonance Method) compared to the results for dynamic modulus determined by using the Universal Testing Machine. The ultimate object is to develop the predictive model for the dynamic modulus of a Linear Visco-Elastic specimen by using the Complex Wave equation Resonance Method(CWRM) came up for an existing study(S. O. Oyadiji; 1985) and the Optimization. METHODS : At the destructive test which uses the Universal Testing Machine, the dynamic modulus results along with the frequency can be used for determining the sigmoidal master curve function related to the reduced frequency by applying Time-Temperature Superposition Principle. RESULTS : The constant to be solved from Eq. (11) is a value of 14.13. The reduced dynamic modulus obtained from the IRT considering the loss factor related to the impact transmissibility has RMSE of 367.7MPa, MPE of 3.7%. When the predictive dynamic modulus model was applied to determine the master curve, the predictive model has RMSE of 583.5MPa, MPE of 3.5% compared to the destructive test results for the dynamic modulus. CONCLUSIONS : Because we considered that the results obtained from the destructive test had the most highest source credibility in this study, the dynamic modulus data obtained respectively from DSRM, CWRM were compared to the results obtained from the destructive test by using th IRT. At the result, the reduced dynamic modulus derived from DSRM has the most lowest error.

• Journal of the Korean Wood Science and Technology
• /
• v.34 no.2
• /
• pp.46-57
• /
• 2006

To estimate nondestructively strength performances of laminated woods, 3-ply parallel- and cross-laminated wood specimens exposed under atmosphere conditions after bending creep test were prepared for this study. The effects of density of species, arrangement of laminae and lamination types on dynamic MOE obtained by flexural vibration were investigated, and regression analyses were conducted in order to estimate static bending strength and bending creep performances. Dynamic MOE of parallel-laminated woods showed 1.0~1.2 times higher values than static bending MOE, and those of cross-laminated woods showed 1.0~1.4 times higher values than static bending MOE. The degree of anisotropy of dynamic MOE perpendicular to the grain of face laminae versus that parallel to the grain of face laminae was markedly decreased by cross-laminating. There were strong correlations between dynamic MOE by flexural vibration and static bending MOE (correlation coefficient r = 0.919~0.972) or bending MOR (correlation coefficient r = 0.811~0.947) of 3-ply laminated woods, and the correlation coefficient were higher in parallel-laminated woods than in cross-laminated woods. It indicated that static bending strength performances were able to be estimated from dynamic MOE by flexural vibration. Also, close correlations between the reciprocal of dynamic MOE by flexural vibration and initial compliance at 0.008 h of 3-ply laminated woods were found (correlation coefficient r = 0.873~0.991). However, the correlation coefficient between the reciprocal of dynamic MOE and creep compliance at 168 h of 3-ply laminated woods was considerably lower than those between dynamic MOE and initial compliance, and it was hard to estimate creep compliance with a high accuracy from dynamic MOE due to the variation of creep deformation.