• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• 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.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 추계학술대회논문집A
• /
• pp.647-652
• /
• 2000

This paper proposes a collision warning/avoidance algorithm using a trajectory prediction method. This algorithm is based on 2-dimensional kinematics and the Kalman filter has been used to obtain the information of the object vehicle. This algorithm has been investigated via computer simulation and showed a good trajectory prediction performance. The proposed collision warning/avoidance algorithm would enhanced driver acceptance for a collision warning/avoidance system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2012-2027
• /
• 2019

Nutritional disorders are one of the most common diseases of crops and they often result in significant loss of agricultural output. Moreover, the imbalance of nutrition element not only affects plant phenotype but also threaten to the health of consumers when the concentrations above the certain threshold. A number of disease identification systems have been proposed in recent years. Either the time consuming or accuracy is difficult to meet current production management requirements. Moreover, most of the systems are hard to be extended, only detect a few kinds of common diseases with great difference. In view of the limitation of current approaches, this paper studies the effects of different trace elements on crops and establishes identification system. Specifically, we analysis and acquire eleven types of tomato nutritional disorders images. After that, we explore training and prediction effects and significances of super resolution of identification model. Then, we use pre-trained enhanced deep super-resolution network (EDSR) model to pre-processing dataset. Finally, we design and implement of diagnosis system based on deep learning. And the final results show that the average accuracy is 81.11% and the predicted time less than 0.01 second. Compared to existing methods, our solution achieves a high accuracy with much less consuming time. At the same time, the diagnosis system has good performance in expansibility and portability.

• Steel and Composite Structures
• /
• 제45권6호
• /
• pp.895-905
• /
• 2022

Composite flooring systems consisting of cold-formed steel joists and reinforced concrete slabs offer an efficient, lightweight solution. However, utilisation of composite action to achieve enhanced strength and economical design has been limited. In this study, finite element modelling was utilised to create a three-dimensional model which was then validated against experimental results for a composite flooring system consisting of cold-formed steel joists, reinforced concrete slab and steel bolt shear connectors. This validated numerical model was then utilised to perform parametric studies on the performance of the structural system. The results from the parametric study demonstrate that increased thickness of the concrete slab and increased thickness of the cold formed steel beam resulted in higher moment capacity and stiffness of the composite flooring system. In addition, reducing the spacing of bolts and spacing of the cold formed steel beams both resulted in enhanced load capacity of the composite system. Increasing the concrete grade was also found to increase the moment capacity of the composite flooring system. Overall, the results show that an efficient, lightweight composite flooring system can be achieved and optimised by selecting suitable concrete slab thickness, cold formed beam thickness, bolt spacing, cold formed beam spacing and concrete grade.

• 한국기계가공학회지
• /
• 제21권4호
• /
• pp.53-59
• /
• 2022

In this study, an enhanced first-order shear deformation theory is proposed to efficiently and accurately predict the thermo-mechanical-viscoelastic coupled behavior of laminated composite structures. To this end, transverse shearstress and displacement fields are independently assumed, and the strain-energy relationship between these fields issystematically established using the mixed variational theorem (MVT). In MVT, the transverse shear stress fields are obtained from the third-order zigzag model, whereas the displacement fields of the conventional first-order model are considered to amplify the benefits of numerical efficiency. Additionally, a transverse displacement field with a smooth parabolic distribution is introduced to accurately predict the thermal behavior of composite structures. Furthermore, the concept of Laplace transformation is newly employed to simplify the viscoelastic problem, similar to the linear-elastic problem. To demonstrate the performance of the proposed theory, the numerical results obtained herein were compared with those available in the literature.

• 분석과학
• /
• 제37권1호
• /
• pp.39-46
• /
• 2024

Alizarin dye, a persistent and hazardous contaminant in aquatic environments, presents a pressing environmental concern. In the quest for efficient removal methods, adsorption has emerged as a versatile and sustainable approach. This study focuses on the development and application of Zinc Oxide/Nickel Oxide (ZnO/NiO) nano-composites as adsorbents for alizarin dye removal. These semiconducting metal oxide nano-composites exhibit synergistic properties, offering enhanced adsorption capabilities. Key parameters affecting alizarin removal, such as contact time, adsorbent dosage, pH, and temperature, were systematically investigated. Notably, the ZnO/NiO nano-composite demonstrated superior performance, with a maximum alizarin removal percentage of 76.9 % at pH 6. The adsorption process followed a monolayer pattern, as suggested by the Langmuir model. The pseudo-second-order kinetics model provided a good fit to the experimental data. Thermodynamic analysis indicated that the process is endothermic and thermodynamically favorable. These findings underscore the potential of ZnO/NiO nano-composites as effective and sustainable adsorbents for alizarin dye removal, with promising applications in wastewater treatment and environmental remediation.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권8호
• /
• pp.353-362
• /
• 2006

This paper illustrates the practical design procedure on a position control of an electrical fin actuator for the guided missile using Time Delay Control(TDC) and Enhanced Time Delay Observer(ETDO). Since TDC is robust to the model uncertainties such as the parameter variation and the external disturbance, it has been frequently used in nonlinear control systems. For a position control of an electrical fin actuator in the missile system, TDC requires the velocity sensor as well as the position sensor. To resolve the problems of the cost, the space and the malfunction due to the velocity sensor, ETDO is used as the velocity observer. ETDO is enhanced version of TDO that has the problems of the reconstruction errors and the restriction on selecting its gains. To maximize the control performance, the parameters of ETDO are optimized by using the genetic algorithm. The effectiveness of this approach is proved through a series of simulation studies and experiments, and the designed controller is compared with the typical TDC and TDC using the reduced oder observer.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권10호
• /
• pp.959-968
• /
• 2020

Research underlined that Small and Medium Enterprises' performance is enhanced by different types of innovation capabilities. This research tends to present a comprehensive model to explain the relationship between innovation capabilities and SMEs' financial and operational performance. Specifically, this study tends to achieve three objectives: explores the set of product, process, organizational and marketing innovation capabilities possessed by owners/managers of SMEs and their impact on Chinese manufacturing SMEs' operational and financial performance dimensions, identify the determinants of innovation capabilities, and determine the contextual factors that moderate innovation capabilities and SMEs' performance. This research employed a qualitative research method using in-depth interviews with eight owners/managers of Chinese manufacturing SMEs. Research findings revealed that product and marketing innovation capabilities have a significant impact on SMEs' financial performance while process and organizational innovation capabilities positively influence SMEs' operational performance. The major determinants of innovation capabilities involved availability of sufficient organizational resources, entrepreneurial orientation, knowledge development and external networks. The contextual moderating factors on the relationship between innovation capabilities and SMEs' performance involved internal factors which are: SME size, SMEs' owner/manager work experience, entrepreneurial mindset; and external factors: market dynamism and cooperation strategies. This paper ends by drawing some concluding remarks and proposing future research avenues.

• 한국산림과학회지
• /
• 제111권1호
• /
• pp.136-149
• /
• 2022

강원지방소나무의 수간곡선 추정에 비선형 혼합효과 모형(nonlinear mixed-effects models: NLME)을 적용하고 몇 가지 성능 척도를 이용하여 비선형 고정효과 모형과 비교하였다. 혼합효과 모형이 고정효과 모형을 개선한 정도를 전체 성능의 측면에서 설명하면, 수간직경에 대해서는 BIAS 26.4%, MAB 42.9%, RMSE 43.1%, FI 0.9%만큼이었고, 수간단면적에 대해서는 BIAS 67.7%, MAB 44.7%, RMSE 45.8%, FI 1.0%만큼이었다. 수간을 12개의 상대수고 구간으로 세분화하여 분석한 결과에서도 수간곡선의 성능은 혼합효과 모형에 의해 크게 개선된 것으로 나타났다. 혼합효과 모형은 모든 상대수고 구간에서 수간직경 및 수간단면적에 대한 성능이 고정효과 모형보다 더 나은 MAB, RMSE, FI를 나타내었고, BIAS의 경우 일부 구간(수간직경: 0.05, 0.2, 0.3, 0.8, 수간단면적: 0.05, 0.3, 0.5, 0.6, 1.0)에서만 고정효과 모형보다 뒤떨어지는 것으로 확인되었다. 특히 지상에 근접한 수간 최하부(수고 0.2 m 지점)에서 수간직경 및 수간단면적 추정 성능이 혼합효과 모형에 의해 크게 향상되었다. 수간직경의 경우 BIAS 84.2%, MAB 69.8%, RMSE 68.7%, FI 3.1%, 수간단면적의 경우 BIAS 98.5%, MAB 70.1%, RMSE 68.7%, FI 3.1%만큼 향상된 것으로 분석되었다. 지상으로부터 0.2 m 높이 지점의 수간단면적이 수간단면적 전체에서 차지하는 비중은 22.7%에 달하였다. 이렇게 수간재적에서 가장 큰 비중을 차지하는 수간 최하부에서의 추정 성능이 크게 향상되었다는 것은 전체 수간재적의 추정 성능 역시 큰 폭으로 향상될 수 있음을 시사한다. 비록 모형 적합 과정이 고정효과 모형보다 까다롭다는 단점이 있지만, 추정 성능의 개선 효과를 고려하면 NLME를 수간곡선 추정의 표준적인 방법으로 사용하는 것을 검토할 필요가 있다.

• 한국해양공학회지
• /
• 제34권6호
• /
• pp.394-405
• /
• 2020

To assess the station-keeping performance of floating structures in the Arctic region, the ice load should be considered along with other environmental loads induced by waves, wind, and currents. However, present methods for performance evaluation in the time domain are not effective in terms of time and cost. An ice load generation module is proposed based on the experimental data measured at the KRISO ice model basin. The developed module was applied to a time domain simulation. Using the results of a captive model test conducted in multiple directions, the statistical characteristics of ice loads were analyzed and processed so that an ice load corresponding to an arbitrary angle of the structure could be generated. The developed module is connected to commercial dynamic analysis software (OrcaFlex) as an external force input. Station-keeping simulation in the time domain was conducted for the same floating structure used in the model test. The mooring system was modeled and included to reflect the designed operation scenario. Simulation results show the effectiveness of the proposed ice generation module and its application to station-keeping performance evaluation. Considering the generated ice load, the designed structure can maintain a heading angle relative to ice up to 4°. Station-keeping performance is enhanced as the heading angle conforms to the drift direction. It is expected that the developed module will be used as a platform to verify station-keeping algorithms for Arctic floating structures with a dynamic positioning system.