• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.116-122
• /
• 2023

Sentiment categorization technique be commonly isolated interested in threes significant classifications name Machine Learning Procedure (ML), Lexicon Based Method (LB) also finally, the Hybrid Method. In Machine Learning Methods (ML) utilizes phonetic highlights with apply notable ML algorithm. In this paper, in classification and identification be complete base under in optimizations technique called sequential minimal optimization with Random Forest algorithm (SMORF) for expanding the exhibition and proficiency of sentiment classification framework. The three existing classification algorithms are compared with proposed SMORF algorithm. Imitation result within experiential structure is Precisions (P), recalls (R), F-measures (F) and accuracy metric. The proposed sequential minimal optimization with Random Forest (SMORF) provides the great accuracy.

• Journal of Electrical Engineering and Technology
• /
• 제13권6호
• /
• pp.2262-2267
• /
• 2018

In electric machine design, there is a large computation cost for finite element analyses (FEA) when analyzing nonlinear characteristics in the machine Therefore, for the optimal design of an electric machine, designers commonly use an optimization algorithm capable of excellent convergence performance. However, robustness consideration, as this factor can guarantee machine performances capabilities within design uncertainties such as the manufacturing tolerance or external perturbations, is essential during the machine design process. Moreover, additional FEA is required to search robust optimum. To address this issue, this paper proposes a computationally efficient robust optimization algorithm. To reduce the computational burden of the FEA, the proposed algorithm employs a useful technique which termed static analysis assisted technique (SAAT). The proposed method is verified via the effective robust optimal design of electric machine to reduce cogging torque at a reasonable computational cost.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 B
• /
• pp.944-946
• /
• 2004

In this paper, a new technique for electromagnetic topology optimization is proposed. The proposed technique is based on the large-step Markov chain (LSMC) method with novel local optimization algorithm. Because the proposed algorithm keeps a good convergence characteristic of LSMC, fast convergence is assured. The proposed LSMC is verified by an application to an inverse reconstruction problem.

• International Journal of Control, Automation, and Systems
• /
• 제5권2호
• /
• pp.192-199
• /
• 2007

This paper proposes a new printed circuit board (PCB) assembly planning method for multi-head surface mounters. We present an integer programming formulation for the optimization problem, and propose a heuristic method to solve the large NP-complete problem within a reasonable time. A dynamic programming technique is then applied to the feeder arrangement optimization and placement sequence optimization to reduce the overall assembly time. Comparative simulation results are finally presented to verify the usefulness of the proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제1권1호
• /
• pp.113-118
• /
• 2001

In this paper, we develop an optimal intelligent digital redesign method for a class of fuzzy-model-based controllers, effective for stabilization of continuous-time complex nonlinear systems. Takagi-Sugeno (TS) fuzzy model is used to extend the results of the classical digital redesign technique to complex nonlinear systems. Unlike the conventional intelligent digital redesign technique reported in the literature, the proposed method utilized the recently developed LMI optimization technique to obtain a digitally redesigned fuzzy-model-based controller. Precisely speaking, the intelligent digital redesign problem is converted to an equivalent optimization problem, and the LMI optimization method is used to find the digitally redesigned fuzzy-model-based controller. A numerical example is provided to evaluate the feasibility of the proposed approach.

• Wind and Structures
• /
• 제14권6호
• /
• pp.559-582
• /
• 2011

This paper presents an integrated wind-induced dynamic analysis and computer-based design optimization technique for minimizing the structural cost of general tall buildings subject to static and dynamic serviceability design criteria. Once the wind-induced dynamic response of a tall building structure is accurately determined and the optimal serviceability design problem is explicitly formulated, a rigorously derived Optimality Criteria (OC) method is to be developed to achieve the optimal distribution of element stiffness of the structural system satisfying the wind-induced drift and acceleration design constraints. The effectiveness and practicality of the optimal design technique are illustrated by a full-scale 60-story building with complex 3D mode shapes. Both peak resultant acceleration criteria and frequency dependent modal acceleration criteria are considered and their influences on the optimization results are highlighted. Results have shown that the use of various acceleration criteria has different implications in the habitability evaluations and subsequently different optimal design solutions. The computer based optimization technique provides a powerful tool for the lateral drift and occupant comfort design of tall building structures.

• 전기의세계
• /
• 제26권1호
• /
• pp.63-70
• /
• 1977

This paper deals with computer analysis technique of the network having 3-terminal elements whose input and output characteristics are defined by nonuniform spacing function group on the volt-ampere space. Developing the algorithms to obtain the solutions of the network mentioned above by computer, we propose optimization technique, which can solve the normal form equations of the network defined in this paper and which involves mode analysis technique to be able to analyze the case that the function group has negative resistance characteristics.

• Journal of Electrical Engineering and Technology
• /
• 제9권4호
• /
• pp.1315-1323
• /
• 2014

Although the power density in Double Stator Switched Reluctance Motor (DSSRM) has been improved, the torque ripple is still very high. So, it is important to reduce the torque ripple for specific applications such as Electric Vehicles (EVs). In This paper, an effective rotor shaping optimization technique for torque ripple reduction of DSSRM is presented. This method leads to the lower torque pulsation without significant reduction in the average torque. The method is based on shape optimization of the rotor using Finite Element Method and Taguchi's optimization method for rotor reshaping for redistribution of the flux so that the phase inductance profile has smoother variation as the rotor poles move into alignment with excited stator poles. To check on new design robustness, mechanical analysis was used to evaluate structural conformity against local electromagnetic forces which cause vibration and deformation. The results show that this shape optimization technique has profound effect on the torque ripple reduction.

• 한국인터넷방송통신학회논문지
• /
• 제12권5호
• /
• pp.177-183
• /
• 2012

스마트폰은 음성이나 문자를 주고받는 단순한 통신 기기에서 벗어나 현대인의 일상생활에서 최고의 필수품이 되었다. 스마트 폰의 성능 최적화를 위해 성능 향상과 여유 메모리 확보가 가장 많이 시도된다. 전체적인 성능 향상을 위해서는 컴퓨터 제조사에서 사용하는 CPU 오버 클락 기법을 사용하며, 앱들의 동작을 원활하게 해주는 여유 메모리 확보 기법 또한 흔히 시도된다. 이 논문에서 우리는 일반 사용자가 스마트폰 성능을 최적화할 수 있는 방법을 제시하고, 대중적인 앤드로이드 폰 모델을 대상으로 이 기법을 적용하는 실험을 하고 그 결과를 제시하였다.

• International Journal of Computer Science & Network Security
• /
• 제23권7호
• /
• pp.39-48
• /
• 2023

Breast cancer screening makes extensive utilization of mammography. Even so, there has been a lot of debate with regards to this application's starting age as well as screening interval. The deep learning technique of transfer learning is employed for transferring the knowledge learnt from the source tasks to the target tasks. For the resolution of real-world problems, deep neural networks have demonstrated superior performance in comparison with the standard machine learning algorithms. The architecture of the deep neural networks has to be defined by taking into account the problem domain knowledge. Normally, this technique will consume a lot of time as well as computational resources. This work evaluated the efficacy of the deep learning neural network like Visual Geometry Group Network (VGG Net) Residual Network (Res Net), as well as inception network for classifying the mammograms. This work proposed optimization of ResNet with Teaching Learning Based Optimization (TLBO) algorithm's in order to predict breast cancers by means of mammogram images. The proposed TLBO-ResNet, an optimized ResNet with faster convergence ability when compared with other evolutionary methods for mammogram classification.