• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.4
• /
• pp.544-553
• /
• 2013

In this paper, we propose the pattern classifier of Radial Basis Function Neural Networks(RBFNNs) for diagnosis of 3-phase partial discharge. Conventional methods map the partial discharge/noise data on 3-PARD map, and decide whether the partial discharge occurs or not from 3-phase or neutral point. However, it is decided based on his own subjective knowledge of skilled experter. In order to solve these problems, the mapping of data as well as the classification of phases are considered by using the general 3-PARD map and PA method, and the identification of phases occurring partial discharge/noise discharge is done. In the sequel, the type of partial discharge occurring on arbitrary random phase is classified and identified by fuzzy clustering-based polynomial Radial Basis Function Neural Networks(RBFNN) classifier. And by identifying the learning rate, momentum coefficient, and fuzzification coefficient of FCM fuzzy clustering with the aid of PSO algorithm, the RBFNN classifier is optimized. The virtual simulated data and the experimental data acquired from practical field are used for performance estimation of 3-phase partial discharge pattern classifier.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1956-1957
• /
• 2011

본 연구는 White LED를 이용하여 주변 밝기 변화에 빠르게 적응하는 퍼지 뉴로 Dimming Control System을 설계한다. 본 논문에서는 방사형기저함수 신경회로망(Radial Basis Function Neural Network: RBFNN)을 설계하여 실제 White LED Dimming Control System에 적용시켜 모델의 근사화 및 일반화 성능을 평가한다. 제안한 모델에서의 은닉층은 방사형기저함수를 사용하여 적합도를 구현하였고, 후반부의 연결가중치는 경사하강법을 사용한다. 이때 멤버쉽 함수의 중심점은 HCM 클러스터링 (Hard C-Means Clustering)을 적용하여 결정한다. 연결가중치는 4가지 형태의 다항식을 대입하여 출력을 평가하였다. 최종 출력의 최적화를 위하여 PSO(Particle Swarm Optimization)을 이용하여 은닉층 노드수 및 다항식 형태를 결정한다. 본 논문에서 제안한 LED Dimming Control System은 Atmega8535를 사용하여 PWM 제어 방식을 사용하고, 조도계(Cds)를 이용하여 LED의 밝기에 따른 주변의 밝기를 감지하여 조명에 적응시키는 방법을 적용하였다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.6
• /
• pp.1060-1069
• /
• 2016

In this paper, we introduce the fingerprint recognition system based on Radial Basis Function Neural Network(RBFNN). Fingerprints are classified as four types(Whole, Arch, Right roof, Left roof). The preprocessing methods such as fast fourier transform, normalization, calculation of ridge's direction, filtering with gabor filter, binarization and rotation algorithm, are used in order to extract the features on fingerprint images and then those features are considered as the inputs of the network. RBFNN uses Fuzzy C-Means(FCM) clustering in the hidden layer and polynomial functions such as linear, quadratic, and modified quadratic are defined as connection weights of the network. Particle Swarm Optimization (PSO) algorithm optimizes a number of essential parameters needed to improve the accuracy of RBFNN. Those optimized parameters include the number of clusters and the fuzzification coefficient used in the FCM algorithm, and the orders of polynomial of networks. The performance evaluation of the proposed fingerprint recognition system is illustrated with the use of fingerprint data sets that are collected through Anguli program.

• Smart Structures and Systems
• /
• v.5 no.6
• /
• pp.681-697
• /
• 2009

Limited, noisy data in vibration testing is a hindrance to the development of structural damage detection. This paper presents a method for optimizing sensor placement and performing damage detection using finite element model updating. Sensitivity analysis of the modal flexibility matrix determines the optimal sensor locations for collecting information on structural damage. The optimal sensor locations require the instrumentation of only a limited number of degrees of freedom. Using noisy modal data from only these limited sensor locations, a method based on model updating and changes in the flexibility matrix successfully determines the location and severity of the imposed damage in numerical simulations. In addition, a steel cantilever beam experiment performed in the laboratory that considered the effects of model error and noise tested the validity of the method. The results show that the proposed approach effectively and robustly detects structural damage using limited, optimal sensor information.

• Applied Chemistry for Engineering
• /
• v.32 no.5
• /
• pp.589-598
• /
• 2021

The purpose of this study was to analyze the efficiency with which phosphorylated spent coffee grounds (PSCG) remove cationic Cu(II) ions from an aqueous solution. The pHpzc of the SCG was 6.43, but it was lowered to 3.96 in the PSCG, confirming that an acidic functional group was attached to the surface of the PSCG. According to FT-IR analysis, phosphorylation of the SCG added P=O, P-O-C (aromatic), P=OOH, and P-O-P groups to the surface of the adsorbent, and the peaks of the carboxyl and OH groups were high and broad. Also, the specific surface area, mesopore range, and ion exchange capacity increased significantly by phosphorylation. The adsorption kinetics and isothermal experiments showed that Cu(II) adsorption using SCG and PSCG was explained by PSO and Langmuir models. The maximum Langmuir adsorption capacity of SCG and PSCG was 42.23 and 162.36 mg/g, respectively. The adsorption process of both SCG and PSCG was close to physical adsorption and endothermic reaction in which the adsorption efficiency increased with temperature. PSCG was very effective in adsorbing Cu(II) in aqueous solution, which has great advantages in terms of recycling resources and adsorbing heavy metals using waste materials.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.341-349
• /
• 2021

Many emerging mobile ad-hoc network application communications are group-oriented. Multicast supports group-oriented applications efficiently, particularly in a mobile environment that has a limited bandwidth and limited power. Energy effectiveness along with safety are 2 key problem in MANET design. Within this paper, MANET is presented with a stable, energy-efficient clustering technique. In this proposed work advanced clustering in the networks with ticket ID cluster manager (TID-CMGR) has formed in MANET. The proposed routing scheme makes secure networking the shortest route possible. In this article, we propose a Cluster manager approach based on TICKET-ID to address energy consumption issues and reduce CH workload. TID-CMGR includes two mechanism including ticket ID controller, ticketing pool, route planning and other components. The CA (cluster agent) shall control and supervise the functions of nodes and inform to TID-CMGR. The CH conducts and transfers packets to the network nodes. As the CH energy level is depleted, CA elects the corresponding node with elevated energy values, and all new and old operations are simultaneously stored by CA at this time. A simulation trial for 20 to 100 nodes was performed to show the proposed scheme performance. The suggested approach is used to do experimental work using the NS- simulator. TIDCMGR is compared with TID BRM and PSO to calculate the utility of the work proposed. The assessment shows that the proposed TICKET-ID scheme achieves 90 percent more than other current systems.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.12
• /
• pp.2352-2360
• /
• 2011

In this paper, we introduce a comprehensive design methodology of Radial Basis Function Neural Networks (RBFNN) that is based on mechanism of clustering and optimization algorithm. We can divide some clusters based on similarity of input dataset by using clustering algorithm. As a result, the number of clusters is equal to the number of nodes in the hidden layer. Moreover, the centers of each cluster are used into the centers of each receptive field in the hidden layer. In this study, we have applied Fuzzy-C Means(FCM) and K-Means(KM) clustering algorithm, respectively and compared between them. The weight connections of model are expanded into the type of polynomial functions such as linear and quadratic. In this reason, the output of model consists of relation between input and output. In order to get the optimal structure and better performance, Particle Swarm Optimization(PSO) is used. We can obtain optimized parameters such as both the number of clusters and the polynomial order of weights connection through structural optimization as well as the widths of receptive fields through parametric optimization. To evaluate the performance of proposed model, NXT equipment offered by National Instrument(NI) is exploited. The situation awareness system-related intelligent model was built up by the experimental dataset of distance information measured between object and diverse sensor such as sound sensor, light sensor, and ultrasonic sensor of NXT equipment.

• Korean Journal of Agricultural Science
• /
• v.40 no.4
• /
• pp.367-375
• /
• 2013

The enzymatic interesterification was performed to produce structured lipids (SLs) with palm mid fraction (PMF) and stearic ethyl ester (STEE) for 1, 3, 6, 9, 12 and 15 hr at $80^{\circ}C$. The reaction was catalyzed by Lipozyme TLIM (immobilized lipase from Thermomyces lanuginosus, amount of 20% by weight of total substrates) in a shaking water bath set at 180 rpm. The optimum condition for synthesis of asymmetric SLs were: substrate molar ratio 1:0.5 (PMF:STEE, by weight), reaction time 6 hr, enzyme 20% (wt%, water activity=0.085) of total substrate and reaction temperature $80^{\circ}C$. After reaction at optimized condition, triacylglycerols (symmetrical and asymmetrical TAGs) from reactants were isolated. POP/PPO (1,3-palmitoyl-2-oleoyl glycerol or 1,2-palmitoyl-3-oleoyl glycerol), POS/PSO (palmitoyl-oleoyl-stearoyl glycerol or palmitoyl-stearoyl-oleoyl glycerol), SOS/SSO (1,3-stearoyl-2-oleoyl glycerol or 1,2-stearoyl-3-oleoyl glycerol) were obtained by solvent fractionation. Finally, refined SLs contained stearic acid of 16.91%. Solid fat index and thermogram of the refined SLs were obtained using differential scanning calorimetry. The degree of asymmetric triacylglycerol in the refined SLs was analyzed by Ag-HPLC equipped with evaporated light scattering detector (ELSD). The refined SLs consisted of symmetric TAG of 41.15 area% and asymmetric TAG of 58.85 area%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.87-92
• /
• 2016

In this paper, optimization technique such as particle swarm optimization was used to optimize the parameters of fuzzy Extreme Learning Machine. While the learning speed of conventional neural networks is very slow, that of Extreme Learning Machine is very fast. Fuzzy Extreme Learning Machine is composed of the Extreme Learning Machine with very fast learning speed and fuzzy logic which can represent the linguistic information of the field experts. The general sigmoid function is used for the activation function of Extreme Learning Machine. However, the activation function of Fuzzy Extreme Learning Machine is the membership function which is defined in the procedure of fuzzy C-Means clustering algorithm. We optimize the parameters of the membership functions by using optimization technique such as Particle Swarm Optimization. In order to validate the classification capability of the proposed classifier, we make several experiments with the various machine learning datas.

• Proceedings of the Korean Magnetic Resonance Society Conference
• /
• 2002.08a
• /
• pp.80-80
• /
• 2002

MnPSO-34 and Mn-impregnated SAPO-34 (Mn-SAPO-34) sample were prepared with various manganese contents and studied by electron spin resonance (ESR) and electron spin-echo modulation (ESEM). Electron spin-echo modulation analysis of 0.07mol ％ Mn(relative to p) in MnAPSO-34 with adsorbed D$_2$O shows two deuteriums at 0.25 nm and two at 0.36 nm from Mn. This suggests that two waters hydrate an MnO4 configuration with a D-O bond orientation for the waters as expect for a negatively charged site at low manganese content (0.07 mol％), the ESR spectra of MnAPSO-34 and MnH-SAPO-34 exhibit the same parameters (g 2.02 and A 87 G), but the spectra obtained from MnAPSO-34 samples are better resolved. TGA of as-synthesized MnAPSO-34 shows that the decomposition temperature in the range 200-$600^{\circ}C$ of the morpholine is 12$^{\circ}C$ higher than that in as-synthesized MnH-SAPO-34. Infrared spectra shows that the position of a band at about 15 cm-1 toward higher energy in MnAPSO-34 versus MnH-SAPO-34. The modulation depth of the two-pulse ESE of MnAPSO-34 with absorbed D$_2$O is deeper than that of MnH-SAPO-34 with absorbed D$_2$O. Three-pulse ESEM of MnAPSO-34 and MnH-SAPO-34 with absorbed deuterium oxide shows that the local environments of manganese in the hydrated samples are different, suggesting that Mn(II) is framework substituted in MnAPSO-34 since it obviously occupies an extra-framework position in MnH-SAPO-34