• 한국정밀공학회지
• /
• 제21권8호
• /
• pp.83-88
• /
• 2004

The Classification of defected oil-seals using a vision system with the artificial neural network is presented. The artificial neural network fur classification consists of 27 input nodes, 10 hidden nodes, and one output node. The selection of the number of the input nodes is based on an observation that the difference among the defected, non-defected, and smeared oil-seals is greatly pronounced in the 26 step gray-scale level thresholding. The number of the hidden nodes is chosen as a result of a trade-off between accuracy and computing time. The back-propagation algorithm is used for teaching the network. The proposed network is capable of successfully classifying the defected from the smeared oil-seals which tend to be classified as the defected ones using the binary thresholding. It is envisaged that the proposed method improves the reliability and productivity of the automotive vision inspection system.

• 대한산업공학회지
• /
• 제31권3호
• /
• pp.257-264
• /
• 2005

This paper suggests a heuristic algorithm for the clustering problem. Clustering involves grouping similar objects into a cluster. Clustering is used in a wide variety of fields including data mining, marketing, and biology. Until now there are a lot of approaches using Self-Organizing Feature Maps(SOFMs). But they have problems with a small output-layer nodes and initial weight. For example, one of them is a one-dimension map of k output-layer nodes, if they want to make k clusters. This approach has problems to classify elaboratively. This paper suggests one-dimensional output-layer nodes in SOFMs. The number of output-layer nodes is more than those of clusters intended to find and the order of output-layer nodes is ascending in the sum of the output-layer node's weight. We can find input data in SOFMs output node and classify input data in output nodes using Euclidean distance. We use the well known IRIS data as an experimental data. Unsupervised clustering of IRIS data typically results in 15 - 17 clustering error. However, the proposed algorithm has only six clustering errors.

• Journal of Communications and Networks
• /
• 제12권3호
• /
• pp.231-239
• /
• 2010

In cluster-based wireless sensor networks, the energy could be saved when the nodes that have data to transmit participate in cooperative multiple-input multiple-output (MIMO). In this paper, by making the idle nodes that have no data to transmit participate in the cooperative MIMO, it is found that much more energy could be saved. The number of the idle nodes that participate in the cooperative MIMO is optimized to minimize the total energy consumption. It is also found that the optimal number of all the nodes participating in cooperative communication does not vary with the number of nodes that have data to transmit. The proposition is proved mathematically. The influence of long-haul distance and modulation constellation size on the total energy consumption is investigated. A cooperative MIMO scheme with help-node participation is proposed and the simulation results show that the proposed scheme achieves significant energy saving.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 춘계학술대회 학술발표 논문집
• /
• pp.87-91
• /
• 2001

This paper discusses the influence of input conductance on the convergece of the continuous Hopfield neural networks. The convergence has been analyzed for the input and output nodes of neurons. Also, the characteristics of equilibrium points has been analyzed depending on different values of the input conductance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권8호
• /
• pp.3823-3840
• /
• 2017

This paper analyzes the nodes deployment optimization problem in energy constrained wireless sensor networks, which multi-hop cooperative beamforming (CB) based cooperative-multi-input-single-output (CMISO) transmission is adopted to reduce the energy consumption. Firstly, we establish the energy consumption models for multi-hop SISO, multi-hop DSTBC based CMISO, multi-hop CB based CMISO transmissions under random nodes deployment. Then, we minimize the energy consumption by searching the optimal nodes deployment for the three transmissions. Furthermore, numerical results present the optimal nodes deployment parameters for the three transmissions. Energy consumption of the three transmissions are compared under optimal nodes deployment, which shows that CB based CMISO transmission consumes less energy than SISO and DSTBC based CMISO transmissions. Meanwhile, under optimal nodes deployment, the superiorities of CB based CMISO transmission over SISO and DSTBC based CMISO transmissions can be more obvious when path-loss-factor becomes low.

• 디지털산업정보학회논문지
• /
• 제11권3호
• /
• pp.45-51
• /
• 2015

In this paper, we discuss the belief propagation decoding algorithm for polar codes. The performance of Polar codes for shorter lengths is not satisfactory. Motivated by this, we propose a novel technique to improve its performance at short lengths. We showed that the probability of messages passed along the factor graph of polar codes, can be increased by multiplying the current message of nodes with their previous message. This is like a feedback path in which the present signal is updated by multiplying with its previous signal. Thus the experimental results show that performance of belief propagation polar decoder can be improved using this proposed technique. Simulation results in binary-input additive white Gaussian noise channel (BI-AWGNC) show that the proposed belief propagation polar decoder can provide significant gain of 2 dB over the original belief propagation polar decoder with code rate 0.5 and code length 128 at the bit error rate (BER) of $10^{-4}$.

• ETRI Journal
• /
• 제36권4호
• /
• pp.564-571
• /
• 2014

Sphere decoding (SD) for multiple-input and multiple-output systems is a well-recognized approach for achieving near-maximum likelihood performance with reduced complexity. SD is a tree search process, whereby a large number of nodes can be searched in an effort to find an estimation of a transmitted symbol vector. In this paper, a simple and generalized approach called layer pruning is proposed to achieve complexity reduction in SD. Pruning a layer from a search process reduces the total number of nodes in a sphere search. The symbols corresponding to the pruned layer are obtained by adopting a QRM-MLD receiver. Simulation results show that the proposed method reduces the number of nodes to be searched for decoding the transmitted symbols by maintaining negligible performance loss. The proposed technique reduces the complexity by 35% to 42% in the low and medium signal-to-noise ratio regime. To demonstrate the potential of our method, we compare the results with another well-known method - namely, probabilistic tree pruning SD.

• 환경영향평가
• /
• 제12권4호
• /
• pp.271-279
• /
• 2003

Temperature and humidity forecasting have been performed using artificial neural networks model(ANN). We composed ANN with multi-layer perceptron which is 2 input layers, 2 hidden layers and 1 output layer. Back propagation algorithm was used to train the ANN. 6 nodes and 12 nodes in the middle layers were appropriate to the temperature model for training. And 9 nodes and 6 nodes were also appropriate to the humidity model respectively. 90% of the all data was used learning set, and the extra 10% was used to model verification. In the case of temperature, average temperature before 15 minute and humidity at present constituted input layer, and temperature at present constituted out-layer and humidity model was vice versa. The sensitivity analysis revealed that previous value data contributed to forecasting target value than the other variable. Temperature was pseudo-linearly related to the previous 15 minute average value. We confirmed that ANN with multi-layer perceptron could support pollutant dispersion model by computing meterological data at real time.

• ETRI Journal
• /
• 제42권3호
• /
• pp.341-350
• /
• 2020

In a wireless sensor network (WSN), the data transmission technique based on the cooperative multiple-input multiple-output (CMIMO) scheme reduces the energy consumption of sensor nodes quite effectively by utilizing the space-time block coding scheme. However, in networks with high node density, the scheme is ineffective due to the high degree of correlated data. Therefore, to enhance the energy efficiency in high node density WSNs, we implemented the distributed source coding (DSC) with the virtual multiple-input multiple-output (MIMO) data transmission technique in the WSNs. The DSC-MIMO first compresses redundant source data using the DSC and then sends it to a virtual MIMO link. The results reveal that, in the DSC-MIMO scheme, energy consumption is lower than that in the CMIMO technique; it is also lower in the DSC single-input single-output (SISO) scheme, compared to that in the SISO technique at various code rates, compression rates, and training overhead factors. The results also indicate that the energy consumption per bit is directly proportional to the velocity and training overhead factor in all the energy saving schemes.

• 대한산업공학회지
• /
• 제39권5호
• /
• pp.361-366
• /
• 2013

Prediction of process parameters is very important in parameter design. If predictions are fairly accurate, the quality improvement process will be useful to save time and reduce cost. The concept of dual response approach based on response surface methodology has widely been investigated. Dual response approach may take advantages of optimization modeling for finding optimum setting of input factor by separately modeling mean and variance responses. This study proposes an alternative dual response approach based on machine learning techniques instead of statistical analysis tools. A hybrid neural network-genetic algorithm has been proposed for the purpose of parameter design. A neural network is first constructed to model the relationship between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Using empirical process data, process parameters can be predicted without performing real experimentations. A genetic algorithm is then applied to find the optimum settings of input factors, where the neural network is used to evaluate the mean and variance response. A drug formulation example from pharmaceutical industry has been studied to demonstrate the procedures and applicability of the proposed approach.