• Korean Management Science Review
• /
• v.29 no.3
• /
• pp.81-89
• /
• 2012

Since introduced by Vining and Myers in 1990, the concept of dual response approach based on response surface methodology has widely been investigated and adopted for the purpose of robust design. Separately estimating mean and variance responses, dual response approach may take advantages of optimization modeling for finding optimum settings of input factors. Explicitly assuming functional relationship between responses and input factors, however, it may not work well enough especially when the behavior of responses are poorly represented. A sufficient number of experimentations are required to improve the precision of estimations. This study proposes an alternative to dual response approach in which additional experiments are not required. An artificial neural network has been applied to model relationships between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Training, validating, and testing a neural network with empirical process data, an artificial data based on the neural network may be generated and used to estimate response functions without performing real experimentations. A drug formulation example from pharmaceutical industry has been investigated to demonstrate the procedures and applicability of the proposed approach.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.11
• /
• pp.852-858
• /
• 1991

An adaptive hierarchical classifier(AHCL) for Korean character recognition using a neural net is designed. This classifier has two neural nets: USACL (Unsupervised Adaptive Classifier) and SACL (Supervised Adaptive Classifier). USACL has the input layer and the output layer. The input layer and the output layer are fully connected. The nodes in the output layer are generated by the unsupervised and nearest neighbor learning rule during learning. SACL has the input layer, the hidden layer and the output layer. The input layer and the hidden layer arefully connected, and the hidden layer and the output layer are partially connected. The nodes in the SACL are generated by the supervised and nearest neighbor learning rule during learning. USACL has pre-attentive effect, which perform partial search instead of full search during SACL classification to enhance processing speed. The input of USACL and SACL is a directional edge feature with a directional receptive field. In order to test the performance of the AHCL, various multi-font printed Hangul characters are used in learning and testing, and its processing its speed and and classification rate are compared with the conventional LVQ(Learning Vector Quantizer) which has the nearest neighbor learning rule.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.91-102
• /
• 2022

With the evolution of wireless sensor network (WSN) technology, the routing policy has foremost importance in the Internet of Things (IoT). A systematic routing policy is one of the primary mechanics to make certain the precise and robust transmission of wireless sensor networks in an energy-efficient manner. In an IoT environment, WSN is utilized for controlling services concerning data like, data gathering, sensing and transmission. With the advantages of IoT potentialities, the traditional routing in a WSN are augmented with decision-making in an energy efficient manner to concur finer optimization. In this paper, we study how to combine IoT-based deep learning classifier with routing called, Kriging Regressive Deep Belief Neural Learning (KR-DBNL) to propose an efficient data packet routing to cope with scalability issues and therefore ensure robust data packet transmission. The KR-DBNL method includes four layers, namely input layer, two hidden layers and one output layer for performing data transmission between source and destination sensor node. Initially, the KR-DBNL method acquires the patient data from different location. Followed by which, the input layer transmits sensor nodes to first hidden layer where analysis of energy consumption, bandwidth consumption and light intensity are made using kriging regression function to perform classification. According to classified results, sensor nodes are classified into higher performance and lower performance sensor nodes. The higher performance sensor nodes are then transmitted to second hidden layer. Here high performance sensor nodes neighbouring sensor with higher signal strength and frequency are selected and sent to the output layer where the actual data packet transmission is performed. Experimental evaluation is carried out on factors such as energy consumption, packet delivery ratio, packet loss rate and end-to-end delay with respect to number of patient data packets and sensor nodes.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.161-169
• /
• 2012

In general, Euclidean minimum spanning tree is a tree connecting input nodes with minimum connecting cost. But the tree may not be optimal when applied to real world problems of three dimension. In this paper, three dimension Euclidean minimum spanning tree is proposed, connecting all input nodes of 3-dimensional space with minimum cost. In experiments for 30,000 input nodes with 100% space ratio, the tree produced by the proposed method can reduce 90.0% connection cost tree, compared with the tree by two dimension Prim's minimum spanning tree. In two dimension plane, the proposed tree increases 251.2% connecting cost, which is pointless in 3-dimensional real world. Therefore, the proposed method can work well for many connecting problems in real world space of three dimensions.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.87-95
• /
• 2012

In this paper, PTAS three-dimensional Steiner minimum tree connecting numerous input nodes rapidly in 3D space is proposed. Steiner minimum tree problem belongs to NP problem domain, and when properly devised heuristic introduces, it is generally superior to other algorithms as minimum spanning tree affiliated with P problem domain. But when the number of input nodes is very large, the problem requires excessive execution time. In this paper, a method using PTAS is proposed to solve the difficulty. In experiments for 70,000 input nodes in 3D space, the tree produced by the proposed 8 space partitioned PTAS method reduced 86.88% execution time, compared with the tree by naive 3D steiner minimum tree method, though increased 0.81% tree length. This affirms the proposed method can work well for applications that many nodes of three dimensions are need to connect swifty, enduring slight increase of tree length.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.19-33
• /
• 2001

Link weight analysis approach is suggested as a heuristic for selection of input nodes in artificial neural network for bankruptcy prediction. That is to analyze each input node\\\\`s link weight-absolute value of link weight between an input node and a hidden node in a well-trained neural network model. Prediction accuracy of three methods in this approach, -weak-linked-neurons elimination method, strong-linked-neurons selection method and integrated link weight model-is compared with that of decision tree and multivariate discrimination analysis. In result, the methods suggested in this study show higher accuracy than decision tree and multivariate discrimination analysis. Especially an integrated model has much higher accuracy than any individual models.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.9
• /
• pp.820-827
• /
• 2014

One of the basic problems in Wireless Sensor Networks (WSNs) is the localization of the sensor nodes based on the known location of numerous anchor nodes. WSNs generally consist of a large number of sensor nodes and recording the location of each sensor nodes becomes a difficult task. On the other hand, based on the application environment, the nodes may be subject to mobility and their location changes with time. Therefore, a scheme that will autonomously estimate or calculate the position of the sensor nodes is desirable. This paper presents an intelligent localization scheme, which is an artificial neural network (ANN) based localization scheme used to estimate the position of the unknown nodes. In the proposed method, three anchors nodes are used. The mobile or deployed sensor nodes request a beacon from the anchor nodes and utilizes the received signal strength indicator (RSSI) of the beacons received. The RSSI values vary depending on the distance between the mobile and the anchor nodes. The three RSSI values are used as the input to the ANN in order to estimate the location of the sensor nodes. A feed-forward artificial neural network with back propagation method for training has been employed. An average Euclidian distance error of 0.70 m has been achieved using a ANN having 3 inputs, two hidden layers, and two outputs (x and y coordinates of the position).

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.11
• /
• pp.15-21
• /
• 1999

The scalability of optical cross-connect nodes is analyzed based on the limiting factor of transmission performance. The limiting factors considered are ASE noise accumulation and gain saturation in the optical amplifiers, and crosstalk in both wavelength multiplexers/demultiplexers and optical switches. When the wavelength multiplexer/demultiplexers crosstalk is lower than 25dB, Power Penalty is below 1dB for the cascaded transmission of 10 nodes with 4 input/output ports. When 10Gbps signals are transmitted through nodes with 4 and 16 input/output Ports, performance degradation due to switch crosstalk is dominant compared to that due to ASE noise accumulation if the switch crosstalk is larger than 30dB and 45dB, respectively. For the single stage transmission of 10Gbps signal with 21dB fiber link loss, the maximum loss of optical cross-connect nodes must be under 34dB to achieve the BER of $10^{-12}$.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.3
• /
• pp.459-466
• /
• 2006

Numerical values of thermodynamic properties such as temperature, pressure, dryness, volume, enthalpy and entropy are required in numerical analysis on evaluating the thermal performance. But the steam table itself cannot be used without modelling. From this point of view the neural network with function approximation characteristics can be an alternative. the multi-layer neural networks were made for saturated vapor region and superheated vapor region separately. For saturated vapor region the neural network consists of one input layer with 1 node, two hidden layers with 10 and 20 nodes each and one output layer with 7 nodes. For superheated vapor region it consists of one input layer with 2 nodes, two hidden layers with 15 and 25 nodes each and one output layer with 3 nodes. The proposed model gives very successful results with ${\pm}0.005%$ of percentage error for temperature, enthalpy and entropy and ${\pm}0.025%$ for pressure and specific volume. From these successful results, it is confirmed that the neural networks could be powerful method in function approximation of the steam table.

• The KIPS Transactions:PartA
• /
• v.17A no.2
• /
• pp.103-112
• /
• 2010

Cluster sensor network is a sensor network where input nodes crowd densely around some nuclei. Steiner minimum tree is a tree connecting all input nodes with introducing some additional nodes called Steiner points. This paper proposes a mechanism for efficient construction of a cluster sensor network connecting all sensor nodes and base stations using connections between nodes in each belonged cluster and between every cluster, and using repetitive constructions of approximate Steiner minimum trees. In experiments, while taking 1170.5% percentages more time to build cluster sensor network than the method of Euclidian minimum spanning tree, the proposed mechanism whose time complexity is O($N^2$) could spend only 20.3 percentages more time for building 0.1% added length network in comparison with the method of Euclidian minimum spanning tree. The mechanism could curtail the built trees' average length by maximum 3.7 percentages and by average 1.9 percentages, compared with the average length of trees built by Euclidian minimum spanning tree method.