• Journal of the Ergonomics Society of Korea
• /
• v.21 no.1
• /
• pp.1-14
• /
• 2002

The main purpose of this paper is to present selection criteria for ROK Airforce pilot training candidates in order to save costs involved in sequential pilot training. We use classification models such Decision Tree, Logistic Regression and Neural Network based on aptitude test results of 288 ROK Air Force applicants in 1994-1996. Different models are compared in terms of classification accuracy, ROC and Lift-value. Neural network is evaluated as the best model for each sequential flight test result while Logistic regression model outperforms the rest of them for discriminating the last flight test result. Therefore we suggest a pilot selection criterion based on this logistic regression. Overall. we find that the factors such as Attention Sharing, Speed Tracking, Machine Comprehension and Instrument Reading Ability having significant effects on the flight results. We expect that the use of our criteria can increase the effectiveness of flight resources.

• Proceedings of the KIEE Conference
• /
• 1994.11a
• /
• pp.397-399
• /
• 1994

In this paper a feature-based automatic neural network signal classifier is presented, where five neural network algorithms such as MLP, RBF, LVQ2, MLP-Tree and LVQ-Tree are combined in parallel to classifiy various signals from their features, based on the majority vote method. To demonstrate the performance and applicability of the proposed signal classifier, some test results for the classification of synthetic waveforms and power disturbances are provided.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12A
• /
• pp.984-993
• /
• 2011

In this paper, we present a new method for efficient mobility management in infrastructure-based ad hoc networks. This type of network inherently takes the tree topology model in which an Internet gateway (IG) becomes a root. Accordingly, the nodes near the IG process get much more number of messages, thereby causing a bottleneck phenomenon that degrades network performance. This problem is known as a funneling effect. We present a method to maximize message aggregation in which the nodes in the networks form tree topology and perform skewed time synchronization according to the depths of the nodes during the tree construction process. We proved by resorting to simulation that the funneling effect is alleviated and network performance is improved greatly.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.8
• /
• pp.149-156
• /
• 2010

As following the development of the USN technology, sensor node used in sensor network has capability of quick data process and storage to support efficient network configuration is enabled. In addition, tree-based structure was transformed to cluster in the construction of sensor network. However, query processing based on existing tree structure could be inefficient under the cluster-based network. In this paper, we suggest energy efficient query processing mechanism using filtering through data attribute classification in cluster-based sensor network. The suggestion mechanism use advantage of cluster-based network so reduce energy of query processing and designed more intelligent query dissemination. And, we prove excellence of energy efficient side with MATLab.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.199-202
• /
• 2001

In this paper, we proposed and analyzed a new class of irregular fault-tolerant multistage interconnection network named as Extended-QT(Quad Tree) network. E-QT network is extended QT network. A unique path MIN usually is low hardware complexity and control algorithm. So we proposes a class of multipath MIN which are obtained by adding self-loop auxiliary links at the a1l stages in QT(Quad Tree) networks so that they can provide more paths between each source-destination pair. The routing of proposed structure is adaptived and is based by a routing tag. Starting with the routing tag for the minimum path between a given source-destination pair, routing algorithm uses a set of rules to select switches and modify routing tag. Trying the self-loop auxiliary link when both of the output links are unavailable. If the trying is failure, the packet discard. In simulation, an index of performance called reliability and cost are introduced to compare different kinds of MINs. As a result, the prouosed MINs have better capacity than 07 networks.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12B
• /
• pp.1514-1523
• /
• 2009

It is well known that the current wireless sensor networks addressing methods do not work efficiently in networks more than a few hundred nodes. A standard protocol in ZigBee-Standard feature in ZigBee 2007 gives balanced tree based address assignment method with distributed manner. However, it was limited to cover less than hundreds of sensor nodes due to the wasteful use of available address space, because composed sensor networks usually make an unbalanced tree topology in the real deployment. In this paper, we proposed the hierarchical cluster tree based address assignment method to support large and scalable networks. This method provides unique address for each node with distributed manner and supports hierarchical cluster tree on-demand. Simulation results show that the proposed method reduces orphan nodes due to the address exhaustion and supports larger network with limited address space compared with the ZigBee distributed address assignment method defined in ZigBee-Standard feature in ZigBee 2007.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.6A
• /
• pp.600-610
• /
• 2010

In this paper, a multicast mechanism is proposed for intermittently disconnected networks where the nodes move forward in formation or within a limited area. The proposed scheme extends the well-known tree-based multicast routing mechanism called MAODV by modifying the tree construction and data delivery scheme. Especially, an algorithm is introduced which determines the flooding hop count k estimating the degree of the movement of children in the tree. The performance evaluation was done by the simulation and the proposed scheme was compared with MAODV and two multicast routing schemes for DTN (Disruption Tolerant Network) including the Epidemic routing and ST-multicast. The evaluation results show that our scheme improves the original MAODV from the aspect of tree reconstruction events and message delivery ratio. Compared with the Epidemic routing scheme, our scheme achieves 85% message delivery ratio with less than 50% message delivery overhead.

• Structural Engineering and Mechanics
• /
• v.89 no.3
• /
• pp.283-300
• /
• 2024

Machine learning (ML) models based on artificial neural network (ANN) and decision tree (DT) were developed for estimation of axial capacity of concrete columns reinforced with fiber reinforced polymer (FRP) bars. Between the design codes, the Canadian code provides better formulation compared to the Australian or American code. For empirical models based on elastic modulus of FRP, Hadhood et al. (2017) model performed best. Whereas for empirical models based on tensile strength of FRP, as well as all empirical models, Raza et al. (2021) was adjudged superior. However, compared to the empirical models, all ML models exhibited superior performance according to all five performance metrics considered. The performance of ANN and DT models were comparable in general. Under the present setup, inclusion of the transverse reinforcement information did not improve the accuracy of estimation with either ANN or DT. With selective use of inputs, and a much simpler ANN architecture (4-3-1) compared to that reported in literature (Raza et al. 2020: 6-11-11-1), marginal improvement in correlation could be achieved. The metrics for the best model from the study was a correlation of 0.94, absolute errors between 420 kN to 530 kN, and the range being 0.39 to 0.51 for relative errors. Though much superior performance could be obtained using ANN/DT models over empirical models, further work towards improving accuracy of the estimation is indicated before design of FRP reinforced concrete columns using ML may be considered for design codes.

• Journal of KIISE:Information Networking
• /
• v.34 no.5
• /
• pp.360-369
• /
• 2007

Since wireless sensor networks consist of nodes with the constrained battery, it is important to construct the topology performing energy-efficient routing while maximizing the whole network lifetime. Previous works related to this do not take into consideration the specific communication pattern in wireless sensor networks. In this paper, we propose a novel routing algorithm, called Up-Down Tree(UDT), which first constructs the tree topology based on distance and then adjusts the transmission range determined by the two different phases, tree setup and data gathering, to adapt the specific communication pattern in wireless sensor networks. Therefore, the UDT can improve energy efficiency, maximize the network lifetime, and block network partition Simulation results show that the UDT has the improved energy efficiency by constructing the optimal topology.

• The KIPS Transactions:PartC
• /
• v.15C no.3
• /
• pp.205-212
• /
• 2008

In the environment with multiple heterogeneous wireless sensor networks with a single point of sensed data collection or a gateway (GW), relay points (RPs) may be required for the energy efficient delivery of sensed data from static or mobile sinks to the GW. The optimal placement of RPs becomes an even more difficult problem if static sinks are dynamically added or the trajectory of mobile sinks can not be known in advance. In order to resolve this problem, we propose a mechanism to deploy RPs in a grid pattern and to use the tree-based relaying network for reducing the cost of the RP and for reducing the control overhead incurred by the route setup from sinks to the GW. For the performance evaluation of our proposed mechanism, we have carried out a numerical analysis on a single route setup from a sink to the GW and, for more general performance evaluations, ns-2 based simulations have been carried out. According to the performance evaluation results, our tree-based relaying network mechanism outperforms that based on AODV in terms of the data delivery time, the network service time and the control overhead.