• Journal of KIISE
• /
• v.44 no.1
• /
• pp.51-56
• /
• 2017

The research area for solving question answering (QA) problems using artificial intelligence models is in a methodological transition period, and one such architecture, the dynamic memory network (DMN), is drawing attention for two key attributes: its attention mechanism defined by neural network operations and its modular architecture imitating cognition processes during QA of human. In this paper, we increased accuracy of the inferred answers, by adapting an automatic data augmentation method for lacking amount of training data, and by improving the ability of time perception. The experimental results showed that in the 1K-bAbI tasks, the modified DMN achieves 89.21% accuracy and passes twelve tasks which is 13.58% higher with passing four more tasks, as compared with one implementation of DMN. Additionally, DMN's word embedding vectors form strong clusters after training. Moreover, the number of episodic passes and that of supporting facts shows direct correlation, which affects the performance significantly.

• KIISE Transactions on Computing Practices
• /
• v.23 no.7
• /
• pp.440-445
• /
• 2017

Due to the advance of e-commerce systems, the number of people using online shopping and products has significantly increased. Therefore, the need for an accurate recommendation system is becoming increasingly more important. Recurrent neural network is a deep-learning algorithm that utilizes sequential information in training. In this paper, an evaluation is performed on the application of recurrent neural networks to recommendation systems. We evaluated three recurrent algorithms (RNN, LSTM and GRU) and three optimal algorithms(Adagrad, RMSProp and Adam) which are commonly used. In the experiments, we used the TensorFlow open source library produced by Google and e-commerce session data from RecSys Challenge 2015. The results using the optimal hyperparameters found in this study are compared with those of RecSys Challenge 2015 participants.

• Journal of Periodontal and Implant Science
• /
• v.48 no.2
• /
• pp.114-123
• /
• 2018

Purpose: The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Methods: Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. Results: The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. Conclusions: We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8S
• /
• pp.2608-2619
• /
• 2000

This paper proposes the Handover Scheme for the mobile and describes the result of the performance analysis. In the conventional scheme of handover request, the withdrawal of terminal may occur because handover request is performed based on fixed signal level without considering network load and terminal mobility. The proposed scheme offers the minimization of withdrawal and handover blocking probability by means of the handover request of terminal based on the network load and terminal mobility. Conventional handover scheme has the sequential procedure that network performs resource check and path rerouting on the handover by MT(Mobile Terminal). Proposed handover scheme pre-processes the resource check before the handover request by predicting the handover request timo so that handover latency can be reduced. Moreover, path optimization is executed after the completion of handover in order to reduce handover latency. The rdduction of handover latency prevents the dropping of service by minimizing backward handover blocking. In summary, we propose the prediction of handover request time and decision method based on terminal, validating the performance of proposed scheme considering various cases of simulation.

• KIEAE Journal
• /
• v.16 no.3
• /
• pp.89-94
• /
• 2016

Purpose: This study aimed at developing an artificial neural network (ANN) model to predict the optimal start moment of the setback temperature during the normal occupied period of a building. Method: For achieving this objective, three major steps were conducted: the development of an initial ANN model, optimization of the initial model, and performance tests of the optimized model. The development and performance testing of the ANN model were conducted through numerical simulation methods using transient systems simulation (TRNSYS) and matrix laboratory (MATLAB) software. Result: The results analysis in the development and test processes revealed that the indoor temperature, outdoor temperature, and temperature difference from the setback temperature presented strong relationship with the optimal start moment of the setback temperature; thus, these variables were used as input neurons in the ANN model. The optimal values for the number of hidden layers, number of hidden neurons, learning rate, and moment were found to be 4, 9, 0.6, and 0.9, respectively, and these values were applied to the optimized ANN model. The optimized model proved its prediction accuracy with the very storing statistical correlation between the predicted values from the ANN model and the simulated values in the TRNSYS model. Thus, the optimized model showed its potential to be applied in the control algorithm.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.46-53
• /
• 2012

The traffic in research network for the new structure of the network and new service research has the various properties. From the perspective of a specific traffic point of view, transmission of traffic with different requirements using a single routing protocol is an obstacle to satisfy requirements. In this study, we classify the properties of the traffic into two types. We propose the way that we can get the overall optimization effect, the experiment proves it by providing independent multiple forwarding path by applying optimized algorithm by types. In order to distinguish each type of traffic we use the ports on the switch and in order to implement independent path we apply OpenFlow system. In other words, we present the measure that can be implemented to improve the satisfaction of the traffic by making multiple paths by OpenFlow controller according to the type of traffic and by enforcing in Forwarder.

• International Journal of Highway Engineering
• /
• v.17 no.3
• /
• pp.97-105
• /
• 2015

PURPOSES : The Toll Collection System (TCS) operated by the Korea Expressway Corporation provides accurate traffic counts between tollgates within the expressway network under the closed-type toll collection system. However, although origin-destination (OD) matrices for a travel demand model can be constructed using these traffic counts, these matrices cannot be directly applied because it is technically difficult to determine appropriate passenger car equivalent (PCE) values for the vehicle types used in TCS. Therefore, this study was initiated to systematically determine the appropriate PCE values of TCS vehicle types for the travel demand model. METHODS : To search for the appropriate PCE values of TCS vehicle types, a traffic demand model based on TCS-based OD matrices and the expressway network was developed. Using the traffic demand model and a genetic algorithm, the appropriate PCE values were optimized through an approach that minimizes errors between actual link counts and estimated link volumes. RESULTS : As a result of the optimization, the optimal PCE values of TCS vehicle types 1 and 5 were determined to be 1 and 3.7, respectively. Those of TCS vehicle types 2 through 4 are found in the manual for the preliminary feasibility study. CONCLUSIONS : Based on the given vehicle delay functions and network properties (i.e., speeds and capacities), the travel demand model with the optimized PCE values produced a MAPE value of 37.7%, RMSE value of 17124.14, and correlation coefficient of 0.9506. Conclusively, the optimized PCE values were revealed to produce estimates of expressway link volumes sufficiently close to actual link counts.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.11
• /
• pp.1397-1405
• /
• 2013

The optimal rib pattern design of B-pillar trim considering occupant head protection can be determined by two methods. One is the conventional approximate optimization method that uses the statistical design of experiments (DOE) and response surface method (RSM). Generally, approximated optimum results are obtained through the iterative process by trial-and-error. The quality of results strongly depends on the factors and levels assigned by a designer. The other is a methodology derived from previous work by the authors, called the sequential design of experiments (SDOE), to reduce the trial-and-error procedure and to find an appropriate condition for using artificial neural network (ANN) systematically. An appropriate condition is determined from the iterative process based on the analysis of means. With this new technique and ANN, it is possible to find an optimum design accurately and efficiently.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.2774-2796
• /
• 2015

Quality-of-service (QoS) provisioning for a cognitive mesh network (CMN) with heterogeneous services has become a challenging area of research in recent days. Considering both real-time (RT) and non-real-time (NRT) traffic in a multihop CMN, [1] studied cross-layer resource management, including joint access control, route selection, and resource allocation. Due to the complexity of the formulated resource allocation problems, which are mixed-integer non-linear programming, a low-complexity yet efficient algorithm was proposed there to approximately solve the formulated optimization problems. In contrast, in this work, we present an application of genetic algorithm (GA) to re-address the hard resource allocation problems studied in [1]. Novel initialization, selection, crossover, and mutation operations are designed such that solutions with enough randomness can be generated and converge with as less number of attempts as possible, thus improving the efficiency of the algorithm effectively. Simulation results show the effectiveness of the newly proposed GA-based algorithm. Furthermore, by comparing the performance of the newly proposed algorithm with the one proposed in [1], more insights have been obtained in terms of the tradeoff among QoS provisioning for RT traffic, throughput maximization for NRT traffic, and time complexity of an algorithm for resource allocation in a multihop network such as CMN.

• Journal of Digital Convergence
• /
• v.13 no.2
• /
• pp.127-133
• /
• 2015

In order for location information to deliver the collected information, it needs Sensor Nodes in an environment of Sensor Network. Each sensor sends data to a base station through the process of routing in a wireless sensor network environment. Therefore, Offering accurate location information is very important in a wireless sensor network environment. Most of existed routing methods save all the informations of nodes at the area of 1-hop. In order to save these informations, unnecessary wasted energy and traffics are generated. Routing Protocol proposed in this paper doesn't save node's location information, and doesn't exchange any periodic location information to reduce wasted energy. It includes transmission range of source nodes and nodes with the location information, however it doesn't include any nodes' routing near 1-hope distance.