• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.144-150
• /
• 2020

Reinforcement learning is a technology that can present successful and creative solutions in many areas. This reinforcement learning technology was used to deploy containers from cloud servers to fog servers to help them learn the maximization of rewards due to reduced traffic. Leveraging reinforcement learning is aimed at predicting traffic in the network and optimizing traffic-based fog computing network environment for cloud, fog and clients. The reinforcement learning system collects network traffic data from the fog server and IoT. Reinforcement learning neural networks, which use collected traffic data as input values, can consist of Long Short-Term Memory (LSTM) neural networks in network environments that support fog computing, to learn time series data and to predict optimized traffic. Description of the input and output values of the traffic-based reinforcement learning LSTM neural network, the composition of the node, the activation function and error function of the hidden layer, the overfitting method, and the optimization algorithm.

• Journal of Internet Computing and Services
• /
• v.10 no.1
• /
• pp.33-41
• /
• 2009

Signals transmitted from access point (AP) or stations in different wireless LANs (WLAN) interfere each other when the WLANs are closely installed. When they are configured to use the same channel, signals from an WLAN get collided with signals from other WLANs so that the delay increases to user stations and the throughput decreases. In this paper, we propose a method in which an AP in a basic service set (BSS) detects other BSSs using the same channel and switches to a different channel not being occupied by any other BSS. We can avoid using the same channel with other BSS in spacially overlapped BSS environment. The proposed scheme is simulated and its characteristics are described with the analysis of the result. The results measured in terms of throughput show that the problems in overlapped wireless LANs can be resolved with the proposed method.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.54 no.4
• /
• pp.65-71
• /
• 2012

The objective of this study was to estimate surface runoff from rice paddy plots using an artificial neural network (ANN). A field experiment with three treatment levels was conducted in the NICS saemangum experimental field located in Iksan, Korea. The ANN model with the optimal network architectures, named Paddy1901 with 19 input nodes, 1 hidden layer with 16 neurons nodes, and 1 output node, was adopted to predict surface runoff from the plots. The model consisted of 7 parameters of precipitation, irrigation rate, ponding depth, average temperature, relative humidity, wind speed, and solar radiation on the daily basis. Daily runoff, as the target simulation value, was computed using a water balance equation. The field data collected in 2011 were used for training and validation of the model. The model was trained based on the error back propagation algorithm with sigmoid activation function. Simulation results for the independent training and testing data series showed that the model can perform well in simulating surface runoff from the study plots. The developed model has a main advantage that there is no requirement for any prior assumptions regarding the processes involved. ANN model thus can be a good tool to predict surface runoff from rice paddy fields.

• Journal of IKEEE
• /
• v.21 no.2
• /
• pp.115-122
• /
• 2017

In vehicular safety service, every vehicle broadcasts Basic Safety Message (BSM) periodically to inform neighbor vehicles of host vehicle information. However, this can cause network congestion in a region that is crowded with vehicles resulting in a reduction in the message delivery ratio and an increase in the end-to-end delay. Therefore, it could destabilize the vehicular safety service system. In this paper, in order to improve the congestion control and to consider the hidden node problem, we propose a congestion control scheme using entire network congestion level estimation combined with transmission power control, data rate control and time slot based transmission control algorithm. The performance of this scheme is evaluated using a Qualnet network simulator. The simulation result shows that our scheme mitigates network congestion in heavy traffic cases and enhances network capacity in light traffic cases, so that packet error rate is perfectly within 10% and entire network load level is maintained within 60~70%. Thus, it can be concluded that the proposed congestion control scheme has quite good performance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.31-36
• /
• 2012

In this paper, we proposed spectrum sensing using cooperative relay to solve problem of sensing performance degradation due to CPE (Customer-Premises equipments) which causes low SNR (signal-to-noise ratio) problem. In cooperative communication system, AF (amplify-and-forward) and DF (decoded-and-forward) is widely used for relay mechanism. Also, it is expected that cooperative relay scheme guarantees the high sensing performance by its diversity gain. Based on these backgrounds, in this paper, we apply to cooperative relay scheme to the CR (Cognitive Radio) system, and simulation results show comparison of the sensing performance.

• Journal of Advanced Navigation Technology
• /
• v.12 no.6
• /
• pp.627-633
• /
• 2008

In the case of traffic accidents, the broadcasting methods used in the mobile ad hoc network (MANET) cannot applied to transmit reliable message since moving high-speed in vehicular ad hoc networks (VANET) environments. In this paper, in order to guarantee transmitting reliable messages, we propose a collision avoidance method based-on directional antenna in VANET. In order to reduce interference from omni-broadcasting and to avoid hidden node problem from moving high-speed, we employed a forward-handed and backward directional antenna. The authors simulated the proposed method based on directional antenna and showed that the proposed method has been improved in respect to network utilization compared to existing VANET protocols.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.2
• /
• pp.267-274
• /
• 2015

In this paper the optimal structure of a neural network based on OpenCV for a golf ball recognition and the intensity of ROI(Region Of Interest) are calculated. The system is composed of preprocess, image processing and machine learning, and a learning model is obtained by multi-layer perceptron using the inputs of 7 Hu's invariant moments, box ration extracted by vertical and horizontal length or ${\pi}$ calculated by area of ROI. Simulation results show that optimal numbers of hidden layer and the node of neuron are selected to 2 and 9 respectively considering the recognition rate and running time, and optimal intensity of ROI is selected to 200.

• Journal of Satellite, Information and Communications
• /
• v.7 no.1
• /
• pp.7-12
• /
• 2012

In this paper, we proposed spectrum sensing using cooperative relay to solve problem of sensing performance degradation due to CPE (Customer-Primise equipments) which causes low SNR (signal-to-noise ratio) problem. In cooperative communication system, AF (amplify-and-forward) and DF (decoded-and-forward) is widely used for relay mechanism. Also, it is expected that cooperative relay scheme guarantees the high sensing performance by its diversity gain. Based on these backgrounds, in this paper, we apply to cooperative relay scheme to the CR (cognitive radio) system, and simulation results show comparison of the sensing performance between AF and DF.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.951-969
• /
• 2017

In this paper, we newly propose a traffic information service model that collects traffic information sensed by an individual vehicle in real time by using a smart device, and which enables drivers to share traffic information on all roads in real time using an application installed on a smart device. In particular, when the driver requests traffic information for a specific area, the proposed driver-personalized service model provides him/her with traffic information on the driving directions in advance by predicting the driving directions of the vehicle based on the learning of the driving records of each driver. To do this, we propose a traffic information management model to process and manage in real time a large amount of online-generated traffic information and traffic information requests generated by each vehicle. We also propose a road node-based indexing technique to efficiently store and manage location-based traffic information provided by each vehicle. Finally, we propose a driving learning and prediction model based on the hidden Markov model to predict the driving directions of each driver based on the driver's driving records. We analyze the traffic information processing performance of the proposed model and the accuracy of the driving prediction model using traffic information collected from actual driving vehicles for the entire area of Seoul, as well as driving records and experimental data.

• Journal of Biosystems Engineering
• /
• v.43 no.4
• /
• pp.352-361
• /
• 2018

Purpose: The objective of this study was to develop a multilayer perceptron (MLP) model to estimate solar radiation using a solar module. Methods: Data for the short-circuit current of a solar module and other environmental parameters were collected for a year. For MLP learning, 14,400 combinations of input variables, learning rates, activation functions, numbers of layers, and numbers of neurons were trained. The best MLP model employed the batch backpropagation algorithm with all input variables and two hidden layers. Results: The root-mean-squared error (RMSE) of each learning cycle and its average over three repetitions were calculated. The average RMSE of the best artificial neural network model was $48.13W{\cdot}m^{-2}$. This result was better than that obtained for the regression model, for which the RMSE was $66.67W{\cdot}m^{-2}$. Conclusions: It is possible to utilize a solar module as a power source and a sensor to measure solar radiation for an agricultural sensor node.