• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.585-594
• /
• 2007

The back propagation algorithm took a long time to learn the input patterns and was difficult to train the additional or repeated learning patterns. So Aleksander proposed the binary neural network which could overcome the disadvantages of BP Network. But it had the limitation of repeated learning and was impossible to extract a generalized pattern. In this paper, we proposed a dynamic 3 dimensional Neuro System which was consisted of a learning network which was based on weightless neural network and a feedback module which could accumulate the characteristic. The proposed system was enable to train additional and repeated patterns. Also it could be produced a generalized pattern by putting a proper threshold into each learning-net's discriminator which was resulted from learning procedures. And then we reused the generalized pattern to elevate the recognition rate. In the last processing step to decide right category, we used maximum response detector. We experimented using the MNIST database of NIST and got 99.3% of right recognition rate for training data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.9
• /
• pp.1682-1688
• /
• 2008

The Counterpropagation algorithm(CP) is a combination of Kohonen competition network as a hidden layer and the outstar structure of Grossberg as an output layer. CP has been used in many real applications for pattern matching, classification, data compression and statistical analysis since its learning speed is faster than other network models. However, due to the Kohonen layer's winner-takes-all strategy, it often causes instable learning and/or incorrect pattern classification when patterns are relatively diverse. Also, it is often criticized by the sensitivity of performance on the learning rate. In this paper, we propose an enhanced CP that has multiple Kohonen layers and dynamic controlling facility of learning rate using the frequency of winner neurons and the difference between input vector and the representative of winner neurons for stable learning and momentum learning for controlling weights of output links. A real world application experiment - pattern recognition from passport information - is designed for the performance evaluation of this enhanced CP and it shows that our proposed algorithm improves the conventional CP in learning and recognition performance.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.7
• /
• pp.27-39
• /
• 2022

The exchange rate is an important macroeconomic variable that influences internal and external balances. Nepal follows a dual exchange rate such that the Nepali rupee (NPR) is pegged with the Indian rupee (INR) but floats with the United States dollar (USD) and all other currencies. There have been very few studies on the exchange rate of Nepal, of which the majority focus on the bivariate relationship between exchange rate and another variable. However, this paper analyses the multivariate relationship between the USD-NPR exchange rate and major macroeconomic variables. Determinants of Nepal's exchange rate have been derived with multiple regression using the ordinary least square (OLS) approach. Since the explanatory variables could not significantly capture the movement of the dependent variable, a long-run relationship between Nepal and India's exchange rate has been analyzed using Engle-Granger cointegration to establish a relationship as suggested by a graphical representation. This explains that Nepal's exchange rate long run is determined by India's exchange rate than its own fundamentals. In addition, the macro-linkages of Nepal's macroeconomic variables have been analyzed using Standard Vector Autoregressive models followed by impulse response analysis which is useful for policy decisions. Some policy implications indicating the sustainability of Nepal's pegged regime have been drawn based on the empirical analysis.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.303-310
• /
• 2023

A single vision system limits the ability to accurately understand the spatial constraints and interactions between robots and dynamic workers caused by gantry robots and collaborative robots during production manufacturing. In this paper, we propose a 3D pose registration method for dynamic workers based on a multi-domain vision system for safety monitoring in manufacturing environments. This method uses OpenPose, a deep learning-based posture estimation model, to estimate the worker's dynamic two-dimensional posture in real-time and reconstruct it into three-dimensional coordinates. The 3D coordinates of the reconstructed multi-domain vision system were aligned using the ICP algorithm and then registered to a single 3D coordinate system. The proposed method showed effective performance in a manufacturing process environment with an average registration error of 0.0664 m and an average frame rate of 14.597 per second.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1223-1230
• /
• 2020

Recently, extensive studies have been conducted to apply deep learning to reinforcement learning to solve the state-space problem. If the state-space problem was solved, reinforcement learning would become applicable in various fields. For example, users can utilize dance-tutorial systems to learn how to dance by watching and imitating a virtual instructor. The instructor can perform the optimal dance to the music, to which reinforcement learning is applied. In this study, we propose a method of reinforcement learning in which the action space is dynamically adjusted. Because actions that are not performed or are unlikely to be optimal are not learned, and the state space is not allocated, the learning time can be shortened, and the state space can be reduced. In an experiment, the proposed method shows results similar to those of traditional Q-learning even when the state space of the proposed method is reduced to approximately 0.33% of that of Q-learning. Consequently, the proposed method reduces the cost and time required for learning. Traditional Q-learning requires 6 million state spaces for learning 100,000 times. In contrast, the proposed method requires only 20,000 state spaces. A higher winning rate can be achieved in a shorter period of time by retrieving 20,000 state spaces instead of 6 million.

• Journal of Communications and Networks
• /
• v.10 no.1
• /
• pp.38-43
• /
• 2008

In this paper, adaptive channel borrowing approach fuzzy neural networks for load balancing (ACB-FNN) is presented to maximized the number of served calls and the depending on asymmetries traffic load problem. In a wireless network, the call's arrival rate, the call duration and the communication overhead between the base station and the mobile switch center are vague and uncertain. A new load balancing algorithm with cell involved negotiation is also presented in this paper. The ACB-FNN exhibits better learning abilities, optimization abilities, robustness, and fault-tolerant capability thus yielding better performance compared with other algorithms. It aims to efficiently satisfy their diverse quality-of-service (QoS) requirements. The results show that our algorithm has lower blocking rate, lower dropping rate, less update overhead, and shorter channel acquisition delay than previous methods.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.19-27
• /
• 2021

Fireworks Algorithm (FWA) is a new heuristic swarm intelligent algorithm inspired by the natural phenomenon of the fireworks explosion. Though it is an effective algorithm for solving optimization problems, FWA has a slow convergence rate and less information sharing between individuals. In this paper, we improve the FWA. Firstly, explosion operator and explosion amplitude are analyzed in detail. The coefficient of explosion amplitude and explosion operator change dynamically with iteration to balance the exploitation and exploration. The convergence performance of FWA is improved. Secondly, differential evolution and commensal learning (CDE) significantly increase the information sharing between individuals, and the diversity of fireworks is enhanced. Comprehensive experiment and comparison with CDE, FWA, and VACUFWA for the 13 benchmark functions show that the improved algorithm was highly competitive.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.11-16
• /
• 2005

Recently, there are a lot of endeavor to implement a fuzzy theory to artificial neural network. Goh proposed the fuzzy single layer perceptron algorithm and advanced fuzzy perceptron based on the generalized delta rule to solve the XOR Problem and the classical Problem. However, it causes an increased amount of computation and some difficulties in application of the complicated image recognition. In this paper, we propose an enhanced fuzzy single layer Perceptron using the dynamic adjustment of threshold. This method is applied to the XOR problem, which used as the benchmark in the field of pattern recognition. The method is also applied to the recognition of digital image for image application. In a result of experiment, it does not always guarantee the convergence. However, the network show improved the learning time and has the high convergence rate.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.6
• /
• pp.289-296
• /
• 2018

Drone detection in FMCW radar system needs complex techniques because a drone beat frequency is highly dynamic and unpredictable. Therefore, the current static signal processing algorithms cannot show appropriate detection accuracy. With dynamic signal fluctuation and environmental clutters, it can fail to detect a drone or make false detection. It affects to the radar system integrity and safety. Constant false alarm rate (CFAR), one of famous static signal process algorithm is effective for static environment. But for drone detection, it shows low detection accuracy. In this paper, we suggest neural network based FMCW radar system for detecting a drone. We use recurrent neural network (RNN) because it is the effective neural network for signal processing. In our FMCW radar system, one transmitter emits FMCW signal and four-way fixed receivers detect reflected drone beat frequency. The coordinate of the drone can be calculated with four receivers information by triangulation. Therefore, RNN only learns and inferences reflected drone beat frequency. It helps higher learning and detection accuracy. With several drone flight experiments, RNN shows false detection rate and detection accuracy as 21.1% and 96.4%, respectively.

• Journal of Information Processing Systems
• /
• v.19 no.2
• /
• pp.149-163
• /
• 2023

Affected by external factors, errors in time series data collected by sensors are common. Using the traditional method of constraining the speed change rate to clean the errors can get good performance. However, they are only limited to the data of stable changing speed because of fixed constraint rules. Actually, data with uneven changing speed is common in practice. To solve this problem, an online cleaning algorithm for time series data based on dynamic speed change rate constraints is proposed in this paper. Since time series data usually changes periodically, we use the extreme learning machine to learn the law of speed changes from past data and predict the speed ranges that change over time to detect the data. In order to realize online data repair, a dual-window mechanism is proposed to transform the global optimal into the local optimal, and the traditional minimum change principle and median theorem are applied in the selection of the repair strategy. Aiming at the problem that the repair method based on the minimum change principle cannot correct consecutive abnormal points, through quantitative analysis, it is believed that the repair strategy should be the boundary of the repair candidate set. The experimental results obtained on the dataset show that the method proposed in this paper can get a better repair effect.