• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.9-11
• /
• 2006

This paper presents JPEG quantization table design using RD optimization and neural network. Using R-D optimization, quantization table with good performance can be obtained. However, it is time-consuming and difficult to adopt to embedded systems. In this paper, a new quantization table design method is proposed using R-D optimization and neural network. Neural network learns the quantization table obtained from R-D optimization and produces a quantization table for the Images. The proposed system is applied to Yale face data. From the simulation results, it has been shown that the proposed codec has better performance than JPEG.

• The Journal of Korea Robotics Society
• /
• v.17 no.2
• /
• pp.133-141
• /
• 2022

This paper introduces model compression algorithms which make a deep neural network smaller and faster for embedded systems. The model compression algorithms can be largely categorized into pruning, quantization and knowledge distillation. In this study, gradual pruning, quantization aware training, and knowledge distillation which learns the activation boundary in the hidden layer of the teacher neural network are integrated. As a large deep neural network is compressed and accelerated by these algorithms, embedded computing boards can run the deep neural network much faster with less memory usage while preserving the reasonable accuracy. To evaluate the performance of the compressed neural networks, we evaluate the size, latency and accuracy of the deep neural network, DenseNet201, for image classification with CIFAR-10 dataset on the NVIDIA Jetson Xavier.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.1015-1018
• /
• 1999

This paper describes a vector quantization for speech signal coding using neural networks. We processed speech signal using LPC method that extracts speech signal feature, and speech signal feature is quantized using competitive neural network kohonen self-organization feature map.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.2
• /
• pp.325-328
• /
• 1996

In this paper, we proposed an estimation method of a posterior probability and PDF(Probability density function) using a feed forward neural network and code books of VQ(vector quantization). In this study, We estimates a posterior probability and probability density function, which compose a new parameter with well-known Mel cepstrum and verificate the performance for the five vowels taking from syllables by NN(neural network) and PNN(probabilistic neural network). In case of new parameter, showed the best result by probabilistic neural network and recognition rates are average 83.02%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.800-804
• /
• 2005

This paper presents a fuzzy learning rule which is the fuzzified version of LVQ(Learning Vector Quantization). This fuzzy learning rule 3 uses fuzzy learning rates. instead of the traditional learning rates. LVQ uses the same learning rate regardless of correctness of classification. But, the new fuzzy learning rule uses the different learning rates depending on whether classification is correct or not. The new fuzzy learning rule is integrated into the improved IAFC(Integrated Adaptive Fuzzy Clustering) neural network. The improved IAFC neural network is both stable and plastic. The iris data set is used to compare the performance of the supervised IAFC neural network 3 with the performance of backprogation neural network. The results show that the supervised IAFC neural network 3 is better than backpropagation neural network.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.4
• /
• pp.374-381
• /
• 1991

As a diagnostic image of hospitl, the utilization of digital image is steadily increasing. Image coding is indispensable for storing and compressing an enormous amount of diagnostic images economically and effectively. In this paper adaptive two stage vector quantization based on Kohonen's neural network for the compression of cardioangiography among typical angiography of radiographic image sequences is presented and the performance of the coding scheme is compare and gone over. In an attempt to exploit the known characteristics of changes in cardioangiography, relatively large blocks of image are quantized in the first stage and in the next stage the bloks subdivided by the threshold of quantization error are vector quantized employing the neural network of frequency sensitive competitive learning. The scheme is employed because the change produced in cardioangiography is due to such two types of motion as a heart itself and body motion, and a contrast dye material injected. Computer simulation shows that the good reproduction of images can be obtained at a bit rate of 0.78 bits/pixel.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.4
• /
• pp.151-156
• /
• 2021

Low-end IoT devices do not have enough computation and memory resources for DNN learning and inference. Integer quantization of real-type neural network models can reduce model size, hardware computational burden, and power consumption. This paper describes the design and implementation of a web-based quantization platform for CNN deep learning accelerator chips. In the web service platform, we implemented visualization of the model through a convenient UI, analysis of each step of inference, and detailed editing of the model. Additionally, a data augmentation function and a management function of files that store models and inference intermediate results are provided. The implemented functions were verified using three YOLO models.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.41 no.5
• /
• pp.533-540
• /
• 1992

The Self Creating and Organizing (SCO) is a new architecture and one of the unsupervized learning algorithm for the artificial neural network. SCO begins with only one output node which has a sufficiently wide response range, and the response ranges of all the nodes decrease automatically whether adapting the weights of existing node or creating a new node. It is compared to the Kohonen's Self Organizing Feature Map (SOFM). The results show that SCONN has lots of advantages over other competitive learning architecture.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.2
• /
• pp.276-283
• /
• 1994

Using a neural network for vector quantization, we can expect to have better codebook design algorithm for its adaptive process. Also, the designed codebook puts the codewords in order by its self-organizing characteristics, which makes it possible to partially search the codebook for real time process. To exploit these features of the neural network, in this paper, we propose a new codebook design algorithm that modified the KSFM(Kohonen`s Self-organizing Feature Map) and then combines the K-means algorithm. Experimental results show the performance improvment and the ability of the partical seach of the codebook for the real time process.

• Journal of Mechanical Science and Technology
• /
• v.19 no.2
• /
• pp.529-539
• /
• 2005

The development of a fast, accurate, and inexpensive position-controlled pneumatic actuator that may be applied to various practical positioning applications with various external loads is described in this paper. A novel modified pulse-width modulation (MPWM) valve pulsing algorithm allows on/off solenoid valves to be used in place of costly servo valves. A comparison between the system response of the standard PWM technique and that of the modified PWM technique shows that the performance of the proposed technique was significantly increased. A state-feedback controller with position, velocity and acceleration feedback was successfully implemented as a continuous controller. A switching algorithm for control parameters using a learning vector quantization neural network (LVQNN) has newly proposed, which classifies the external load of the pneumatic actuator. The effectiveness of this proposed control algorithm with smooth switching control has been demonstrated through experiments with various external loads.