• Journal of IKEEE
• /
• v.25 no.1
• /
• pp.180-192
• /
• 2021

One widely used algorithm for image recognition and pattern detection is the convolution neural network (CNN). To efficiently handle convolution operations, which account for the majority of computations in the CNN, we use hardware accelerators to improve the performance of CNN applications. In using these hardware accelerators, the CNN fetches data from the off-chip DRAM, as the massive computational volume of data makes it difficult to derive performance improvements only from memory inside the hardware accelerator. In other words, data communication between off-chip DRAM and memory inside the accelerator has a significant impact on the performance of CNN applications. In this paper, a simulator for the CNN is developed to analyze the main memory or DRAM access with respect to the size of the on-chip memory or global buffer inside the CNN accelerator. For AlexNet, one of the CNN architectures, when simulated with increasing the size of the global buffer, we found that the global buffer of size larger than 100kB has 0.8x as low a DRAM access count as the global buffer of size smaller than 100kB.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.154-162
• /
• 2003

In this paper, Associative Memory with Cellular Neural Networks classifies and recognizes image patterns as an operator applied to image process. CNN processes nonlinear data in real-time like neural networks, and made by cell which communicates with each other directly through its neighbor cells as the Cellular Automata does. It is applied to the optimization problem, associative memory, pattern recognition, and computer vision. Image processing with CNN is appropriate to 2-D images, because each cell which corresponds to each pixel in the image is simultaneously processed in parallel. This paper shows the method for designing the structure of associative memory based on CNN and getting output image by choosing the most appropriate weight pattern among the whole learned weight pattern memories. Each template represents weight values between cells and updates them by learning. Hebbian rule is used for learning template weights and LMS algorithm is used for classification.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.411-412
• /
• 2023

Speech emotion recognition(SER) is one of the interesting topics in the machine learning field. By developing SER, we can get numerous benefits. By using a convolutional neural network and Long Short Term Memory (LSTM ) method as a part of Artificial intelligence, the SER system can be built.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.6
• /
• pp.545-555
• /
• 1991

In this paper, We discuss optical implementation of new optical adaptive patern recognition system based on single layer perception with learning capability and associative memory model having error corrective capability. The single layer perceptron is optically implemented by using 2 D LCTV spatial light modulators through the nonlinear quantization and polarization encoding methods, and 2 D hopfield associative memory is also implemented by using multifocus holographic lens. From some experimental results on classfication of Arabic numbers into even & edd numbers, it is shown that the proposed system can classify the patterns to the right classes correctly even for the partial and erronenous input patterns. Accordingly, the proposed optical adaptive pattern recognition system can be suggested for practical application in the fields of image processing and pattern recognition.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_1
• /
• pp.693-698
• /
• 2021

As technology advances, there is increasing need for research in different fields where this technology is applied. On of the most researched topic in computer vision is Human activity recognition (HAR), which has widely been implemented in various fields which include healthcare, video surveillance and education. We therefore present in this paper a human activity recognition system based on scale and rotation while employing the Kinect depth sensors to obtain the human skeleton joints. In contrast to previous approaches that use joint angles, in this paper we propose that each limb has an angle with the X, Y, Z axes which we employ as feature vectors. The use of the joint angles makes our system scale invariant. We further calculate the body relative direction in the egocentric coordinates in order to provide the rotation invariance. For the system parameters, we employ 8 limbs with their corresponding angles each having the X, Y, Z axes from the coordinate system as feature vectors. The extracted features are finally trained and tested with the Long short term memory (LSTM) Network which gives us an average accuracy of 98.3%.

• Communications for Statistical Applications and Methods
• /
• v.29 no.2
• /
• pp.161-176
• /
• 2022

There has been active research in image classification using deep learning convolutional neural network (CNN) models. ImageNet large-scale visual recognition challenge (ILSVRC) (2010-2017) was one of the most important competitions that boosted the development of efficient deep learning algorithms. This paper introduces and compares six monumental models that achieved high prediction accuracy in ILSVRC. First, we provide a review of the models to illustrate their unique structure and characteristics of the models. We then compare those models under a unified framework. For this reason, additional devices that are not crucial to the structure are excluded. Four popular data sets with different characteristics are then considered to measure the prediction accuracy. By investigating the characteristics of the data sets and the models being compared, we provide some insight into the architectural features of the models.

• The Journal of the Korea Contents Association
• /
• v.10 no.6
• /
• pp.80-90
• /
• 2010

In this paper, we introduce some issues to implement an agent system to support service mobility in home network environment, and describe detailed design method in terminal as well as server agent. Specifically, we describe user recognition module, signaling message receiving/parsing module of terminal agent and signaling message receiving/parsing module, multimedia switching module, memory management module of server agent. We define several parameters managed in IP sharing device and design binding table structure to support mobility. And we utilize M/M/1/K queueing theory to obtain relations between memory size, blocking probability and memory utilization. From the obtained results, we show that memory size can be predicted in server agent mounted on IP sharing device.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.480-488
• /
• 2022

Images of tobacco retail licenses have complex unstructured characteristics, which is an urgent technical problem in the robot process automation of tobacco marketing. In this paper, a novel recognition approach using a double attention mechanism is presented to realize the automatic recognition and information extraction from such images. First, we utilized a DenseNet network to extract the license information from the input tobacco retail license data. Second, bi-directional long short-term memory was used for coding and decoding using a continuous decoder integrating dual attention to realize the recognition and information extraction of tobacco retail license images without segmentation. Finally, several performance experiments were conducted using a largescale dataset of tobacco retail licenses. The experimental results show that the proposed approach achieves a correction accuracy of 98.36% on the ZY-LQ dataset, outperforming most existing methods.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.159-172
• /
• 2024

The number of healthcare products available for pets has increased in recent times, which has prompted active research into wearable devices for pets. However, the data collected through such devices are limited by outliers and missing values owing to the anomalous and irregular characteristics of pets. Hence, we propose pet behavior recognition based on a hybrid one-dimensional convolutional neural network (CNN) and long short- term memory (LSTM) model using pet wearable devices. An Arduino-based pet wearable device was first fabricated to collect data for behavior recognition, where gyroscope and accelerometer values were collected using the device. Then, data augmentation was performed after replacing any missing values and outliers via preprocessing. At this time, the behaviors were classified into five types. To prevent bias from specific actions in the data augmentation, the number of datasets was compared and balanced, and CNN-LSTM-based deep learning was performed. The five subdivided behaviors and overall performance were then evaluated, and the overall accuracy of behavior recognition was found to be about 88.76%.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.49.2-49
• /
• 2002

This paper describes the configuration of a multi-agent system that can recognize human intentions. This system constructs ontologies of human intentions and enables knowledge acquisition and sharing between intelligent agents operating in different environments. This is achieved by using a bi-directional associative memory network. The process of intention recognition is based on fuzzy association inferences. This paper shows the process of information sharing by using ontologies. The purpose of this research is to create human-centered systems that can provide a natural interface in their interaction with people.