• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1552-1559
• /
• 2021

Convolution neural networks (CNNs) show notable performance in image processing and are used as representative core models. CNNs extract and learn features from large amounts of train dataset. In general, it has a structure in which a convolution layer and a fully connected layer are stacked. The core of CNN is the convolution layer. The size of the kernel used for feature extraction and the number that affect the depth of the feature map determine the amount of weight parameters of the CNN that can be learned. These parameters are the main causes of increasing the computational complexity and memory usage of the entire neural network. The most computationally expensive components in CNNs are fully connected and spatial convolution computations. In this paper, we propose a Fourier Convolution Neural Network that performs the operation of the convolution layer in the Fourier domain. We work on modifying and improving the amount of computation by applying the fast fourier transform method. Using the MNIST dataset, the performance was similar to that of the general CNN in terms of accuracy. In terms of operation speed, 7.2% faster operation speed was achieved. An average of 19% faster speed was achieved in experiments using 1024x1024 images and various sizes of kernels.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.4
• /
• pp.341-348
• /
• 1990

This paper describes an algorithm for evaluating the Loss of Load Probability (LOLP) and calculating the production cost for all the generators in the system using Fast Hartley Transform (FHT). It also suggests the deconvolution procedure which is necessary for the generation expansion planning. The FHT is as fast as or faster than the Fast Fourier Transform (FFT) and serves for all the uses such as spectral, digital processing, and convolution to which the FFT is normally applied. The transformed function using FFT has complex numbers. However, the transformed function using FHT has real numbers and the convolution become quite simple. This method has been applied for the IEEE reliability test system and practical size model system. The test results show the effectiveness of the proposed method.

• Proceedings of the KIEE Conference
• /
• 1988.11a
• /
• pp.131-134
• /
• 1988

This Paper describes a algorithm for evaluating the loss of load probability of a generating system using Fast Hartley Transform. The Fast Hartley Transform(FHT) Is as fast as or faster than the Fast Fourier Transform(FHT) and serves for all the uses such as spectral, digital processing and convolution to which the FFT is at present applied. The method has been tested by applying to IEEE reliability test system and the effectiveness is demonstrated.

• Journal of Korea Multimedia Society
• /
• v.23 no.6
• /
• pp.756-764
• /
• 2020

A typical algorithm used for image analysis is the Convolutional Neural Network(CNN). R-CNN, Fast R-CNN, Faster R-CNN, etc. have been studied to improve the performance of the CNN, but they essentially require large amounts of data and high algorithmic complexity., making them inappropriate for small and medium-sized services. Therefore, in this paper, the image label prediction algorithm based on CNN with collaborative layer with low complexity, high accuracy, and small amount of data was proposed. The proposed algorithm was designed to replace the part of the neural network that is performed to predict the final label in the existing deep learning algorithm by implementing collaborative filtering as a layer. It is expected that the proposed algorithm can contribute greatly to small and medium-sized content services that is unsuitable to apply the existing deep learning algorithm with high complexity and high server cost.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.263-264
• /
• 2006

In this paper, an efficient and fast algorithm to reduce calculation amount of FIR(Finite Impulse Responses) filtering is proposed. Proposed algorithm enables arbitrary size of parallel processing, and their structures are also easily derived. Furthermore, it is shown that the number of multiplication/sample is reduced, and number of instructions using MAC(Multiplication and Accumulation) processor are also reduced. For theoretical improvement, numbers of sub filters are compared with those of conventional algorithm. In addition to the theoretical improvement, it is shown that number of element for hardwired implementation are reduced comparison to those of the conventional algorithm.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.4
• /
• pp.625-634
• /
• 2006

In this paper, an efficient and fast algorithm to reduce calculation amount of FIR(Finite Impulse Responses) filtering is proposed. Proposed algorithm enables arbitrary size of parallel processing, and their structures are also easily derived. Furthermore, it is shown that the number of multiplication/sample is remarkably reduced. For theoretical improvement, numbers of sub filters are compared with those of conventional algorithm. In addition to the theoretical improvement, it is shown that number of element for hardwired implementation are reduced comparison to those of the conventional algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.187-194
• /
• 2005

In this paper, an efficient and fast algerian to reduce calculation amount of FIR(Finite Impulse Responses) filtering is proposed. Proposed algorithm enables arbitrary size of parallel processing, and their structures are also easily derived. Furthermore, it is shown that the number of multiplication/sample is reduced, and number of instructions using MAC(Multiplication and Accumulation) processor are also reduced. For theoretical improvement numbers of sub filters are compared with those of conventional algorithm. In addition to the theoretical improvement, it is shown that number of element for hardwired implementation are reduced comparison to those of the conventional algorithm.

• Journal of Broadcast Engineering
• /
• v.14 no.5
• /
• pp.543-550
• /
• 2009

The most widely used block convolution method is the overlap save algorithm (OSA), where a block of M data to be convolved with a filter is concatenated with the previous block and 2M-point FFT and multiplications are performed for this overlapped block. By discarding half of the results, we obtain linear convolution results from the circular convolution. This paper proposes a new transform which reduces the block size to only M for the block convolution. The proposed transform can be implemented as the M multiplications followed by M-point FFT Hence, existing efficient FFT libraries and hardware can be exploited for the implementation of proposed method. Since the required transform size is half that of the conventional method, the overall computational complexity is reduced. Also the reduced transform size results in the reduction of data access time and cash miss-hit ratio, and thus the overall CPU time is reduced. Experiments show that the proposed method requires less computation time than the conventional OSA.

• The KIPS Transactions:PartB
• /
• v.13B no.1 s.104
• /
• pp.27-34
• /
• 2006

In this study, we propose this new algorithm that generates score function in ICA(Independent Component Analysis) using entropy theory. To generate score function, estimation of probability density function about original signals are certainly necessary and density function should be differentiated. Therefore, we used kernel density estimation method in order to derive differential equation of score function by original signal. After changing formula to convolution form to increase speed of density estimation, we used FFT algorithm that can calculate convolution faster. Proposed score function generation method reduces the errors, it is density difference of recovered signals and originals signals. In the result of computer simulation, we estimate density function more similar to original signals compared with Extended Infomax and Fixed Point ICA in blind source separation problem and get improved performance at the SNR(Signal to Noise Ratio) between recovered signals and original signal.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.365-372
• /
• 2022

The accurate object recognition is important for the precise and accurate manipulation. To enhance the recognition performance, we can use various types of sensors. In general, acquired data from sensors have a high sampling rate. So, in the past, the RNN-based model is commonly used to handle and analyze the time-series sensor data. However, the RNN-based model has limitations of excessive parameters. CNN-based model also can be used to analyze time-series input data. However, CNN-based model also has limitations of the small receptive field in early layers. For this reason, when we use a CNN-based model, model architecture should be deeper and heavier to extract useful global features. Thus, traditional methods like RN N -based and CN N -based model needs huge amount of learning parameters. Recently studied result shows that Fast Fourier Convolution (FFC) can overcome the limitations of traditional methods. This operator can extract global features from the first hidden layer, so it can be effectively used for feature extracting of sensor data that have a high sampling rate. In this paper, we propose the algorithm to recognize objects using tactile sensor data and the FFC model. The data was acquired from 11 types of objects to verify our posed model. We collected pressure, current, position data when the gripper grasps the objects by random force. As a result, the accuracy is enhanced from 84.66% to 91.43% when we use the proposed FFC-based model instead of the traditional model.