• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.41 no.8
• /
• pp.914-921
• /
• 1992

In this paper, we introduce a Walsh network and an LMS algorithm, and show how these can be realized as an adaptive equalizer. The Walsh network is built from a set of Walsh and Block pulse functions. In the LMS algorithm, the convergence factor is an important design parameter because it governs stability and convergence speed, which depend on the proper choice of the convergence facotr. The conventional adaptation techniques use a fixed time constant convergence factor by the method of trial and error. In this paper, we propose an optimal method in the choice of the convergence factor. The proposed algorithm depends on the received signal and the output of the Walsh network in real time.

• Proceedings of the KIEE Conference
• /
• 1991.11a
• /
• pp.357-360
• /
• 1991

In this paper, we have introduced a network and showed how this can be realised as an adaptive equalizer. The walsh equlizer is built from a set of Walsh-Block pulse functions and LMS algorithms with the optimal convergence factor(C.F.). The convergence and the adaptation speed of this algorithms depends on the proper choice of a design factor $\mu$ called the C.F.. Conventional adaptation techniques use the fixed time constant C.F. by the method of trial and error. In this paper, we propose to adaptive C.F. which are optimally tailored to adapt C.F. in real time so that their values are kept optimum for a new set of input variables.

• Journal of the Korea Convergence Society
• /
• v.10 no.12
• /
• pp.29-34
• /
• 2019

If it takes much time to calculate the fitness of the solution in genetic algorithms, it is essential to create a metamodel. Much research has been completed to improve the performance of metamodels. In this study, we tried to get a better performance of metamotel using discrete Walsh transform in discrete domain. We transforms the basis of the solution and creates a metamodel using the transformed solution. We experimented with NK-landscape, a representative function of the pseudo-boolean function, and provided empirical evidence on the performance of the proposed model. When we performed the genetic algorithm using the proposed model, we confirmed that the genetic algorithm found a better solution. In particular, our metamodel showed better performance than that using the radial basis function network that modified the similarity function for the discrete domain.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.1
• /
• pp.6-12
• /
• 2004

Identification rate and time are very important in the identification of RFID tag, and the tag requires simple structure to use economically large quantity of tags. These factors make the MAC protocols of wired or wireless network environment result in different requirements. In the paper, we propose a method to apply spread spectrum scheme using orthogonal channel via Walsh function as the anti-collision communication system for the purpose of non-collision identification of multiple tags, and consider its property. The proposed system use two step identification. in the first step, collision is resolved via constructing to respond after specific delay time based on unique n, and conventional polling scheme follows in the second step.

• Journal of the Korean Institute of Gas
• /
• v.2 no.4
• /
• pp.60-66
• /
• 1998

The hot stove system is a process that is continuously and constantly generating the hot combustion air required for the blast furnace. The hot stove process is considered as a main energy consumption process because it consumes about $20\%$ of the total energy in steel making works. So, many researchers have interested in the improvement of the heat efficiency of the hot stove to reduce the energy consumption. But they have difficulties in improving the heat efficiency of the hot stove because there is no precise information on heat transformation occurring during the heating period. In order to model the relationship between the operating conditions and heat efficiencies, we propose a neural network using feature extraction as one of experimental modeling methods. In order to show the performance of the model, we compare it with Partial Least Square (PLS) method. Both methods have similarities in using the dimension reduction technique. And then we present the simulation results on the prediction of the heat efficiency of the hot stove.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.974-976
• /
• 1995

Segmentation of image data is an important problem in computer vision, remote sensing, and image analysis. Most objects in the real world have textured surfaces. Segmentation based on texture information is possible even if there are no apparent intensity edges between the different regions. There are many existing methods for texture segmentation and classification, based on different types of statistics that can be obtained from the gray-level images. In this paper, we use a neural network model --- ART-2 (Adaptive Resonance Theory) for textures in an image, proposed by Carpenter and Grossberg. In our experiments, we use Walsh matrix as feature value for textured image.

• The korean journal of orthodontics
• /
• v.52 no.4
• /
• pp.268-277
• /
• 2022

Objective: Poor experience with Invisalign treatment affects patient compliance and, thus, treatment outcome. Knowing the potential discomfort level in advance can help orthodontists better prepare the patient to overcome the difficult stage. This study aimed to construct artificial neural networks (ANNs) to predict patient experience in the early stages of Invisalign treatment. Methods: In total, 196 patients were enrolled. Data collection included questionnaires on pain, anxiety, and quality of life (QoL). A four-layer fully connected multilayer perception with three backpropagations was constructed to predict patient experience of the treatment. The input data comprised 17 clinical features. The partial derivative method was used to calculate the relative contributions of each input in the ANNs. Results: The predictive success rates for pain, anxiety, and QoL were 87.7%, 93.4%, and 92.4%, respectively. ANNs for predicting pain, anxiety, and QoL yielded areas under the curve of 0.963, 0.992, and 0.982, respectively. The number of teeth with lingual attachments was the most important factor affecting the outcome of negative experience, followed by the number of lingual buttons and upper incisors with attachments. Conclusions: The constructed ANNs in this preliminary study show good accuracy in predicting patient experience (i.e., pain, anxiety, and QoL) of Invisalign treatment. Artificial intelligence system developed for predicting patient comfort has potential for clinical application to enhance patient compliance.

• Journal of Intelligence and Information Systems
• /
• v.17 no.2
• /
• pp.97-107
• /
• 2011

Nowadays there are a lot of issues about copyright infringement in the Internet world because the digital content on the network can be copied and delivered easily. Indeed the copied version has same quality with the original one. So, copyright owners and content provider want a powerful solution to protect their content. The popular one of the solutions was DRM (digital rights management) that is based on encryption technology and rights control. However, DRM-free service was launched after Steve Jobs who is CEO of Apple proposed a new music service paradigm without DRM, and the DRM is disappeared at the online music market. Even though the online music service decided to not equip the DRM solution, copyright owners and content providers are still searching a solution to protect their content. A solution to replace the DRM technology is digital audio watermarking technology which can embed copyright information into the music. In this paper, the author proposed a new audio watermarking algorithm with two approaches. First, the watermark information is generated by two dimensional barcode which has error correction code. So, the information can be recovered by itself if the errors fall into the range of the error tolerance. The other one is to use chirp sequence of CDMA (code division multiple access). These make the algorithm robust to the several malicious attacks. There are many 2D barcodes. Especially, QR code which is one of the matrix barcodes can express the information and the expression is freer than that of the other matrix barcodes. QR code has the square patterns with double at the three corners and these indicate the boundary of the symbol. This feature of the QR code is proper to express the watermark information. That is, because the QR code is 2D barcodes, nonlinear code and matrix code, it can be modulated to the spread spectrum and can be used for the watermarking algorithm. The proposed algorithm assigns the different spread spectrum sequences to the individual users respectively. In the case that the assigned code sequences are orthogonal, we can identify the watermark information of the individual user from an audio content. The algorithm used the Walsh code as an orthogonal code. The watermark information is rearranged to the 1D sequence from 2D barcode and modulated by the Walsh code. The modulated watermark information is embedded into the DCT (discrete cosine transform) domain of the original audio content. For the performance evaluation, I used 3 audio samples, "Amazing Grace", "Oh! Carol" and "Take me home country roads", The attacks for the robustness test were MP3 compression, echo attack, and sub woofer boost. The MP3 compression was performed by a tool of Cool Edit Pro 2.0. The specification of MP3 was CBR(Constant Bit Rate) 128kbps, 44,100Hz, and stereo. The echo attack had the echo with initial volume 70%, decay 75%, and delay 100msec. The sub woofer boost attack was a modification attack of low frequency part in the Fourier coefficients. The test results showed the proposed algorithm is robust to the attacks. In the MP3 attack, the strength of the watermark information is not affected, and then the watermark can be detected from all of the sample audios. In the sub woofer boost attack, the watermark was detected when the strength is 0.3. Also, in the case of echo attack, the watermark can be identified if the strength is greater and equal than 0.5.