• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.571-576
• /
• 2002

There have been a lot of considerations dealing with improving the performance of neuro-fuzzy system. The studies on the neuro-fuzzy modeling have largely been devoted to two approaches. First is to improve performance index of system. The other is to reduce the structure size. In spite of its satisfactory result, it should be noted that these are difficult to extend to high dimensional input or to increase the membership functions. We propose a novel neuro-fuzzy system based on the efficient clustering method for initializing the parameters of the premise part. It is a very useful method that maintains a few number of rules and improves the performance. It combine the various algorithms to improve the performance. The Expectation-Maximization algorithm of Gaussian mixture model is an efficient estimation method for unknown parameter estimation of mirture model. The obtained parameters are used for fuzzy clustering method. The proposed method satisfies these two requirements using the Gaussian mixture model and neuro-fuzzy modeling. Experimental results indicate that the proposed method is capable of giving reliable performance.

• Economic and Environmental Geology
• /
• v.36 no.3
• /
• pp.243-255
• /
• 2003

The mathematical models for GIS-based spatial data integration have been developed for geological applications such as mineral potential mapping or landslide susceptibility analysis. Among various models, the effectiveness of fuzzy logic based integration of multiple sets of geological data is investigated and discussed. Unlike a traditional target-driven fuzzy integration approach, we propose a data-driven approach that is derived from statistical relationships between the integration target and related spatial geological data. The proposed approach consists of four analytical steps; data representation, fuzzy combination, defuzzification and validation. For data representation, the fuzzy membership functions based on the likelihood ratio functions are proposed. To integrate them, the fuzzy inference network is designed that can combine a variety of different fuzzy operators. Defuzzification is carried out to effectively visualize the relative possibility levels from the integrated results. Finally, a validation approach based on the spatial partitioning of integration targets is proposed to quantitatively compare various fuzzy integration maps and obtain a meaningful interpretation with respect to future events. The effectiveness and some suggestions of the schemes proposed here are illustrated by describing a case study for landslide susceptibility analysis. The case study demonstrates that the proposed schemes can effectively identify areas that are susceptible to landslides and ${\gamma}$ operator shows the better prediction power than the results using max and min operators from the validation procedure.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.18-31
• /
• 2002

In this study, we introduce a concept of advanced neurofuzzy polynomial networks(ANFPN), a hybrid modeling architecture combining neurofuzzy networks(NFN) and polynomial neural networks(PNN). These networks are highly nonlinear rule-based models. The development of the ANFPN dwells on the technologies of Computational Intelligence(Cl), namely fuzzy sets, neural networks and genetic algorithms. NFN contributes to the formation of the premise part of the rule-based structure of the ANFPN. The consequence part of the ANFPN is designed using PNN. At the premise part of the ANFPN, NFN uses both the simplified fuzzy inference and error back-propagation learning rule. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. As the consequence structure of ANFPN, PNN is a flexible network architecture whose structure(topology) is developed through learning. In particular, the number of layers and nodes of the PNN are not fixed in advance but is generated in a dynamic way. In this study, we introduce two kinds of ANFPN architectures, namely the basic and the modified one. Here the basic and the modified architecture depend on the number of input variables and the order of polynomial in each layer of PNN structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the ANFPN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed ANFPN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• The Journal of the Korea Contents Association
• /
• v.13 no.11
• /
• pp.322-331
• /
• 2013

The purpose of the present study was to develop a convergent education contents for dementia prevention, operating on the web network applying modern information technology(IT). At the preparation stage, local and worldwide literatures related to dementia were analyzed followed by surveying industry demands, based on which the program was designed and developed. In the following enhancement stage, the program was modified as much as possible by advices obtained from experts in various fields. Development results of the present program are summarized as follows. Firstly, 645 intellect development model to prevent dementia was established through peer review and verification of convergent education theories by expert groups. This model was named as "Garisani" meaning "cognition capable of judging objects" in the Korean language. Secondly, 'Find a way' and 'Connect a line' modules were developed in the numeric field as well as 'Identify a letter(I, II)' modules, in the language field for web-based left brain training program. Thirdly, 'Find my car' and 'Vision training' modules in the attention field and 'Object inference' and 'Compare pictures' modules in the cognition field were developed for web-based right brain training program. Fourth, 'Pentomino' and 'BQmaze'(Brain Quotient and maze) modules in the space perception field and 'Visual training' in the memory field were developed for web-based left and right brains training. Fifth, all results were integrated leading to a 52 week Garisani convergent education program for dementia prevention.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.5
• /
• pp.169-176
• /
• 2020

Recently, deep neural networks (DNNs) have brought revolutions to many mobile and embedded devices by providing human-level machine intelligence for various applications. However, high inference accuracy of such DNNs comes at high computational costs, and, hence, there have been significant efforts to reduce computational overheads of DNNs either by compressing off-the-shelf models or by designing a new small footprint DNN architecture tailored to resource constrained devices. One notable recent paradigm in designing small footprint DNN models is sharing parameters in several layers. However, in previous approaches, the parameter-sharing techniques have been applied to large deep networks, such as ResNet, that are known to have high redundancy. In this paper, we propose a parameter-sharing method for already parameter-efficient small networks such as ShuffleNetV2. In our approach, small templates are combined with small layer-specific parameters to generate weights. Our experiment results on ImageNet and CIFAR100 datasets show that our approach can reduce the size of parameters by 15%-35% of ShuffleNetV2 while achieving smaller drops in accuracies compared to previous parameter-sharing and pruning approaches. We further show that the proposed approach is efficient in terms of latency and energy consumption on modern embedded devices.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.59-66
• /
• 2021

Humans mainly recognize surrounding objects using visual and auditory information among the five senses (sight, hearing, smell, touch, taste). Major research related to the latest object recognition mainly focuses on analysis using image sensor information. In this paper, after emitting various chirp audio signals into the observation space, collecting echoes through a 2-channel receiving sensor, converting them into spectral images, an object recognition experiment in 3D space was conducted using an image learning algorithm based on deep learning. Through this experiment, the experiment was conducted in a situation where there is noise and echo generated in a general indoor environment, not in the ideal condition of an anechoic room, and the object recognition through echo was able to estimate the position of the object with 83% accuracy. In addition, it was possible to obtain visual information through sound through learning of 3D sound by mapping the inference result to the observation space and the 3D sound spatial signal and outputting it as sound. This means that the use of various echo information along with image information is required for object recognition research, and it is thought that this technology can be used for augmented reality through 3D sound.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.3-12
• /
• 2022

Image deblurring aims to remove image blur, which can be generated while shooting the pictures by the movement of objects, camera shake, blurring of focus, and so forth. With the rise in popularity of smartphones, it is common to carry portable digital cameras daily, so image deblurring techniques have become more significant recently. Originally, image deblurring techniques have been studied using traditional optimization techniques. Then with the recent attention on deep learning, deblurring methods based on convolutional neural networks have been actively proposed. However, most of them have been developed while focusing on better performance. Therefore, it is not easy to use in real situations due to the speed of their algorithms. To tackle this problem, we propose a novel deep learning-based deblurring algorithm that can be operated in real-time on HD resolution. In addition, we improved the training and inference process and could increase the performance of our model without any significant effect on the speed and the speed without any significant effect on the performance. As a result, our algorithm achieves real-time performance by processing 33.74 frames per second at 1280×720 resolution. Furthermore, it shows excellent performance compared to its speed with a PSNR of 29.78 and SSIM of 0.9287 with the GoPro dataset.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1693-1705
• /
• 2023

Rural areas, which account for about 90% of the country's land area, are increasing in importance and value as a space that performs various public functions. However, facilities that adversely affect residents' lives, such as livestock facilities, factories, and solar panels, are being built indiscriminately near residential areas, damaging the rural environment and landscape and lowering the quality of residents' lives. In order to prevent disorderly development in rural areas and manage rural space in a planned manner, detection and monitoring of hazardous facilities in rural areas is necessary. Data can be acquired through satellite imagery, which can be acquired periodically and provide information on the entire region. Effective detection is possible by utilizing image-based deep learning techniques using convolutional neural networks. Therefore, U-Net model, which shows high performance in semantic segmentation, was used to classify potentially hazardous facilities in rural areas. In this study, KOMPSAT ortho-mosaic optical imagery provided by the Korea Aerospace Research Institute in 2020 with a spatial resolution of 0.7 meters was used, and AI training data for livestock facilities, factories, and solar panels were produced by hand for training and inference. After training with U-Net, pixel accuracy of 0.9739 and mean Intersection over Union (mIoU) of 0.7025 were achieved. The results of this study can be used for monitoring hazardous facilities in rural areas and are expected to be used as basis for rural planning.

• Informatization Policy
• /
• v.31 no.2
• /
• pp.3-38
• /
• 2024

Hallucination is a significant barrier to the utilization of large-scale language models or multimodal models. In this study, we collected 654 computer science papers with "hallucination" in the abstract from arXiv from December 2022 to January 2024 following the advent of Chat GPT and conducted frequency analysis, knowledge network analysis, and literature review to explore the latest trends in hallucination research. The results showed that research in the fields of "Computation and Language," "Artificial Intelligence," "Computer Vision and Pattern Recognition," and "Machine Learning" were active. We then analyzed the research trends in the four major fields by focusing on the main authors and dividing them into data, hallucination detection, and hallucination mitigation. The main research trends included hallucination mitigation through supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), inference enhancement via "chain of thought" (CoT), and growing interest in hallucination mitigation within the domain of multimodal AI. This study provides insights into the latest developments in hallucination research through a technology-oriented literature review. This study is expected to help subsequent research in both engineering and humanities and social sciences fields by understanding the latest trends in hallucination research.