• Journal of Biosystems Engineering
• /
• v.26 no.2
• /
• pp.147-154
• /
• 2001

In Korea and Japan, dried oak mushrooms are classified into 12 to 16 different categories based on its external visual quality. And grading used to be done manually by the human expert and is limited to the randomly sampled oak mushrooms. Visual features of dried oak mushrooms dominate its quality and are distributed over both sides of the gill and the cap. The 2nd prototype computer vision based automatic grading and sorting system for dried oak mushrooms was developed based on the 1st prototype. Sorting function was improved and overall system for grading was simplified to one stage grading instead of two stage grading by inspecting both front and back sides of mushrooms. Neuro-net based side(gill or cap) recognition algorithm of the fed mushroom was adopted. Grading was performed with both images of gill and cap using neural network. A real time simultaneous discharge algorithm, which is good for objects randomly fed individually and for multi-objects located along a series of discharge buckets, was developed and implemented to the controller and the performance was verified. Two hundreds samples chosen from 10 samples per 20 grade categories were used to verify the performance of each unit such as feeding, reversing, grading, and discharging unites. Test results showed that success rates of one-line feeding, reversing, grading, and discharging functions were 93%, 95%, 94%, and 99% respectively. The developed prototype revealed successful performance such as the approximate sorting capability of 3,600 mushrooms/hr per each line i.e. average 1sec/mushroom. Considering processing time of approximate 0.2 sec for grading, it was desired to reduce time to reverse a mushroom to acquire the reversed surface image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.1957-1980
• /
• 2021

The significant aim of this research has always been to evaluate the mechanism for efficient and inherently aware usage of vitality in-home devices, thus improving the information of smart metering systems with regard to the usage of selected homes and the time of use. Advances in information processing are commonly used to quantify gigantic building activity data steps to boost the activity efficiency of the building energy systems. Here, some smart data mining models are offered to measure, and predict the time series for energy in order to expose different ephemeral principles for using energy. Such considerations illustrate the use of machines in relation to time, such as day hour, time of day, week, month and year relationships within a family unit, which are key components in gathering and separating the effect of consumers behaviors in the use of energy and their pattern of energy prediction. It is necessary to determine the multiple relations through the usage of different appliances from simultaneous information flows. In comparison, specific relations among interval-based instances where multiple appliances use continue for certain duration are difficult to determine. In order to resolve these difficulties, an unsupervised energy time-series data clustering and a frequent pattern mining study as well as a deep learning technique for estimating energy use were presented. A broad test using true data sets that are rich in smart meter data were conducted. The exact results of the appliance designs that were recognized by the proposed model were filled out by Deep Convolutional Neural Networks (CNN) and Recurrent Neural Networks (LSTM and GRU) at each stage, with consolidated accuracy of 94.79%, 97.99%, 99.61%, for 25%, 50%, and 75%, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.21-30
• /
• 2023

The study proposes a model that utilizes Python-based deep learning text classification techniques to detect the legality of illegal financial advertising posts on the internet. These posts aim to promote unlawful financial activities, including the trading of bank accounts, credit card fraud, cashing out through mobile payments, and the sale of personal credit information. Despite the efforts of financial regulatory authorities, the prevalence of illegal financial activities persists. By applying this proposed model, the intention is to aid in identifying and detecting illicit content in internet-based illegal financial advertisining, thus contributing to the ongoing efforts to combat such activities. The study utilizes convolutional neural networks(CNN) and recurrent neural networks(RNN, LSTM, GRU), which are commonly used text classification techniques. The raw data for the model is based on manually confirmed regulatory judgments. By adjusting the hyperparameters of the Korean natural language processing and deep learning models, the study has achieved an optimized model with the best performance. This research holds significant meaning as it presents a deep learning model for discerning internet illegal financial advertising, which has not been previously explored. Additionally, with an accuracy range of 91.3% to 93.4% in a deep learning model, there is a hopeful anticipation for the practical application of this model in the task of detecting illicit financial advertisements, ultimately contributing to the eradication of such unlawful financial advertisements.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2002.07b
• /
• pp.1097-1102
• /
• 2002

For detecting of Faulty Insulator, a new Lateral Information Propagation Networks (LIPN) has been proposed. Energized insulator is reduced the rate of insulation extremely, and taken the results dirty and injured. It is necessary to be actions that detect the faulty insulator and exchange the new one. And thus, we have designed the LIPN to be detected that insulators by the real time computation method through the inter-node diffusion. In the network, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. Information propagates among neighbor nodes laterally and inter-node interpolation is achieved. Through several simulation experiments,real time reconstruction of the nonlinear image information is processed.

• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.769-776
• /
• 2003

DNA computing has used to solve MCP (Maximal Clique Problem). However, when current DNA computing is applied to MCP. it can't efficiently express vertices and edges and it has a problem that can't look for solutions, by misusing wrong restriction enzyme. In this paper we proposed ACO (Algorithm for Code Optimization) that applies DNA coding method to DNA computing to solve MCP's problem. We applied ACO to MCP and as a result ACO could express DNA codes of variable lengths and generate codes without unnecessary vertices than Adleman's DNA computing algorithm could. In addition, compared to Adleman's DNA computing algorithm, ACO could get about four times as many as Adleman's final solutions by reducing search time and biological error rate by 15%.

• Electronics and Telecommunications Trends
• /
• v.36 no.2
• /
• pp.32-42
• /
• 2021

The rapid growth of deep-learning applications has invoked the R&D of artificial intelligence (AI) processors. A dedicated software framework such as a compiler and runtime APIs is required to achieve maximum processor performance. There are various compilers and frameworks for AI training and inference. In this study, we present the features and characteristics of AI compilers, training frameworks, and inference engines. In addition, we focus on the internals of compiler frameworks, which are based on either basic linear algebra subprograms or intermediate representation. For an in-depth insight, we present the compiler infrastructure, internal components, and operation flow of ETRI's "AI-Ware." The software framework's significant role is evidenced from the optimized neural processing unit code produced by the compiler after various optimization passes, such as scheduling, architecture-considering optimization, schedule selection, and power optimization. We conclude the study with thoughts about the future of state-of-the-art AI compilers.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.1
• /
• pp.1-9
• /
• 2023

The problem of classifying a non-line-of-sight (NLOS) signal in a multipath channel is important to improve global navigation satellite system (GNSS) positioning accuracy in urban areas. Conventional deep learning-based NLOS signal classifiers use GNSS satellite measurements such as the carrier-to-noise-density ratio (CN_0), pseudorange, and elevation angle as inputs. However, there is a computational inefficiency with use of these measurements and the NLOS signal features expressed by the measurements are limited. In this paper, we propose a Convolutional Neural Network (CNN)-based NLOS signal classifier that receives successive Auto-correlation function (ACF) outputs according to a time-series, which is the most primitive output of GNSS signal processing. We compared the proposed classifier to other DL-based NLOS signal classifiers such as a multi-layer perceptron (MLP) and Gated Recurrent Unit (GRU) to show the superiority of the proposed classifier. The results show the proposed classifier does not require the navigation data extraction stage to classify the NLOS signals, and it has been verified that it has the best detection performance among all compared classifiers, with an accuracy of up to 97%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.329-330
• /
• 2020

본 논문에서는 Azure 클라우드 플랫폼의 가상서버 호스팅을 이용해 데이터 수집 환경을 구축하고, Azure에서 제공하는 자동화된 기계학습(Automated Machine Learning, AutoML)을 기반으로 데이터 분석 방법에 관한 연구를 수행했다. 가상 서버 호스팅 환경에 LAMP(Linux, Apache, MySQL, PHP)를 설치하여 데이터 수집환경을 구축했으며, 수집된 데이터를 Azure AutoML에 적용하여 자동화된 기계학습을 수행했다. Azure AutoML은 소모적이고 반복적인 기계학습 모델 개발을 자동화하는 프로세스로써 기계학습 솔루션 구현하는데 시간과 자원(Resource)를 절약할 수 있다. 특히, AutoML은 수집된 데이터를 분류와 회귀 및 예측하는데 있어서 학습점수(Training Score)를 기반으로 보유한 데이터에 가장 적합한 기계학습 모델의 순위를 제공한다. 이는 데이터 분석에 필요한 기계학습 모델을 개발하는데 있어서 개발 초기 단계부터 코드를 설계하지 않아도 되며, 전체 기계학습 시스템을 개발 및 구현하기 전에 모델의 구성과 시스템을 설계해볼 수 있기 때문에 매우 효율적으로 활용될 수 있다. 본 논문에서는 NPU(Neural Processing Unit) 학습에 필요한 데이터 수집 환경에 관한 연구를 수행했으며, Azure AutoML을 기반으로 데이터 분류와 회귀 등 가장 효율적인 알고리즘 선정에 관한 연구를 수행했다.

• Earthquakes and Structures
• /
• v.24 no.2
• /
• pp.127-140
• /
• 2023

The vibration of microtubule in human cells is the source of electrical field around it and inside cell structure. The induction of electrical field is a direct result of the existence of dipoles on the surface of the microtubules. Measuring the electrical fields could be performed using nano-scale sensors and the data could be transformed to other computers using internet of things (IoT) technology. Processing these data is feasible by artificial intelligence-based methods. However, the first step in analyzing the vibrational behavior is to study the mechanics of microtubules. In this regard, the vibrational behavior of the microtubules is investigated in the present study. A shell model is utilized to represent the microtubules' structure. The displacement field is assumed to obey first order shear deformation theory and classical theory of elasticity for anisotropic homogenous materials is utilized. The governing equations obtained by Hamilton's principle are further solved using analytical method engaging Navier's solution procedure. The results of the analytical solution are used to train, validate and test of the deep neural network. The results of the present study are validated by comparing to other results in the literature. The results indicate that several geometrical and material factors affect the vibrational behavior of microtubules.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.165-171
• /
• 2022

Human heart rate can be used to measure exercise intensity as an important indicator. If heart rate can be predicted, exercise can be performed more efficiently by regulating the intensity of exercise in advance. In this paper, a FitRec-based prediction model is proposed for estimating running heart rate for users. Endomondo data is utilized for training the proposed prediction model. The processing algorithms for time-series data, such as LSTM(long short term memory) and GRU(gated recurrent unit), are employed to compare their performance. On the basis of simulation results, it was demonstrated that the proposed model trained with running exercise performed better than the model trained with several cardiac exercises.