• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.31-38
• /
• 2022

This paper applies an expert independent unsupervised neural network learning-based multivariate time series data analysis model, MSCRED(Multi-Scale Convolutional Recurrent Encoder-Decoder), and to overcome the limitation, because the MCRED is based on Auto-encoder model, that train data must not to be contaminated, by using learning data sampling technique, called Subset Sampling Validation. By using the vibration data of power plant equipment that has been labeled, the classification performance of MSCRED is evaluated with the Anomaly Score in many cases, 1) the abnormal data is mixed with the training data 2) when the abnormal data is removed from the training data in case 1. Through this, this paper presents an expert-independent anomaly diagnosis framework that is strong against error data, and presents a concise and accurate solution in various fields of multivariate time series data.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.227-233
• /
• 2021

Predictive maintenance has been one of important applications of data science technology that creates a predictive model by collecting numerous data related to management targeted equipment. It does not predict equipment failure with just one or two signs, but quantifies and models numerous symptoms and historical data of actual failure. Statistical methods were used a lot in the past as this predictive maintenance method, but recently, many machine learning-based methods have been proposed. Such proposed machine learning-based methods are preferable in that they show more accurate prediction performance. However, with the exception of some learning models such as decision tree-based models, it is very difficult to explicitly know the structure of learning models (Black-Box Model) and to explain to what extent certain attributes (features or variables) of the learning model affected the prediction results. To overcome this problem, a recently proposed study is an explainable artificial intelligence (AI). It is a methodology that makes it easy for users to understand and trust the results of machine learning-based learning models. In this paper, we propose an explainable AI method to further enhance the explanatory power of the existing learning model by targeting the previously proposedpredictive model [5] that learned data from a core facility (Hyper Compressor) of a domestic chemical plant that produces polyethylene. The ensemble prediction model, which is a black box model, wasconverted to a white box model using the Explainable AI. The proposed methodology explains the direction of control for the major features in the failure prediction results through the Explainable AI. Through this methodology, it is possible to flexibly replace the timing of maintenance of the machine and supply and demand of parts, and to improve the efficiency of the facility operation through proper pre-control.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.827-833
• /
• 2022

This study aims to prevent secondary traffic accidents with high severity by overcoming the limitations of existing traffic information collection systems through analysis of traffic information collection detectors and various algorithms used to detect unexpected situations. In other words, this study is meaningful present that analyzing the 'unexpected situation that causes secondary traffic accidents' and 'Existing traffic information collection system' accordingly presenting a solution that can preemptively prevent secondary traffic accidents, intelligent traffic information collection system that enables accurate information collection on all sections of the road. As a result of the experiment, the reliability of data transmission reached 97% based on 95%, the data transmission speed averaged 209ms based on 1000ms, and the network failover time achieved targets of 50sec based on 120sec.

• Journal of the Korean Society of Safety
• /
• v.37 no.2
• /
• pp.1-9
• /
• 2022

Most factories deal with toxic or flammable chemicals in their industrial processes. These hazardous substances pose a risk of leakage due to accidents, such as fire and explosion. In the event of chemical release, massive casualties and property damage can result; hence, quantitative risk prediction and assessment are necessary. Several methods are available for evaluating chemical dispersion in the atmosphere, and most analyses are considered neutral in dispersion models and under far-field wind condition. The foregoing assumption renders a model valid only after a considerable time has elapsed from the moment chemicals are released or dispersed from a source. Hence, an initial dispersion model is required to assess risk quantitatively and predict the extent of damage because the most dangerous locations are those near a leak source. In this study, the dispersion model for initial consequence analysis was developed with three-dimensional unsteady advective diffusion equation. In this expression, instantaneous leakage is assumed as a puff, and wind velocity is considered as a coordinate transform in the solution. To minimize the buoyant force, ethane is used as leaked fuel, and two different diffusion coefficients are introduced. The calculated concentration field with a molecular diffusion coefficient shows a moving circular iso-line in the horizontal plane. The maximum concentration decreases as time progresses and distance increases. In the case of using a coefficient for turbulent diffusion, the dispersion along the wind velocity direction is enhanced, and an elliptic iso-contour line is found. The result yielded by a widely used commercial program, ALOHA, was compared with the end point of the lower explosion limit. In the future, we plan to build a more accurate and general initial risk assessment model by considering the turbulence diffusion and buoyancy effect on dispersion.

• Journal of Space Technology and Applications
• /
• v.1 no.3
• /
• pp.302-318
• /
• 2021

A basic study was conducted on how to determine the launch timing of a space probe targeting an Earth-approaching asteroid. In the future, when a probe mission targeting an asteroid approaching Earth's orbit is conducted in Korea, in order to determine the launch time, an appropriate solution should be obtained by applying the Global Optimization technique. For this, accurate current orbit information of each asteroid must be obtained first, and prior scenarios such as Earth's orbit information, main engine performance information of the probe and launch vehicle, the number of gravity-assisted maneuvers, and maximum flight time limit should be discussed. Also, the criteria for optimization should be determined first. In this paper, based on these prerequisites and information, a method for finding the launch time of an asteroid probe was studied using the open source software such as PyKEP and Evolutionary Mission Trajectory Generator (EMTG) which are the programs for interplanetary trajectory generation purpose.

• Advances in nano research
• /
• v.13 no.6
• /
• pp.513-525
• /
• 2022

In this study, it was aimed to evaluate direct oxidation of aqueous solution containing cefalexin antibiotic with new generation Sn/Sb/Ni: 500/8/1 anode. The fact that there is no such a study on treatment of cefalexin with these new anode made this study unique. According to the operating parameters evaluation COD graphs showed clearer results compared to TOC and CLX and thus, it was it was chosen as major parameter. Furthermore, pseudo-first degree kd values were calculated from CLX results to show more accurate and specific results. Experimental results showed that after 60 min of electrochemical oxidation, complete removal of COD and TOC was accomplished with 750 mg L^-1 KCl, at pH 7, 50 mA cm^-2 current density and 1 cm anode-cathode distance. Also, the stability of the Sn/Sb/Ni anode was evaluated by taking SEM and AFM images and XRD analysis before and after of electrochemical oxidation processes. According to the results, it was not occurred too much change on the anode surface even after 300 h of electrolysis. Thus, it was thought that the anode material was not corroded to a large extent. Furthermore, the removal efficiencies were very high for almost all the time and conditions. According to the results of the study, electrochemical oxidation with new generation Sn/Sb/Ni anodes for the removal of cefalexin antibiotic was found very successful and applicable due to require less reaction time complete mineralization and doesn't require pH adjustment step compared to other studies in literature. In future studies, different antibiotic types should be studied with this anode and maybe with real wastewaters to test applicability of the process in treatment of pharmaceutical wastewaters containing antibiotics, in a better way.

• Journal of Acupuncture Research
• /
• v.39 no.4
• /
• pp.310-316
• /
• 2022

Background: Verbenalin is an iridoid glucoside, which is among the active components of some medicinal herbs such as Verbena officinalis Linn, and Cornus officinalis Siebold and Zucc. Previous studies have confirmed the antioxidant activity and neuroprotective potential of verbenalin. To confirm the safety of verbenalin, an approximate lethal dose was determined based on a single oral dose toxicity study. Methods: Institute of Cancer Research mice were randomly assigned to three verbenalin exposure groups (250, 500, and 1,000 mg/kg) and a control group (5% methylcellulose solution). There were (5 male and 5 female mice per group). Mortality, clinical signs, and body weight were monitored for 14 days, and necropsies were conducted. Results: No mortalities were observed in the control group or the verbenalin 250 mg/kg group, whereas mortalities were observed in the 500 mg/kg and 1,000 mg/kg verbenalin groups. During the observation period, stool abnormalities such as mucous stools were observed. Clinical signs such as loss of locomotor activity were observed in the 500 mg/kg and 1,000 mg/kg verbenalin groups. During the study period, significant changes in body weight were observed in the 500 mg/kg and 1,000 mg/kg verbenalin groups; however, no gross abnormalities were observed at necropsy. Overall, no toxicity was found in the 250 mg/kg group. Conclusion: The approximate lethal dose of verbenalin was estimated to be 500 mg/kg. For a more accurate assessment of the safety of verbenalin, other types of studies such as repeated-dose toxicity studies should also be conducted.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.26 no.4
• /
• pp.185-223
• /
• 2022

The classical equation of Jonathan Homer Lane and Robert Emden, a nonlinear second-order ordinary differential equation, models the isothermal spherical clouded gases under the influence of the mutual attractive interaction between the gases' molecules. In this paper, the Adomian decomposition method (ADM) is presented to obtain highly accurate and reliable analytical solutions of a class of generalised Lane-Emden equations with strong nonlinearities. The nonlinear term f(y(x)) of the proposed problem is given by the integer powers of a continuous real-valued function h(y(x)), that is, f(y(x)) = h^m(y(x)), for integer m ≥ 0, real x > 0. In the end, numerical comparisons are presented between the analytical results obtained using the ADM and numerical solutions using the eighth-order nested second derivative two-step Runge-Kutta method (NSDTSRKM) to illustrate the reliability, accuracy, effectiveness and convenience of the proposed methods. The special cases h(y) = sin y(x), cos y(x); h(y) = sinh y(x), cosh y(x) are considered explicitly using both methods. Interestingly, in each of these methods, a unified result is presented for an integer power of any continuous real-valued function - compared with the case by case computations for the nonlinear functions f(y). The results presented in this paper are a generalisation of several published results. Several examples are given to illustrate the proposed methods. Tables of expansion coefficients of the series solutions of some special Lane-Emden type equations are presented. Comparisons of the two results indicate that both methods are reliably and accurately efficient in solving a class of singular strongly nonlinear ordinary differential equations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.133-152
• /
• 2022

Rice is a fundamental staple food commodity all around the world. Globally, it is grown over 167 million hectares and occupies almost 1/5^th of total cultivated land under cereals. With a total production of 782 million metric tons in 2018. In Pakistan, it is the 2^nd largest crop being produced and 3^rd largest food commodity after sugarcane and rice. The stem borers a type of pest in rice and other crops, Scirpophaga incertulas or the yellow stem borer is very serious pest and a major cause of yield loss, more than 90% damage is recorded in Pakistan on rice crop. Yellow stem borer population of rice could be stimulated with various environmental factors which includes relative humidity, light, and environmental temperature. Focus of this study is to find the environmental factors changes i.e., temperature, relative humidity and rainfall that can lead to cause outbreaks of yellow stem borers. this study helps to find out the hot spots of insect pest in rice field with a control of farmer's palm. Proposed system uses temperature, relative humidity, and rain sensor along with artificial neural network to predict yellow stem borer attack and generate warning to take necessary precautions. result shows 85.6% accuracy and accuracy gradually increased after repeating several training rounds. This system can be good IoT based solution for pest attack prediction which is cost effective and accurate.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.