• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.242-252
• /
• 2021

Following the intuition that the local information in time instances is hardly incorporated into the posterior sequence in long short-term memory (LSTM), this paper proposes an attention augmented mechanism for fault diagnosis of the complex chemical process data. Unlike conventional fault diagnosis and classification methods, an attention mechanism layer architecture is introduced to detect and focus on local temporal information. The augmented deep network results preserve each local instance's importance and contribution and allow the interpretable feature representation and classification simultaneously. The comprehensive comparative analyses demonstrate that the developed model has a high-quality fault classification rate of 95.49%, on average. The results are comparable to those obtained using various other techniques for the Tennessee Eastman benchmark process.

• 한국산업보건학회지
• /
• 제23권2호
• /
• pp.156-163
• /
• 2013

Objectives: Numerous poisonous substances are used in paint manufacture, but there are differences in the results of GHS classification between the Ministry of Labor(MOL) and the Ministry of Environment(MOE). Therefore, paint manufacturers suffer confusion as to how to classify a given chemical's risk and hazard level. This paper was designed to compare the classification results of chemicals by the MOL and the MOE and suggest a harmonization measure. Methods: After selecting 25 poisonous substances from among the organic solvents, pigments, and additives used in paint manufacturer, the GHS classification results by MOL and MOE were compared. Further the logic and classification of the GHS proposed by each Ministry was analyzed. Based on the derived results, a harmonization plan was proposed. Results: Based on the GHS classification of the poisonous substances, the concordance is 10.0-66.6 %, excluded flammable liquid. The GHS classifications differed based on the suggested building blocks, the sub-classification method used, the references(data sources), and subjective judgment of the experts from each Ministry. In order to pursue the harmonization plan, cooperation is demanded from the MOL and MOE.

• 대한원격탐사학회지
• /
• 제28권6호
• /
• pp.611-622
• /
• 2012

This study proposed two multisensor fusion methods for segment-based image classification utilizing a region-growing segmentation. The proposed algorithms employ a Gaussian-PDF measure and an evidential measure respectively. In remote sensing application, segment-based approaches are used to extract more explicit information on spatial structure compared to pixel-based methods. Data from a single sensor may be insufficient to provide accurate description of a ground scene in image classification. Due to the redundant and complementary nature of multisensor data, a combination of information from multiple sensors can make reduce classification error rate. The Gaussian-PDF method defines a regional measure as the PDF average of pixels belonging to the region, and assigns a region into a class associated with the maximum of regional measure. The evidential fusion method uses two measures of plausibility and belief, which are derived from a mass function of the Beta distribution for the basic probability assignment of every hypothesis about region classes. The proposed methods were applied to the SPOT XS and ENVISAT data, which were acquired over Iksan area of of Korean peninsula. The experiment results showed that the segment-based method of evidential measure is greatly effective on improving the classification via multisensor fusion.

• 대한안전경영과학회지
• /
• 제14권3호
• /
• pp.143-150
• /
• 2012

In Korea more than 38,000 types of hazardous material(HAZMAT) are distributed, accordingly the accidents during transportation are also increasing. The agencies related to HAZMAT such as Environment Ministry, National Emergency Management Agency and National Police Agency have their own regulations. However, the classification criteria of HAZMAT are different to each other, which causes many problems in response to transportation accidents. In this study the classification standard of HAZMAT and the classification code using CAS number are suggested to manage HAZMAT efficiently. Through efficient management and standard classification of HAZMAT, the rapid and systematic response to transportation accidents related to HAZMAT is expected to be possible.

• 한국컴퓨터정보학회논문지
• /
• 제18권1호
• /
• pp.177-183
• /
• 2013

본 논문에서는 데이터 마이닝에서 분류 작업을 실시할 때 그 분류정확도을 측정하기 위해 Cohen의 kappa 계수와 weighted kappa 계수를 제안하였다. kappa 계수는 우연에 의해 생기는 분류를 보정하여 분류정확도을 측정하며 명목척도와 순서척도의 데이터에 대해 사용된다. 특히 순서척도의 데이터에서는 오분류의 크기를 가중치에 의해 정량화하여 분류정확도을 측정하는 weighted kappa 계수가 더 유용하게 사용된다. weighted kappa 계수 계산을 위해서는 2가지 가중치(일차형 가중치, 이차형 가중치)를 사용하였다.. 또한 실제 데이터인 지방간 데이터에 대해 kappa 계수와 weighted kappa 계수를 계산하여 비교하였다.

• 대한안전경영과학회지
• /
• 제13권1호
• /
• pp.195-202
• /
• 2011

The study interprets each of three classification models based on Bath-Tub Failure Rate (BTFR), Extreme Value Distribution (EVD) and Conjugate Bayesian Distribution (CBD). The classification model based on BTFR is analyzed by three failure patterns of decreasing, constant, or increasing which utilize systematic management strategies for reliability of time. Distribution model based on BTFR is identified using individual factors for each of three corresponding cases. First, in case of using shape parameter, the distribution based on BTFR is analyzed with a factor of component or part number. In case of using scale parameter, the distribution model based on BTFR is analyzed with a factor of time precision. Meanwhile, in case of using location parameter, the distribution model based on BTFR is analyzed with a factor of guarantee time. The classification model based on EVD is assorted into long-tailed distribution, medium-tailed distribution, and short-tailed distribution by the length of right-tail in distribution, and depended on asymptotic reliability property which signifies skewness and kurtosis of distribution curve. Furthermore, the classification model based on CBD is relied upon conjugate distribution relations between prior function, likelihood function and posterior function for dimension reduction and easy tractability under the occasion of Bayesian posterior updating.

• 품질경영학회지
• /
• 제48권4호
• /
• pp.553-566
• /
• 2020

Purpose: The purpose of this study was to design a framework for generating one-class classification algorithm based on Hyper-Rectangle(H-RTGL) in a distributed environment connected by network. Methods: At first, we devised one-class classifier based on H-RTGL which can be performed by distributed computing nodes considering model and data parallelism. Then, we also designed facilitating components for execution of distributed processing. In the end, we validate both effectiveness and efficiency of the classifier obtained from the proposed framework by a numerical experiment using data set obtained from UCI machine learning repository. Results: We designed distributed processing framework capable of one-class classification based on H-RTGL in distributed environment consisting of physically separated computing nodes. It includes components for implementation of model and data parallelism, which enables distributed generation of classifier. From a numerical experiment, we could observe that there was no significant change of classification performance assessed by statistical test and elapsed time was reduced due to application of distributed processing in dataset with considerable size. Conclusion: Based on such result, we can conclude that application of distributed processing for generating classifier can preserve classification performance and it can improve the efficiency of classification algorithms. In addition, we suggested an idea for future research directions of this paper as well as limitation of our work.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.230-237
• /
• 2022

It is difficult to predict industrial accidents in the construction industry because many accident factors, such as human-related factors and environment-related factors, affect the accidents. Many studies have analyzed the severity of injuries and types of accidents; however, there were few studies on the prediction of injured body parts. This study aims to develop a classification model to predict the part of the injured body based on accident-related factors. Construction accident cases from June 2018 to July 2021 provided by the Korea Construction Safety Management Integrated Information were collected through web crawling and then preprocessed. A naïve Bayes classifier, one of the supervised learning algorithms, was employed to construct a classification model of the injured body part, which has four categories: 1) torso, 2) upper extremity, 3) head, and 4) lower extremity. The predictor variables are accident type, type of work, facility type, injury source, and activity type. As a result, the average accuracy for each injured body part was 50.4%. The accuracy of the upper extremity and lower extremity was relatively higher than the cases of the torso and head. Unlike the other classifications, such as spam mail filtering, a naïve Bayes classifier does not provide a good classification performance in construction accidents. The reasons are discussed in the study. Based on the results of this study, more detailed guidelines for construction safety management can be provided, which help establish safety measures at the construction site.

• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.67-72
• /
• 2023

In the past decade, Autonomous Vehicle Systems (AVS) have advanced at an exponential rate, particularly due to improvements in artificial intelligence, which have had a significant impact on social as well as road safety and the future of transportation systems. The fusion of light detection and ranging (LiDAR) and camera data in real-time is known to be a crucial process in many applications, such as in autonomous driving, industrial automation and robotics. Especially in the case of autonomous vehicles, the efficient fusion of data from these two types of sensors is important to enabling the depth of objects as well as the classification of objects at short and long distances. This paper presents classification of objects using CNN based vision and Light Detection and Ranging (LIDAR) fusion in autonomous vehicles in the environment. This method is based on convolutional neural network (CNN) and image up sampling theory. By creating a point cloud of LIDAR data up sampling and converting into pixel-level depth information, depth information is connected with Red Green Blue data and fed into a deep CNN. The proposed method can obtain informative feature representation for object classification in autonomous vehicle environment using the integrated vision and LIDAR data. This method is adopted to guarantee both object classification accuracy and minimal loss. Experimental results show the effectiveness and efficiency of presented approach for objects classification.

• 스마트미디어저널
• /
• 제13권3호
• /
• pp.27-35
• /
• 2024

본 연구는 GAN(Generative Adversarial Network)을 기반으로 한 Semi Supervised Learning을 활용하여 이미지 생성과 ResNet50을 이용한 이미지 분류를 결합하는 방법에 대해 다루고 있다. 이를 통해 새로운 접근법을 제시하여 이미지 생성과 분류를 통합함으로써 더 정확하고 다양한 결과를 얻을 수 있도록 하였다. 생성자와 판별자를 학습시켜 생성된 이미지와 실제 이미지를 구별하고, ResNet50을 활용하여 이미지 분류를 수행한다. 실험 결과에서는 생성된 이미지의 품질이 epoch에 따라 변화함을 확인할 수 있었으며, 이를 통해 산업재해 예측 정확성을 향상하고자 한다. 또한, GAN과 ResNet50의 결합을 통해 이미지 생성의 품질을 향상시키고 이미지 분류의 정확도를 높이는 효율적인 방법을 제시하고자 한다.