• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.311-318
• /
• 2022

Tobacco sales enterprises often need to summarize and verify the daily sales bills, which may consume substantial manpower, and manual verification is prone to occasional errors. The use of artificial intelligence technology to realize the automatic identification and verification of such bills offers important practical significance. This study presents a novel multi-branch residual network for tobacco sales bills to improve the efficiency and accuracy of tobacco sales. First, geometric correction and edge alignment were performed on the input sales bill image. Second, the multi-branch residual network recognition model is established and trained using the preprocessed data. The comparative experimental results demonstrated that the correct recognition rate of the proposed method reached 98.84% on the China Tobacco Bill Image dataset, which is superior to that of most existing recognition methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.151-153
• /
• 2023

Federated learning (FL)-based network intrusion detection techniques have enormous potential for securing the Industrial Internet of Things (IIoT) cybersecurity. The openness and connection of systems in smart industrial facilities can be targeted and manipulated by malicious actors, which emphasizes the significance of cybersecurity. The conventional centralized technique's drawbacks, including excessive latency, a congested network, and privacy leaks, are all addressed by the FL method. In addition, the rich data enables the training of models while combining private data from numerous participants. This research aims to create an FL-based architecture to improve cybersecurity and intrusion detection in IoT networks. In order to assess the effectiveness of the suggested approach, we have utilized well-known cybersecurity datasets along with centralized and federated machine learning models.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.11 no.1
• /
• pp.26-33
• /
• 2001

The goal of this study was to evaluate the relationship between ambient hexavalent chromium concentration and the concentration of the chromium in whole blood, plasma, erythrocytes, and its urinary excretion of male rats after inhalation exposure of sodium chromate during 1, 2, and 3 weeks. 1. Differences of mean chromium concentration in urine, whole blood, erythrocytes, and plasma of male rats exposed to sodium chromate by exposure level were statistically significance, respectively. 2. At low and high exposure groups, differences of mean chromium concentration in urine, whole blood, erythrocytes, and plasma of male rats by duration of inhalation exposure were statistically significance, respectively. 3. Ratio of whole blood chromium to plasma chromium increased with the increased duration of inhalation exposure of sodium chromate. 4. Ambient hexavalent chromium was positively and strongly correlated with in erythrocyte chromium, and also erythrocyte chromium was strongly correlated with in whole blood chromium. In conclusion, this study showed that chromium in erythrocyte increased with the increased exposure level and exposure duration, therefore this study suggests that chromium in erythrocytes is a good biological exposure index of the internal dose from exposure to soluble hexavalent chromium compound.

• Journal of the Korea Safety Management & Science
• /
• v.16 no.1
• /
• pp.169-176
• /
• 2014

This research discusses the characteristics and the implementation strategies for two types of quality metrics to analyze innovation effects in six sigma projects: fixed specification type and moving specification type. $Z_{st}$, $P_{pk}$ are quality metrics of fixed specification type that are influenced by predetermined specification. In contrast, the quality metrics of moving specification type such as Strictly Standardized Mean Difference(SSMD), Z-Score, F-Statistic and t-Statistic are independent from predetermined specification. $Z_{st}$ sigma level obtains defective rates of Parts Per Million(PPM) and Defects Per Million Opportunities(DPMO). However, the defective rates between different industrial sectors are incomparable due to their own technological inherence. In order to explore relative method to compare defective rates between different industrial sectors, the ratio of specification and natural tolerance called, $P_{pk}$, is used. The drawback of this $P_{pk}$ metric is that it is highly dependent on the specification. The metrics of F-Statistic and t-Statistic identify innovation effect by comparing before-and-after of accuracy and precision. These statistics are not affected by specification, but affected by type of statistical distribution models and sample size. Hence, statistical significance determined by above two statistics cannot give a same conclusion as practical significance. In conclusion, SSMD and Z-Score are the best quality metrics that are uninfluenced by fixed specification, theoretical distribution model and arbitrary sample size. Those metrics also identify the innovation effects for before-and-after of accuracy and precision. It is beneficial to use SSMD and Z-Score methods along with popular methods of $Z_{st}$ sigma level and $P_{pk}$ that are commonly employed in six sigma projects. The case studies from national six sigma contest from 2011 to 2012 are proposed and analyzed to provide the guidelines for the usage of quality metrics for quality practitioners.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.447-451
• /
• 2010

It is quite important for manufacturing firms to stably secure water, because industrial water is used for a variety of purposes as one of the important inputs in the production process. Despite the significance of industrial water use and the increase of industrial water demand, relatively little has studied regarding the industrial water use in Korea. This paper employs the marginal productivity approach in order to estimate the economic value of water in Korean manufacturing industry, and we use the information of 53,912 factories surveyed in 2003. The result of the likelihood ratio test shows that Trans-log is an appropriate model for estimating the data of this study. In Trans-log function model, the industry-wide output elasticity of water is 0.0104, and the marginal value is KRW 1,156 per ton. The estimated values differ across the sectors and these values range from the high value of about KRW 13,760 per ton in the transportation equipment sector to low values of KRW 428 per ton in the precision instrument sector. The research provides useful information to help policy-makers in developing and implementing more appropriate policies regarding the management and distribution of water resources by estimating the value of water resources by sector. In addition, Korean government enables the drafting of future water pricing scenarios based on the estimated value information.

• Journal of the Korean Society of Safety
• /
• v.33 no.5
• /
• pp.101-108
• /
• 2018

This study was carried out to obtain baseline data on the causes of industrial accidents and their prevention by investigating structural models between the Shipyard workers' egogram ego-states (CP: Critical Parent, NP: Nurturing Parent, A: Adult, FC: Free Child, AC: Adapted Child), safe and unsafe behaviors, and industrial accidents (frequency/severity). In order to achieve this goal, 378 workers from 3 locations of major corporations in Geojedo Island and Ulsan took a questionnaire, which was then analyzed with a structural equation model using the SPSS 23.0 and AMOS 24 statistics package, and the main results of the study are as follows. First, NP and A's ego-states had a positive influence on safe behavior, AC's ego-state had a negative influence on safe behavior, and A's ego-state had the largest influence on safe behavior. Second, CP and AC's ego-states had a positive influence on unsafe behavior, and A's ego-state had a negative influence on unsafe behavior. AC's ego-state had the largest influence on unsafe behavior. Third, safe behavior did not have a significant influence on industrial accidents. However, unsafe behavior had a positive influence on industrial accident frequency and industrial accident severity, both sub-factors of industrial accidents. This study, despite its limitations, such as sampling limitations, has the following significance. First, this study verified that ego-state, a psychological characteristic, is an important factor for predicting unsafe behavior that induces industrial accidents. Second, in order to reduce industrial accidents, there is a need to stimulate the A ego-states, and promote continuous safety management and safety education to neutralize the AC ego-state. Third, previous studies were limited in the area of practical methods for reducing unsafe behaviors, but this study presents practical methods for reducing unsafe behaviors by verifying the structural relationship between safe/unsafe behaviors and industrial accidents by selecting ego-gram ego-states, variable personality theory, as an independent variable.

• Journal of the Korean Academic Society of Industrial Cluster
• /
• v.2 no.1
• /
• pp.1-13
• /
• 2008

Despite growing recognition of the significance of industrial clusters to regional economic success, there has been only limited attention paid to the effectiveness of cluster policies in old industrial regions. Many of these regions still retain functioning industrial clusters, or have clusters which are adopting new strategies as part of a process of regeneration. This paper argues that the effectiveness of cluster policies in old industrial regions depends upon the extent to which they recognise the evolutionary nature of industrial clusters. It reviews the literature on the transformation of old industrial regions in Europe, and examines how cluster policies have risen to prominence as a policy tool. These strands ate brought together in an exploration of cluster policies in old industrial regions. A brief case study is presented of the evolution of the steel industry supply chain in north east England. The conclusions focus upon the data requirements that form a starting point for informed policy intervention into presses of cluster evolution.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.290-298
• /
• 2017

This study compared the median nerve, ulnar never, and F waves of patients diagnosed with early Carpal Tunnel Syndrome to a control group to determine whether F waves could be a useful indicator in the diagnosis of early CTS. The terminal motor latency (TML), terminal motor amplitude and sensory nerve conduction velocity (SNCV) of the section from the palms to the wrists, which are the key indicators to use in a nerve conduction study, and F waves were compared with the control group using the t-test. A correlation analysis was performed to analyze the correlation between the main indicators. The comparison between the median nerve's TML of the early CTS patients and that of the control group shows that there are 2 sections which have high significance (p<0.001). In the comparison of the SNCV of the median nerve between the control group and early CTS patients, high significance was observed (p<0.001). In the analysis of the F waves, there was high significance (p<0.001) between the control group and early CTS patients for the median nerve, but not for the ulnar nerve. The correlation analysis revealed that both the SNCV-TML and F wave-TML had significance. These results suggested that, along with TML and SNCV, F waves can be a useful indicator to diagnose CTS.

• Journal of Preventive Medicine and Public Health
• /
• v.28 no.3 s.51
• /
• pp.726-733
• /
• 1995

This study was carried out to assess the present level of atmospheric metals. Five metals - lead, cadmium, chromium, manganese, vanadium - were checked on the industrial(Sasang) and residental area(Daeshindong) in the city of Pusan. Sampling period was the year of 1986, 1990 and 1994, and the sampling time was 2 days of each site. As the result of comparison with the atmospheric standard of ASHRAE(1980), the average concentrations of lead was above the standard, the average concentrations of chromium was around the standard, and the average concentrations of cadmium and vanadium was below the standard. The average concentrations of manganese was above the standard of industrial environment. And the average concentrations of five metals was higher in the industrial area than the residental area. The average concentrations of lead, cadmium and chromium showed the increase tendency by the year, and the average concentrations of vanadium showed no change, and the average concentrations of manganese showed the decrease tendency. As a result of correlation analysis, lead and cadmium(r=0.31), vanadium and manganese(r=0.24), vanadium and chromium(r=0.19) showed significance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.1
• /
• pp.272-277
• /
• 2010

In respect complication of group, rate of arrearage in domestic bank is composed of various factors. This paper studies focus on estimating the determinants of the rate of arrearage in domestic bank using panel data model. The volume of analysis consist of 3 groups(loaned patterns of enterprise, housekeeping, credit card). Analyzing period be formed over a 54 point(2005. 1~ 2009. 06). In this paper dependent variable setting up rate of arrearage in domestic bank, explanatory(independent) variables composed of the consumer price index, composite stock price index, rate of exchange, the coincident composite index, national housing bonds and employment rate. The result of estimating the rate of arrearage in domestic bank provides empirical evidences of significance positive relationships between the consumer price index However this study provides empirical evidences of significance negative relationships between the coincident composite index and the composite stock price index. The explanatory variables, that is, rate of exchange, national housing bonds and the employment rate are non-significance variables of negative factor. Implication of these findings are discussed for content research and practices.