• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.12
• /
• pp.6018-6033
• /
• 2018

Fires are a common cause of catastrophic personal injuries and devastating property damage. Every year, many fires occur and threaten human lives and property around the world. Providing early important sign for early fire detection, and therefore the detection of smoke is always the first step in fire-alarm systems. In this paper we propose an automatic smoke detection system built on camera surveillance and image processing technologies. The key features used in our algorithm are to detect and track smoke as moving objects and distinguish smoke from non-smoke objects using a convolutional neural network (CNN) model for cascade classification. The results of our experiment, in comparison with those of some earlier studies, show that the proposed algorithm is very effective not only in detecting smoke, but also in reducing false positives.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.101-106
• /
• 2021

Breast cancer is the number one cause of deaths from cancer in women, knowing the type of breast cancer in the early stages can help us to prevent the dangers of the next stage. The performance of the deep learning depends on large number of labeled data, this paper presented convolutional neural network for classification breast cancer from images to benign or malignant. our network contains 11 layers and ends with softmax for the output, the experiments result using public BreakHis dataset, and the proposed methods outperformed the state-of-the-art methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2904-2926
• /
• 2022

Currently, diabetes is the most common chronic disease in the world, affecting 23.7% of the population in the Kingdom of Saudi Arabia. Diabetes may be the cause of lower-limb amputations, kidney failure and blindness among adults. Therefore, diagnosing the disease in its early stages is essential in order to save human lives. With the revolution in technology, Artificial Intelligence (AI) could play a central role in the early prediction of diabetes by employing Machine Learning (ML) technology. In this paper, we developed a diagnosis system using machine learning models for the detection of type 2 diabetes among adults, through the adoption of two different diabetes datasets: one for training and the other for the testing, to analyze and enhance the prediction accuracy. This work offers an enhanced classification accuracy as a result of employing several pre-processing methods before applying the ML models. According to the obtained results, the implemented Random Forest (RF) classifier offers the best classification accuracy with a classification score of 98.95%.

• Journal of Digestive Cancer Research
• /
• v.5 no.1
• /
• pp.5-15
• /
• 2017

Hepatocellular carcinoma (HCC) is the sixth most common cancer and second leading cause of cancer-related death in the world. The aggressive but not always predictable pattern of HCC causes the limited treatment option and poorer outcome. Many researches had already proven the heterogeneity of HCC is one of the major challenges for treatment option and prognosis prediction. Molecular subtyping of HCC and selection of patient based on molecular profile can provide the optimization in the treatment and prognosis prediction. In this review, we have tried to summarize the molecular classification of HCC proposed by different valuable researches presented in the logistic way.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.1
• /
• pp.61-64
• /
• 2024

As research on autonomous driving technology becomes more active, various studies on signal recognition of traffic lights are also being conducted. When recognizing traffic lights with different purposes and shapes, such as pedestrian traffic lights, vehicle-only traffic lights, and right-turn traffic lights, existing classification methods may cause misrecognition problems. Therefore, in this study, we studied a model that allows accurate signal recognition by subdividing the classification of signals according to the purpose and type of traffic lights. A signal recognition model was created by classifying traffic lights according to their shape and purpose into horizontal, vertical, right turn, etc., and by comparing them with the existing signal recognition model based on YOLOv5, it was confirmed that more correct and accurate recognition was possible.

• The Journal of the Korea Contents Association
• /
• v.7 no.11
• /
• pp.309-319
• /
• 2007

Right comprehension of the natural disaster could reduce the damage of human life and property by explaining the cause of the disaster and considering a counterplan to decrease or prevent it. To do this, it should precede to clarify the category of the natural disaster and classification. Also, when the disaster occurs, swift site survey and the establishment of the data by the professionals should be done for clarifying the reason. Our classification of the natural disaster is written on the Law of the Nature Disaster Relief. But, this classification is made for the management of the disaster, so it is required to review the establishment of the technical information by the professionals. Therefore, the Korean type classification is required considered by the professionals who collect and study the information of the natural disaster for the other countries. If the DB of the natural disaster is made, it is able to get various services through the internet virtual space and it will be helpful to prepare the prevent countermeasures against the disaster. In this research, the korean type classification plan of the natural disaster is suggested which is suitable to the professional technology by collecting and analyzing the domestic and the international classification of the natural disaster.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.5
• /
• pp.3219-3221
• /
• 2013

Background: This study used receiver operating characteristic (ROC) curves to screen Surveillance, Epidemiology and End Results (SEER) skin melanoma data to identify and quantify the effects of socioeconomic factors on cause specific survival. Methods: 'SEER cause-specific death classification' used as the outcome variable. The area under the ROC curve was to select best pretreatment predictors for further multivariate analysis with socioeconomic factors. Race and other socioeconomic factors including rural-urban residence, county level % college graduate and county level family income were used as predictors. Univariate and multivariate analyses were performed to identify and quantify the independent socioeconomic predictors. Results: This study included 49,999 parients. The mean follow up time (SD) was 59.4 (17.1) months. SEER staging (ROC area of 0.08) was the most predictive foctor. Race, lower county family income, rural residence, and lower county education attainment were significant univariates, but rural residence was not significant under multivariate analysis. Living in poor neighborhoods was associated with a 2-4% disadvantage in actuarial cause specific survival. Conclusions: Racial and socioeconomic factors have a significant impact on the survival of melanoma patients. This generates the hypothesis that ensuring access to cancer care may eliminate these outcome disparities.

• Proceedings of the Safety Management and Science Conference
• /
• 2007.04a
• /
• pp.113-123
• /
• 2007

Through so that accident of semiconductor industry deduces unsafe factor of the person center on unsafe behaviour that incident history and questionnaire and I made starting point that extract very important factor. It served as a momentum that make up base that analyzes factors that happen based on factor that extract factor cause classification for the first factor, the second factor and the third factor and presents model of human error. Factor for whole defines factor component for human factor and to cause analysis 1 stage in human factor and step that wish to do access of problem and it do analysis cause of data of 1 step. Also, see significant difference that analyzes interrelation between leading persons about human mistake in semiconductor industry and connect interrelation of mistake by this. Continuously, dictionary road map to human error theoretical background to basis traditional accidental cause model and modern accident cause model and leading persons. I wish to present model and new model in semiconductor industry by backbone that leading persons of existing scholars who present model of existent human error deduce relation. Finally, I wish to deduce backbone of model of pre-suppression about accident leading person of the person center.

• The Journal of Pediatrics of Korean Medicine
• /
• v.16 no.2
• /
• pp.111-128
• /
• 2002

Objectives : The aim of this study was to investigate the classification methods of the cause of Allergic Rhinitis for Children. Methods : We surveyed the oriental & western medical book concerning the Allergic Rhinitis for Children. Results : 1. The Oriental medicine, Allergic Rhinitis is belong to the BiGu, BunChe and the symptoms are watery rhinorrhea, sneezing and nasal obstruction. 2. The cause of disease is the weak of lung, spleen and kidney, and invasion in to nasal cavity of Poong Han etc a wrong air. 3. In children, the cause of disease is the weak of lung and spleen. and the aim of the treatment is helping the vital energy and expelling the vice.

• Journal of Korean Society of Water and Wastewater
• /
• v.25 no.2
• /
• pp.141-152
• /
• 2011

In this study, we extracted effective factors of pipe burst from the status data of water asset, operating data of pressure, volume and etc. and 7 years' pipe burst and repair records. The extracted factors were sorted by each attribution and then a statistical analysis was performed to generate a pipe burst probability function using the logistic regression model. As the result, material, diameter, length, laying year, pressure and road width affected to pipe burst significantly. Especially, in case of small diameter, laying year was most effective factor and in case of steel pipe, external loading was main cause of burst, and in case of cast iron, PE, PC, HP pipes, the deterioration of joint was main cause. The other side, as a result of Hosmer-Lemeshow goodness of fit test the models are turned out significant statistically. Also the classification criteria were determined to minimize the total cost from classification errors, when the predicted probability was more than 18% this pipe could have a chance of burst.