• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.6
• /
• pp.7-14
• /
• 2019

The automatic monitoring and detection of crowd behavior in the surveillance videos has obtained significant attention in the field of computer vision due to its vast applications such as security, safety and protection of assets etc. Also, the field of crowd analysis is growing upwards in the research community. For this purpose, it is very necessary to detect and analyze the crowd behavior. In this paper, we proposed a deep learning-based method which detects abnormal activities in surveillance cameras installed in a smart city. A fine-tuned VGG-16 model is trained on publicly available benchmark crowd dataset and is tested on real-time streaming. The CCTV camera captures the video stream, when abnormal activity is detected, an alert is generated and is sent to the nearest police station to take immediate action before further loss. We experimentally have proven that the proposed method outperforms over the existing state-of-the-art techniques.

• The Plant Pathology Journal
• /
• v.37 no.5
• /
• pp.437-445
• /
• 2021

Tilletia laevis Kuhn (syn. Tilletia foetida (Wallr.) Liro.) causes wheat common bunt, which is one of the most devastating plant diseases in the world. Common bunt can result in a reduction of 80% or even a total loss of wheat production. In this study, the characteristics of T. laevis infection in compatible wheat plants were defined based on the combination of scanning electron microscopy, transmission electron microscopy and laser scanning confocal microscopy. We found T. laevis could lead to the abnormal growth of wheat tissues and cells, such as leakage of chloroplasts, deformities, disordered arrangements of mesophyll cells and also thickening of the cell wall of mesophyll cells in leaf tissue. What's more, T. laevis teliospores were found in the roots, stems, flag leaves, and glumes of infected wheat plants instead of just in the ovaries, as previously reported. The abnormal characteristics caused by T. laevis may be used for early detection of this pathogen instead of molecular markers in addition to providing theoretical insights into T. laevis and wheat interactions for breeding of common bunt resistance.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.7
• /
• pp.3637-3641
• /
• 2016

To determine the prevalence of human papillomavirus (HPV) among women with atypical squamous cells of undetermined significance (ASC-US) referred to colposcopy and the implications for clinical management in low- and middle-income countries (LMIC), the present study was conducted. We included 200 women living in $Maring{\acute{a}}$/Brazil referred to colposcopy service between August 2012 and March 2013 due to an abnormal cytology from ASC-US until high-grade intraepithelial lesion (HSIL). HPV was detected and genotyped by polymerase chain reaction (PCR). The mean age was $36.8{\pm}10.5$ years, and women with and without ASC-US had similar mean ages ($37.4{\pm}11.5$ and $36.4{\pm}9.96$ years, respectively). The highest prevalence of ASC-US occurred at 20-24 years (40%). HPV-DNA was positive in 164 (82.0%) women.Of the 57 women with ASC-US, 30 (52.6%) were HPV-DNA-positive and 21 (70%) were high-risk HPV-positive (HR-HPV); the latter was similar to women without ASC-US (76.9%) but with other abnormal cytological findings present. Our data demonstrated that performing tests for HR-HPV can be used for management of women with ASC-US to support the decision of which women should be referred for an immediate or later colposcopy. The same conclusions can be applied to other LMICs for which HPV testing for primary screening has not been adopted.

• Tribology and Lubricants
• /
• v.27 no.3
• /
• pp.125-133
• /
• 2011

The purpose of this study is to develop an engine oil quality monitoring system to warn the abnormal condition of engine oil. To do this, first of all, it is needed a personal controller development to measure the capacitance of a pre-developed engine oil deterioration detection sensor integrated with an oil filter. To measure the capacitance of engine oil in the sensor, it is used the way measuring the electric charging time in a capacitor by impressing DC volt. This method has merits on cost and signal stability. The measured capacitance is compensated by comparing with the one measured by an impedance analyzer. Also, using the dielectric constant gained by an impedance analyzer, the calculating equation of the dielectric constant of engine oil related with the currently developed sensor is decided. Then, the deterioration degree of engine oil is estimated according to the change rate of dielectric constant between green oil and used oil. Finally, using this dielectric constant information together with engine oil temperature and pressure, the currently developed engine oil quality monitoring system is to tell the abnormal state of engine oil.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.5 no.1
• /
• pp.27-37
• /
• 1997

Internal combustion engine is the main source of environmental pollutants and therefore better technology is required to reduce harmful elements from the exhaust gases all over the world. Especially, harmful elements from the exhaust gases are caused by incomplete combustion of mixture inside the engine cylinder and this abnormal combustion like misfire or partial burning is the direct cause of the air pollution and engine performance degradation. the object of this research is to detect abnormal combustion like misfire and to keep the engine performance in the optimal operating state. Development of a new system therefore could be applied to a real car. To realize this, the spark-plug in a conventional ignition system is used as a misfire detection sensor and breakdown voltage is analyzed. In this research, bias voltage(about 3kV) was applied to the electrodes of spark-plug and breakdown voltage signal is obtained. This breakdown voltage signal is analyzed and found that a combustion phenomena in engine cylinder has close relationship with harmonic coefficient K which was introduced in this research. Newly developed combustion diagnostic method( breakdown voltage signal analysis) from this research can be used for the combustion diagnostic and combustion control system in an real car.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.632-657
• /
• 2022

Detecting web attacks is a major challenge, and it is observed that the use of simple models leads to low sensitivity or high false positive problems. In this study, we aim to develop a robust two-stage deep learning based stacked ensemble web application firewall. Normal and abnormal classification is carried out in the first stage of the proposed WAF model. The classification process of the types of abnormal traffics is postponed to the second stage and carried out using an integrated stacked ensemble model. By this way, clients' requests can be served without time delay, and attack types can be detected with high sensitivity. In addition to the high accuracy of the proposed model, by using the statistical similarity and diversity analyses in the study, high generalization for the ensemble model is achieved. Within the study, a comprehensive, up-to-date, and robust multi-class web anomaly dataset named GAZI-HTTP is created in accordance with the real-world situations. The performance of the proposed WAF model is compared to state-of-the-art deep learning models and previous studies using the benchmark dataset. The proposed two-stage model achieved multi-class detection rates of 97.43% and 94.77% for GAZI-HTTP and ECML-PKDD, respectively.

• Proceedings of the KIEE Conference
• /
• 2000.07b
• /
• pp.1286-1288
• /
• 2000

Commutation failure can be considered as the severest abnormal operation of thyristor HVDC converter. During the failure, power conversion from DC to AC is stopped until the AC voltage get recovered. The process of thyristor converter is subscribed at normal and abnormal state, respectively. The detection and the protection for Cheju HVDC are explained by computer simulation results.

• IE interfaces
• /
• v.20 no.3
• /
• pp.288-297
• /
• 2007

Success of semiconductor/LCD industry depends on its yield and quality of product. For the purpose, FDC (Fault Detection and Classification) system is used to diagnose fault state in main manufacturing processes by monitoring time series data collected by equipment sensors which represent various conditions of the equipment. The data set is segmented at the start and end of each product lot processing by a trigger event module. However, in practice, segmented sensor data usually have the features of data asynchronization such as different start points, end points, and data lengths. Due to the asynchronization problem, false alarm (type I error) and missed alarm (type II error) occur frequently. In this paper, we propose a robust process fault detection system by integrating a process event detection method and a similarity measuring method based on dynamic time warping algorithm. An experiment shows that the proposed system is able to recognize abnormal condition correctly under the asynchronous data situation.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.7
• /
• pp.1-5
• /
• 2007

This paper presents the new detection method for the end of life on fluorescent lamps. At the end of lamp life, the lamp voltage and current asymmetrically increase and decrease more than normal state. If the ballast system does not have the protection function especially for T4 and T5 lamps, we may see the melting socket which is connected to the end of the lamp. To protect from this kind of abnormal status is the most important thing in the ballast system that has very old lamps.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.300-302
• /
• 2006

Middleware offers function that user application program can transmit data independently of network device. Connection management about network connection of module is important for normal service of module base personal robot. Unpredictable network disconnection is influenced to whole robot performance in module base personal robot. For this, Middleware must be offer two important function. The first is function of error detection and reporting about abnormal network disconnection. Therefore, middleware need method for network error detection and module management to consider special quality that each network device has. The second is the function recovering that makes the regular service possible. When the module closed from connection reconnects, as this service reports connection state of the corresponding module, the personal robot resumes the existing service. In this paper proposed method of network connection management for to support fault tolerant about network error of network module based personal robot.