• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.451-457
• /
• 2018

We propose an automatic detection and classification system of sewer damage database based on artificial intelligence and deep learning. In order to optimize the performance, we implemented a robust system against various environmental variations such as illumination and shadow changes. In our proposed system, a crack detection and damage classification method using a deep learning based Convolutional Neural Network (CNN) is implemented. For optimal results, 9,941 CCTV images with $256{\times}256$ pixel resolution were used for machine learning on the damaged area based on the CNN model. As a result, the recognition rate of 98.76% was obtained. Total of 646 images of $720{\times}480$ pixel resolution were extracted from various sewage DB for performance evaluation. Proposed system presents the optimal recognition rate for the automatic detection and classification of damage in the sewer DB constructed in various environments.

• Journal of Environmental Science International
• /
• v.29 no.5
• /
• pp.551-558
• /
• 2020

This study aims to increase the ability to adapt to the ecosystem and promote a sustainable use of the natural environment, by classifying the types of damaged lands according to various factors, such as the characteristics of the target area and form, cause, and impact of damage. Moreover, the study suggests the development of evaluation categories and criteria by each type. The results obtained are as follows: first, for the assessment of damaged lands, the changed areas were identified utilizing land cover maps. Video analysis was performed to increase the accuracy, and 88 sites were obtained. Second, the types of damage were classified into ecological infrastructure and ecological environment, and the sub-factors of the cause of damage were classified into 12 factors. Third, each evaluation system for the types of damage was composed of four steps, considering each type of damage and the level of evaluators being higher than paraprofessionals. To supplement this study, it will be necessary to utilize the database of damaged lands other than the Seoul Metropolitan Area and conduct an on-site survey for verification in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.786-799
• /
• 2021

Road damage detection is important for road maintenance. With the development of deep learning, more and more road damage detection methods have been proposed, such as Fast R-CNN, Faster R-CNN, Mask R-CNN and RetinaNet. However, because shallow and deep layers cannot be extracted at the same time, the existing methods do not perform well in detecting objects with fewer samples. In addition, these methods cannot obtain a highly accurate detecting bounding box. This paper presents a Multi-level Feature Pyramids method based on M2det. Because the feature layer has multi-scale and multi-level architecture, the feature layer containing more information and obvious features can be extracted. Moreover, an attention mechanism is used to improve the accuracy of local boundary boxes in the dataset. Experimental results show that the proposed method is better than the current state-of-the-art methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.4
• /
• pp.685-693
• /
• 2017

This study aims to effectively respond to urban local rainstorms by classifying the risk against flood damage for each use district. The risk classification is based on sensitivity analysis of the socio-economic damage caused by local rainstorms in Changwon city, Korea by a Fuzzy model using data, such as the districts that provide institutional bases for land use, land prices, which estimate the property values, and floor area ratios, which measures the density and areas of flood damage. The analysis result indicated that flood damage in five districts of Changwon (Masan happo-gu, Masan Hoewon-gu, Sungsan-gu, Euichang-gu, and Jinhae-gu) is highest in the order of commercial areas, residential areas, industrial areas, and forests, which was attributed to high land price and floor area ratio of commercial areas. On the other hand, specific analysis in Masan Hoewon-gu and Sungsan-gu was different from the previous result, indicating that the risk against flood damage may vary according to the districts depending on their local conditions. The analysis from this study can be applied to future urban planning and be used as a guideline to estimate the potential flood damage. Overall, this study is meaningful in that it proposes an effective management of land use as a new resolution to mitigate of urban flood damage within a broader perspective of climate change and urbanization.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.403-413
• /
• 2022

Classification and analysis are improved factors for the realtime automation system. In the field of agriculture, the cultivation of different paddy crop depends on the atmosphere and the soil nature. We need to analyze the moisture level in the area to predict the type of paddy that can be cultivated. For this process, Ensemble Modulation Pattern system and Block Probability Neural Network based classification models are used to analyze the moisture and temperature of land area. The dataset consists of the collections of moisture and temperature at various data samples for a land. The Ensemble Modulation Pattern based feature analysis method, the extract of the moisture and temperature in various day patterns are analyzed and framed as the pattern for given dataset. Then from that, an improved neural network architecture based on the block probability analysis are used to classify the data pattern to predict the class of paddy crop according to the features of dataset. From that classification result, the measurement of data represents the type of paddy according to the weather condition and other features. This type of classification model assists where to plant the crop and also prevents the damage to crop due to the excess of water or excess of temperature. The result analysis presents the comparison result of proposed work with the other state-of-art methods of data classification.

• Journal of Korean Foot and Ankle Society
• /
• v.11 no.2
• /
• pp.130-134
• /
• 2007

Purpose: To investigate the relationship between classification based on simple radiographic findings and arthroscopic findings of the cartilage lesions in medial degenerative arthritis of the ankle joint. Materials and Methods: We studied 41 ankles of 36 patients with asymmetrical narrowing of the medial joint space. Degenerative arthritis following fracture and those with generalized arthritic disease were excluded, but those with a history of ankle sprain were included. Standing radiographs of all patients were graded according to the Takakura classification and the Kellgren-Lawrence (K/L) classification. Arthroscopic findings were classified according to the depth, width, and anteroposterior dimension of articular cartilage damage. Results: According to the Takakura classification, 29 ankles were classified as stage II, 7 cases as stage IIIA and 2 cases as stage IIIB. According to our classification of arthroscopic findings of 29 ankles in stage II, 1 ankle was graded as Grade I, 3 ankles as grade II, 10 ankles as grade III, and 15 ankles as grade IV. Spearman correlation coefficient between Takakura classification and arthroscopic classification was 0.342 (P=0.028), and coefficient between K/L classification and arthroscopic classification was 0.480 (P=0.001). Conclusion: Degenerative changes of the articular cartilage are more advanced than radiographic findings in many patients with ankle degenerative arthritis with asymmetrical narrowing of medial joint space. Therefore, we conclude that more aggressive effort should be made for correct diagnosis and treatment of degenerative arthritis.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.1A
• /
• pp.135-146
• /
• 2008

In this paper, a hybrid damage monitoring scheme for prestressed concrete (PSC) girder bridges by using sequential acceleration and impedance signatures is newly proposed. Damage types of interest include prestress-loss in tendon and flexural stiffness-loss in a concrete girder. The hybrid scheme mainly consists of three sequential phases: damage alarming, damage classification, and damage estimation. In the first phase, the global occurrence of damage is alarmed by monitoring changes in acceleration features. In the second phase, the type of damage is classified into either prestress-loss or flexural stiffness-loss by recognizing patterns of impedance features. In the third phase, the location and the extent of damage are estimated by using two different ways: a mode shape-based damage detection to detect flexural stiffness-loss and a natural frequency-based prestress prediction to identify prestress-loss. The feasibility of the proposed scheme is evaluated on a laboratory-scaled PSC girder model for which hybrid vibration-impedance signatures were measured for several damage scenarios of prestress-loss and flexural stiffness-loss.

• Smart Structures and Systems
• /
• v.20 no.6
• /
• pp.669-682
• /
• 2017

The normalised version of bispectrum, the so-called bicoherence, has often proved a reliable method of damage detection on engineering applications. Indeed, higher-order spectral analysis (HOSA) has the advantage of being able to detect non-linearity in the structural dynamic response while being insensitive to ambient vibrations. Skewness in the response may be easily spotted and related to damage conditions, as the majority of common faults and cracks shows bilinear effects. The present study tries to extend the application of HOSA to damage localisation, resorting to a neural network based classification algorithm. In order to validate the approach, a non-linear finite element model of a 4-meters-long cantilever beam has been built. This model could be seen as a first generic concept of more complex structural systems, such as aircraft wings, wind turbine blades, etc. The main aim of the study is to train a Neural Network (NN) able to classify different damage locations, when fed with bispectra. These are computed using the dynamic response of the FE nonlinear model to random noise excitation.

• Journal of Ocean Engineering and Technology
• /
• v.36 no.5
• /
• pp.295-302
• /
• 2022

The initial response to a marine accident can play a key role to minimize the accident. Therefore, various decision support systems have been developed using sensors, simulations, and active response equipment. In this study, we developed an algorithm to predict damage locations using ship motion data with bidirectional long short-term memory (BiLSTM), a type of recurrent neural network. To reflect the low frequency ship motion characteristics, 200 time-series data collected for 100 s were considered as input values. Heave, roll, and pitch were used as features for the prediction model. The F1-score of the BiLSTM model was 0.92; this was an improvement over the F1-score of 0.90 of a prior model. Furthermore, 53 of 75 locations of damage had an F1-score above 0.90. The model predicted the damage location with high accuracy, allowing for a quick initial response even if the ship did not have flood sensors. The model can be used as input data with high accuracy for a real-time progressive flooding simulator on board.

• Journal of the Korean Society of Safety
• /
• v.31 no.2
• /
• pp.119-126
• /
• 2016

Across the world, the industrialization has increased the frequency of climate anomaly. The size of damage due to recent natural disasters is growing large and fast, and the human damage and economic loss due to disasters are consistently increasing. Urbanization has a structure vulnerable to natural disasters. Therefore, in order to reduce damage from natural disasters, both hardware and software approaches should be utilized. Currently, however, the development of a statistical access process for 'analysis of disaster occurrence factor' and 'prediction of damage costs' for disaster prevention and overall disaster management is inadequate. In case of local governments, overall disaster management system is not established, or even if it is established, unscientific classification system and management lead to low utility of natural statistics of disaster year book. Therefore, in order to minimize disaster damage and for rational disaster management, the disaster damage survey process should be improved. This study selected gale as the focused analysis target among natural disasters recorded in disaster year book such as storm, torrential rain, gale, high seas, and heavy snow, and analyzed disaster survey process. Based on disaster year book, the gale damage size was analyzed and the issues occurring from the correlation of gale and damage amount were examined, so as to suggest an improvement plan for reliable natural disaster information collection and systematic natural disaster damage survey.