• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.959-979
• /
• 2024

Rice pest identification is essential in modern agriculture for the health of rice crops. As global rice consumption rises, yields and quality must be maintained. Various methodologies were employed to identify pests, encompassing sensor-based technologies, deep learning, and remote sensing models. Visual inspection by professionals and farmers remains essential, but integrating technology such as satellites, IoT-based sensors, and drones enhances efficiency and accuracy. A computer vision system processes images to detect pests automatically. It gives real-time data for proactive and targeted pest management. With this motive in mind, this research provides a novel farmland fertility algorithm with a deep learning-based automated rice pest detection and classification (FFADL-ARPDC) technique. The FFADL-ARPDC approach classifies rice pests from rice plant images. Before processing, FFADL-ARPDC removes noise and enhances contrast using bilateral filtering (BF). Additionally, rice crop images are processed using the NASNetLarge deep learning architecture to extract image features. The FFA is used for hyperparameter tweaking to optimise the model performance of the NASNetLarge, which aids in enhancing classification performance. Using an Elman recurrent neural network (ERNN), the model accurately categorises 14 types of pests. The FFADL-ARPDC approach is thoroughly evaluated using a benchmark dataset available in the public repository. With an accuracy of 97.58, the FFADL-ARPDC model exceeds existing pest detection methods.

• Structural Engineering and Mechanics
• /
• v.31 no.5
• /
• pp.507-526
• /
• 2009

Based on numerical and experimental methods, a systematic structural evaluation of a steel natatorium in service was carried out in detail in this paper. Planning of inspection tasks was proposed firstly according to some national codes in China in order to obtain the economic and reliable results. The field visual inspections and static computation were conducted in turn under in-service environmental conditions. Further a three-dimensional finite element model was developed according to its factual geometry properties obtained from the field inspection. An analytical modal analysis was performed to provide the analytical modal properties. The field vibration tests on the natatorium were conducted and then two different system identification methods were used to obtain the dynamic characteristics of the natatorium. A good correlation was achieved in results obtained from the two system identification methods and the finite element method (FEM). The numerical and experimental results demonstrated that the main structure of the natatorium in its present status is safe and it still satisfies the demand of the national codes in China. But the roof system such as purlines and skeletons must be removed and rebuilt completely. Moreover the system identification results showed that field vibration test is sufficient to identify the reliable dynamic properties of the natatorium. The constructive suggestion on structural evaluation of the natatorium is that periodic assessment work must be maintained to ensure the natatorium's safety in the future.

• Korean Journal of Remote Sensing
• /
• v.19 no.1
• /
• pp.61-70
• /
• 2003

This paper proposes an autonomous approach to localize the center of fiducial marks included in aerial photographs without precise geometric information and human interactions. For this localization, we present a conceptual model based on two assumptions representing symmetric characteristics of fiducial area and fiducial mark. The model makes it possible to locate exact center of a fiducial mark by checking the symmetric characteristics of pixel value distribution around the mark. The proposed approach is composed of three steps: (a) determining the symmetric center of fiducial area, (b) finding the center of a fiducial mark with unit pixel accuracy, and finally (c) localizing the exact center up to sub-pixel accuracy. The symmetric center of the mark is calculated tv successively applying three geometric filters: simplified ${\nabla}^2$G (Laplacian of Gaussian) filter, symmetry enhancement filter, and high pass filter. By introducing a self-diagnosis function based on the self-similarity measurement, a way of rejecting unreliable cases of center calculation is proposed, as well. The experiments were done with respect to 284 samples of fiducial marks composed of RMK- and RC-style ones extracted from 51 scanned aerial photographs. It was evaluated in the visual inspection that the proposed approach had resulted the erroneous identification with respect to only one mark. Although the proposed approach is based on weak constraints, being free from the exact geometric model of the fiducial marks, experimental results showed that the proposed approach is sufficiently robust and reliable.

• Structural Engineering and Mechanics
• /
• v.41 no.4
• /
• pp.539-558
• /
• 2012

The diagnosis of bridge serviceability is carried out by a combination of in-situ visual inspection, static and dynamic loading tests and analyses. Structural health monitoring (SHM) using information technology and sensors is increasingly being used for providing a better estimate of structural performance characteristics rather than above traditional methods. Because the mechanical behavior of bridges with various kinds of damage can not be made clear, it is very difficult to estimate both the damage mode and degree of damage of existing bridges. In this paper, the sensitivity of both static and dynamic behaviors of bridges are studied as a measure of damage assessment through experiments on model bridges induced with some specified artificial damages. And, a method of damage assessment of bridges based on those behaviors is discussed in detail. Finally, based on the results, a possible application for structural health monitoring systems for existing bridges is also discussed.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.2_1
• /
• pp.169-176
• /
• 2022

Prognostics and health management (PHM) is recently converging throughout the industry, one of the trending issue is to detect abnormal conditions at decanter centrifuge during water treatment facilities. Wastewater treatment operation produces corrosive gas which results failures on attached sensors. This scenario causes frequent sensor replacement and requires highly qualified manager's visual inspection while replacing important parts such as bearings and screws. In this paper, we propose anomaly detection by measuring the vibration of the decanter centrifuge based on the video camera images. Measuring the vibration of the screw decanter by applying the optical flow technique, the amount of movement change of the corresponding pixel is measured and fed into the LST M model. As a result, it is possible to detect the normal/warning/dangerous state based on LSTM classification. In the future work, we aim to gather more abnormal data in order to increase the further accuracy so that it can be utilized in the field of industry.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.511-516
• /
• 2024

The recently enacted detailed guidelines on the performance evaluation of track facilities presented the necessary requirements regarding the evaluation procedures and implementation methods of track performance evaluation. However, the grade of rail surface damage is determined by external inspection (visual inspection), and there is no choice but to rely only on qualitative evaluation based on the subjective judgment of the inspector. Therefore, in this study, we attempted to develop a diagnostic application that can diagnose rail internal defects using rail surface damage. In the field investigation, rail surface damage was investigated and patterns were analyzed. Additionally, in the indoor test, SEM testing was used to construct image data of rail internal damage, and crack length, depth, and angle were quantified. In this study, a deep learning model (Fast R-CNN) using image data constructed from field surveys and indoor tests was applied to the application. A rail surface damage diagnosis application (App) using a deep learning model that can be used on smart devices was developed. We developed a smart diagnosis system for rail surface damage that can be used in future track diagnosis and performance evaluation work.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.5
• /
• pp.187-195
• /
• 2018

In this study, using real-time gaze tracking and head tracking method, we intended to quantitatively evaluate the deviation between the patient's head and gaze direction while minimizing inspection errors due to apraxia of conventional paper-based examination respectively. As a result, we developed a software that can quantitatively measure gaze and head movement information, and computerized the line bisection and star cancelation test, which are generally used as conventional paper test. In addition, for the rehabilitation training, contents corresponding to the visual technology of Warren's visual hierarchical model lower level are implemented and can be performed repetitively and independently. This allows the patient to actively participate in rehabilitation and quantitatively compare the degree of improvement.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.19 no.4
• /
• pp.517-532
• /
• 2021

Safe geological disposal of spent nuclear fuel (SNF) requires knowledge of the deep hydrochemical characteristics of the repository site. Here, we conducted a set of deep hydrochemical investigations using a 750-m borehole drilled in a model granite system in Wonju, South Korea. A closed investigation system consisting of a double-packer, Waterra pump, flow cell, and water-quality measurement unit was used for in situ water quality measurements and subsequent groundwater sampling. We managed the drilling water labeled with a fluorescein dye using a recycling system that reuses the water discharged from the borehole. We selected the test depths based on the dye concentrations, outflow water quality parameters, borehole logging, and visual inspection of the rock cores. The groundwater pumped up to the surface flowed into the flow cell, where the in situ water quality parameters were measured, and it was then collected for further laboratory measurements. Atmospheric contact was minimized during the entire process. Before hydrochemical measurements and sample collection, pumping was performed to purge the remnant drilling water. This study on a model borehole can serve as a reference for the future development of deep hydrochemical investigation procedures and techniques for siting processes of SNF repositories.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.10
• /
• pp.65-76
• /
• 2021

There is a possibility of cavities occurring inside and behind the lining of an aged tunnel structure. In most cases, it is not easy to check the cavity because it exists in a place where visual inspection is impossible. Recently, attempts have been made to evaluate the condition of the tunnel lining and the backfill materials using non-destructive tests such as Ground Penetrating Radar, and various related model tests and numerical analysis studies have been conducted. In this study, the GPR signal characteristics for tunnel lining model testing were analyzed using gprMax software, which was compared with model test results. The numerical model applied to the model test reasonably simulated the electromagnetic wave signal according to the change of the material such as tunnel lining and internal cavity. Using the verified GPR model, B-scan data for the development of the GPR signal analysis technique were obtained, which can evaluate the thickness of the tunnel lining, the presence of the cavity, the effect of the waterproof membrane, and the frequency band.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.6
• /
• pp.665-676
• /
• 2021

As the number of deteriorated buildings increases, the importance of safety diagnosis and maintenance of buildings has been rising. Existing visual investigations and building safety diagnosis objectivity and reliability are poor due to their reliance on the subjective judgment of the examiner. Therefore, this study presented the limitations of the previously conducted appearance investigation and proposed 3D Point Cloud data to increase the accuracy of existing detailed inspection data. In addition, this study conducted a calculation of an objective building safety grade using a Deep-Neural Network(DNN) structure. The DNN structure is generated using the existing detailed inspection data and precise safety diagnosis data, and the safety grade is calculated after applying the state evaluation data obtained using a 3D Point Cloud model. This proposed process was applied to 10 deteriorated buildings through the case study, and achieved a time reduction of about 50% compared to a conventional manual safety diagnosis based on the same building area. Subsequently, in this study, the accuracy of the safety grade calculation process was verified by comparing the safety grade result value with the existing value, and a DNN with a high accuracy of about 90% was constructed. This is expected to improve economic feasibility in the future by increasing the reliability of calculated safety ratings of old buildings, saving money and time compared to existing technologies.