• Korean Journal of Remote Sensing
• /
• v.25 no.2
• /
• pp.175-184
• /
• 2009

This study attempts to analyze the difference among the variations of ecological distribution in Gobi desert and Manchuria through satellite based land cover classification. This was motivated by two well-known facts: 1) Gobi desert, which is an old source region, had been gradually expanded eastward; 2) Manchuria, which is located in east of Gobi desert, was observed as a new source region of yellow dust. An unsupervised classification called ISODATA clustering method was employed to detect the land cover change and to characterize the status of desertification and its expanding trends using NDVI (Normalized Difference Vegetation Index) derived from VEGETATION sensor onboard the SPOT satellite for 1999 and 2007. We analyzed NDVI annual variation pattern for every classes and divide into 5 level according to their vegetation's density level based on NDVI. As results, Gobi desert is showed positive variation: a decrease $78,066km^2$ in central Gobi desert and out skirts of Gobi desert (level-0) but Manchuria area is worse than previous time: an increase $25,744km^2$.

• Korean Journal of Remote Sensing
• /
• v.20 no.6
• /
• pp.369-382
• /
• 2004

The purpose of this study is the investigation of applicability of LSMA(Linear Spectral Mixture Analysis) on the geological uses with different radiometric and spatial types of sensor images such as Terra ASTER and LANDSAT 7 ETM+. As for the actual application case, geologic mapping for mineral exploration using ASTER and ETM+ at the Mongolian plateau region was carried out. After the pre-processing such as the geometric corrections and calibration of radiance, 7 endmembers, as spectral classes for geologic rock types, related to spectral signature deviation for the given application was determined by the pre-surveyed geological mapping information and the correlation matrix analysis, and total 20 images of ASTER and ETM+ were used to LSMA processing. As the results, fraction maps showing individual mineral types in the study area are presented. It concluded that this approach based on LSMA using ETM+ and ASTER is regarded as one of the effective schemes for geologic remote sensing.

• Korean Journal of Remote Sensing
• /
• v.20 no.6
• /
• pp.419-425
• /
• 2004

This study has proposed a data fusion method based on the Dempster-Shafer evidence theory The Dempster-Shafer fusion uses mass functions obtained under the assumption of class-independent Gaussian assumption. In the Dempster-Shafer approach, uncertainty is represented by 'belief interval' equal to the difference between the values of 'belief' function and 'plausibility' function which measure imprecision and uncertainty By utilizing the Dempster-Shafer scheme to fuse the data from multiple sensors, the results of classification can be improved. It can make the users consider the regions with mixed classes in a training process. In most practices, it is hard to find the regions with a pure class. In this study, the proposed method has applied to the KOMPSAT-EOC panchromatic image and LANDSAT ETM+ NDVI data acquired over Yongin/Nuengpyung. area of Kyunggi-do. The results show that it has potential of effective data fusion for multiple sensor imagery.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.19-27
• /
• 2020

In this paper, we propose a machine learning method for diagnosing the failure of a gas pressure regulator. Originally, when implementing a machine learning model for detecting abnormal operation of a facility, it is common to install sensors to collect data. However, failure of a gas pressure regulator can lead to fatal safety problems, so that installing an additional sensor on a gas pressure regulator is not simple. In this paper, we propose various machine learning approach for diagnosing the abnormal operation of a gas pressure regulator with only the flow rate and gas pressure data collected from a gas pressure regulator itself. Since the fault data of a gas pressure regulator is not enough, the model is trained in all classes by applying the over-sampling method. The classification model was implemented using Gradient boosting, 1D Convolutional Neural Networks, and LSTM algorithm, and gradient boosting model showed the best performance among classification models with 99.975% accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.7
• /
• pp.935-941
• /
• 2020

People estimation is important to provide IoT services. Most people counting technologies use camera or sensor data. However, the conventional technologies have the disadvantages of invasion of privacy and the need to install extra infrastructure. This paper proposes a method for estimating the number of people using a Wi-Fi AP. We use channel state information of Wi-Fi and analyze that using deep learning technology. It can be achieved by pre-installed Wi-Fi infrastructure that reduce cost for people estimation and privacy infringement. The proposed algorithm uses a k-binding data for pre-processing process and a 1D-CNN learning model. Two APs were installed to analyze the estimation results of six people. The result of the accurate number estimation was 64.8%, but the result of classifying the number of people into classes showed a high result of 84.5%. This algorithm is expected to be applicable to estimate the density of people in a small space.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.296-302
• /
• 2021

This paper proposes an approach to the classification of respiratory states of humans based on visual information. An ultra-wide-band radar sensor acquired respiration signals, and the respiratory states were classified based on two-dimensional (2D) images instead of one-dimensional (1D) vectors. The 1D vector-based classification of respiratory states has limitations in cases of various types of normal respiration. The deep neural network model was employed for the classification, and the model learned the 2D images of respiration signals. Conventional classification methods use the value of the quantified respiration values or a variation of them based on regression or deep learning techniques. This paper used 2D images of the respiration signals, and the accuracy of the classification showed a 10% improvement compared to the method based on a 1D vector representation of the respiration signals. In the classification experiment, the respiration states were categorized into three classes, normal-1, normal-2, and abnormal respiration.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1267-1267
• /
• 2001

The existing fruit sorter has the method of tilting tray and extracting fruits by the action of solenoid or springs. In peaches, the most sort processing is supported by man because the sorter make fatal damage to peaches. In order to sustain commodity and quality of peach non-destructive, non-contact and real time based sorter was needed. This study was performed to develop peach sorter using near-infrared spectroscopy in real time and nondestructively. The prototype was developed to decrease internal and external damage of peach caused by the sorter, which had a way of extracting tray with it. To decrease positioning error of measuring sugar contents in peaches, fiber optic with two direction diverged was developed and attached to the prototype. The program for sorting and operating the prototype was developed using visual basic 6.0 language to measure several quality index such as chlorophyll, some defect, sugar contents. The all sorting result was saved to return farmers for being index of good quality production. Using the prototype, program and MLR(multiple linear regression) model, it was possible to estimate sugar content of peaches with the determination coefficient of 0.71 and SEC of 0.42bx using 16 wavelengths. The developed MLR model had determination coefficient of 0.69, and SEP of 0.49bx, it was better result than single point measurement of 1999's. The peach sweetness grading system based on NIR reflectance method, which consists of photodiode-array sensor, quartz-halogen lamp and fiber optic diverged two bundles for transmitting the light and detecting the reflected light, was developed and evaluated. It was possible to predict the soluble solid contents of peaches in real time and nondestructively using the system which had the accuracy of 91 percentage and the capacity of 7,200 peaches per an hour for grading 2 classes by sugar contents. Draining is one of important factors for production peaches having good qualities. The reason why one farm's product belows others could be estimated for bad draining, over-much nitrogen fertilizer, soil characteristics, etc. After this, the report saved by the peach grading system will have to be good materials to farmers for production high quality peaches. They could share the result or compare with others and diagnose their cultural practice.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.131-138
• /
• 2024

The ability of Combat Management System(CMS) to respond quickly and accurately to threat to a naval vessel is directly related to the survivability and combat power of the vessel. However, current method for detecting enemy submarine periscope in CMS rely on manual and subjective method that require operators to manually verify and analyze information received from sensor. This delays the response time to the threat, making the vessel less viable. This paper introduces a periscope detection algorithm that classifies the plot information generated by High Resolution Range Profile(HRRP) into probability-based suspicion classes and dramatically reduces threat response time through classified notifications. Algorithm validation showed 133.3791 × 10⁶ times faster and 12.78%p higher detection rate than operator, confirming the potential for reduces threat response time to increase vessel survivability.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.27 no.4
• /
• pp.1-14
• /
• 2024

Otters, designated as Class I endangered wildlife due to population declines resulting from urban development and stream burial, have seen increased appearances in freshwater environments since the nationwide ban on stream filling in 2020 and the implementation of urban stream restoration projects. There is a pressing need for scientific and strategic conservation measures for otters, an umbrella and vulnerable species in aquatic ecosystems. Therefore, this study predicts potential otter habitats using the species distribution model MaxEnt, focusing on Hwangguji Stream in Suwon, and proposes conservation strategies. Otter signs were surveyed over three years from 2019 to 2021 with citizen scientists, serving as presence data for the model. The model's outcomes were enhanced by analyzing 'river nature map' as a boundary. MaxEnt compared the performance of 60 combinations of feature classes and regularization multipliers to prevent model complexity and overfitting. Additionally, unmanned sensor cameras observed otter density for model validation, confirming correlations with the species distribution model results. The 'LQ-5.0' parameter combination showed the highest explanatory power with an AUC of 0.853. The model indicated that the 'adjacent land use' variable accounted for 31.5% of the explanation, with a preference for areas around cultivated lands. Otters were found to prefer shelter rates of 10-30% in riparian forests within 2 km of bridges. Higher otter densities observed by unmanned sensors correlated with increasing model values. Based on these results, the study suggests three conservation strategies: establishing stable buffer zones to enhance ecological connectivity, improving water quality against non-point source pollution, and raising public awareness. The study provides a scientific basis for potential otter habitat management, effective conservation through governance linking local governments, sustainable biodiversity goals, and civil organizations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.10
• /
• pp.633-639
• /
• 2018

High-resolution images using remote sensing (RS) is importance to secure for spatial classification depending on the characteristics of the complex and various factors that make up the river environment. The purpose of this study is to evaluate the accuracy of the classification results and to suggest the possibility of applying the high resolution hyperspectral images obtained by using the drone to perform spatial classification. Hyperspectral images obtained from study area were reduced the dimensionality with PCA and MNF transformation to remove effects of noise. Spatial classification was performed by supervised classifications such as MLC(Maximum Likelihood Classification), SVM(Support Vector Machine) and SAM(Spectral Angle Mapping). In overall, the highest classification accuracy was showed when the MLC supervised classification was used by MNF transformed image. However, it was confirmed that the misclassification was mainly found in the boundary of some classes including water body and the shadowing area. The results of this study can be used as basic data for remote sensing using drone and hyperspectral sensor, and it is expected that it can be applied to a wider range of river environments through the development of additional algorithms.