• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.51-59
• /
• 2024

In this work, we focused on reducing the amount of image data to be sent by extracting and progressively sending prominent image features to high-performance computing systems taking into consideration the right amount of image data required by object identification application. We demonstrate that with our technique called Progressive Object Detection over a Lossless Network using Fragmented DCT Coefficients (Proficient), object identification applications can detect objects with at least 70% combined confidence level by using less than half of the image data.

• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.211-221
• /
• 2024

Pakistan is a top producer and exporter of high-quality rice, but traditional methods are still being used for detecting rice diseases. This research project developed an automated rice blast disease diagnosis technique based on deep learning, image processing, and transfer learning with pre-trained models such as Inception V3, VGG16, VGG19, and ResNet50. The modified connection skipping ResNet 50 had the highest accuracy of 99.16%, while the other models achieved 98.16%, 98.47%, and 98.56%, respectively. In addition, CNN and an ensemble model K-nearest neighbor were explored for disease prediction, and the study demonstrated superior performance and disease prediction using recommended web-app approaches.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1557-1564
• /
• 2014

In this paper, we propose a signal detection technique based on the parallel orthogonal matching pursuit (POMP) is proposed for generalized shift space keying (GSSK) systems, which is a modified version of the orthogonal matching pursuit (OMP) that is widely used as a greedy algorithm for sparse signal recovery. The signal recovery problem in the GSSK systems is similar to that in the compressed sensing (CS). In the proposed POMP technique, multiple indexes which have the maximum correlation between the received signal and the channel matrix are selected at the first iteration, while a single index is selected in the OMP algorithm. Finally, the index yielding the minimum residual between the received signal and the M recovered signals is selected as an estimate of the original transmitted signal. POMP with Quantization (POMP-Q) is also proposed, which combines the POMP technique with the signal quantization at each iteration. The proposed POMP technique induces the computational complexity M times, compared with the OMP, but the performance of the signal recovery significantly outperform the conventional OMP algorithm.

• Journal of the Korean earth science society
• /
• v.38 no.7
• /
• pp.535-545
• /
• 2017

Maritime accidents around the Korean Peninsula are increasing, and the ship detection research using remote sensing data is consequently becoming increasingly important. This study presented a new ship detection algorithm using hyperspectral images that provide the spectral information of several hundred channels in the ship detection field, which depends on high resolution optical imagery. We applied a spectral matching algorithm between the reflection spectrum of the ship deck obtained from two field observations and the ship and seawater spectrum of the hyperspectral sensor of an airborne visible/infrared imaging spectrometer. A total of five detection algorithms were used, namely spectral distance similarity (SDS), spectral correlation similarity (SCS), spectral similarity value (SSV), spectral angle mapper (SAM), and spectral information divergence (SID). SDS showed an error in the detection of seawater inside the ship, and SAM showed a clear classification result with a difference between ship and seawater of approximately 1.8 times. Additionally, the present study classified the vessels included in hyperspectral images by presenting the adaptive thresholds of each technique. As a result, SAM and SID showed superior ship detection abilities compared to those of other detection algorithms.

• Journal of the Korea Society for Simulation
• /
• v.24 no.1
• /
• pp.25-34
• /
• 2015

It is necessary for us to undergo trial and error for eliciting the rational requirement of the acquisition of weapon systems, but the M&S is general approach due to costs and risk of the development. In addition to the acquisition of weapon systems, M&S is extensively employed in the analysis and the training of developed weapon systems. The ADD (Agency for Defense Development) has developed DEVS integrated development environment (QUEST) that provides M&S general ground technique composed of simulation model implementation services, simulation result analysis services, and simulation interface services. This paper describes the interface architecture and the implementation of torpedo target detection section interface simulation system using QUEST. The torpedo target detection section interface simulation system is composed of torpedo target detection section which calculates a result of target detection and the QUEST scenario generator which provides simulation scenario for performance test of the torpedo target detection section. The interface architecture of torpedo target detection section interface simulation system is designed to verify the interface and performance of the torpedo target detection section by linking with the QUEST scenario generator.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.12
• /
• pp.471-480
• /
• 2016

Recently, the damage of cyber attack toward infra-system, national defence and security system is gradually increasing. In this situation, military recognizes the importance of cyber warfare, and they establish a cyber system in preparation, regardless of the existence of threaten. Thus, the study of Intrusion Detection System(IDS) that plays an important role in network defence system is required. IDS is divided into misuse and anomaly detection methods. Recent studies attempt to combine those two methods to maximize advantagesand to minimize disadvantages both of misuse and anomaly. The combination is called Hybrid IDS. Previous studies would not be inappropriate for near real-time network environments because they have computational complexity problems. It leads to the need of the study considering the structure of IDS that have high detection rate and low computational cost. In this paper, we proposed a Hybrid IDS which combines C4.5 decision tree(misuse detection method) and Weighted K-means algorithm (anomaly detection method) hierarchically. It can detect malicious network packets effectively with low complexity by applying mutual information and genetic algorithm based efficient feature selection technique. Also we construct upgraded the the hierarchical structure of IDS reusing feature weights in anomaly detection section. It is validated that proposed Hybrid IDS ensures high detection accuracy (98.68%) and performance at experiment section.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.3
• /
• pp.13-20
• /
• 2009

Techniques for change detection using satellite images enable efficient detection of natural and artificial changes in use of land through multi-phase images. As for change detection, different results are made based on methods of calibration of satellite images, types of input data, and techniques in change analysis. Thus, an analytic technique that is appropriate to objectives of a study shall be applied as results are different based on diverse conditions even when an identical satellite and an identical image are used for change detection. In this study, Normalized Difference Vegetation Index (NDVI) and Principal Component Analysis (PCA) were conducted after geometric calibration of satellite images which went through absolute and relative radiometric calibrations and change detection analysis was conducted using Image Difference (ID) and Image Rationing (IR). As a result, ID-NDVI showed excellent accuracy in change detection related to vegetation. ID-PCA showed 90% of accuracy in all areas. IR-NDVI had 90% of accuracy while it was 70% and below as for paddies and dry fields${\rightarrow}$grassland. IR-PCA had excellent change detection over all areas.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.320-330
• /
• 2020

Fire is difficult to achieve good performance in image detection using deep learning because of its high irregularity. In particular, there is little data on fire detection in underground utility facilities, which have poor light conditions and many objects similar to fire. These make fire detection challenging and cause low performance of deep learning models. Therefore, this study proposed a fire detection model using deep learning and estimated the performance of the model. The proposed model was designed using a combination of a basic convolutional neural network, Inception block of GoogleNet, and Skip connection of ResNet to optimize the deep learning model for fire detection under underground utility facilities. In addition, a training technique for the model was proposed. To examine the effectiveness of the method, the trained model was applied to fire images, which included fire and non-fire (which can be misunderstood as a fire) objects under the underground facilities or similar conditions, and results were analyzed. Metrics, such as precision and recall from deep learning models of other studies, were compared with those of the proposed model to estimate the model performance qualitatively. The results showed that the proposed model has high precision and recall for fire detection under low light intensity and both low erroneous and missing detection capabilities for things similar to fire.

• Journal of Advanced Navigation Technology
• /
• v.25 no.1
• /
• pp.115-123
• /
• 2021

Pine nuts are Korea's representative nut forest products and profitable crops. However, pine nuts are harvested by climbing the trees themselves, thus the risk is high. In order to solve this problem, it is necessary to harvest pine nuts using a robot or an unmanned aerial vehicle(UAV). In this paper, we propose a deep learning based detection method for harvesting pine nut in UAV aerial images. For this, a video was recorded in a real pine forest using UAV, and a data augmentation technique was used to supplement a small number of data. As the data for 3D detection, Unity3D was used to model the virtual pine nut and the virtual environment, and the labeling was acquired using the 3D transformation method of the coordinate system. Deep learning algorithms for detection of pine nuts distribution area and 2D and 3D detection of pine nuts objects were used DeepLabV3+, YOLOv4, and CenterNet, respectively. As a result of the experiment, the detection rate of pine nuts distribution area was 82.15%, the 2D detection rate was 86.93%, and the 3D detection rate was 59.45%.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.101-125
• /
• 2022

Recently, with the development of computing technology and the improvement of the cloud environment, deep learning technology has developed, and attempts to apply deep learning to various fields are increasing. A typical example is anomaly detection, which is a technique for identifying values or patterns that deviate from normal data. Among the representative types of anomaly detection, it is very difficult to detect a contextual anomaly that requires understanding of the overall situation. In general, detection of anomalies in image data is performed using a pre-trained model trained on large data. However, since this pre-trained model was created by focusing on object classification of images, there is a limit to be applied to anomaly detection that needs to understand complex situations created by various objects. Therefore, in this study, we newly propose a two-step pre-trained model for detecting abnormal situation. Our methodology performs additional learning from image captioning to understand not only mere objects but also the complicated situation created by them. Specifically, the proposed methodology transfers knowledge of the pre-trained model that has learned object classification with ImageNet data to the image captioning model, and uses the caption that describes the situation represented by the image. Afterwards, the weight obtained by learning the situational characteristics through images and captions is extracted and fine-tuning is performed to generate an anomaly detection model. To evaluate the performance of the proposed methodology, an anomaly detection experiment was performed on 400 situational images and the experimental results showed that the proposed methodology was superior in terms of anomaly detection accuracy and F1-score compared to the existing traditional pre-trained model.