• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.5
• /
• pp.591-603
• /
• 2014

In this paper, we have described the characteristics of the Underwater Distributed Sensor Network (UDSN) and proposed the conceptual design guideline by an effectiveness analysis. To perform the effectiveness analysis, we defined an battlefield environment, and then analyzed principal components which compose the UDSN to find out simulation parameters and system constraints. We have chosen a measure of effectiveness based on a target trajectory, which could enhance intuitive understanding about current status, and performed various simulations to reveal critical design parameters in terms of sensor node types, arrangement, cost and combination of detection information.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.10
• /
• pp.148-158
• /
• 2015

It is difficult to test a detection system in underwater acoustics channel environments. The system can be evaluated by using simulation analysis tool. In this paper, a simulation tool is proposed to analyze the effectiveness of underwater acoustics detection based on database for real environments. First, the underwater environment is built based on HYCOM underwater environment database. Then, a multipath characteristic is considered through calculating underwater acoustics propagation path/pressure based on the ray theory. Also, hydrophone thermal noise and underwater ambient noise are considered to reflect underwater noise characteristics.

• Journal of the Korea Society for Simulation
• /
• v.19 no.2
• /
• pp.63-72
• /
• 2010

In the future warfare, the importance of the counter-fire operation is increasing. The counter-fire operation is divided into offensive counter-fire operation and defensive counter-fire operation. Reviewing the researches done so far, the detection asset of offensive counter-fire operation called UAV(Unmanned Aerial Vehicle) and its operational effectiveness analysis is continually progressing. However, the analysis of the detection asset of defensive counterfire called Target Acquisition Radar(TAR) and its quantitative operational effectiveness are not studied yet. Therefore, in this paper, we studied operational effectiveness of TAR using C2 Theory & MANA Simulation model, and showed clear quantitative analysis results by comparing both cases of using TAR and not using TAR.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.4
• /
• pp.316-321
• /
• 2008

Advanced computer network technology enables computers to be connected in an open network environment. Despite the growing numbers of security threats to networks, most intrusion detection identifies security attacks mainly by detecting misuse using a set of rules based on past hacking patterns. This pattern matching has a high rate of false positives and can not detect new hacking patterns, which makes it vulnerable to previously unidentified attack patterns and variations in attack and increases false negatives. Intrusion detection and analysis technologies are thus required. This paper investigates the asymmetric costs of false errors to enhance the performances the detection systems. The proposed method utilizes the network model to consider the cost ratio of false errors. By comparing false positive errors with false negative errors, this scheme achieved better performance on the view point of both security and system performance objectives. The results of our empirical experiment show that the network model provides high accuracy in detection. In addition, the simulation results show that effectiveness of anomaly traffic detection is enhanced by considering the costs of false errors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.3076-3092
• /
• 2020

An IKPCA-ELM-based intrusion detection method is developed to address the problem of the low accuracy and slow speed of intrusion detection caused by redundancies and high dimensions of data in the network. First, in order to reduce the effects of uneven sample distribution and sample attribute differences on the extraction of KPCA features, the sample attribute mean and mean square error are introduced into the Gaussian radial basis function and polynomial kernel function respectively, and the two improved kernel functions are combined to construct a hybrid kernel function. Second, an improved particle swarm optimization (IPSO) algorithm is proposed to determine the optimal hybrid kernel function for improved kernel principal component analysis (IKPCA). Finally, IKPCA is conducted to complete feature extraction, and an extreme learning machine (ELM) is applied to classify common attack type detection. The experimental results demonstrate the effectiveness of the constructed hybrid kernel function. Compared with other intrusion detection methods, IKPCA-ELM not only ensures high accuracy rates, but also reduces the detection time and false alarm rate, especially reducing the false alarm rate of small sample attacks.

• Smart Structures and Systems
• /
• v.12 no.3_4
• /
• pp.291-308
• /
• 2013

A novel concept of transmissibility based on a wavelet transform for structural damage detection is presented in this paper. The main objective of the research was the development of a method for detecting slight damage at the incipient stage. As a vibration-based approach, the concept of transmissibility has attracted considerable interest because of its advantages and effectiveness in damage detection. However, like other vibration-based methods, transmissibility-based approaches suffer from insensitivity to slight local damage because of the regularity of the traditional Fourier transform. Therefore, the powerful signal processing techniques must be found to solve this problem. Wavelet transform that is able to capture subtle information in measured signals has received extensive attention in the field of damage detection in recent decades. In this paper, we first propose a novel transmissibility concept based on the wavelet transform. Outlier analysis was adopted to construct a damage detection algorithm with wavelet-based transmissibility. The feasibility of the proposed method was numerically investigated with a typical six-degrees-of-freedom spring-mass system, and comparative investigations were performed with a conventional transmissibility approach. The results demonstrate that the proposed transmissibility is more sensitive than conventional transmissibility, and the former is a promising tool for structural damage detection at the incipient stage.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.177-189
• /
• 2023

Malware detection is an increasingly important operational focus in cyber security, particularly given the fast pace of such threats (e.g., new malware variants introduced every day). There has been great interest in exploring the use of machine learning techniques in automating and enhancing the effectiveness of malware detection and analysis. In this paper, we present a deep recurrent neural network solution as a stacked Long Short-Term Memory (LSTM) with a pre-training as a regularization method to avoid random network initialization. In our proposal, we use global and short dependencies of the inputs. With pre-training, we avoid random initialization and are able to improve the accuracy and robustness of malware threat hunting. The proposed method speeds up the convergence (in comparison to stacked LSTM) by reducing the length of malware OpCode or bytecode sequences. Hence, the complexity of our final method is reduced. This leads to better accuracy, higher Mattews Correlation Coefficients (MCC), and Area Under the Curve (AUC) in comparison to a standard LSTM with similar detection time. Our proposed method can be applied in real-time malware threat hunting, particularly for safety critical systems such as eHealth or Internet of Military of Things where poor convergence of the model could lead to catastrophic consequences. We evaluate the effectiveness of our proposed method on Windows, Ransomware, Internet of Things (IoT), and Android malware datasets using both static and dynamic analysis. For the IoT malware detection, we also present a comparative summary of the performance on an IoT-specific dataset of our proposed method and the standard stacked LSTM method. More specifically, of our proposed method achieves an accuracy of 99.1% in detecting IoT malware samples, with AUC of 0.985, and MCC of 0.95; thus, outperforming standard LSTM based methods in these key metrics.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.12
• /
• pp.5309-5314
• /
• 2016

Background: Breast cancer is the most common type of cancer amongst women throughout the world. Currently, there are various follow-up strategies implemented in Iran, which are usually dependent on clinic policies and agreement among the resident oncologists. Purpose: A cost-effectiveness analysis was performed to assess the cost-effectiveness of intensive follow-up versus standard models for early breast cancer patients in Iran. Materials and methods: This cross sectional study was performed with 382 patients each in the intensive and standard groups. Costs were identified and measured from a payer perspective, including direct medical outlay. To assess the effectiveness of the two follow-up models we used a decision tree along with indicators of detection of recurrence and metastasis, calculating expected costs and effectiveness for both cases; in addition, incremental cost-effectiveness ratios were determined. Results: The results of decision tree showed expected case detection rates of 0.137 and 0.018 and expected costs of US$24,494.62 and US$6,859.27, respectively, for the intensive and standard follow-up models. Tornado diagrams revealed the highest sensitivity to cost increases using the intensive follow-up model with an ICER=US$148,196.2. Conclusion: Overall, the results showed that the intensive follow-up method is not cost-effective when compared to the standard model.

• Geomechanics and Engineering
• /
• v.38 no.1
• /
• pp.29-44
• /
• 2024

This research investigates the effectiveness of data augmentation techniques in the automated analysis of B-scan images from ground-penetrating radar (GPR) using deep learning. In spite of the growing interest in automating GPR data analysis and advancements in deep learning for image classification and object detection, many deep learning-based GPR data analysis studies have been limited by the availability of large, diverse GPR datasets. Data augmentation techniques are widely used in deep learning to improve model performance. In this study, we applied four data augmentation techniques (geometric transformation, color-space transformation, noise injection, and applying kernel filter) to the GPR datasets obtained from a testbed. A deep learning model for GPR data analysis was developed using three models (Faster R-CNN ResNet, SSD ResNet, and EfficientDet) based on transfer learning. It was found that data augmentation significantly enhances model performance across all cases, with the mAP and AR for the Faster R-CNN ResNet model increasing by approximately 4%, achieving a maximum mAP (Intersection over Union = 0.5:1.0) of 87.5% and maximum AR of 90.5%. These results highlight the importance of data augmentation in improving the robustness and accuracy of deep learning models for GPR B-scan analysis. The enhanced detection capabilities achieved through these techniques contribute to more reliable subsurface investigations in geotechnical engineering.

• Journal of the Korea Society for Simulation
• /
• v.19 no.2
• /
• pp.17-28
• /
• 2010

Since a homing torpedo system consists of various subsystems, organic interactions of which dictate the performance of the torpedo system, it is necessary to estimate the effects of individual subsystems in order to obtain an optimized design of the overall system. This paper attempts to gain some insight into the detection mechanism of a torpedo run, and analyze the relative importance of various parameters of a torpedo system. A database for the analysis was generated using a simulation model based on the combined discrete event and discrete time architecture. Multiple search schemes, including the snake-search method, were applied to the torpedo model, and some parameters of the torpedo were found to be stochastic. We then analyzed the effectiveness of torpedo’s detection capability according to the torpedo speed, the target speed, and the maximum detection range.