Synthetic Aperture Radar (SAR) images are affected by noise called speckle, which is very severe and may hinder image exploitation. Despeckling is an important task that aims to remove such noise so as to improve the accuracy of all downstream image processing tasks. Many different schemes have been proposed for the restoration of SAR images. Among the different possible approaches, methods based on convolutional neural networks(CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. DnCNN(DeNoising Convolutional Neural Network) is one of the most widely used neural network architecture embedded in baseline SAR image despeckling methods. In military applications of SAR satellite image, fast processing is the most critical factor except the precision rate of the recognition. In this paper, we propose an improved DnCNN architecture for faster SAR image despeckling. The experimental results on real-world SAR images show that our proposed method takes faster processing time than the original DnCNN architecture without despeckling performance downgrade. Subjective visual inspection demonstrates that the proposed method has great potential in preserving the image signal details and suppressing speckle noise.

Anomaly detection for each industrial machine is recognized as one of the essential techniques for machine condition monitoring and preventive maintenance. Anomaly detection of industrial machinery relies on various diagonal data from equipped sensors, such as temperature, pressure, electric current, vibration, and sound, to name a few. Among these data, sound data are easy to collect in the factory due to the relatively low installation cost of microphones to existing facilities. We develop a real time anomalous sound detection (ASD) system with the use of Autoencoder (AE) models in the industrial environments. The proposed processing pipeline makes use of the audio features extracted from the streaming audio signal captured by a single-channel microphone. The pipeline trains AE model by the collected normal sound. In real factory applications, the reconstruction error generated by the trained AE model with new input sound streaming is calculated to measure the degree of abnormality of the sound event. The sound is identified as anomalous if the reconstruction error exceeds the preset threshold. In our experiment on the CNC milling machining, the proposed system shows 0.9877 area under curve (AUC) score.

송국리형 주거지의 이용 및 폐기과정은 청동기시대의 흥미로운 연구 과제 중 하나이며, 특히 내부 흑색토층의 존재는 많은 관심을 끌어왔다. 송국리 유적 제24차와 25차 발굴조사에서 내부 흑색토층 이 확인된 주거지(98호, 100호, 107호)를 대상으로 환경고고학적 연구(토양 미세형태분석 및 규소체 분석)를 수행하였다. 토양 미세형태분석 결과, 내부 흑색토층은 탄화물이 집적된 층으로 보이며 탄화 가 비교적 가까운 곳에서 일어났을 가능성을 시사한다. 아마도 지붕이나 벽체를 비롯한 상부 구조물 이 탄화되어 집적된 층일 가능성이 높다. 한편 100호 주거지의 규소체분석 결과, 중간 흑색토층 및 상부 퇴적토에서 벼와 조의 규소체가 다량으로 확인되었다. 그리고 사초과 식물의 규소체와 해면동물 골편이 출토된 것으로 보아 저지대(예, 수전) 토양을 벽체 등의 건축재로 사용했던 것으로 보인다. 또 한, 내부 흑색토층이 보이는 주거지와 수혈유구는 연접한 경우가 많아, 화재에 의한 탄화물이 주거지 와 인근 수혈 내부로 흘러 들어간 것으로 생각된다. 이를 종합하여 보면 일부 주거지는 사용이 중지된 이후, 기둥과 같은 주요 건축재를 해체하여 반출한 다음 재활용이 어려운 나머지 잔존 구조물을 소각 했던 것으로 보인다. 그리하여 탄화물이 집적되어 수혈 중간부에 흑색토층을 생성했던 것으로 추정된 다. 본 연구에서는 토양 미세형태분석과 규소체분석이 상호보완적으로 함께 수행되어 해석의 지평을 넓힐 수 있었다.

Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation. We first generate gridded trajectory images by mapping the raw vessel trajectories into two dimensional matrix. Based on the gridded image input, we test the proposed model along with the other deep autoencoder-based models for the abnormal trajectory data generated through rotation and speed variation from normal trajectories. We show that the proposed model improves detection accuracy for the generated abnormal trajectories compared to the other models.

Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation.

The sensory stimulation of a cosmetic product has been deemed to be an ancillary aspect until a decade ago. That point of view has drastically changed on different levels in just a decade. Nowadays cosmetic formulators should unavoidably meet the needs of consumers who want sensory satisfaction, although they do not have much time for new product development. The selection of new products from candidate products largely depend on the panel of human sensory experts. As new product development cycle time decreases, the formulators wanted to find systematic tools that are required to filter candidate products into a short list. Traditional statistical analysis on most physical property tests for the products including tribology tests and rheology tests, do not give any sound foundation for filtering candidate products. In this paper, we suggest a deep learning-based analysis method to identify hand cream products by raw electric signals from tribological sliding test. We compare the result of the deep learning-based method using raw data as input with the results of several machine learning-based analysis methods using manually extracted features as input. Among them, ResNet that is a deep learning model proved to be the best method to identify hand cream used in the test. According to our search in the scientific reported papers, this is the first attempt for predicting test cosmetic product with only raw time-series friction data without any manual feature extraction. Automatic product identification capability without manually extracted features can be used to narrow down the list of the newly developed candidate products.

Recently there was an incident that military radars, coastal CCTVs and other surveillance equipment captured a small rubber boat smuggling a group of illegal immigrants into South Korea, but guards on duty failed to notice it until after they reached the shore and fled. After that, the detection of such vessels before it reach to the Korean shore has emerged as an important issue to be solved. In the fields of marine navigation, Automatic Identification System (AIS) is widely equipped in vessels, and the vessels incessantly transmits its position information. In this paper, we propose a method of automatically identifying abnormally behaving vessels with AIS using convolutional autoencoder (CAE). Vessel anomaly detection can be referred to as the process of detecting its trajectory that significantly deviated from the majority of the trajectories. In this method, the normal vessel trajectory is gridded as an image, and CAE are trained with images from historical normal vessel trajectories to reconstruct the input image. Features of normal trajectories are captured into weights in CAE. As a result, images of the trajectories of abnormal behaving vessels are poorly reconstructed and end up with large reconstruction errors. We show how correctly the model detects simulated abnormal trajectories shifted a few pixel from normal trajectories. Since the proposed model identifies abnormally behaving ships using actual AIS data, it is expected to contribute to the strengthening of security level when it is applied to various maritime surveillance systems.

In a series of recent launch tests, North Korea has been improving the firepower of its missiles that can target South Korea. North Korea’s missiles and submarines are capable of threatening targets in South Korea and are likely faster and more covert than the systems previously seen in North Korea. The advanced threats require that ROK Navy should not only detect them earlier than ever but also response quicker than ever. In addition to increasing threats, the number of young man that can be enlisted for military service has been dramatically decreasing. To deal with these difficulty, ROK navy has been making various efforts to acquire a SMART warship having enhanced defense capability with fewer human resources. For quick response time with fewer operators, ROK Navy should improve the efficiency of systems and control tower mounted on the ship by promoting the Ship System Integration. Total Ship Computing Environment (TSCE) is a method of providing single computing environment for all ship systems. Though several years have passed since the first proposal of TSCE, limited information has been provided and domestic research on the TSCE is still in its infancy. In this paper, we apply TSCE with open architecture (OA) to solve the problems that ROK Navy is facing in order to meet the requirements for the SMART ship. We first review the level of Ship System Integration of both domestic and foreign ships. Then, based on analyses of integration demands for SMART warship, we apply real time OA to design architecture for TSCE from functional view and physical view. Simulation result shows that the proposed architecture has faster response time than the response time of the existing architecture and satisfies its design requirements.

The transition from “More-of-Less” markets (economies of scale) to “Less-of-More” markets (economies of scope) is supported by advances of disruptive manufacturing and reconfigurable-supply-chain management technologies. With the prevalence of cyber-physical manufacturing systems, additive manufacturing technology is of great impact on industry, the economy, and society. Traditionally, backbone structures are built via bottom-up manufacturing with either pre-fabricated building blocks such as bricks or with layer-by-layer concrete casting such as climbing form-work casting. In both cases, the design selection is limited by form-work design and cost. Accordingly, the tool-less building of architecture with high design freedom is attractive. In the present study, we review the technological trends of additive manufacturing for construction-scale additive manufacturing in particular. The rapid tooling of patterns or molds and rapid manufacturing of construction parts or whole structures is extensively explored through uncertainties from technology. The future regulation still has drawbacks in the adoption of additive manufacturing in construction industries.

Reliability analysis of the components frequently starts with the data that manufacturer provides. If enough failure data are collected from the field operations, the reliability should be recomputed and updated on the basis of the field failure data. However, when the failure time record for a component contains only a few observations, all statistical methodologies are limited. In this case, where the failure records for multiple number of identical components are available, a valid alternative is combining all the data from each component into one data set with enough sample size and utilizing the useful information in the censored data. The ROK Navy has been operating multiple Patrol Killer Guided missiles (PKGs) for several years. The Korea Multi-Function Control Console (KMFCC) is one of key components in PKG combat system. The maintenance record for the KMFCC contains less than ten failure observations and a censored datum. This paper proposes a Bayesian approach with a Dirichlet mixture model to estimate failure time density for KMFCC. Trends test for each component record indicated that null hypothesis, that failure occurrence is renewal process, is not rejected. Since the KMFCCs have been functioning under different operating environment, the failure time distribution may be a composition of a number of unknown distributions, i.e. a mixture distribution, rather than a single distribution. The Dirichlet mixture model was coded as probabilistic programming in Python using PyMC3. Then Markov Chain Monte Carlo (MCMC) sampling technique employed in PyMC3 probabilistically estimated the parameters’ posterior distribution through the Dirichlet mixture model. The simulation results revealed that the mixture models provide superior fits to the combined data set over single models.

Quantum-inspired Genetic Algorithm (QGA) is a probabilistic search optimization method combined quantum computation and genetic algorithm. In QGA, the chromosomes are encoded by qubits and are updated by quantum rotation gates, which can achieve a genetic search. Asset-based weapon target assignment (WTA) problem can be described as an optimization problem in which the defenders assign the weapons to hostile targets in order to maximize the value of a group of surviving assets threatened by the targets. It has already been proven that the WTA problem is NP-complete. In this study, we propose a QGA and a hybrid-QGA to solve an asset-based WTA problem. In the proposed QGA, a set of probabilistic superposition of qubits are coded and collapsed into a target number. Q-gate updating strategy is also used for search guidance. The hybrid-QGA is generated by incorporating both the random search capability of QGA and the evolution capability of genetic algorithm (GA). To observe the performance of each algorithm, we construct three synthetic WTA problems and check how each algorithm works on them. Simulation results show that all of the algorithm have good quality of solutions. Since the difference among mean resulting value is within 2%, we run the nonparametric pairwise Wilcoxon rank sum test for testing the equality of the means among the results. The Wilcoxon test reveals that GA has better quality than the others. In contrast, the simulation results indicate that hybrid-QGA and QGA is much faster than GA for the production of the same number of generations.

We studied the efficiency of service quality of loan consultants contracted to a bank in Korea. Since the consultant is not an employee of the bank, he/she is paid solely in proportion to how much he/she sell loans. In this study, a consultant is considered as a decision making unit (DMU) in the DEA (Data Envelopment Analysis) model. We use a principal component analysis-data envelopment analysis (PCADEA) model to evaluate quality efficiency of the consultants. In the first stage, we use PCA to obtain 6 synthetic indicators, including 4 input indicators and 2 output indicators, from survey results in which questionnaire items are constructed on the basis of SERVQUAL model. In the second stage, 3 DEA models allowing negative values are used to calculate the relative efficiency of each DMU. An example illustrates the proposed process of evaluating the relative quality efficiency of the loan consultants.

Loan consultants assist clients with loan application processing and loan decisions. Their duties may include contacting people to ask if they want a loan, meeting with loan applicants and explaining different loan options. We studied the efficiency of service quality of loan consultants contracted to a bank in Korea. They do not work as a team, but do work independently. Since he/she is not an employee of the bank, the consultant is paid solely in proportion to how much he/she sell loans. In this study, a consultant is considered as a decision making unit (DMU) in the DEA (Data Envelopment Analysis) model. We use a principal component analysis-data envelopment analysis (PCA-DEA) model integrated with Shannon’s Entropy to evaluate quality efficiency of the consultants. We adopt a three-stage process to calculate the efficiency of service quality of the consultants. In the first stage, we use PCA to obtain 6 synthetic indicators, including 4 input indicators and 2 output indicators, from survey results in which questionnaire items are constructed on the basis of SERVQUAL model. In the second stage, 3 DEA models allowing negative values are used to calculate the relative efficiency of each DMU. In the third stage, the weight of each result is calculated on the basis of Shannon’s Entropy theory, and then we generate a comprehensive efficiency score using it. An example illustrates the proposed process of evaluating the relative quality efficiency of the loan consultants and how to use the efficiency to improve the service quality of the consultants.

When offense launches missiles at valuable assets of the defense, the defense must assign its weapons to these missiles so as to maximize the total value of surviving assets threatened by them. Recently, a new asset-based linear approximation model was proposed for weapon target assignment problem with shootlook- shoot engagement policy and fixed set-up time between each anti-missile launch from each defense unit. In this paper, we apply the proposed to several ballistic missile defense examples and we show their weapon target assignment results specified with launch order time.

A missile defense system is composed of radars detecting incoming missiles aiming at defense assets, command control units making the decisions on weapon target assignment, and artillery batteries firing of defensive weapons to the incoming missiles. Although, the technology behind the development of radars and weapons is very important, effective assignment of the weapons against missile threats is much more crucial. When incoming missile targets toward valuable assets in the defense area are detected, the asset-based weapon target assignment model addresses the issue of weapon assignment to these missiles so as to maximize the total value of surviving assets threatened by them. In this paper, we present a model for an asset-based weapon assignment problem with shoot-look-shoot engagement policy and fixed set-up time between each anti-missile launch from each defense unit. Then, we show detailed linear approximation process for nonlinear portions of the model and propose final linear approximation model. After that, the proposed model is applied to several ballistic missile defense scenarios. In each defense scenario, the number of incoming missiles, the speed and the position of each missile, the number of defense artillery battery, the number of anti-missile in each artillery battery, single shot kill probability of each weapon to each target, value of assets, the air defense coverage are given. After running lpSolveAPI package of R language with the given data in each scenario in a personal computer, we summarize its weapon target assignment results specified with launch order time for each artillery battery. We also show computer processing time to get the result for each scenario.

The Hausdorff distance is commonly used as a similarity measure between two-dimensional binary images. Since the document images may be contaminated by a variety of noise sources during transmission, scanning or conversion to digital form, the measure should be robust to the noise. Original Hausdorff distance has been known to be sensitive to outliers. Transforming the given image to grayscale image is one of methods to deal with the noises. In this paper, we propose a Hausdorff distance applied to grayscale images. The proposed method is tested with synthetic images with various levels of noises and compared with other methods to show its robustness.

The conventional clustering approaches are mostly based on minimizing total dissimilarity of input and output. However, the clustering approach may not be helpful in some cases of clustering decision making units (DMUs) with production feature converting multiple inputs into multiple outputs because it does not care converting functions. Data envelopment analysis (DEA) has been widely applied for efficiency estimation of such DMUs since it has non-parametric characteristics. We propose a new clustering method to identify groups of DMUs that are similar in terms of their input-output profiles. A real world example is given to explain the use and effectiveness of the proposed method. And we calculate similarity value between its result and the result of a conventional clustering method applied to the example. After the efficiency value was added to input of K-means algorithm, we calculate new similarity value and compare it with the previous one.

F-Measure is one of the external measures for evaluating the validity of clustering results. Though it has clear advantages over other widely used external measures such as Purity and Entropy, F-Measure has inherently been less sensitive than other validity measures. This insensitivity owes to the definition of F-Measure that counts only most influential portions. In this research, we present Fn-Measure, an external cluster evaluation measure based on F-Measure. Fn-Measure is so sensitive that it can detect their difference in the cases that F-Measure cannot detect the difference in clustering results. We compare Fn-Measure to F-Measure for a few clustering results and show which measure draws better result based upon homogeneity and completeness

F-Measure is one of the external validity indexes for evaluating clustering results and has been widely used.Though it has clear advantage over other widely usedexternal measures such as Purity and Entropy, FMeasure has inherently been less sensitive than other validity indexes in some cases. This insensitivity owes to the definition of F-Measure that counts only most influential portions. In this research, we define a new validity index based on F-Measure, called Fn-Measure and show that it can detect the difference in the cases that original F-Measure cannot detect the difference in clustering results.