• 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.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.11
• /
• pp.27-37
• /
• 2007

Downhole seismic method is very economic and easy to operate because it uses only one borehole and simple surface source to obtain the shear wave velocity profile of a site. In this study, automatic shear wave source was developed for efficient downhole seismic testing. This source is motor-spring type and easy to control. It can lessen the labor of operator and the working time. Moreover, it can provide better and repetitive signals for data interpretation. By combining developed automatic source with automatic receiver system, PC based data acquisition system, advanced managing program, and semi-automatic downhole performing system were constructed. Through comparison test with manual source, advantages of automatic source were verified. Constructed semi-automatic downhole testing system including automatic shear wave source was applied to the soft soil site. The applicability and reliability were verified and the importance of automating testing system for obtaining reliable result was emphasized.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.13-21
• /
• 2023

In the recent era of the fourth industrial revolution, many industries aim to maximize the efficiency of products and services by introducing cutting-edge technologies such as artificial intelligence and big data. In this situation, organizational culture is changing a lot due to the influx of the MZ generation with strong individualistic tendencies and the decreased face-to-face communication between members. However, active communication with colleagues is still essential to maximize performance, and the margins created by simplifying work processes and automating processes must be used for creating work performance. This requires cooperation and commitment through the job immersion of members who have an active attitude. This study analyzed how the organization's autonomous work environment and trust among members, which are creative work performance conditions, affect job immersion using raw data from the Occupational Safety and Health Research Institute. As a result, it was found that both the organization's autonomous working environment and trust among members significantly effected the members' job immersion. in order to achieve productivity and value improvement in companies, efforts are needed to increase workers' job immersion by building an autonomous working environment and trust among members. The results of this study are expected to contribute significantly to the search for ways to increase workers' job commitment to improve organizational productivity.

• Composites Research
• /
• v.36 no.2
• /
• pp.108-116
• /
• 2023

In this paper, kinematic design and multi-body dynamics analysis were conducted to develop a small manipulator platform for automating the maintenance of structures made of composite materials. To design manipulator kinematically, the existing composite repair process was considered. The 3D design was conducted after selecting the basic specifications of manipulator and end-effecter in consideration of the patch lamination process for repair. Then, variables necessary for simulation and control were generated in MATLAB through inverse kinematic analysis. To evaluate the structural stability of platform, multibody dynamics analysis was conducted using Altair Inspire and Optistruct. Based on the simulation conducted in Inspire, multibody dynamics analysis was conducted in Optistruct, and structural stability was verified through the results of maximum displacement and Von-Mises stress over time. To verify the design, manufacturing and controlling of platform were conducted and compared with the simulation. It was confirmed that the actual repair process path and the simulation showed a good agreement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1773-1793
• /
• 2023

Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.821-830
• /
• 2023

The advancement of Internet network technology has triggered the emergence of new OTT video content platforms, increasing demand for content and altering consumption patterns. This trend is bringing positive changes to the South Korean animation industry, where diverse and high-quality animation content is becoming increasingly important. As investment in technology grows, video production technology continues to advance. Specifically, 3D animation and VFX production technologies are enabling effects that were previously unthinkable, offering detailed and realistic graphics. The Fourth Industrial Revolution is providing new opportunities for this technological growth. The rise of Artificial Intelligence (AI) is automating repetitive tasks, thereby enhancing production efficiency and enabling innovations that go beyond traditional production methods. Cutting-edge technologies like 3D animation and VFX are being continually researched and are expected to be more actively integrated into the production process. Digital technology is also expanding the creative horizons for artists. The future of AI and advanced technologies holds boundless potential, and there is growing anticipation for how these will elevate the video content industry to new heights.

• Land and Housing Review
• /
• v.14 no.4
• /
• pp.95-102
• /
• 2023

Numerous investigations have explored the integration of machine leaning algorithms with high-resolution drone image for object detection in urban settings. However, a prevalent limitation in vehicle extraction studies involves the reliance on bounding boxes rather than instance segmentation. This limitation hinders the precise determination of vehicle direction and exact boundaries. Instance segmentation, while providing detailed object boundaries, necessitates labour intensive labelling for individual objects, prompting the need for research on automating unsupervised instance segmentation in vehicle extraction. In this study, a novel approach was proposed for vehicle extraction utilizing unsupervised SVM classification applied to vehicle bounding boxes in drone images. The method aims to address the challenges associated with bounding box-based approaches and provide a more accurate representation of vehicle boundaries. The study showed promising results, demonstrating an 89% accuracy in vehicle extraction. Notably, the proposed technique proved effective even when dealing with significant variations in spectral characteristics within the vehicles. This research contributes to advancing the field by offering a viable solution for automatic and unsupervised instance segmentation in the context of vehicle extraction from image.

• Journal of radiological science and technology
• /
• v.46 no.6
• /
• pp.527-533
• /
• 2023

The purpose of this study is to evaluate the clinical risk of spinal radiosurgery by calculating the dose difference due to dose calculation algorithm and multi-leaf collimator positioning error. The images acquired by the CT simulator were recalculated by correcting the multi-leaf collimator position in the dose verification program created using MATLAB and applying stoichiometric calibration and Monte Carlo algorithm. With multi-leaf collimator positioning error, the clinical target volume (CTV) showed a dose difference of up to 13% in the dose delivered to the 95% volume, while the gross tumor volume (GTV) showed a dose difference of 9%. The average dose delivered to the total volume showed dose variation from -8.9% to 9% and -10.1% to 10.2% for GTV and CTV, respectively. The maximum dose delivered to the total volume of the spinal cord showed a dose difference from -14.2% to 19.6%, and the dose delivered to the 0.35 ㎤ volume showed a dose difference from -15.5% to 19.4%. In future research, automating the linkage between treatment planning systems and dose verification programs would be useful for spinal radiosurgery.

• Convergence Security Journal
• /
• v.23 no.3
• /
• pp.29-36
• /
• 2023

With the recent surge in exposure to fake advertising phishing sites in search engines, the damage caused by poor search quality and personal information leakage is increasing. In particular, the seriousness of the problem is worsening faster as the possibility of automating the creation of advertising phishing sites through tools such as ChatGPT increases. In this paper, the source code of fake advertising phishing sites was statically analyzed to derive structural commonalities, and among them, a detection crawler that filters sites step by step based on foreign domains and redirection was developed to confirm that fake advertising posts were finally detected. In addition, we demonstrate the need for new guide lines by verifying that the redirection page of fake advertising sites is divided into three types and returns different sites according to each situation. Furthermore, we propose new detection guidelines for fake advertising phishing sites that cannot be detected by existing detection methods.

• Journal of Information Technology Services
• /
• v.22 no.5
• /
• pp.71-86
• /
• 2023

Recently, various geographic information systems have been used based on spatial information of geographic information systems. Accordingly, it is essential to produce a large-scale map as a small-scale map for various uses of spatial information. However, maps currently being produced have inconsistencies between data due to production timing and limitations in expression, and productivity efficiency is greatly reduced due to errors in products or overlapping processes. In order to improve this, various efforts are being made, such as publishing research and reports for automating domestic mapping, but because there is no specific result, it relies on editors to make maps. This is mainly done by hand, so the time required for mapping is excessive, and quality control for each producer is different. In order to solve these problems, technology that can be automatically produced through computer programs is needed. Research has been conducted to apply the rule base to geometric generalization. The algorithm tolerance setting applied to rule-based modeling is a factor that greatly affects the result, and the level of the result changes accordingly. In this paper, we tried to study the effectiveness of mapping according to tolerance setting. To this end, the utility was verified by comparing it with a manually produced map. In addition, the original data and reduction rate were analyzed by applying generalization algorithms and tolerance values. Although there are some differences by region, it was confirmed that the complexity decreased on average. Through this, it is expected to contribute to the use of spatial information-based services by improving tolerances suitable for small-scale mapping regulations in order to secure spatial information data that guarantees consistency and accuracy.