Search

Machine learning models find extensive application across diverse domains, with their performance heavily reliant on the data quality employed during the learning process. However, real-world datasets include some missing data due to limitations and errors in data collection methods, incomplete or inconsistent data-gathering processes, and human errors during processing. Consequently, effective handling of missing values becomes imperative to ensure optimal model performance. A common way to deal with missing data is to either delete the data containing the missing values or to impute them appropriately. Deletion is straightforward, but at the cost of information loss. Imputation, on the other hand, can result in a loss of variability in the dataset and skewed correlations between variables. The proposed scheme reduces dimensionality by utilizing variables without missing values and employs the outcomes to estimate the missing values. Experimental validations affirm that the proposed scheme mitigates the performance degradation of various machine learning models compared to existing methods. [ABSTRACT FROM AUTHOR]

In the era of Fourth Industrial Revolution, secure networking technology is playing an essential role in the defense weapon systems. Encryption technology is used for information security. The safety of cryptographic technology, according to Kerchoff's principles, is based on secure key management of cryptographic technology, not on cryptographic algorithms. However, traditional centralized key management is one of the problematic issues in battlefield environments since the frequent movement of the forces and the time-varying quality of tactical networks. Alternatively, the system resources of each node used in the IoBT(Internet of Battlefield Things) environment are limited in size, capacity, and performance, so a lightweight key management system with less computation and complexity is needed than a conventional key management algorithm. This paper proposes a novel key escrow scheme in a lightweight manner for the IoBT environment. The safety and performance of the proposed technique are verified through numerical analysis and simulations. [ABSTRACT FROM AUTHOR]

As the number of signal sources with low detectability by using various modulation techniques increases, research to classify signal modulation methods is steadily progressing. Recently, a Convolutional Neural Network (CNN) deep learning technique using FFT as a preprocessing process has been proposed to improve the performance of received signal classification in signal interference or noise environments. However, due to the characteristics of the FFT in which the window is fixed, it is not possible to accurately classify the change over time of the detection signal. Therefore, in this paper, we propose a CNN model that has high resolution in the time domain and frequency domain and uses wavelet transform as a preprocessing process that can express various types of signals simultaneously in time and frequency domains. It has been demonstrated that the proposed wavelet transform method through simulation shows superior performance regardless of the SNR change in terms of accuracy and learning speed compared to the FFT transform method, and shows a greater difference, especially when the SNR is low. [ABSTRACT FROM AUTHOR]

Purpose To construct a standard dataset of contrast-enhanced CT images of liver tumors to test the performance and safety of artificial intelligence (AI)-based algorithms for clinical decision support systems (CDSSs). Materials and Methods A consensus group of medical experts in gastrointestinal radiology from four national tertiary institutions discussed the conditions to be included in a standard dataset. Seventy-five cases of hepatocellular carcinoma, 75 cases of metastasis, and 30–50 cases of benign lesions were retrieved from each institution, and the final dataset consisted of 300 cases of hepatocellular carcinoma, 300 cases of metastasis, and 183 cases of benign lesions. Only pathologically confirmed cases of hepatocellular carcinomas and metastases were enrolled. The medical experts retrieved the medical records of the patients and manually labeled the CT images. The CT images were saved as Digital Imaging and Communications in Medicine (DICOM) files. Results The medical experts in gastrointestinal radiology constructed the standard dataset of contrast-enhanced CT images for 783 cases of liver tumors. The performance and safety of the AI algorithm can be evaluated by calculating the sensitivity and specificity for detecting and characterizing the lesions. Conclusion The constructed standard dataset can be utilized for evaluating the machine-learningbased AI algorithm for CDSS. [ABSTRACT FROM AUTHOR]

This paper proposes a design for a photonics-based radar system for high-resolution inverse synthetic-aperture radar (ISAR) images. The proposed radar system can derive broadband characteristics using optical elements, such as phase modulator, laser source, and dual parallel Mach-Zehnder modulator (DPMZM). The detection performance and ISAR images for the target are observed according to the bandwidth of the radar system using modeling and simulation (M&S) for the proposed radar system. To verify the effectiveness of the bandwidth of the radar system, the proposed radar system are fabricated, and its performances are measured using a small drone in a practical environment. The results prove that the proposed FMCW radar system is a suitable candidate to overcome the limitations of bandwidth and high resolution. [ABSTRACT FROM AUTHOR]

As the drones industry evolved, the security of the drone network has been important. In this paper, MTD (Moving Target Detection) technique is applied to the drone network for improving security. The existing MTD scheme has a risk that the hash value is exposed during the wireless communication process, and it is restricted to apply the one-to-many network. Therefore, we proposed PHT (Preposition Hash Table) scheme to prevent exposure of hash values during wireless communication. By reducing the risk of cryptographic key exposure, the use time of the cryptographic key can be extended and the security of the drone network will be improved. In addition, the cryptographic key exchange is not performed during flight, it is advantageous to apply PHT for a swarm drone network. Through simulation, we confirmed that the proposed scheme can contribute to the security of the drone network. [ABSTRACT FROM AUTHOR]

In this paper, we propose an efficient dynamic slot re-assignment scheme for swarming drone networks in which networks members merged and split frequently. The leader drone of each network recognizes the slot allocation information of neighbor networks by periodic information exchange among between the drones. Using the information, the leader drone makes a decision how to reallocate the slots between members in case of network merge. The non-competitive method in the proposed scheme can re-assign the slots without any slot collision and shows always superior performance than competitive scheme. The competitive method in the proposed scheme reduces the number of slots that should be re-assigned in case of network merge. The experimental performance analysis shows that the proposed scheme performs better or at least equal to the performance of the competitive scheme in a swarming drone network. [ABSTRACT FROM AUTHOR]

The purpose of this study is to examine the effects of the Mobile Smart-Work IT resources on the work efficiency based on moderating effects of the perceived usefulness in the Resource Based View. The study has academic meanings and practical implications that studied widely based on moderating effects of the perceived usefulness through the Hierarchical regression furthermore on the existing study on hypothesis by standard multiple regression. The results showed that IT　Infrastructure in the Mobile Smart-work IT resources by moderating effects of the perceived usefulness was found to bring positive effect on individual work efficiency and teamwork efficiency. On the other hand Business Application was found to bring positive effect on teamwork efficiency. Therefore, we expect that business firm and employees actively use the effects of the perceived usefulness with the trust that Mobile Smart-work IT resources bring positive effects on the work efficiency. It can improve this work efficiency and lead to strengthening the firm competitiveness. [ABSTRACT FROM AUTHOR]

We introduce the design technique and test results of a millimeter-wave compact antenna test range. Physical optics is employed for the analysis of the plane wave collimated by an electrical large parabolic reflector of the compact range in the test zone. The performance of the manufactured compact range is verified with the field probing test on the quiet zone and the measurement of high gain antenna. A millimeter-wave compact range designed in the frequency range of 75～110 GHz with a diameter of the test zone of 50 cm shows the magnitude variation of less than 0.75 dB. [ABSTRACT FROM AUTHOR]

The purpose of this study is to examine the effects of the IT resources on the work efficiency and corporate performance in Mobile Smart-Work Environment with IT convergence Technology by applying the Resource-Based View. The study has an academic meaning by empirically analyzing the effects of factors identified based on the existing study on the IT resources in Mobile Smart-Work, and practical implications to identify how the significance of the Mobile Smart-Work used as a platform of variety industries in manufacturing, logistics, service, distribution, finance, public institutions, and so on positively affects improvement of corporate efficiency and performance. The results showed that IT　Infrastructure and IT skills in the Mobile Smart-work environment were found to bring positive effects on individual work efficiency, and IT skills had positive influence on team work efficiency. Also, we confirmed the individual and team work efficiency positively affect financial and market performance of business firms. Finally, we expect that business firm equipped with IT resources in the Mobile Smart-Work environment with IT convergence Technology. It can improve this work efficiency and the performance, which leads to strengthening the core competency. [ABSTRACT FROM AUTHOR]

We design a displaced-axis Gregorian dual antenna in the form of a metal reflectarray antenna for millimeter wave region, W-band. Unlike a reflectarray composed of printed patch antennas on a dielectric substrate, metallic rectangular waveguide unit-cells are proposed to avoid the loss of substrate and take an advantage of ease of typical metal machining fabrication. In this paper, the radiation characteristics of constructed metal reflectarray antennas show ultra high-gain antenna over 50 dBi at a target frequency in W-band. The experimental measurements are conducted in millimeter-wave compact range antenna measurement system. [ABSTRACT FROM AUTHOR]

With advances in IT Smart-Work is emerging as a new way of conducting business and several companies are considering to introduce the Smart-Work digital convergence technology. In this paper, we examined the effects of the Smart-Work IT resources on the work efficiency and the corporate performances in service industry by applying the Resource-Based View. The results of the structural equation modelling analysis showed that Smart-Work IT infrastructure and individual IT skills had positive influence on individual work efficiency while business application software and IT skills affected team work efficiency. Also, we confirmed that individual and team work efficiency positively affect financial and market performance of business firms. With the findings of the study, we expect that the introduction of Smart-Work would have positive effect, at least in service industry, on work efficiency and corporate performance, which will in turn lead to gaining competitive advantage for those firms adopting Smart-Work. [ABSTRACT FROM AUTHOR]