• ETRI Journal
• /
• v.41 no.5
• /
• pp.560-573
• /
• 2019

Two supervised learning algorithms, a basic neural network and a long short-term memory recurrent neural network, are applied to traffic including DDoS attacks. The joint effects of preprocessing methods and hyperparameters for machine learning on performance are investigated. Values representing attack characteristics are extracted from datasets and preprocessed by two methods. Binary classification and two optimizers are used. Some hyperparameters are obtained exhaustively for fast and accurate detection, while others are fixed with constants to account for performance and data characteristics. An experiment is performed via TensorFlow on three traffic datasets. Three scenarios are considered to investigate the effects of learning former traffic on sequential traffic analysis and the effects of learning one dataset on application to another dataset, and determine whether the algorithms can be used for recent attack traffic. Experimental results show that the used preprocessing methods, neural network architectures and hyperparameters, and the optimizers are appropriate for DDoS attack detection. The obtained results provide a criterion for the detection accuracy of attacks.

• Journal of Advanced Navigation Technology
• /
• v.19 no.5
• /
• pp.363-369
• /
• 2015

This paper describes deployment of a sea based sensor platform for the detection of a submarine launched ballistic missile (SLBM). Recently, North Korea successfully conducted the underwater launching test of the SLBM, which will seriously threaten the global security. To defend these threats successfully, a sensor platform of the ballistic missile defense (BMD) should be deployed in the area of high detection probability of the missile. The maximum detection range characteristics of the typical radar sensor system, however, depend on the radar cross section (RCS) and flight trajectories of the target. In this point of view, this work analyzed the flight trajectories based on the tactics and calculated the RCS of the SLBM. In addition, sea based sensor platform position is proposed from the analysis of the detection time.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.6A
• /
• pp.586-592
• /
• 2006

In this paper, a novel detection method called the joint multiple frequency cell (JMFC) detection is addressed for spread spectrum code acquisition in the presence of residual Doppler frequency offset (RDFO). When the RDFO exists, the correlation peak used for detection during the acquisition process is split into several lower neighboring peaks, resulting in severe degradation in the detection performance, and consequently, in the overall acquisition performance. In the JMFC detection, a decision variable for detection is formed by combining several consecutive correlator outputs, so that the reduction in the correlation value due to the RDFO can be alleviated. Numerical results show that the proposed scheme can offer better detection performance over the conventional scheme based on the cell-by-cell detection.

• Biomedical Science Letters
• /
• v.29 no.4
• /
• pp.220-230
• /
• 2023

Identification of the pathogens causing infection is important in terms of patient's health management and infection control. Synovial fluids could be used as clinical samples to detect causative pathogens of prosthetic joint infections (PJIs) using molecular diagnostic assays, therefore, normalization and validation of clinical samples are necessary. Microbial culture is considered the gold standard for all infections, including PJIs. Recently, molecular diagnostic methods have been developed to overcome the limitation of microbial culture. Therefore, guideline for validating clinical samples to provide reliable results of molecular diagnostic assays for infectious diseases is required in clinical field. The present study aimed to develop an accurate validating method of synovial fluid clinical samples using GAPDH gene as an internal control to perform the quantitative PCR TaqMan probe assay to detect pathogens causing PJIs.

• ETRI Journal
• /
• v.40 no.2
• /
• pp.218-226
• /
• 2018

Multiuser detection (MUD) and channel estimation techniques in space-division multiple-access aided orthogonal frequency-division multiplexing systems recently has received intensive interest in receiver design technologies. The maximum likelihood (ML) MUD that provides optimal performance has the cost of a dramatically increased computational complexity. The minimum mean-squared error (MMSE) MUD exhibits poor performance, although it achieves lower computational complexity. With almost the same complexity, an MMSE with successive interference cancellation (SIC) scheme achieves a better bit error rate performance than a linear MMSE multiuser detector. In this paper, hybrid ML-MMSE with SIC adaptive multiuser detection based on the joint channel estimation method is suggested for signal detection. The simulation results show that the proposed method achieves good performance close to the optimal ML performance at low SNR values and a low computational complexity at high SNR values.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.709-712
• /
• 1987

In this paper, a mathematical model for the purpose of QRS detection is considered in the case of the occurrence of nonoverlapping pulse-shaped waveforms corrupted with white noise. The number of waveforms, the arrival times, amplitudes, and widths of QRS complexes are regarded as random variables. The joint MAP estimation of all the unknown quantities consists of linear filtering followed by an optimization procedure. Because of time-consuming, the optimization procedure is modified so that a threshold test is obtained. The model formulation with nonoverlapping waveforms leads to a standard procedure covering a segment before as well as after an accepted event. Adaptivity of the detector is gained by utilizing past signal properties in determining threshold for QRS detection.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.7C
• /
• pp.633-641
• /
• 2005

In this paper, we address the derivation of joint distributions and correlation coefficients for three pairs of statistics used commonly in a number of signal detection schemes. The upper and lower bounds of the correlation coefficients for the three pairs are obtained, and interesting relationships between the correlation coefficients are derived. Explicit values of the correlation coefficients evaluated for some meaningful distributions are given in the form of tables and figures for easy reference. The results in this paper should be useful in comparing various detection statistics.

• Proceedings of the KIEE Conference
• /
• 2008.09a
• /
• pp.214-217
• /
• 2008

To detect partial discharge of 154kV joint box, we have made experiment by using the HFCT sensor. Generally the signals which are detected in partial discharge test of underground power transmission cable are accompanied with both noises of high voltage and noises of surrounding Power cable. The most noise in near to end part of joint box is corona, beside other noises flowed from surrounding area. Partial discharge test is difficulty due to these noises. First, we test reliability on both injection of calibration signal in NJB and removal of low frequency. After that, we had analyzed frequencies by measuring signals in IJB with 300[m] distance from NJB. Also we had measured S/N ratio by using the indirected injection method of calibration signal in IJB. In this experiment, two measurement methods were difference of detection acquisition, but these had the equal frequency properties.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.4
• /
• pp.1679-1691
• /
• 2016

Successive interference cancellation (SIC) is an effective means of multi-packet reception to combat interference at the physical layer. We investigate the joint optimization issue of channel access and power control for capacity maximization in SIC-enabled wireless networks. We propose a new interference model to characterize the sequential detection nature of SIC. Afterward, we formulize the joint optimization problem, prove it to be a nondeterministic polynomial-time-hard problem, and propose a novel approximation approach based on the genetic algorithm (GA). Finally, we discuss the design and parameter setting of the GA approach and validate its performance through extensive simulations.

• Journal of Veterinary Clinics
• /
• v.19 no.1
• /
• pp.103-106
• /
• 2002

Specific diagnosis of orthopedic disease can be diffcult in canine practice. Failure to detect the clinical signs of a disorder during physical examination of dogs with acute or chronic lameness is the most common reason for failure to make specific diagnosis. A 6-month-old, female doberman with history of swelling and non-weight-bearing lameness in the left forelimb was referred to Beterinary Teaching Hospital of Chungbuk National University. Physical examination, plain radiography, and conventional three-phase radionuclide bone scan were performed in the patient. Based on the physical exam and radiography, this case was diagnosed as elbow strain and subluxation. Conventional three-phase bone scan detected soft tissue inflammation and osteochondral lesions of elbow joint, and revealed good agreement with clinical findings. Therefore, conventional three-phase bone scan was able to provide the precise information about inflammation of soft tissue and osteochondral lesions of joint.