• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.394-400
• /
• 2002

In digital speech communications, the quality of service can be increased by speech coding scheme that is adaptive to the error rate of voice packet transmission. However, current communication protocol in cellular and internet communications does not provide the function that transmits the channel error information. To solute this problem, in this paper, new method for real-time transmission of channel error information is proposed, where channel error information is embedded in voice packet. The proposed method utilizes the pulse positions of codevector in ACELP speech codec, which results in little degradation in speech quality and low false alarm rate. The simulations with various speech data show that the proposed method meets the requirement in speech quality, detection rate, and false alarm rate.

• Journal of Biomedical Engineering Research
• /
• v.29 no.1
• /
• pp.25-31
• /
• 2008

It is well known that temporal information, i.e speech onset, about input speech can be represented to the response nerve signal of auditory nerve better depending on the adaptation effect occurred in the auditory nerve synapse. In addition, the performance of a speech processor of cochlear implant can be improved by the adaptation effect. In this paper, we observed the emphasis characteristic of speech onset in the recently proposed adaptation algorithm, analyzed the characteristic of performance change according to the variation of parameters and compared with transient emphasis spectral maxima (TESM) is the previous typical strategy. When observing false peaks which are generated everywhere except speech onset, in the case of the proposed model, the false peak were generated much less than in the case of the TESM and it is more distinguishable under noise.

• Journal of Information Science Theory and Practice
• /
• v.7 no.1
• /
• pp.52-71
• /
• 2019

An insider threat is a threat that comes from people within the organization being attacked. It can be described as a function of the motivation, opportunity, and capability of the insider. Compared to managing the dimensions of opportunity and capability, assessing one's motivation in committing malicious acts poses more challenges to organizations because it usually involves a more obtrusive process of psychological examination. The existing body of research in psycholinguistics suggests that automated text analysis of electronic communications can be an alternative for predicting and detecting insider threat through unobtrusive behavior monitoring. However, a major challenge in employing this approach is that it is difficult to minimize the risk of missing any potential threat while maintaining an acceptable false alarm rate. To deal with the trade-off between the risk of missed catches and the false alarm rate, we propose a unified psycholinguistic framework that consolidates multiple text analyzers to carry out sentiment analysis, emotion analysis, and topic modeling on electronic communications for unobtrusive psychological assessment. The user scenarios presented in this paper demonstrated how the trade-off issue can be attenuated with different text analyzers working collaboratively to provide more comprehensive summaries of users' psychological states.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• Journal of Positioning, Navigation, and Timing
• /
• v.4 no.4
• /
• pp.173-180
• /
• 2015

In this study, an algorithm that detects a spoofing signal for a GPS L1 signal was proposed, and the performance was verified through RF spoofing signal simulation. The proposed algorithm determines the reception of a spoofing signal by detecting a correlation distortion of GPS L1 C/A code caused by the spoofing signal. To detect the correlation distortion, a detection criterion of a spoofing signal was derived from the relationship among the Early, Prompt, and Late tap correlation values of a receiver correlator; and a detection threshold was calculated from the false alarm probability of spoofing signal detection. In this study, an RF spoofing environment was built using the GSS 8000 simulator (Spirent). For the RF spoofing signal generated from the simulator, the RF spoofing environment was verified using the commercial receiver DL-V3 (Novatel Inc.). To verify the performance of the proposed algorithm, the RF signal was stored as IF band data using a USRP signal collector (NI) so that the data could be processed by a CNU software receiver (software defined radio). For the performance of the proposed algorithm, results were obtained using the correlation value of the software receiver, and the performance was verified through the detection of a spoofing signal and the detection time of a spoofing signal.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1649-1656
• /
• 2016

Performance of the existing sensor-based fire detection system is limited according to factors in the environment surrounding the sensor. A number of image-based fire detection systems were introduced in order to solve these problem. But such a system can generate a false alarm for objects similar in appearance to fire due to algorithm that directly defines the characteristics of a flame. Also fir detection systems using movement between video flames cannot operate correctly as intended in an environment in which the network is unstable. In this paper, we propose an image-based fire detection method using CNN (Convolutional Neural Network). In this method, firstly we extract fire candidate region using color information from video frame input and then detect fire using trained CNN. Also, we show that the performance is significantly improved compared to the detection rate and missing rate found in previous studies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.3
• /
• pp.428-451
• /
• 2010

Traffic matrix-based anomaly detection and DDoS attacks detection in networks are research focus in the network security and traffic measurement community. In this paper, firstly, a new type of unidirectional flow called IF flow is proposed. Merits and features of IF flows are analyzed in detail and then two efficient methods are introduced in our DDoS attacks detection and evaluation scheme. The first method uses residual variance ratio to detect DDoS attacks after Recursive Least Square (RLS) filter is applied to predict IF flows. The second method uses generalized likelihood ratio (GLR) statistical test to detect DDoS attacks after a Kalman filter is applied to estimate IF flows. Based on the two complementary methods, an evaluation formula is proposed to assess the seriousness of current DDoS attacks on router ports. Furthermore, the sensitivity of three types of traffic (IF flow, input link and output link) to DDoS attacks is analyzed and compared. Experiments show that IF flow has more power to expose anomaly than the other two types of traffic. Finally, two proposed methods are compared in terms of detection rate, processing speed, etc., and also compared in detail with Principal Component Analysis (PCA) and Cumulative Sum (CUSUM) methods. The results demonstrate that adaptive filter methods have higher detection rate, lower false alarm rate and smaller detection lag time.

• Journal of Korea Multimedia Society
• /
• v.19 no.5
• /
• pp.818-825
• /
• 2016

The existing R-peak detection research suggests improving the distortion of the signal such as baseline variations in ECG signals by using preprocessing techniques such as a bandpass filtering. However, preprocessing can introduce another distortion, as it can generate a false detection in the R-wave detection. In this paper, we propose an R-peak detection algorithm in ECG signal, based on primitive signal in order to detect reliably an R-peak in baseline variation. First, the proposed algorithm decides the primitive signal to represent the QRS complex in ECG signal, and by scaling the time axis and voltage axis, extracts multiple primitive signals. Second, the algorithm detects the candidates of the R-peak using the value of the voltage. Third, the algorithm measures the similarity between multiple primitive signals and the R-peak candidates. Finally, the algorithm detects the R-peak using the mean and the standard deviation of similarity. Throughout the experiment, we confirmed that the algorithm detected reliably a QRS group similar to multiple primitive signals. Specifically, the algorithm can achieve an R-peak detection rate greater than an average rate of 99.9%, based on eight records of MIT-BIH ADB used in this experiment.

• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.359-375
• /
• 2017

We developed fog detection algorithm (KNU_FDA) based on the optical and textural properties of fog using satellite (COMS) and ground observation data. The optical properties are dual channel difference (DCD: BT3.7 - BT11) and albedo, and the textural properties are normalized local standard deviation of IR1 and visible channels. Temperature difference between air temperature and BT11 is applied to discriminate the fog from other clouds. Fog detection is performed according to the solar zenith angle of pixel because of the different availability of satellite data: day, night and dawn/dusk. Post-processing is also performed to increase the probability of detection (POD), in particular, at the edge of main fog area. The fog probability is calculated by the weighted sum of threshold tests. The initial threshold and weighting values are optimized using sensitivity tests for the varying threshold values using receiver operating characteristic analysis. The validation results with ground visibility data for the validation cases showed that the performance of KNU_FDA show relatively consistent detection skills but it clearly depends on the fog types and time of day. The average POD and FAR (False Alarm Ratio) for the training and validation cases are ranged from 0.76 to 0.90 and from 0.41 to 0.63, respectively. In general, the performance is relatively good for the fog without high cloud and strong fog but that is significantly decreased for the weak fog. In order to improve the detection skills and stability, optimization of threshold and weighting values are needed through the various training cases.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.2
• /
• pp.313-320
• /
• 2015

While various phishing attacks are getting to be increased in constant, their response methods still stay on the stage of responding after identifying an attack. To detect a phishing site ahead of an attack, a method has been suggested with utilizing the Referer header field of HTTP. However, it has a limitation to implement a traffic gathering system for each of prospective target hosts. This paper presents a unknown phishing site detection method in the Interior network environment. Whenever a user try to connect a phishing site, its traffic is pre-processed with considering of the characteristics of HTTP protocol and phishing site. The phishing site detection phase detects a suspicious site under phishing with analysing HTTP content. To validate the proposed method, some evaluations were conducted with 100 phishing URLs along with 100 normal URLs. The experimental results show that our method achieves higher phishing site detection rate than that of existing detection methods, as 66% detection rate for the phishing URLs, and 0% false negative rate for the normal URLs.