• Korean Journal of Food Science and Technology
• /
• v.30 no.3
• /
• pp.509-516
• /
• 1998

Thermoluminescence measurements were applied to the detection of seasoned-powered foods such as shellfish extract powder, seasoned marine products, Ramen soup powder and sardine extract powder whether they are irradiated or not. Correlation coefficients $(R^2)$ between irradiation doses and corresponding TL responses were more than 0.5966 in all samples and 0.9500 in Ramen soup powder. TL threshold value was pre-established for the detection of unknown Ramen soup powders by verifying TL responses with a re-irradiation step. Threshold values were maximum 1.37 for the nonirradiated samples and minimum 6.06 for the 2.5 kGy-irradiated samples. The samples showing values between 1.37 and 6.06 were subjected to a re-irradiation step for their detection, which results were reconfirmed by enumerating the total bacterial load of the detected samples. Pre-established threshold values were successfully applicable to the detection of 167 coded unknown samples, both nonirradiated and irradiated with gamma or electron-beam energy. In the assessment of irradiated doses, three calibration curves were pre-established by plotting TL intensity versus applied doses, of which a quadratic equation was obtained for the potential estimation of irradiated doses with some variations from the real doses.

• Journal of Sensor Science and Technology
• /
• v.10 no.4
• /
• pp.239-249
• /
• 2001

LAPS is a device which is dependent on the bias potential between a pH sensitivity and alternating photocurrent. We implemented the multichannel LAPS device and the detection system which was able to effectively measure the sensor's output by a synchronized detection circuit and multiple methods. The implemented LAPS was structured the multiple sensing sites for analyzing a various components simultaneously. And the system included a time-division method using one pre-amplifier being able to detect the multichannel pH concentration preserving a high S/N ratio and a control part. System hardware consists of a pre-amplifier, digital unit and sensor unit, and software consists of a system program and PC program. As results, we verified the successful operations of system including an implemented pre-amplifier and signal processing units.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.4
• /
• pp.895-902
• /
• 2015

This paper presents a high-speed sensing and noise cancellation technique for large touch screens, which is called FDCS (Frequency Division Concurrent Sensing). Most conventional touch screen detection methods apply excitation pulses sequentially and analyze the sensing signals sequentially, and so are often unacceptably slow for large touch screens. The proposed technique applies sinusoidal signals of orthogonal frequencies simultaneously to all drive lines, and analyzes the signals from each sense line in frequency domain. Its parallel driving allows high speed detection even for a very large touch screens. It enhances the sensing SNR (Signal to Noise Ratio) by introducing a frequency domain noise filtering scheme. We also propose a pre-distortion equalizer, which compensates the drive signals using the inverse transfer function of touch screen panel to further enhance the sensing SNR. Experimental results with a 23" large touch screen show that the proposed technique enhances the frame scan rate by 273% and an SNR by 43dB compared with a conventional scheme.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1601-1614
• /
• 2008

The number of web service users has been increased rapidly as existing services are changed into the web-based internet applications. Therefore, it is necessary for us to use web log pre-processing technique to detect attacks on diverse web service transactions and it is also possible to extract web mining information. However, existing mechanisms did not provide efficient pre-processing procedures for a huge volume of web log data. In this paper, we proposed both a field based parsing and a high-speed log indexing mechanism based on the suggested B-tree Index Vector structure for performance enhancement. In experiments, the proposed mechanism provides an efficient web log pre-processing and search functions with a session classification. Therefore it is useful to enhance web attack detection function.

• The Journal of Information Systems
• /
• v.18 no.4
• /
• pp.41-57
• /
• 2009

Although financial information is a great influence upon determining of the group which use them, detection of management fraud and earning manipulation is a difficult task using normal audit procedures and corporate credit evaluation processes, due to the shortage of knowledge concerning the characteristics of management fraud, and the limitation of time and cost. These limitations suggest the need of systemic process for !he effective risk of earning manipulation for credit evaluators, external auditors, financial analysts, and regulators. Moot researches on management fraud have examined how various characteristics of the company's management features affect the occurrence of corporate fraud. This study examines financial characteristics of companies engaged in fraudulent financial reporting and suggests a model and system for detecting GAAP violations to improve reliability of accounting information and transparency of their management. Since the detection of management fraud has limited proven theory, this study used the detecting method of outlier(upper, and lower bound) financial ratio, as a real-field application. The strength of outlier detecting method is its use of easiness and understandability. In the suggested model, 14 variables of the 7 useful variable categories among the 76 financial ratio variables are examined through the distribution analysis as possible indicators of fraudulent financial statements accounts. The developed model from these variables show a 80.82% of hit ratio for the holdout sample. This model was developed as a financial outlier detecting system for a financial institution. External auditors, financial analysts, regulators, and other users of financial statements might use this model to pre-screen potential earnings manipulators in the credit evaluation system. Especially, this model will be helpful for the loan evaluators of financial institutes to decide more objective and effective credit ratings and to improve the quality of financial statements.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.2
• /
• pp.35-41
• /
• 2021

In this study, improved path tracking control algorithm based on pure pursuit algorithm is newly proposed by using improved lane detection algorithm through real time post-processing with interpolation methodology. Since the original pure pursuit works well only at speeds below 20 km/h, the look-ahead distance is implemented as a sigmoid function to work well at an average speed of 45 km/h to improve tracking performance. In addition, a smoothing filter was added to reduce the steering angle vibration of the original algorithm, and the stability of the steering angle was improved. The post-processing algorithm presented has implemented more robust lane recognition system using real-time pre/post processing method with deep learning and estimated interpolation. Real time processing is more cost-effective than the method using lots of computing resources and building abundant datasets for improving the performance of deep learning networks. Therefore, this paper also presents improved lane detection performance by using the final results with naive computer vision codes and pre/post processing. Firstly, the pre-processing was newly designed for real-time processing and robust recognition performance of augmentation. Secondly, the post-processing was designed to detect lanes by receiving the segmentation results based on the estimated interpolation in consideration of the properties of the continuous lanes. Consequently, experimental results by utilizing driving guidance line information from processing parts show that the improved lane detection algorithm is effective to minimize the lateral offset error in the diverse maneuvering roads.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.11-17
• /
• 2023

This paper proposes a lightweight deep learning network for detecting an image splicing forgery. The research on image forgery detection using CNN, a deep learning network, and research on detecting and localizing forgery in pixel units are in progress. Among them, CAT-Net, which learns the discrete cosine transform coefficients of images together with images, was released in 2022. The DCT coefficients presented by CAT-Net are combined with the JPEG artifact learning module and the backbone model as pre-learning, and the weights are fixed. The dataset used for pre-training is not included in the public dataset, and the backbone model has a relatively large number of network parameters, which causes overfitting in a small dataset, hindering generalization performance. In this paper, this learning module is designed to learn the characterization depending on the DCT domain in real-time during network training without pre-training. The DCT RRU-Net proposed in this paper is a network that combines RRU-Net which detects forgery by learning only images and JPEG artifact learning module. It is confirmed that the network parameters are less than those of CAT-Net, the detection performance of forgery is better than that of RRU-Net, and the generalization performance for various datasets improves through the network architecture and training method of DCT RRU-Net.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.370-376
• /
• 2023

In the underwater image, it is not clear to distinguish the shape of the target due to underwater noise and low resolution. In addition, as an input of deep learning, underwater images require pre-processing and segmentation must be preceded. Even after pre-processing, the target is not clear, and the performance of detection and identification by deep learning may not be high. Therefore, it is necessary to distinguish and clarify the target. In this study, the importance of target shadows is confirmed in underwater images, object detection and target area acquisition by shadows, and data containing only the shape of targets and shadows without underwater background are generated. We present the process of converting the shadow image into a 3-mode image in which the target is white, the shadow is black, and the background is gray. Through this, it is possible to provide an image that is clearly pre-processed and easily discriminated as an input of deep learning. In addition, if the image processing code using Open Source Computer Vision (OpenCV)Library was used for processing, the processing speed was also suitable for real-time processing.

• 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.

• The Korean Journal of Emergency Medical Services
• /
• v.17 no.1
• /
• pp.21-39
• /
• 2013

Purpose : The purpose of this study is to provide the basic data to improve pre-hospital phase emergency care for acute myocardial infarction (AMI) patients by analyzing AMI patients' clinical characteristics and emergency care situations. Methods : Data were collected through medical records of 385 AMI patients including ambulance records of 107 AMI patients transferred to the emergency medical center for three and a half years. Results : Regarding emergency care for AMI patients in pre-hospital phase, 47% of the care revealed moderate level or higher, and appropriateness of pre-hospital phase emergency care for cardiopulmonary complaints practiced by paramedics showed statistically significant improvement in recent years (p<.001). The time from onset of symptom to ballooning intervention by 119 emergency services was shorter than that in other cases. However, emergency care by paramedic was mainly basic life support. Conclusion : Since prognosis of AMI shows vast differences depending on prompt detection and medical intervention, cooperation between pre-hospital and in-hospital phase is highly required. 119 paramedics should be trained focusing on the accurate assessment and emergency care, and medical direction should be activated. In addition, regulation on 12-lead EKG, cardiac enzyme analysis, use of analgesics and thrombolytic agents should be legally implemented.