• The Journal of the Acoustical Society of Korea
• /
• v.37 no.1
• /
• pp.31-38
• /
• 2018

Based on the measured data in the south western sea of Jeju Island during the SAVEX15(Shallow Water Acoustic Variability EXperiment 2015), the effect of internal waves on the PPD (Predictive Probability of Detection) of a sonar system was analyzed. The southern west sea of Jeju Island has complex flows due to internal waves and USC (Underwater Sound Channel). In this paper, sonar performance is predicted by probabilistic approach. The LFM (Linear Frequency Modulation) and MLS (Maximum Length Sequence) signals of 11 kHz - 31 kHz band of SAVEX15 data were processed to calculate the TL (Transmission Loss) and NL (Noise Level) at a distance of approximately 2.8 km from the source and the receiver. The PDF (Probability Density Function) of TL and NL is convoluted to obtain the PDF of the SE (Signal Excess) and the PPD according to the depth of the source and receiver is calculated. Analysis of the changes in the PPD over time when there are internal waves such as soliton packet and internal tide has confirmed that the PPD value is affected by different aspects.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.3
• /
• pp.285-292
• /
• 2024

When calculating sonar detection probability, underwater acoustic uncertainty is assumed to be normal distributed with a standard deviation of 8 dB to 9 dB. However, due to the variability in experimental areas and ocean environmental conditions, predicting detection performance requires accounting for underwater acoustic uncertainty based on ocean experimental data. In this study, underwater acoustic uncertainty was determined using measured mid-frequency (2.3 kHz, 3 kHz) noise level and transmission loss data collected in the shallow water of the East Sea. After calculating the predictable probability of detection reflecting underwater acoustic uncertainty based on ocean experimental data, we compared it with the conventional detection probability results, as well as the predictable probability of detection results considering the uncertainty of the Rayleigh distribution and a negatively skewed distribution. As a result, we confirmed that differences in the detection area occur depending on each underwater acoustic uncertainty.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.348-358
• /
• 2022

Software fault prediction is a method to compute fault in the software sections using software properties which helps to evaluate the quality of software in terms of cost and effort. Recently, several software fault detection techniques have been proposed to classifying faulty or non-faulty. However, for such a person, and most studies have shown the power of predictive errors in their own databases, the performance of the software is not consistent. In this paper, we propose a hybrid soft computing technique for SFP based on optimal feature extraction and classification (HST-SFP). First, we introduce the bat induced butterfly optimization (BBO) algorithm for optimal feature selection among multiple features which compute the most optimal features and remove unnecessary features. Second, we develop a layered recurrent neural network (L-RNN) based classifier for predict the software faults based on their features which enhance the detection accuracy. Finally, the proposed HST-SFP technique has the more effectiveness in some sophisticated technical terms that outperform databases of probability of detection, accuracy, probability of false alarms, precision, ROC, F measure and AUC.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.17
• /
• pp.7607-7612
• /
• 2015

Aims: The purpose of our study was to evaluate the diagnostic performance of breast magnetic resonance imaging (MRI) in the evaluation of contralateral breast in patients with diagnosed breast cancer. A secondary objective was to determine accuracy of breast MRI in diagnosing multi-focal and multicentric lesions in the ipsilateral breast. Materials and Methods: Using a non-probability convenience sampling technique, patients with histopathologically diagnosed breast cancer with MRI of breast performed to exclude additional lesions were included. MRI findings were correlated with histopathology. In addition, follow-up imaging with mammography and ultrasound was also assessed for establishing stability of negative findings and for the detected of benign lesions. Results: Out of 157 MRI breast conducted during the period of 2008 to 2013, 49 were performed for patients with diagnosed breast cancer. The sample comprised of all females with mean age $50.7{\pm}11.0years$. The patient follow-up imaging was available for a period of 2-5 years. The sensitivity, specificity, and positive and negative predictive values of MRI in the detection of multifocal/multicenteric lesions was 85.7%, 88.8%, 60% and 96.6% respectively and for the detection of lesions in the contralateral breast were 100%, 97%, 83.3% and 100% respectively. Conclusions: Our study highlights the diagnostic performance and the added value of MRI in the detection of multifocal/multicenteric and contralateral malignant lesions. In patients with diagnosed breast cancer having dense breast parenchyma and with infiltrating lobular carcinoma as the index lesion MRI is particularly useful with excellent negative predictive value in the exclusion of additional malignant foci in the ipsilateral and contralateral breasts.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.1
• /
• pp.25-29
• /
• 2024

In this study, research was conducted to predict the probability of cervical cancer occurrence associated with the use of hormonal contraceptives. Cervical cancer is influenced by various environmental factors; however, the human papillomavirus (HPV) is detected in 99% of cases, making it the primary attributed cause. Additionally, although cervical cancer ranks 10th in overall female cancer incidence, it is nearly 100% preventable among known cancers. Early-stage cervical cancer typically presents no symptoms but can be detected early through regular screening. Therefore, routine tests, including cytology, should be conducted annually, as early detection significantly improves the chances of successful treatment. Thus, we employed artificial intelligence technology to forecast the likelihood of developing cervical cancer. We utilized the logistic regression algorithm, a predictive model, through Microsoft Azure. The classification model yielded an accuracy of 80.8%, a precision of 80.2%, a recall rate of 99.0%, and an F1 score of 88.6%. These results indicate that the use of hormonal contraceptives is associated with an increased risk of cervical cancer. Further development of the artificial intelligence program, as studied here, holds promise for reducing mortality rates attributable to cervical cancer.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.157-173
• /
• 2011

As the Internet use explodes recently, the malicious attacks and hacking for a system connected to network occur frequently. This means the fatal damage can be caused by these intrusions in the government agency, public office, and company operating various systems. For such reasons, there are growing interests and demand about the intrusion detection systems (IDS)-the security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. The intrusion detection models that have been applied in conventional IDS are generally designed by modeling the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. These kinds of intrusion detection models perform well under the normal situations. However, they show poor performance when they meet a new or unknown pattern of the network attacks. For this reason, several recent studies try to adopt various artificial intelligence techniques, which can proactively respond to the unknown threats. Especially, artificial neural networks (ANNs) have popularly been applied in the prior studies because of its superior prediction accuracy. However, ANNs have some intrinsic limitations such as the risk of overfitting, the requirement of the large sample size, and the lack of understanding the prediction process (i.e. black box theory). As a result, the most recent studies on IDS have started to adopt support vector machine (SVM), the classification technique that is more stable and powerful compared to ANNs. SVM is known as a relatively high predictive power and generalization capability. Under this background, this study proposes a novel intelligent intrusion detection model that uses SVM as the classification model in order to improve the predictive ability of IDS. Also, our model is designed to consider the asymmetric error cost by optimizing the classification threshold. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, when considering total cost of misclassification in IDS, it is more reasonable to assign heavier weights on FNE rather than FPE. Therefore, we designed our proposed intrusion detection model to optimize the classification threshold in order to minimize the total misclassification cost. In this case, conventional SVM cannot be applied because it is designed to generate discrete output (i.e. a class). To resolve this problem, we used the revised SVM technique proposed by Platt(2000), which is able to generate the probability estimate. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 1,000 samples from them by using random sampling method. In addition, the SVM model was compared with the logistic regression (LOGIT), decision trees (DT), and ANN to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell 4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on SVM outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that our model reduced the total misclassification cost compared to the ANN-based intrusion detection model. As a result, it is expected that the intrusion detection model proposed in this paper would not only enhance the performance of IDS, but also lead to better management of FNE.

• Journal of Veterinary Clinics
• /
• v.26 no.2
• /
• pp.130-133
• /
• 2009

The use of screening tests as part of a diagnostic work-up is common in domestic canine practice, but understanding of the diagnostic test characteristics and factors affecting diagnostic accuracy is not clear among clinicians. This article was aimed to provide clinicians with a better understanding on the selection of test kits and with a proper interpretation of test results using an example from heartworm(Dirofilaria immitis) studies. From the literatures, diagnostic accuracy varied depending on the kits: percent average sensitivity and specificity of ELISA antigen-detecting kits were DiroChek(Synbiotics, USA) 78.1 and 95.2, SNAP(IDEXX, USA) 66.3 and 98.1, and Solo Step(Heska, Switzerland) 69.5 and 97.5, respectively, while the values for three hematological methods(Modified Knott's, direct smear and capillary tube) ranged from 38.4 to 81.8% and from 96.9 to 100%, respectively. Furthermore, it was also reported that the prevalence of heartworm disease in domestic dog populations varied depending on the regions studied: 2.5-22.8% for microfilarial test and 2.2-66.3% by ELISA. The values of predictive values for positive(PPV) and negative(NPV) provide useful information to clinicians on the probability of heartworm infection, but the PPV and NPV are greatly dependent on the heartworm prevalence. This suggests that PPV or NPV values of a test should be interpreted carefully in different clinical settings. Practical methods on the interpretation taking into account heartworm prevalence were discussed.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.22
• /
• pp.10039-10043
• /
• 2014

Background: In Pakistan thyroid cancer is responsible for 1.2% cases of all malignant tumors. Ultrasonography (US) is helpful in detecting cancerous thyroid nodules on basis of different features like echogenicity, margins, microcalcifications, size, shape and abnormal neck lymph nodes. We therefore aimed to calculate diagnostic accuracy of ultrasound in detection of carcinoma in thyroid nodules taking fine needle aspiration cytology as the reference standard. Materials and Methods: A cross-sectional analytical study was designed to prospectively collect data from December 2010 till December 2012 from the Department of Radiology in Aga Khan University Hospital, Karachi, Pakistan. A total of 100 patients of both genders were enrolled after informed consent via applying non-probability consecutive sampling technique. Patients referred to Radiology department of Aga Khan University to perform thyroid ultrasound followed by fine-needle aspiration cytology of thyroid nodules were included. They were excluded if proven for thyroid malignancy or if their US or FNAC was conducted outside our institution. Results: The subjects comprised 76 (76%) females and 24 males. Mean age was $41.8{\pm}SD$ 12.3 years. Sensitivity and specificity with 95%CI of ultrasound in differentiating malignant thyroid nodule from benign thyroid nodule calculated to be 91.7% (95%CI, 0.72-0.98) and 78.94% (0.68-0.87) respectively. Reported positive predictive value and negative PV were 57.9% (0.41-0.73) and 96.8% (0.88-0.99) and overall accuracy was 82%. Likelihood ratio (LR) positive was computed to be 4.3 and LR negative was 0.1. Conclusions: Ultrasonography has a high diagnostic accuracy in detecting malignancy in thyroid nodules on the basis of features like echogenicity, margins, micro calcifications and shape.

• Journal of Trauma and Injury
• /
• v.20 no.2
• /
• pp.57-64
• /
• 2007

Purpose: Clinically, acute respiratory distress syndrome (ARDS) occurs within 72 hours after acute exposure of risk factors. Because of its high fatality rate once ARDS progresses, early detection and management are essential to reduce the mortality rate. Accordingly, studies on early changes of ARDS were started, and serum ferritin, as well the as injury severity score (ISS), which has been addressed in previous studies, thought to be an early predictive indicator for ARDSMethods: From March 2003 to March 2005, we investigated 50 trauma patients who were admitted to the intensive care unit in Dongguk University Medical Center, Gyeongju. The patients were characterized according to age, sex, ISS, onset of ARDS, time onset of ARDS, serum ferritin level (posttraumatic $1^{st}\;&\;2^{nd}$ day), amount of transfused blood, and death. Abdominal computed topography was performed as an early diagnostic tool to evaluate the onset of ARDS according to its diagnostic criteria. The serum ferritin was measured by using a $VIDAS^{(R)}$ Ferritin (bioMeriux, Marcy-1' Etoile, France) kit with an enzyme-linked fluorescent assay method. For statistical analysis, Windows SPSS 13.0 and MedCalc were used to confirm the probability of obtaining a predictive measure from the receiver operating characteristics (ROC) curve. Results: The ISS varied from 14 to 66 (mean: 33.8) whereas the onset of ARDS could be predicted with the score above 30 (sensitivity: 90.0%, specificity: 60.0%, p<0.05). On the posttraumatic $1^{st}$ day, the serum ferritin levels were measured to be from 31 mg/dL to 1,200 mg/dL (mean: 456 mg/dL), and the onset of ARDS could be predicted when the value was over 340 mg/dL (sensitivity: 80.0%, specificity: 65.0%, p<0.05). On the posttraumatic $2^{nd}$ day, the serum ferritin levels were measured to be from 73 mg/dL to 1,200 mg/dL (mean: 404 mg/dL), and the onset of ARDS could be predicted when the value was over 627 mg/dL (sensitivity: 60.0%, specificity: 92.5%, p<0.05). The serum ferritin levels and the ISS were significantly higher on the posttraumatic $1^{st}$ and $2^{nd}$ day in the ARDS group, suggesting that they are suitable indices predicting the onset of ARDS, however relationship between the serum ferritin levels and the ISS was not statistically significant. Conclusion: In this study, we discovered increasing serum ferritin levels in multiple- trauma patients on the posttraumatic $1^{st}$ & $2^{nd}$ day and concluded that both the serum ferritin level and the ISS were good predictors of ARDS. Although they do not show statistically significant relationship to each other, they can be used as independent predictive measures for ARDS. Since ARDS causes high mortality, further studies, including the types of surgery and the methods of anesthesia on a large number of patients are essential to predict the chance of ARDS earlier and to reduce the incidence of death.