• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.

• Journal of the Korean Society of Radiology
• /
• v.81 no.4
• /
• pp.886-898
• /
• 2020

Purpose The purpose of our study was to evaluate digital breast tomosynthesis as a breast cancer screening modality for women with gynecologic cancer. Materials and Methods This retrospective study included patients with underlying gynecologic malignancies who underwent screening digital breast tomosynthesis for breast cancer. The cancer detection rate, recall rate, sensitivity, specificity, and positive predictive value (PPV) were calculated. PPV1 was defined as the percentage of all positive screening exams that have a tissue diagnosis of cancer within a year. PPV2 was defined as the percentage of all diagnostic exams (and Breast Imaging Reporting and Data System category 4, 5 from screening setting) with a recommendation for tissue diagnosis that have cancer within a year. PPV3 was defined as the percentage of all known biopsies actually performed that resulted in a tissue diagnosis of cancer within the year. For each case of screen-detected cancer, we analyzed the age, type of underlying gynecologic malignancy, breast density, imaging features, final Breast Imaging Reporting and Data System assessment, histologic type, T and N stages, molecular subtype, and Ki-67 index. Results Among 508 patients, 7 with breast cancer were identified after a positive result. The cancer detection rate was 13.8 per 1000 screening exams, and the recall rate was 17.9%. The sensitivity was 100%, and the specificity was 83.2%. The false negative rate was 0 per 1000 exams. The PPV1, PPV2, and PPV3 were 7.7, 31.8, and 31.8, respectively. Conclusion Digital breast tomosynthesis may be a promising breast cancer screening modality for women with gynecologic cancer, based on the high cancer detection rate, high sensitivity, high PPV, and high detection rate of early-stage cancer observed in our study.

• Parasites, Hosts and Diseases
• /
• v.30 no.2
• /
• pp.141-146
• /
• 1992

A total of 197 fecal specimens was prepared for quantitative examination of helminth eggs by modified Kato's cellophane thick smear (M.C.T.S.) and Stoll's dilution egg counting technique (D.E,C.T.). The comparative effectiveness of two techniques was evaluated and conversion function was deduced. The average time required for the microscopic examination on one slide by M.C.T.S. was 12.6 minutes and that of D.E.C.T. was 14.6 minutes. M.C.T.S. showed lower false negative rate than D.E.C.T in light worm burden cases. Functions to convert the counts obtained by M.C.T.S. to E.P.G. by Stoll's dilution egg counting technique were $47.86{\times}10^{0.87{\;}logM.C.T.S.},{\;}$ in A. lumbricoides, $41.69{\times}10^{0.82{\;}logM.C.T.S.}$ in T. trichiura and $63.10{\times}10^{0.85{\;}logM.C.T.S.}$ in C. sinensis. It was suggested M.C.T.S. be better than D.E.C.T. for the quantitative examination of intestinal helminthiases such as A. lumbricoides, T. trichiura, and C. sinensis infections even in the cases with low worm burden.

• Journal of Nutrition and Health
• /
• v.24 no.5
• /
• pp.450-457
• /
• 1991

The iron status of 57 female college students was evaluated by measurements of hemoglobinCHb). hematocritCHct) and serum ferritin(Ferritin). Mean values for Hb, Hct and Ferritin were $13.9\pm$ 0.96g/dl, $41.4\pm$ 2.85% and $20.7\pm$ l5.5ng/mL respectively. Ferritin as well as Hb. Hct were not statistically different from normal distribution. although ferritin were skewed to the right. The prevalence of anemia defined by Hb < 12g/dI. Hct ~36 % and Ferritin <12ng/ml were found to be 5.3, 10.3 and 36.8%, respectively. By using Hb as a screening tool at a cutoff point of 12g/dI. 2.8% of healthy subjects will be incorrectly classified as anemic and 90.5 % of anemic as healthy. Sensitivity and specificity were calculated at various cutoff points of Hb and Hct. The estimates of sensitivity and specificity allow Hb 14.0g/dl as cutoff point for good predictor of anemia.

• Korean Journal of Veterinary Service
• /
• v.45 no.1
• /
• pp.1-11
• /
• 2022

A novel porcine circovirus 4 (PCV4) was recently identified in Chinese and Korean pig herds. Although several conventional polymerase chain reaction (cPCR) and real-time PCR (qPCR) assays were used for PCV4 detection, more sensitive and reliable qPCR assay is needed that can simultaneously detect PCV4 and internal positive control (IPC) to avoid false-negative results. In the present study, a duplex qPCR (dqPCR) assay was developed using primers/probe sets targeting the PCV4 Cap gene and pig (glyceraldehyde-3-phosphate dehydrogenase) GAPDH gene as an IPC. The developed dqPCR assay was specifically detected PCV4 but not other PCVs and porcine pathogens, indicating that the newly designed primers/probe set is specific to the PCV4 Cap gene. Furthermore, GAPDH was stably amplified by the dqPCR in all tested viral and clinical samples containing pig cellular materials, indicating the high reliability of the dqPCR assay. The limit of detection of the assay 5 copies of the target PCV4 genes, but the sensitivity of the assay was higher than that of the previously described assays. The assay demonstrated high repeatability and reproducibility, with coefficients of intra-assay and inter-assay variation of less than 1.0%. Clinical evaluation using 102 diseased pig samples from 18 pig farms showed that PCV4 circulated in the Korean pig population. The detection rate of PCV4 obtained using the newly developed dqPCR was 26.5% (27/102), which was higher than that obtained using the previously described cPCR and TaqMan probe-based qPCR and similar to that obtained using the previously described SYBR Green-based qPCR. The dqPCR assay with IPC is highly specific, sensitive, and reliable for detecting PCV4 from clinical samples, and it will be useful for etiological diagnosis, epidemiological study, and control of the PCV4 infections.

• Journal of the Korean Society of Radiology
• /
• v.84 no.3
• /
• pp.676-685
• /
• 2023

Purpose To investigate the incidence, outcomes, and imaging characteristics of clustered microcysts detected on breast US in asymptomatic women, and suggest appropriate management guidelines. Materials and Methods We identified and reviewed the lesions recorded as "clustered microcysts" on breast US performed in asymptomatic women between August 2014 and December 2019. The final diagnosis was based on pathology and imaging follow-up results for at least 12 months. Results The incidence was 1.5% and 100 patients with 117 lesions were included. Among 117 lesions, 3 (2.6%), 2 (1.7%), and 112 (95.7%) were malignant, high-risk benign, and benign lesions, respectively. The malignant lesions included two cases of ductal carcinoma in situ and one invasive ductal carcinoma. Two of them were assessed as category 4, showing mammographic suspicious microcalcifications and internal vascularity on Doppler US. The remainder was a false negative case and showed echo pattern change on the 12-month follow-up US. Conclusion The incidence of clustered microcysts on breast US in asymptomatic women was 1.5% and malignancy rate was 2.6% (3 of 117). Knowledge of outcomes and imaging features of benign and malignant clustered microcysts may be helpful for radiologists, thereby aiding categorization and management recommendations.

• Tuberculosis and Respiratory Diseases
• /
• v.50 no.2
• /
• pp.222-228
• /
• 2001

Backgrounds : Recent technological developments have introduced a new method to identifying M. tuberculosis complex DNA in clinical samples directly. The direct amplification test (DAT) is approved for identifying M. tuberculosis complex in respiratory specimens that are smear-positive for acid-fast bacilli (AFB). When there is a discrepancy between the AFB smear and DAT, no information on their clinical utility is currently available. In this study, the diagnostic reliability of DAT was investigated in suspected pulmonary tuberculosis patients whose sputum AFB smear was negative. Methods : From June 1, 1998 through May 30, 1999, 909 patients with presumed active pulmonary tuberculosis were enrolled. A sputum AFB stain, culture, DAT and/or biopsy were performed. Using the criteria of clinical tuberculosis or confirmed tuberculosis, the positive predictive value of DAT in diagnosing pulmonary tuberculosis was investigated. Results : The positive predictive value of DAT was 82.1% by the clinically active tuberculosis criteria. However, it decreased to 61.5% when diagnosis was restricted to only to culture positive or biopsy proven cases. The false positive rate of DAT was 18.0%. Conclusion : The DAT is a valuable diagnostic method in suspected patients whose sputum AFB is was negative.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.125-141
• /
• 2012

These days, the malicious attacks and hacks on the networked systems are dramatically increasing, and the patterns of them are changing rapidly. Consequently, it becomes more important to appropriately handle these malicious attacks and hacks, and there exist sufficient interests and demand in effective network security systems just like intrusion detection systems. Intrusion detection systems are the network security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. Conventional intrusion detection systems have generally been designed using the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. However, they cannot handle new or unknown patterns of the network attacks, although they perform very well under the normal situation. As a result, recent studies on intrusion detection systems use artificial intelligence techniques, which can proactively respond to the unknown threats. For a long time, researchers have adopted and tested various kinds of artificial intelligence techniques such as artificial neural networks, decision trees, and support vector machines to detect intrusions on the network. However, most of them have just applied these techniques singularly, even though combining the techniques may lead to better detection. With this reason, we propose a new integrated model for intrusion detection. Our model is designed to combine prediction results of four different binary classification models-logistic regression (LOGIT), decision trees (DT), artificial neural networks (ANN), and support vector machines (SVM), which may be complementary to each other. As a tool for finding optimal combining weights, genetic algorithms (GA) are used. Our proposed model is designed to be built in two steps. At the first step, the optimal integration model whose prediction error (i.e. erroneous classification rate) is the least is generated. After that, in the second step, it explores the optimal classification threshold for determining intrusions, which minimizes the total misclassification cost. To calculate the total misclassification cost of intrusion detection system, we need to understand its asymmetric error cost scheme. 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, total misclassification cost is more affected by FNE rather than FPE. 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 10,000 samples from them by using random sampling method. Also, we compared the results from our model with the results from single techniques to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell R4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on GA outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that the proposed model outperformed all the other comparative models in the total misclassification cost perspective. Consequently, it is expected that our study may contribute to build cost-effective intelligent intrusion detection systems.

• Journal of Chest Surgery
• /
• v.43 no.1
• /
• pp.39-46
• /
• 2010

Background: Preoperative chemotherapy has been adopted in our hospital as a standard treatment for non-small cell lung cancer patients with N2 disease. However, there have been cases of pathologic N2 disease that have been detected after curative-intent surgical resection. We retrospectively studied the outcomes of initial surgical treatment without neoadjuvant therapy in patients with unexpected N2 non-small cell lung cancer. Material and Method: Between January 1995 and June 2007, 225 patients were diagnosed with pathologic N2 disease after they underwent initial pulmonary resection without neoadjuvant therapy. Among them, 170 patients were preoperatively diagnosed with lymph node stage N0 or N1. We retrospectively reviewed their medical record and analyzed the outcomes. Result: The overall 5-year survival rate was 35.4%. The prognostic factors that were significantly associated with survival were no adjuvant therapy, histologic cell types other than adenocarcinoma or squamous cell carcinoma, a pathologic T stage more than T1, old age (${\geq}$70 years) and no mediastinoscopic biopsy. During the follow-up, 79 patients (46.5%) experienced tumor recurrence, including loco-regional recurrence in 20 patients (25.3%) and distant metastasis in 56 (70.9%). The 5-year recurrence-free survival rate was 33.7%. Conclusion: Based on our findings, the survival was good for patients with unexpected N2 non-small cell lung cancer and who underwent initial pulmonary resection without neoadjuvant therapy. A prospective comparative analysis is needed to obtain more conclusive and persuasive results.

• Journal of Yeungnam Medical Science
• /
• v.2 no.1
• /
• pp.221-227
• /
• 1985

Thirty-four patients with suspected ectopic pregnancy whose serum hCG levels had been measured by beta-hCG EIA before surgery were evaluated retrospectively. The results were as follows: 1. Final diagnosis of thirty-four patients with suspected ectopic pregnancy comprised twenty- eight tubal pregnancy, five ruptures of hemorrhagic corpus luteum and, one tubo-ovarian abscess. One of the five patients with rupture of hemorrhagic corpus luteum was accompanied by missed abortion. 2. Range of serum hCG levels in twenty-eight patients with tubal pregnancy was 59-21,980 mIU/ml and that of four patients with rupture of hemorrhagic corpus luteum and one patient with tubo-ovarian abscess was 0.6-6.6mIU/ml. Serum hCG level of a patient with rupture of hemorrhagic corpus luteum who was accompanied by missed abostion was 200 mIU/ml. 3. Serum hCG levels in twenty-two of twenty-eight patients with tubal pregnancy were lower than 3,000 mIU/ml. Low serum hCG level below 100mIU/ml and high serum hCG level above 6,500 mIU/ml were noticed in four and six patients with tubal pregnancy, respectively. 4. Mean serum hCG levels (${\pm}SD$) of twelve patients with tubal pregnancy who had intra-abdominal free blood of less than 500ml and sixteen patients with tubal pregnancy who had intra-abdominal free blood of more than 500ml were 4,131 (${\pm}7,801$) mIU/ml and 3,208 (${\pm}5,081$) mIU/ml, respectively. There was no statistical difference in the mean level of serum hCG between both group (P>0.05). 5. Mean serum hCG levels (${\pm}SD$) of thirteen patients with unruptured tubal pregnancy and fifteen patients with ruptured tubal pregnancy were 2,628 (${\pm}5,448$) mIU/ml and 4,449 (${\pm}6,938$) mIU/ml, respectively. Mean level of serum hCG was statistically higher in ruptured tubal pregnancy (P<0.01). 6. Positive rate of urine pregnancy test in the diagnosis of ectopic pregnancy was 64% (16/25) and mean range of serum hCG level of nine patients with false negative result were 353 mIU/ml and 59-933 mIU/ml.