• Asian Pacific Journal of Cancer Prevention
• /
• 제15권5호
• /
• pp.2069-2074
• /
• 2014

Purpose: To appraise the frequency of cervical cytological abnormalities in a population at normal risk via analysing the archive records of cytology for the period of approximately 9,5 years, comparing them with patient demographic charecteristics, and discuss the results for women under age of 35. Materials and Methods: A total of 32,578 cases of Pap smears were retrieved and analysed from our archive included the Pap tests performed between January 2001 and April 2010 at the Early Cancer Screening, Diagnosing and Education Center by the consent of three pathologists via utilizing the Bethesda System Criteria 2001 and the results were compared with some demographical characteristics. Results: Our rate of the cervical cytological abnormality was 1.83%, with ASCUS in 1.18%, LSIL in 0.39, HSIL in 0.16%, AGUS in 0.07%, squamous cell carcinoma in 0.02%, and adenoarcinoma in 0.006%. Cytological abnormalities were detected mostly in those with higher age, lower parity, and premenopausal period whereas the smoking status was without influence. Bacterial vaginosis (5.6%) was the most frequent infectious finding (Candida albicans 2.7%; Actinomyces sp. 1.3%; and Trichomonas vaginalis 0.2%) detected on the smears. The rate of abnormal cervical cytology was 9.5% among the women aged between 30-34. Conclusions: Early detection of the cervical abnormalities by means of the regular cervical cancer screening programmes is useful to attenuate the incidence, mortality, and morbidity of cervical cancer. Our prevalence of the cytological abnormalities was much lower than the one in Western populations in general but very similar to those reported from other Islamic countries that may be explained by the conservative lifestyle and the lower prevalence of HPV in Turkey. A remarkable rate of abnormal cervical cytology of women aged 30-34 was pointed out in the present study.

• 한국수정란이식학회지
• /
• 제30권1호
• /
• pp.51-57
• /
• 2015

This study was aimed to determine the biometry of genital organs, incidence of gynecological disorders and pregnancy loss in Black Bengal goat (Capra hircus). Genitalia of 118 does were collected from local abattoirs. Biometric parameters of genital organs were measured and gross and histopathological examinations were carried out for detection of abnormalities. For gravid uterus, age of the fetus was determined by measuring crown-rump length. There was no significant difference in the length, width and weight of right and left ovaries (P>0.05). However, the number of follicles between left ($5.3{\pm}2.3$) and right ovaries ($7.4{\pm}2.7$) varied significantly (P<0.05). The mean length of right fallopian tube and uterine horn were not varied with those of left fallopian tube and uterine horn. The length of uterine body, cervix and vagina were $1.3{\pm}0.1cm$, $3.3{\pm}0.5cm$ and $6.8{\pm}1.3cm$, respectively. Overall, 29 (24.6%) genitalia had abnormalities. Fifteen genitalia (12.7%) had ovarian abnormalities including ovaro-bursal adhesions (6.8%), parovarian cyst (5.1%) and follicular cyst (0.9%). Uterine abnormalities were found in 12 genitalia (10.2%) and predominant uterine lesion was endometritis (6.8%) followed by adenomyosis (1.7%), hemorrhagic lesion on endometrial surface (0.9%) and cyst in broad ligament (0.9%). In addition, cyst in fallopian tube (0.9%) and vagina (0.9%) were recorded. The proportion of slaughtered pregnant goats was 15.3% (18/118). The pregnancy wastage was highest in the first month (50.0%) followed by second (33.3%) and third (16.7%) month. It can be concluded that ovaro-bursal adhesions, parovarian cyst and endometritis are the gynecological disorders of major concern in Black Bengal goat.

• 정보보호학회논문지
• /
• 제25권1호
• /
• pp.133-146
• /
• 2015

전자금융사기의 고도화와 함께 지능적인 수법들이 동원됨에 따라 전자금융 사용자들의 피해사례가 늘어나고 있다. 이에 대한 대응 방안으로 금융당국은 사용자 구간에 집중된 기존 보안 대책 외에 이의 한계성을 극복하기 위한 이상거래 탐지 시스템의 도입을 확대 권고하고 있다. 이상거래 탐지 시스템은 실시간으로 고객의 거래를 확인하고 이상거래 유무를 판별하여 전자금융 사고를 방지할 수 있도록 하는 시스템으로 거래 정보를 빠르게 분석하여 이상거래를 식별하는 것이 핵심이다. 본 논문에서는 사고 데이터분석을 통해 이상 징후 패턴을 파악하고 탐지 룰을 설정하고, 이렇게 설정된 룰을 기반으로 고객 개인별 거래 패턴과 고객 프로파일을 비교하여 이상거래 여부를 판단하고자 한다. 이때 의사결정나무를 사용하여 탐지 룰을 정규화 하여 효과적으로 이상거래를 탐지 할 수 있도록 하는 방법을 제안하고자 한다. 실증 분석을 위해 국내 모 은행의 전자금융 사고 데이터를 바탕으로 패턴 정보와 고객 프로파일 정보를 도출하였고 이를 통하여 탐지 룰을 설정하였다. 그리고 탐지된 룰을 의사결정나무를 사용하여 정규화 한 결과를 순차적인 탐지 방식과 비교하여 제시된 방안이 효과적임을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.348-369
• /
• 2024

With the advancement of Industry 4.0 and Industrial Internet of Things (IIoT), manufacturing increasingly seeks automation and intelligence. Temperature and vibration monitoring are essential for machinery health. Traditional abnormal state detection methodologies often overlook the intricate frequency characteristics inherent in vibration time series and are susceptible to erroneously reconstructing temperature abnormalities due to the highly similar waveforms. To address these limitations, we introduce synergistic, end-to-end, unsupervised Frequency-Time Domain Memory-Enhanced Autoencoders (FTD-MAE) capable of identifying abnormalities in both temperature and vibration datasets. This model is adept at accommodating time series with variable frequency complexities and mitigates the risk of overgeneralization. Initially, the frequency domain encoder processes the spectrogram generated through Short-Time Fourier Transform (STFT), while the time domain encoder interprets the raw time series. This results in two disparate sets of latent representations. Subsequently, these are subjected to a memory mechanism and a limiting function, which numerically constrain each memory term. These processed terms are then amalgamated to create two unified, novel representations that the decoder leverages to produce reconstructed samples. Furthermore, the model employs Spectral Entropy to dynamically assess the frequency complexity of the time series, which, in turn, calibrates the weightage attributed to the loss functions of the individual branches, thereby generating definitive abnormal scores. Through extensive experiments, FTD-MAE achieved an average ACC and F1 of 0.9826 and 0.9808 on the CMHS and CWRU datasets, respectively. Compared to the best representative model, the ACC increased by 0.2114 and the F1 by 0.1876.

• 센서학회지
• /
• 제28권1호
• /
• pp.13-16
• /
• 2019

The analysis of electrocardiogram (ECG) signals facilitates the detection of various abnormal conditions of the human heart. The QRS complex is the most critical part of the ECG waveform. Further, different diseases can be identified based on the QRS complex. In this paper, a new algorithm based on the well-known Pan-Tompkins algorithm has been proposed. In the proposed scheme, the QRS complex is initially extracted by removing the background noise. Subsequently, the R-R interval and heart rate are calculated to detect whether the ECG is normal or has some abnormalities such as tachycardia and bradycardia. The accuracy of the proposed algorithm is found to be almost the same as the Pan-Tompkins algorithm and increases the R peak detection processing speed. For this work, samples are used from the MIT-BIH Arrhythmia Database, and the simulation is carried out using MATLAB 2016a.

• 센서학회지
• /
• 제32권6호
• /
• pp.378-385
• /
• 2023

Human biosignals provide essential information for diagnosing diseases such as dementia and Parkinson's disease. Owing to the shortcomings of current clinical assessments, noninvasive solutions are required. Machine learning (ML) on wearable sensor data is a promising method for the real-time monitoring and early detection of abnormalities. ML facilitates disease identification, severity measurement, and remote rehabilitation by providing continuous feedback. In the context of wearable sensor technology, ML involves training on observed data for tasks such as classification and regression with applications in clinical metrics. Although supervised ML presents challenges in clinical settings, unsupervised learning, which focuses on tasks such as cluster identification and anomaly detection, has emerged as a useful alternative. This review examines and discusses a variety of ML algorithms such as Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Neural Networks (NN), and Deep Learning for the analysis of complex clinical data.

• 한국BIM학회 논문집
• /
• 제13권3호
• /
• pp.12-20
• /
• 2023

Deep learning-based anomaly detection technology is used in various fields such as computer vision, speech recognition, and natural language processing. In particular, this technology is applied in various fields such as monitoring manufacturing equipment abnormalities, detecting financial fraud, detecting network hacking, and detecting anomalies in medical images. However, in the field of construction and architecture, research on deep learning-based data anomaly detection technology is difficult due to the lack of digitization of domain knowledge due to late digital conversion, lack of learning data, and difficulties in collecting and processing field data in real time. This study acquires necessary data through IoT (Internet of Things) from the viewpoint of monitoring for environmental management of architectural spaces, converts them into a database, learns deep learning, and then supports anomaly patterns using AI (Artificial Infelligence) deep learning-based anomaly detection. We propose an implementation process. The results of this study suggest an effective environmental anomaly pattern detection solution architecture for environmental management of architectural spaces, proving its feasibility. The proposed method enables quick response through real-time data processing and analysis collected from IoT. In order to confirm the effectiveness of the proposed method, performance analysis is performed through prototype implementation to derive the results.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권12호
• /
• pp.7193-7196
• /
• 2013

Ovarian cancer patients need a surveillance program for the detection of tumor progression after completion of treatment. The methods generally consist of history taking, physical examination, tumor marker monitoring and imaging. However, the details of recurrence detection with each method are not well defined. To clarify this issue, ovarian cancer patients who achieved complete or partial responses and developed tumor progression at the follow up time between January 2004 and December 2010 in University Hospital Chiang Mai, Thailand, were reviewed. Clinical data, CA 125 level and imaging results at the tumor progression time were recorded and analyzed. There were 144 ovarian cancer patients meeting the inclusion criteria with the mean age of 51 years and 62.5% of them were in an advanced stage. Complete response was achieved in 89 patients (61.8%) after primary treatment. The median progression free survival and overall survival were 15.5 months and 37.5 months, respectively. Abnormal symptoms presented in 49.3% of the studied patients and 59.7% developed physical examination abnormalities. In addition, CA 125 was elevated in 89.6% while in 74.3% of tumor progression was identified by CT-scan. Short treatment time period and a high level of CA 125 were significant independent prognostic factors in these patients. In conclusion, careful history taking, physical examination and monitoring of CA 125 levels are important methods for tumor progression detection in a surveillance program for epithelial ovarian cancer patients.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권14호
• /
• pp.5613-5618
• /
• 2015

Clinicians should looking for techniques that helps to early diagnosis of cancer, because early cancer detection is critical to increase survival and cost effectiveness of treatment, and as a result decrease mortality rate. Medical images are the most important tools to provide assistance. However, medical images have some limitations for optimal detection of some neoplasias, originating either from the imaging techniques themselves, or from human visual or intellectual capacity. Image processing techniques are allowing earlier detection of abnormalities and treatment monitoring. Because the time is a very important factor in cancer treatment, especially in cancers such as the lung and breast, imaging techniques are used to accelerate diagnosis more than with other cancers. In this paper, we outline experience in use of image processing techniques for lung and breast cancer diagnosis. Looking at the experience gained will help specialists to choose the appropriate technique for optimization of diagnosis through medical imaging.

• 한국건강관리협회지
• /
• 제3권1호
• /
• pp.110-120
• /
• 2005

The ultrasonography(US) is one of very important item for abdominal evaluation. Especially for the routine check of the abdomen, the US becomes the essential part of the precedure. Though the abdominal US is simple and easy, its value is very high for detection of various morphological changes of abdominal organs. The study techniques of US, common abdominal abnormalities, standardization of image interpretation, and clinical significance of the lesions, etc, were discussed.