Machine Learning Approaches for the Prediction of Prostate Cancer according to Age and the Prostate-Specific Antigen Level

Jaegeun Lee(이재근),Seung Woo Yang(양승우),Seunghee Lee(이승희),Yun Kyong Hyon(현윤경),Jinbum Kim(김진범),Long Jin(김용),Ji Yong Lee(이지용),Jong Mok Park(박종목),Taeyoung Ha(하태영),Ju Hyun Shin(신주현),Jae Sung Lim(임재성),Yong Gi 대한비뇨기종양학회 2019 대한비뇨기종양학회지 Vol.17 No.2

Purpose: The aim of this study was to evaluate the applicability of machine learning methods that combine data on age and prostate-specific antigen (PSA) levels for predicting prostate cancer. Materials and Methods: We analyzed 943 patients who underwent transrectal ultrasonography (TRUS)-guided prostate biopsy at Chungnam National University Hospital between 2014 and 2018 because of elevated PSA levels and/or abnormal digital rectal examination and/or TRUS findings. We retrospectively reviewed the patients’ medical records, analyzed the prediction rate of prostate cancer, and identified 20 feature importances that could be compared with biopsy results using 5 different algorithms, viz., logistic regression (LR), support vector machine, random forest (RF), extreme gradient boosting, and light gradient boosting machine. Results: Overall, the cancer detection rate was 41.8%. In patients younger than 75 years and with a PSA level less than 20 ng/mL, the best prediction model for prostate cancer detection was RF among the machine learning methods based on LR analysis. The PSA density was the highest scored feature importances in the same patient group. Conclusions: These results suggest that the prediction rate of prostate cancer using machine learning methods not inferior to that using LR and that these methods may increase the detection rate for prostate cancer and reduce unnecessary prostate biopsy, as they take into consideration feature importances affecting the prediction rate for prostate cancer.

Sensitivity analysis for a groundwater flow simulation with simultaneous changes of hydraulic parameters and domain resolution

Jaegeun Jung,Hyoun-Tae Hwang,Sung-Wook Jeen 대한지질학회 2020 대한지질학회 학술대회 Vol.2020 No.10

Predictors of Change in Behavioral Psychological Symptoms of Dementia in Patients With Alzheimer’s Disease in Korea

Jaegeun Jung,Minsook Gim 대한노인정신의학회 2021 노인정신의학 Vol.25 No.2

Objective: The purpose of our study was to identify the correlation between clinical characteristics and behavioral psychological symptoms of dementia (BPSD) and to identify factors that predict BPSD changes. Methods: Demographic characteristics were collected and BPSD was assessed using the Korean version of Neuropsychiatric Inventory (K-NPI) for 213 patients with Alzheimer’s disease. BPSD was reassessed to identify changes in the K-NPI score for 65 of the 213 patients. Seoul Neuropsychological Screening Battery was conducted to evaluate specific cognitive functions. Correlation and stepwise regression analyses were conducted to identify the association between several factors and the baseline K-NPI total score. Logistic regression analysis was conducted to identify predictors of improvement of BPSD. Results: Stepwise analysis showed that the baseline K-NPI total score was significantly affected by higher Seoul-Instrumental Activities of Daily Living and having family history of dementia. Multivariate logistic regression analysis showed that improvement of BPSD was significantly associated with a higher baseline K-NPI total score. However, changes in BPSD were not predicted by any specific cognitive functions. Conclusion: Severe BPSD at baseline is a significant predictor of improvement of BPSD. The findings support that severe BPSD at baseline had more chance to benefit from the intervention. Therefore, clinicians need more intensive observation and early intervention for patients in the early stages of dementia.

Exploiting Thread-Level Parallelism in Lockstep Execution by Partially Duplicating a Single Pipeline

Jaegeun Oh,Seok Joong Hwang,Huong Giang Nguyen,Areum Kim,김선욱,김철우,김종국 한국전자통신연구원 2008 ETRI Journal Vol.30 No.4

In most parallel loops of embedded applications, every iteration executes the exact same sequence of instructions while manipulating different data. This fact motivates a new compiler-hardware orchestrated execution framework in which all parallel threads share one fetch unit and one decode unit but have their own execution, memory, and write-back units. This resource sharing enables parallel threads to execute in lockstep with minimal hardware extension and compiler support. Our proposed architecture, called multithreaded lockstep execution processor (MLEP), is a compromise between the single-instruction multiple-data (SIMD) and symmetric multithreading/chip multiprocessor (SMT/CMP) solutions. The proposed approach is more favorable than a typical SIMD execution in terms of degree of parallelism, range of applicability, and code generation, and can save more power and chip area than the SMT/CMP approach without significant performance degradation. For the architecture verification, we extend a commercial 32-bit embedded core AE32000C and synthesize it on Xilinx FPGA. Compared to the original architecture, our approach is 13.5% faster with a 2-way MLEP and 33.7% faster with a 4-way MLEP in EEMBC benchmarks which are automatically parallelized by the Intel compiler.

Development of Seat-mounted Non-Intrusive ECG Sensing System

Jaegeun Lee,Hosang Oh,Joonwoo Son 대한인간공학회 2012 대한인간공학회 학술대회논문집 Vol.2012 No.11

Objective: The aim of this study is to measure driver’s ECG signal non-intrusively using a seat-mounted conductive sensor system. Background: Driving workload has been identified as one of the leading causes of traffic accidents and this fact made many research groups to study the driver’s workload state monitoring during driving. The workload can be estimated by measuring driver’s heart rate. Method: The proposed non-intrusive ECG sensor system consists of conductive sensors and amplifier, Bluetooth transmitter, and post signal processing system. The sensors which mounted on a driver seat back, detect the local electric potential, and the sensing data is transmitted to post signal processing system via Bluetooth modules. The transmitted data was sampled and stored digitally on the laptop. The data was filtered through anti-aliasing band-pass filters. For evaluating the accuracy from this system, comparisons between proposed system and commercially available surface electrode based ECG measurement system were conducted. R-R interval and ECG correlation were used for evaluating accuracy. Conclusion: This system can be used for measuring ECG signal non-intrusively during driving. Application: The use of this system can help to develop systems for monitoring driver’s workload in real-time.

CUDA를 활용한 스케일링 필터 및 트랜스코더의 성능향상

한재근(JaeGeun Han),고영섭(YoungSub Ko),서성한(SungHan Suh),하순회(Soonhoi Ha) 한국정보과학회 2010 정보과학회 컴퓨팅의 실제 논문지 Vol.16 No.4

본 논문은 GPGPU가속을 이용한 스케일링 필터(scaling filter) 및 트랜스코딩(Transcoding)의 성능 향상 방법을 제안한다. 트랜스코딩 기술은 다양한 요구조건을 지닌 멀티미디어 기기에 적합하게 동영상을 가공하는 기술로, 오늘날 여러 분야에서 활용되는 중요한 기술이다. 그러나 트랜스코딩에는 대량의 연산이 필요하기 때문에 기존 트랜스코더(Transcoder) 사용자들은 오랜 처리시간을 감내해야만 했는데, 이는 CPU만을 이용한 트랜스코딩이 충분히 효율적이지 못하기 때문이다. 본 연구에서는 고성능의 연산이 가능한 GPGPU기술을 활용하여, 트랜스코더의 스케일링 필터를 GPU 상에서 높은 병렬성을 가지고 동작하도록 개선함으로써 트랜스코더의 전체적인 성능을 향상시켰다. 개선된 트랜스코더는 다양한 크기의 동영상과 여러 종류의 스케일링 필터 옵션들에 대해 잘 동작함이 검증되었으며, 기본 옵션에서 36%, 최대 101%의 성능향상을 보였다. In this paper, we propose to enhance the performance of software transcoder by using GPGPU for scaling filters. Video transcoding is a technique that translates a video file to another video file that has a different coding algorithm and/or a different frame size. Its demand increases as more multimedia devices with different specification coexist in our daily life. Since transcoding is computationally intensive, a software transcoder that runs on a CPU takes long processing time. In this paper, we achieve significant speed-up by parallelizing the scaling filter using a GPGPU that can provide significantly large computation power. Through extensive experiments with various video scripts of different size and with various scaling filter options, it is verified that the enhanced transcoder could achieve 36% performance improvement in the default option, and up to 101% in a certain option.

나노초 레이저와 펨토초 레이저의 LiFePO4 양극에 대한 레이저 가공성 비교

신재근(Jaegeun Shin),성민철(Mincheoul Seong),박명호(Myeong Ho Park),이동경(Dongkyung Lee) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11

나노초 레이저와 펨토초 레이저의 LiFePO4 양극에 대한 레이저 가공성 비교

신재근(Jaegeun Shin),성민철(Mincheoul Seong),박명호(Myeong Ho Park),이동경(Dongkyung Lee) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11

수상태양광 효율 향상 방안 고찰

송재근(Jaegeun Song),정한상(Hansang Jung) 한국신재생에너지학회 2016 한국신재생에너지학회 학술대회논문집 Vol.2016 No.5

경제정의교육에의 두 가지 접근

김재근 ( Jaegeun Kim ) 한국경제교육학회 2017 경제교육연구 Vol.24 No.1

본 논문은 그 동안 경제교육의 관심사에서 멀어져있던 `경제정의`의 문제를 두 가지 대비되는 접근방법을 통해 다시금 조명해보고 있다. 이를 위해 먼저 경제정의에 대한 주류적인 접근은 무엇이며, 어떤 특징을 가지고 있는지를 밝히고, 이러한 주류적 접근의 한계는 무엇인지 비판적으로 탐구한다. 지금까지 경제정의에 대한 접근이 공정한 분배를 어떻게 달성할 것인가 하는 정의의 방법에 초점을 두고 있다는 점, 그리고 그것의 제도적 해결에 의존한다는 점, 근대적 주체개념을 계승하고 있다는 점 등이 비판점으로 제시된다. 이어서 이러한 비판적 분석에 기초하여 경제정의와 경제정의교육에 대한 대안적 접근, 즉 타자지향적 경제정의교육의 가능성을 제안한다. 특히 경제정의에 대한 타자지향적 접근은 왜 정의가 필요한지, 누구를 위한 정의인지에 대답하려 한다는 점, 그리고 주체의 근본적인 존재원리를 타자로부터 찾고자 한다는 점 등이 주로 논의된다. 이에 타자에 대한 조건 없는 환대와 비대칭적인 책임으로서의 경제정의의 가능성이 제시되고 있으며, 마지막으로 이러한 타자 지향적 접근이 경제정의교육에 시사하는 바는 무엇인지 탐색해본다 This study examines two different approaches to the issue of economic justice: Subject-centered approach and Others-oriented approach. The Subject-centered approach to economic justice is based on the question of `How to achieve justice?` Since it focuses on the `method` of justice, the ensuing answers are tied to principles and theories of justice, and the creation of just institutions. In general, economic justice from this approach is regarded to be a just distribution of economic resources such as wealth and income. Compared to that, an Others-oriented approach asks the question of `Why justice?` and the answer for the reason of economic justice is `the face of Other,` which comes up to us as an irresistible imperative. It demands us to respond to the vocation of the Other, to give away what we possess, to replace my space for the suffering Other, and to offer unconditional hospitality. Based on the comparison of these two different approaches, this study suggests to re-conceptualize economic justice education as responding to the vocation of the Others.