• Title/Summary/Keyword: Normalization

Search Result 1,421, Processing Time 0.028 seconds

CNN-LSTM-based Upper Extremity Rehabilitation Exercise Real-time Monitoring System (CNN-LSTM 기반의 상지 재활운동 실시간 모니터링 시스템)

  • Jae-Jung Kim;Jung-Hyun Kim;Sol Lee;Ji-Yun Seo;Do-Un Jeong
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.24 no.3
    • /
    • pp.134-139
    • /
    • 2023
  • Rehabilitators perform outpatient treatment and daily rehabilitation exercises to recover physical function with the aim of quickly returning to society after surgical treatment. Unlike performing exercises in a hospital with the help of a professional therapist, there are many difficulties in performing rehabilitation exercises by the patient on a daily basis. In this paper, we propose a CNN-LSTM-based upper limb rehabilitation real-time monitoring system so that patients can perform rehabilitation efficiently and with correct posture on a daily basis. The proposed system measures biological signals through shoulder-mounted hardware equipped with EMG and IMU, performs preprocessing and normalization for learning, and uses them as a learning dataset. The implemented model consists of three polling layers of three synthetic stacks for feature detection and two LSTM layers for classification, and we were able to confirm a learning result of 97.44% on the validation data. After that, we conducted a comparative evaluation with the Teachable machine, and as a result of the comparative evaluation, we confirmed that the model was implemented at 93.6% and the Teachable machine at 94.4%, and both models showed similar classification performance.

Numerical analysis of geomorphic changes in rivers due to dam pulse discharge of Yeongju Dam (댐 펄스방류로 인한 하천의 지형변화 수치모의 분석(영주댐 중심으로))

  • Baek, Tae Hyoa;Jang, Chang-Laeb;Lee, Kyung Su
    • Journal of Korea Water Resources Association
    • /
    • v.56 no.12
    • /
    • pp.871-881
    • /
    • 2023
  • This study investigates the geomorphic changes and Bed Relief Index of the river downstream of the Yeongju Dam by Nays2DH, a two-dimensional numerical model, in order to grasp the dynamics of the downstream river while applying various flow patterns such as pulse discharge. It shows that the geomorphic and the bed elevations changes are the largest under the condition of the normalized pulse discharge. The total change in the riverbed is 29.88 m for uniform flow, 27.46 m for normalized hydrograph, 29.63 m for pulse flow and 31.87 m for pulse flow with normalized hydrograph which result in the largest variation in scour and deposition. The Bed Relief Index (BRI) increases with time under conditions of uniform flow, pulse flow and pulse flow with normalized hydrograph. However, BRI increased rapidly until 30 hrs after the peak flow (14 hrs), but decreased from 56 hrs under the condition of normalized hydrograph. Therefore, the condition of normalized hydrograph gives greater dynamics than the condition of a single flood or constant flow, and the dynamics increase downstream than upstream, resulting in an effect on improving the environment of the river downstream of the dam.

Analyzing the Impact of Multivariate Inputs on Deep Learning-Based Reservoir Level Prediction and Approaches for Mid to Long-Term Forecasting (다변량 입력이 딥러닝 기반 저수율 예측에 미치는 영향 분석과 중장기 예측 방안)

  • Hyeseung Park;Jongwook Yoon;Hojun Lee;Hyunho Yang
    • The Transactions of the Korea Information Processing Society
    • /
    • v.13 no.4
    • /
    • pp.199-207
    • /
    • 2024
  • Local reservoirs are crucial sources for agricultural water supply, necessitating stable water level management to prepare for extreme climate conditions such as droughts. Water level prediction is significantly influenced by local climate characteristics, such as localized rainfall, as well as seasonal factors including cropping times, making it essential to understand the correlation between input and output data as much as selecting an appropriate prediction model. In this study, extensive multivariate data from over 400 reservoirs in Jeollabuk-do from 1991 to 2022 was utilized to train and validate a water level prediction model that comprehensively reflects the complex hydrological and climatological environmental factors of each reservoir, and to analyze the impact of each input feature on the prediction performance of water levels. Instead of focusing on improvements in water level performance through neural network structures, the study adopts a basic Feedforward Neural Network composed of fully connected layers, batch normalization, dropout, and activation functions, focusing on the correlation between multivariate input data and prediction performance. Additionally, most existing studies only present short-term prediction performance on a daily basis, which is not suitable for practical environments that require medium to long-term predictions, such as 10 days or a month. Therefore, this study measured the water level prediction performance up to one month ahead through a recursive method that uses daily prediction values as the next input. The experiment identified performance changes according to the prediction period and analyzed the impact of each input feature on the overall performance based on an Ablation study.

Early Detection of hyperemia with Magnetic Resonance Fluid Attenuation Inversion Recovery Imaging after Superficial Temporal Artery to Middle Cerebral Artery Anastomosis

  • Jin Eun;Ik Seong Park
    • Journal of Korean Neurosurgical Society
    • /
    • v.67 no.4
    • /
    • pp.442-450
    • /
    • 2024
  • Objective : Cerebral hyperperfusion syndrome (CHS) manifests as a collection of symptoms brought on by heightened focal cerebral blood flow (CBF), afflicting nearly 30% of patients who have undergone superficial temporal artery (STA)-middle cerebral artery (MCA) anastomosis. The aim of this study was to investigate whether the amalgamation of magnetic resonance imaging (MRI) fluid-attenuated inversion recovery (FLAIR) and apparent diffusion coefficient (ADC) imaging via MRI can discern cerebral hyperemia after STA-MCA anastomosis surgery. Methods : A retrospective study was performed of patients who underwent STA-MCA anastomosis due to Moyamoya disease or atherosclerotic steno-occlusive disease. A protocol aimed at preventing CHS was instituted, leveraging the use of MRI FLAIR. Patients underwent MRI diffusion with FLAIR imaging 24 hours after STA-MCA anastomosis. A high signal on FLAIR images signified the presence of hyperemia at the bypass site, triggering a protocol of hyperemia care. All patients underwent hemodynamic evaluations, including perfusion MRI, single-photon emission computed tomography (SPECT), and digital subtraction angiography, both before and after the surgery. If a high signal intensity is observed on MRI FLAIR within 24 hours of the surgery, a repeat MRI is performed to confirm the presence of hyperemia. Patients with confirmed hyperemia are managed according to a protocol aimed at preventing further progression. Results : Out of a total of 162 patients, 24 individuals (comprising 16 women and 8 men) exhibited hyperemia on their MRI FLAIR scans following the procedure. SPECT was conducted on 23 patients, and 11 of them yielded positive results. All 24 patients underwent perfusion MRI, but nine of them showed no significant findings. Among the patients, 10 displayed elevations in both CBF and cerebral blood volume (CBV), three only showed elevation in CBF, and two only showed elevation in CBV. Follow-up MRI FLAIR scans conducted 6 months later on these patients revealed complete normalization of the previously observed high signal intensity, with no evidence of ischemic injury. Conclusion : The study determined that the use of MRI FLAIR and ADC mapping is a competent means of early detection of hyperemia after STA-MCA anastomosis surgery. The protocol established can be adopted by other neurosurgical institutions to enhance patient outcomes and mitigate the hazard of permanent cerebral injury caused by cerebral hyperemia.

Analysis of Keywords in national river occupancy permits by region using text mining and network theory (텍스트 마이닝과 네트워크 이론을 활용한 권역별 국가하천 점용허가 키워드 분석)

  • Seong Yun Jeong
    • Smart Media Journal
    • /
    • v.12 no.11
    • /
    • pp.185-197
    • /
    • 2023
  • This study was conducted using text mining and network theory to extract useful information for application for occupancy and performance of permit tasks contained in the permit contents from the permit register, which is used only for the simple purpose of recording occupancy permit information. Based on text mining, we analyzed and compared the frequency of vocabulary occurrence and topic modeling in five regions, including Seoul, Gyeonggi, Gyeongsang, Jeolla, Chungcheong, and Gangwon, as well as normalization processes such as stopword removal and morpheme analysis. By applying four types of centrality algorithms, including stage, proximity, mediation, and eigenvector, which are widely used in network theory, we looked at keywords that are in a central position or act as an intermediary in the network. Through a comprehensive analysis of vocabulary appearance frequency, topic modeling, and network centrality, it was found that the 'installation' keyword was the most influential in all regions. This is believed to be the result of the Ministry of Environment's permit management office issuing many permits for constructing facilities or installing structures. In addition, it was found that keywords related to road facilities, flood control facilities, underground facilities, power/communication facilities, sports/park facilities, etc. were at a central position or played a role as an intermediary in topic modeling and networks. Most of the keywords appeared to have a Zipf's law statistical distribution with low frequency of occurrence and low distribution ratio.

Comparison of Kinematics and Myoelectrical Activity during Deadlift, with and without Variable Banded Resistance, in Healthy, Trained Athletes

  • Everett B. Lohman;Mansoor Alameri;Fulden Cakir;Chih Chieh Chia;Maxine Shih;Owee Mulay;Kezia Marceline;Simran Jaisinghani;Gurinder Bains;Michael DeLeon;Noha Daher
    • Physical Therapy Rehabilitation Science
    • /
    • v.13 no.1
    • /
    • pp.53-70
    • /
    • 2024
  • Background: The conventional deadlift is a popular exercise for enhancing trunk, core, and lower extremity strength. However, its use in sports medicine is constrained by concerns of lumbar injuries, despite evidence supporting its safety and rehabilitative benefits. To optimize muscle activation using resistive bands in variable resistance therapy, we explored their feasibility in the deadlift. Design: Comparative experimental design Methods: Surface electromyography recorded muscle activity in the trunk and lower extremities during lifting, with normalization to the isometric Floor Lift using Maximal Voluntary Contraction. Kinematics were measured using inclinometer sensors to track hip and trunk sagittal plane angles. To prevent fatigue, each subject only used one of the three pairs of bands employed in the study. Results: Our study involved 45 healthy subjects (mean age: 30.4 ± 6.3 years) with similar baseline characteristics, except for years of lifting and strength-to-years-of-lifting ratio. Various resistance band groups exhibited significantly higher muscle activity than conventional deadlifts during different phases. The minimal resistance band group had notably higher muscle activity in the trunk, core, and lower extremity muscles, particularly in the end phase. The moderate resistance band group showed increased muscle activity in the mid-and end-phases. The maximum resistance band group demonstrated greater muscle activity in specific muscles during the early phase and overall higher activity in all trunk and lower extremity muscles in the mid and end phases of the deadlift (p<0.05). Conclusion: Our findings provide valuable insights into muscle activation with various resistance bands during deadlift exercise in clinical and gym settings. There appears to be a dose-response relationship between increased resistance bandwidth, external load, myoelectric activation, and range.

MRI Assessment of Complete Response to Preoperative Chemoradiation Therapy for Rectal Cancer: 2020 Guide for Practice from the Korean Society of Abdominal Radiology

  • Seong Ho Park;Seung Hyun Cho;Sang Hyun Choi;Jong Keon Jang;Min Ju Kim;Seung Ho Kim;Joon Seok Lim;Sung Kyoung Moon;Ji Hoon Park;Nieun Seo;Korean Society of Abdominal Radiology Study Group for Rectal Cancer
    • Korean Journal of Radiology
    • /
    • v.21 no.7
    • /
    • pp.812-828
    • /
    • 2020
  • Objective: To provide an evidence-based guide for the MRI interpretation of complete tumor response after neoadjuvant chemoradiation therapy (CRT) for rectal cancer using visual assessment on T2-weighted imaging (T2) and diffusion-weighted imaging (DWI). Materials and Methods: PubMed MEDLINE, EMBASE, and Cochrane Library were searched on November 28, 2019 to identify articles on the following issues: 1) sensitivity and specificity of T2 or DWI for diagnosing pathologic complete response (pCR) and the criteria for MRI diagnosis; 2) MRI alone vs. MRI combined with other test(s) in sensitivity and specificity for pCR; and 3) tests to select patients for the watch-and-wait management. Eligible articles were selected according to meticulous criteria and were synthesized. Results: Of 1615 article candidates, 55 eligible articles (for all three issues combined) were identified. Combined T2 and DWI performed better than T2 alone, with a meta-analytic summary sensitivity of 0.62 (95% confidence interval [CI], 0.43-0.77; I2 = 80.60) and summary specificity of 0.89 (95% CI, 0.80-0.94; I2 = 92.61) for diagnosing pCR. The criteria for the complete response on T2 in most studies had the commonality of remarkable tumor decrease to the absence of mass-like or nodular intermediate signal, although somewhat varied, as follows: (near) normalization of the wall; regular, thin, hypointense scar in the luminal side with (near) normal-appearance or homogeneous intermediate signal in the underlying wall; and hypointense thickening of the wall. The criteria on DWI were the absence of a hyperintense signal at high b-value (≥ 800 sec/mm2) in most studies. The specific algorithm to combine T2 and DWI was obscure in half of the studies. MRI combined with endoscopy was the most utilized means to select patients for the watch-and-wait management despite a lack of strong evidence to guide and support a multi-test approach. Conclusion: This systematic review and meta-analysis provide an evidence-based practical guide for MRI assessment of complete tumor response after CRT for rectal cancer.

The Workflow for Computational Analysis of Single-cell RNA-sequencing Data (단일 세포 RNA 시퀀싱 데이터에 대한 컴퓨터 분석의 작업과정)

  • Sung-Hun WOO;Byung Chul JUNG
    • Korean Journal of Clinical Laboratory Science
    • /
    • v.56 no.1
    • /
    • pp.10-20
    • /
    • 2024
  • RNA-sequencing (RNA-seq) is a technique used for providing global patterns of transcriptomes in samples. However, it can only provide the average gene expression across cells and does not address the heterogeneity within the samples. The advances in single-cell RNA sequencing (scRNA-seq) technology have revolutionized our understanding of heterogeneity and the dynamics of gene expression at the single-cell level. For example, scRNA-seq allows us to identify the cell types in complex tissues, which can provide information regarding the alteration of the cell population by perturbations, such as genetic modification. Since its initial introduction, scRNA-seq has rapidly become popular, leading to the development of a huge number of bioinformatic tools. However, the analysis of the big dataset generated from scRNA-seq requires a general understanding of the preprocessing of the dataset and a variety of analytical techniques. Here, we present an overview of the workflow involved in analyzing the scRNA-seq dataset. First, we describe the preprocessing of the dataset, including quality control, normalization, and dimensionality reduction. Then, we introduce the downstream analysis provided with the most commonly used computational packages. This review aims to provide a workflow guideline for new researchers interested in this field.

Hepatitis Complicated with Mycoplasma pneumoniae Infection (Mycoplasma pneumoniae 폐렴에 합병된 간염)

  • Lee, Jin-Tae;Kim, Hee-Sup;Tchah, Hann
    • Pediatric Gastroenterology, Hepatology & Nutrition
    • /
    • v.4 no.2
    • /
    • pp.207-212
    • /
    • 2001
  • Purpose: Mycoplasma pneumoniae infection is relatively common in childhood. Its extrapulmonary manifestations have been reported so much, but hepatitis associated with it has not been studied yet until now in Korea. Methods: We performed the prospective study of 19 cases that had AST and ALT>50 IU/L respectively without evidence of hepatitis A, B, C, cytomegalovirus, and Ebstein-Barr virus infections amongst 143 patients with M. pneumoniae pneumonia who were admitted to the Department of Pediatrics, Seoul Red Cross Hospital from Jan. 1999 to Dec. 2000. Results: 1) Hepatitis occurred in 13.3% of Mycoplasma pneumoniae infection, especially in fall and winter times. The average age was 4.86 years and male to female ratio was 2.2:1. 2) Vomiting was developed in 21.1%, diarrhea in 36.8%, and hepatomegaly in 21.1%, respectively. And leukocytosis was noted in 21.1%, eosinophilia in 15.4%, anemia in 10.5%, and thrombocytosis in 5.3%, respectively. The average level of C-reactive protein was $6.34{\pm}4.82$ mg/dl. 3) There was no hyperbilirubinemia, but hypoalbuminemia was detected in 42.1%. The average serum levels of AST and ALT were $214.05{\pm}183.22$ IU/L and $284.16{\pm}286.84$ IU/L, respectively. 4) Chest radiology showed lobar or lobular consolidation in 73.7%, bronchial infiltration in 26.3%, and pleural effusion in 31.6%. 5) The average length of hospitalization was 7.9 days, and the average length of normalization of serum transaminases was 8.8 days. All patients recovered within 2 weeks completely. Conclusion: The prognosis of M. pneumoniae hepatitis is good. However, its incidence is not so low that liver function should be considerately checked in case of M. pneumoniae infection.

  • PDF

Three Years' Cumulative Therapeutic Efficacy and Long-term Durability of Lamivudine in Korean Children with Chronic Hepatitis B (소아 만성 B형 간염에서 라미부딘 치료의 3년 누적 치료 반응과 장기 지속성)

  • Jang, You Cheol;Cho, Min Hyun;Choe, Byung-Ho
    • Pediatric Gastroenterology, Hepatology & Nutrition
    • /
    • v.7 no.2
    • /
    • pp.197-207
    • /
    • 2004
  • Purpose: To evaluate the long-term therapeutic efficacy and durability of lamivudine in Korean children with chronic hepatitis B. Methods: A total of 48 children (31 male and 17 female; age, 1~18 years, mean, 8 years) with chronic hepatitis B who received lamivudine for at least six months from March 1999 to September 2004 were followed for a mean period of 29 months (8~66 months) at Department of Pediatrics, Kyungpook National University Hospital in Korea. Response to treatment was defined as the normalization of ALT and HBV DNA levels, and HBeAg seroconversion after the initiation of treatment. Results: Twenty nine (60%) among the 48 children treated with lamivudine responded and nine (19%) children lost HBsAg during therapy. ALT and HBV DNA level had normalized in 94% one year after the initiation of treatment. Kaplan-Meier estimates of cumulative HBeAg seroconversion rates over the years were 13% (0.5 year), 34% (1 year), 50% (1.5 years), 68% (2 years), 79% (2.5 years) and 90% at 3 years respectively. Above all, among the 22 children treated before the age of seven, loss of HBsAg occurred in eight (36%), which showed superior rate of HBsAg loss (p=0.002 vs age >7). Conclusion: Long-term treatment of lamivudine improved the rate of HBeAg seroconversion in Korean children with chronic hepatitis B. After three years' observation, most of treated children have sustained HBeAg clearance. We believe that lamivudine should be tried as the first therapeutic option for children with chronic hepatitis B in immune clearance phase.

  • PDF