Yuan-Chin Ivan Chang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuan-Chin Ivan Chang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
Zhanfeng Wang
Department of Statistics and Finance University of Science and Technology of China Anhui China
7 shared publications- Chia-Jung Li
Department of Obstetrics and Gynecology, Kaohsiung Veterans General Hospital , Kaohsiung
2 shared publications - Chung Chang
Department of Applied Mathematics, National Sun Yat-Sen University, Kaohsiung 804, Taiwan
2 shared publications - Hsiang-Ling Hsu
National University of Kaohsiung, Taiwan
2 shared publications - Jim Jinn-Chyuan Sheu
Institute of Biomedical Sciences, National Sun Yat-Sen University, Kaohsiung, Taiwan
2 shared publications - Ray-Bing Chen
Institute of Statistics and Data Science National Tsing Hua University Hsinchu 30013 Taiwan nthu.edu.tw
2 shared publications
Latest Publications
- 15 March 2025
- Published by Wiley in Statistics in Medicine
- Vol. 44 (6) , e70002
Ensemble of Sequential Learning Models With Distributed Data Centers and Its Applications
Handling massive datasets poses a significant challenge in modern data analysis, particularly within epidemiology and medicine. In this study, we introduce a novel approach using sequential ensemble learning to effectively analyze extensive datasets. Our method prioritizes efficiency from both statistical and computational perspectives, addressing challenges such as data communication and privacy, as discussed in federated learning literature. To demonstrate the efficacy of our approach, we present compelling real‐world examples using COVID‐19 data alongside simulation studies.
- 15 March 2025
- Published by Wiley in Statistics in Medicine
- Vol. 44 (6) , e70002
Ensemble of Sequential Learning Models With Distributed Data Centers and Its Applications
Handling massive datasets poses a significant challenge in modern data analysis, particularly within epidemiology and medicine. In this study, we introduce a novel approach using sequential ensemble learning to effectively analyze extensive datasets. Our method prioritizes efficiency from both statistical and computational perspectives, addressing challenges such as data communication and privacy, as discussed in federated learning literature. To demonstrate the efficacy of our approach, we present compelling real‐world examples using COVID‐19 data alongside simulation studies.
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3158 (1) , 040004
Classifying wet and dry events using reconnaissance drought index: A rainfall duration-severity analysis based on copula model
Effective water resource management hinges on a profound understanding of rainfall patterns, a paramount concern in regions like Peninsular Malaysia, where wate Effective water resource management hinges on a profound understanding of rainfall patterns, a paramount concern in regions like Peninsular Malaysia, where wate
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3158 (1) , 040004
Classifying wet and dry events using reconnaissance drought index: A rainfall duration-severity analysis based on copula model
Effective water resource management hinges on a profound understanding of rainfall patterns, a paramount concern in regions like Peninsular Malaysia, where wate Effective water resource management hinges on a profound understanding of rainfall patterns, a paramount concern in regions like Peninsular Malaysia, where wate
- Open Access
Distributed sequential federated learning
The analysis of data stored in multiple sites has become more popular, raising new concerns about the security of data storage and communication. Federated learning, which does not require centralizing data, is a common approach to preventing heavy data transportation, securing valued data, and protecting personal information protection. Therefore, determining how to aggregate the information obtained from the analysis of data in separate local sites has become an important statistical issue. The commonly used averaging methods may not be suitable due to data nonhomogeneity and incomparable results among individual sites, and applying them may result in the loss of information obtained from the individual analyses. Using a sequential method in federated learning with distributed computing can facilitate the integration and accelerate the analysis process. We develop a data-driven method for efficiently and effectively aggregating valued information by analyzing local data without encountering potential issues such as information security and heavy transportation due to data communication. In addition, the proposed method can preserve the properties of classical sequential adaptive design, such as data-driven sample size and estimation precision when applied to generalized linear models. We use numerical studies of simulated data and an application to COVID-19 data collected from 32 hospitals in Mexico, to illustrate the proposed method.
Open AccessDistributed sequential federated learning
The analysis of data stored in multiple sites has become more popular, raising new concerns about the security of data storage and communication. Federated learning, which does not require centralizing data, is a common approach to preventing heavy data transportation, securing valued data, and protecting personal information protection. Therefore, determining how to aggregate the information obtained from the analysis of data in separate local sites has become an important statistical issue. The commonly used averaging methods may not be suitable due to data nonhomogeneity and incomparable results among individual sites, and applying them may result in the loss of information obtained from the individual analyses. Using a sequential method in federated learning with distributed computing can facilitate the integration and accelerate the analysis process. We develop a data-driven method for efficiently and effectively aggregating valued information by analyzing local data without encountering potential issues such as information security and heavy transportation due to data communication. In addition, the proposed method can preserve the properties of classical sequential adaptive design, such as data-driven sample size and estimation precision when applied to generalized linear models. We use numerical studies of simulated data and an application to COVID-19 data collected from 32 hospitals in Mexico, to illustrate the proposed method.
- 14 February 2022
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 53 (2) , 897-911
Active learning with logistic models featuring simultaneous variable and subject selection
Modern computing and communication technologies can make data collection procedures very efficient, while our ability to analyze and extract information from large data sets is hard-pressed to keep up with our capacity for data collection. If we are interested in learning a classification/prediction rule that was not considered in the original data collection procedure, then there is usually a lack of label information in the original data. Thus, how to start with minimum number of labeled data and aggressively selected most informative samples for being labeled becomes an important issue. The thoughts of active learning, with subjects to be selected sequentially without using label information, is a possible outlet for this situation. In addition, if we can identify variables, from the lengthy variable list of the data set, for constructing an effective classification rule with good interpretation ability will be better. Here, we propose an active learning procedure targeted the maximum area under the receiver operating characteristic curve via a commonly use logistic model, which can sequentially select the effective informative subjects and variables, simultaneously. We discuss the asymptotic properties of the proposed procedure and illustrate it with some synthesized and real data sets.
- 14 February 2022
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 53 (2) , 897-911
Active learning with logistic models featuring simultaneous variable and subject selection
Modern computing and communication technologies can make data collection procedures very efficient, while our ability to analyze and extract information from large data sets is hard-pressed to keep up with our capacity for data collection. If we are interested in learning a classification/prediction rule that was not considered in the original data collection procedure, then there is usually a lack of label information in the original data. Thus, how to start with minimum number of labeled data and aggressively selected most informative samples for being labeled becomes an important issue. The thoughts of active learning, with subjects to be selected sequentially without using label information, is a possible outlet for this situation. In addition, if we can identify variables, from the lengthy variable list of the data set, for constructing an effective classification rule with good interpretation ability will be better. Here, we propose an active learning procedure targeted the maximum area under the receiver operating characteristic curve via a commonly use logistic model, which can sequentially select the effective informative subjects and variables, simultaneously. We discuss the asymptotic properties of the proposed procedure and illustrate it with some synthesized and real data sets.
- Open Access
Acetyl Coenzyme A Synthase 2 Acts as a Prognostic Biomarker Associated with Immune Infiltration in Cervical Squamous Cell Carcinoma
Cervical squamous cell carcinoma (CESC) is one of the most common malignant tumors in women worldwide with a low survival rate. Acetyl coenzyme A synthase 2 (ACSS2) is a conserved nucleosidase that converts acetate to acetyl-CoA for energy production. Our research intended to identify the correlations of ACSS2 with clinical prognosis and tumor immune infiltration in CESC. ACSS2 is highly expressed in many tumors and is involved in the progression and metastasis of these tumors. However, it is not clear how ACSS2 affects CESC progression and immune infiltration. Analysis of the cBioPortal, GEPIA2, UALCAN, and TCGA databases showed that ACSS2 transcript levels were significantly upregulated in multiple cancer types including CESC. Quantitative RT-PCR analysis confirmed that ACSS2 expression was significantly upregulated in human cervical cancer cells. Here, we performed tissue microarray analysis of paraffin-embedded tissues from 240 cervical cancer patients recorded at FIGO/TNM cancer staging. The results showed that ACSS2 and PDL1 were highly expressed in human CESC tissues, and its expression was associated with the clinical characteristics of CESC patients. TIMER database analysis showed that ACSS2 expression in CESC was associated with tumor infiltration of B cells, CD4+ and CD8+ T cells, and cancer-associated fibroblasts (CAF). Kaplan–Meier survival curve analysis showed that CESC with high ACSS2 expression was associated with shorter overall survival. Collectively, our findings establish ACSS2 as a potential diagnostic and prognostic biomarker for CESC.
Open AccessAcetyl Coenzyme A Synthase 2 Acts as a Prognostic Biomarker Associated with Immune Infiltration in Cervical Squamous Cell Carcinoma
Cervical squamous cell carcinoma (CESC) is one of the most common malignant tumors in women worldwide with a low survival rate. Acetyl coenzyme A synthase 2 (ACSS2) is a conserved nucleosidase that converts acetate to acetyl-CoA for energy production. Our research intended to identify the correlations of ACSS2 with clinical prognosis and tumor immune infiltration in CESC. ACSS2 is highly expressed in many tumors and is involved in the progression and metastasis of these tumors. However, it is not clear how ACSS2 affects CESC progression and immune infiltration. Analysis of the cBioPortal, GEPIA2, UALCAN, and TCGA databases showed that ACSS2 transcript levels were significantly upregulated in multiple cancer types including CESC. Quantitative RT-PCR analysis confirmed that ACSS2 expression was significantly upregulated in human cervical cancer cells. Here, we performed tissue microarray analysis of paraffin-embedded tissues from 240 cervical cancer patients recorded at FIGO/TNM cancer staging. The results showed that ACSS2 and PDL1 were highly expressed in human CESC tissues, and its expression was associated with the clinical characteristics of CESC patients. TIMER database analysis showed that ACSS2 expression in CESC was associated with tumor infiltration of B cells, CD4+ and CD8+ T cells, and cancer-associated fibroblasts (CAF). Kaplan–Meier survival curve analysis showed that CESC with high ACSS2 expression was associated with shorter overall survival. Collectively, our findings establish ACSS2 as a potential diagnostic and prognostic biomarker for CESC.
- 10 May 2021
- Published by Springer Nature in Journal of Classification
- Vol. 38 (3) , 544-555
A Model-Free Subject Selection Method for Active Learning Classification Procedures
- 10 May 2021
- Published by Springer Nature in Journal of Classification
- Vol. 38 (3) , 544-555
A Model-Free Subject Selection Method for Active Learning Classification Procedures
- Open Access
- 30 December 2020
- Published by MDPI AG in Biomolecules
- Vol. 11 (1) , 37
UBE2C Drives Human Cervical Cancer Progression and Is Positively Modulated by mTOR
Cervical cancer is a common gynecological malignancy, accounting for 10% of all gynecological cancers. Recently, targeted therapy for cervical cancer has shown unprecedented advantages. Several studies have shown that ubiquitin conjugating enzyme E2 (UBE2C) is highly expressed in a series of tumors, and participates in the progression of these tumors. However, the possible impact of UBE2C on the progression of cervical squamous cell carcinoma (CESC) remains unclear. Here, we carried out tissue microarray analysis of paraffin-embedded tissues from 294 cervical cancer patients with FIGO/TNM cancer staging records. The results indicated that UBE2C was highly expressed in human CESC tissues and its expression was related to the clinical characteristics of CESC patients. Overexpression and knockdown of UBE2C enhanced and reduced cervical cancer cell proliferation, respectively, in vitro. Furthermore, in vivo experiments showed that UBE2C regulated the expression and activity of the mTOR/PI3K/AKT pathway. In summary, we confirmed that UBE2C is involved in the process of CESC and that UBE2C may represent a molecular target for CESC treatment.
- 30 December 2020
- Published by MDPI AG in Biomolecules
- Vol. 11 (1) , 37
Open AccessUBE2C Drives Human Cervical Cancer Progression and Is Positively Modulated by mTOR
Cervical cancer is a common gynecological malignancy, accounting for 10% of all gynecological cancers. Recently, targeted therapy for cervical cancer has shown unprecedented advantages. Several studies have shown that ubiquitin conjugating enzyme E2 (UBE2C) is highly expressed in a series of tumors, and participates in the progression of these tumors. However, the possible impact of UBE2C on the progression of cervical squamous cell carcinoma (CESC) remains unclear. Here, we carried out tissue microarray analysis of paraffin-embedded tissues from 294 cervical cancer patients with FIGO/TNM cancer staging records. The results indicated that UBE2C was highly expressed in human CESC tissues and its expression was related to the clinical characteristics of CESC patients. Overexpression and knockdown of UBE2C enhanced and reduced cervical cancer cell proliferation, respectively, in vitro. Furthermore, in vivo experiments showed that UBE2C regulated the expression and activity of the mTOR/PI3K/AKT pathway. In summary, we confirmed that UBE2C is involved in the process of CESC and that UBE2C may represent a molecular target for CESC treatment.
- 1 May 2020
- Published by Elsevier in Computational Statistics & Data Analysis
- Vol. 145
Active learning in multiple-class classification problems via individualized binary models
- 1 May 2020
- Published by Elsevier in Computational Statistics & Data Analysis
- Vol. 145
Active learning in multiple-class classification problems via individualized binary models
- 10 October 2019
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 76 (2) , 496-507
Sequential adaptive variables and subject selection for GEE methods
Modeling correlated or highly stratified multiple‐response data is a common data analysis task in many applications, such as those in large epidemiological studies or multisite cohort studies. The generalized estimating equations method is a popular statistical method used to analyze these kinds of data, because it can manage many types of unmeasured dependence among outcomes. Collecting large amounts of highly stratified or correlated response data is time‐consuming; thus, the use of a more aggressive sampling strategy that can accelerate this process—such as the active‐learning methods found in the machine‐learning literature—will always be beneficial. In this study, we integrate adaptive sampling and variable selection features into a sequential procedure for modeling correlated response data. Besides reporting the statistical properties of the proposed procedure, we also use both synthesized and real data sets to demonstrate the usefulness of our method.
- 10 October 2019
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 76 (2) , 496-507
Sequential adaptive variables and subject selection for GEE methods
Modeling correlated or highly stratified multiple‐response data is a common data analysis task in many applications, such as those in large epidemiological studies or multisite cohort studies. The generalized estimating equations method is a popular statistical method used to analyze these kinds of data, because it can manage many types of unmeasured dependence among outcomes. Collecting large amounts of highly stratified or correlated response data is time‐consuming; thus, the use of a more aggressive sampling strategy that can accelerate this process—such as the active‐learning methods found in the machine‐learning literature—will always be beneficial. In this study, we integrate adaptive sampling and variable selection features into a sequential procedure for modeling correlated response data. Besides reporting the statistical properties of the proposed procedure, we also use both synthesized and real data sets to demonstrate the usefulness of our method.
- 1 February 2019
- Published by Elsevier in Neurocomputing
- Vol. 329, 495-505
Active learning with simultaneous subject and variable selections
- 1 February 2019
- Published by Elsevier in Neurocomputing
- Vol. 329, 495-505
Active learning with simultaneous subject and variable selections