Suresh Pokharel

ORCID: 0000-0002-1567-9373
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Machine Learning in Healthcare
  • Biomedical Text Mining and Ontologies
  • Topic Modeling
  • Artificial Intelligence in Healthcare
  • Time Series Analysis and Forecasting
  • COVID-19 diagnosis using AI
  • Rough Sets and Fuzzy Logic
  • Mental Health Research Topics
  • Machine Learning and Data Classification
  • Web Data Mining and Analysis
  • Data Mining Algorithms and Applications
  • Customer churn and segmentation
  • Expert finding and Q&A systems
  • Big Data and Business Intelligence
  • Renal function and acid-base balance
  • Semantic Web and Ontologies
  • Sepsis Diagnosis and Treatment
  • Imbalanced Data Classification Techniques
  • Advanced Graph Neural Networks
  • Forecasting Techniques and Applications
  • Data Visualization and Analytics

The University of Queensland
2018-2022

Queensland University of Technology
2020-2022

Asian Institute of Technology
2012

The study addresses customer churn, a major issue in service-oriented sectors like telecommunications, where it refers to the discontinuation of subscriptions. research emphasizes importance recognizing satisfaction for retaining clients, focusing specifically on early churn prediction as key strategy. Previous approaches mainly used generalized classification techniques but often neglected aspect interpretability, vital decision-making. This introduces explainer models address this gap,...

10.2139/ssrn.4725863 preprint EN 2024-01-01

Colorectal cancer is a heterogeneous disease. Its response to targeted therapies associated with various factors, and the treatment effect differ significantly between individuals. Personalize medical (PMT), which takes into consideration of individual patient characteristics, most effective way deal this issue. Patient similarity clustering analysis an important part in PMT. Earlier works mainly focused on computation among patients but overlook preserve relationships. This paper presents...

10.1109/bibm49941.2020.9313144 article EN 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2020-12-16

Fraud detection especially in credit card is one of the challenging issues these days. Finding irregularities even more difficult due to high volume data during transaction. Many mining techniques are applied by researchers for solving problems. In this research, we explore K-Nearest Neighbor (KNN) and k-means algorithms which widely used classification clustering respectively. These research find out better among them. Moreover, also optimize system finding most dominant influencing factor...

10.3126/jost.v3i1.69064 article EN Journal of Science and Technology. 2023-12-31

Online discussion forums are popular resource for finding solutions various problems. Solutions found in the repositories of and their automated extraction is an important task. People interested only those which contain answers. Effective techniques mining can significantly reduce searching navigation time to find a solution. This paper describes methodology identifying answered threads from forum. To achieve this goal, question post detected first then thread classified as or unanswered by...

10.1109/ahici.2012.6408454 article EN 2012-11-01

Abstract Background Colorectal cancer (CRC) is a heterogeneous disease with different responses to targeted therapies due various factors, and the treatment effect differs significantly between individuals. Personalize medical (PMT) method that takes individual patient characteristics into consideration, making it most effective way deal this issue. Patient similarity clustering analysis an important aspect of PMT. This paper describes how build knowledge base using formal concept (FCA),...

10.1186/s12911-021-01728-y article EN cc-by BMC Medical Informatics and Decision Making 2022-11-23
Coming Soon ...