Hoang Vu Nguyen

ORCID: 0009-0003-9053-3221
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Anomaly Detection Techniques and Applications
  • Face and Expression Recognition
  • Sparse and Compressive Sensing Techniques
  • Neural Networks and Applications
  • Advancements in Photolithography Techniques
  • Data Management and Algorithms
  • Data Mining Algorithms and Applications
  • Time Series Analysis and Forecasting
  • Network Security and Intrusion Detection
  • Mathematics Education and Teaching Techniques
  • Integrated Circuits and Semiconductor Failure Analysis
  • Electron and X-Ray Spectroscopy Techniques
  • Imbalanced Data Classification Techniques
  • Face recognition and analysis
  • Open Education and E-Learning
  • Data Stream Mining Techniques
  • Advanced DC-DC Converters
  • Human Pose and Action Recognition
  • Advanced Image and Video Retrieval Techniques
  • Advanced Statistical Methods and Models
  • Water Systems and Optimization
  • Hand Gesture Recognition Systems
  • Advanced Database Systems and Queries
  • Multilevel Inverters and Converters
  • History and Theory of Mathematics

Hội Gastroenterology Việt Nam
2023-2024

Can Tho University
2024

Hanoi University of Science and Technology
2022-2024

Hanoi National University of Education
2024

Ho Chi Minh City Medicine and Pharmacy University
2022

University of Transport and Communications
2021

Tien Giang General Hospital
2020

Tra Vinh University
2019

GlobalFoundries (United States)
2016-2018

Ho Chi Minh City University of Technology
2017

Previous chapter Next Full AccessProceedings Proceedings of the 2013 SIAM International Conference on Data Mining (SDM)CMI: An Information-Theoretic Contrast Measure for Enhancing Subspace Cluster and Outlier DetectionHoang Vu Nguyen, Emmanuel Müller, Jilles Vreeken, Fabian Keller, Klemens BöhmHoang Böhmpp.198 - 206Chapter DOI:https://doi.org/10.1137/1.9781611972832.22PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAboutAbstract In many real world...

10.1137/1.9781611972832.22 article EN 2013-05-02

In many real-world applications, data is collected in multi-dimensional spaces. However, not all dimensions are relevant for analysis. Instead, interesting knowledge hidden correlated subsets of (i.e., subspaces the original space). Detecting these independent underlying mining task an open research problem. It challenging due to exponential search space. Existing methods have tried tackle this by utilizing Apriori schemes. they show poor scalability and miss high quality subspaces. This...

10.1109/bigdata.2013.6691596 article EN 2013-10-01

Facial anthropometrics are measurements of human faces and important figures that used in many different fields, such as cosmetic surgery, protective gear design, reconstruction, etc. Therefore, the first procedure is to extract facial landmarks, then carried out by professional devices or based on experience. The aim this review provide an update 3D measurements, nasal reconstruction literature. novel methods detect landmarks including non-deep deep learning also introduced paper. Moreover,...

10.3390/app12199548 article EN cc-by Applied Sciences 2022-09-23

Semiconductor manufacturing of 14 nm devices has presented numerous engineering and challenges from newly introduced FinFETs in the FEOL to double patterned trenches self-aligned vias BEOL. Voids are a common defect found metal interconnects BEOL any technology, more generally occurring thinner pitch size copper wires. manifest themselves many forms like line voids, island seam end point etc., depending on location, orientation mechanism occurrence. Small process marginality between CuMn...

10.1109/asmc.2016.7491104 article EN 2016-05-01

In a database, besides known dependencies among columns (e.g., foreign key and primary constraints), there are many other correlations unknown to the database users. Extraction of such hidden is be useful for various tasks in optimization data analytics. However, task challenging due lack measures quantify column correlations. Correlations may exist different types value domains, which makes techniques based on matching inapplicable. Besides, have multiple semantics, does not allow disjoint...

10.1145/2618243.2618251 article EN 2014-06-24

Different tool platforms are used in conjunction for patterned wafer inspection like 9xxx & 29xx provided by KLA Tencor. Depending on the sensitivity throughput requirements, a chip fabrication plant mixes and matches inline strategies to ensure early detection of defects chip, which could cause yield loss or reliability problems. This paper discusses use novel concept high strategy using tool. is achieved unique combination Broad-Band light with Dark Field Apertures. application can be...

10.1109/asmc.2016.7491124 article EN 2016-05-01

As the scaling continues and industry moves to sub 1× nm nodes, Defect Review Scanning Electron Microscopy (DR-SEM) faces increasingly difficult challenges. The Defects of Interest (DOI) shrink as features shrinks leading imaging difficulty purely based on scale. defect signal gets immersed in noise challenge separating false from true is larger than ever. Also, more complex analysis required for DOIs with 3D morphology previous layer DOI. A smart approach DR-SEM must be adopted which allows...

10.23919/mipro.2017.7966585 article EN 2017-05-01

As the scaling continues and industry moves to sub 1× nm nodes, Defect Review Scanning Electron Microscopy (DR-SEM) faces increasingly difficult challenges. The Defects of Interest (DOI) shrink as features shrinks leading imaging difficulty purely based on scale. defect signal gets immersed in noise challenge separating false from true is larger than ever. Also, more complex analysis required for DOIs with 3D morphology previous layer DOI. A smart approach DR-SEM must be adopted which allows...

10.1109/asmc.2017.7969238 article EN 2017-05-01

Based on the recent success of Low-Rank matrix Representation (LRR), we propose a novel classification method for robust face recognition, named LRR-based Classification (LRRC). By ideal that if each data class is linearly spanned by subspace unknown dimensions and are noiseless, lowest-rank representations set test vector samples with respect to training have nature being both dense within-class affinity almost zero between-class affinities. Consequently, LRR exactly reveals data. Our...

10.1109/chicc.2014.6895722 article EN 2014-07-01

Ge0.07GaN films were successfully made on Si (100), SiO2/Si (100) substrates by a radio frequency reactive sputtering technique at various deposition conditions listed as range of 100–400 °C and 90–150 W with single ceramic target containing 7 % dopant Ge. The results showed that different RF power heating temperature affected the structural, electrical optical properties sputtered films. as-deposited had an structural polycrystalline. GeGaN distorted structure under growth conditions....

10.3390/coatings9100645 article EN Coatings 2019-10-06
Coming Soon ...