NGUYEN ANH HOANG PHUC

Ho Chi Minh city, Vietnam adt6ok@r.postjobfree.com +84-94-305-**** www.linkedin.com/in/phucnguyen4499 github.com/PhucNguyenAH

EDUCATION

Long An High School for the Gifted Long An, Vietnam Gifted class in Information Technology Aug 2014 – Jun 2017 Ho Chi Minh City University of Technology (HCMUT) Ho Chi Minh city, Vietnam Computer Science - Bachelor of Engineering - GPA: 8.52 / 10.00 Aug 2017 – Oct 2021 Research interests: AI, Machine Learning, Computer Vision, Deep Learning, Speech Synthesis, NLP Having achieved outstanding academic performance in Faculty of Computer Science Ho Chi Minh city, Vietnam And Engineering Apr - 2022

Certifications

• IELTS Certificate Overall: 6.5 (10 Oct 2022)

• The Global Project Based Learning - organized in HCMUT in collaboration with Shibaura Institute of Technology (SIT)

• Machine Learning Online Course by Stanford University

• Neural Networks and Deep Learning Online Course by Stanford University Awards

• Second Prize - OISP Community Day & Presentation Contest 2017

• Top 20 - Bach Khoa Innovation 2020

• Third Prize -The 8th Science and Technology Symposium for OISP Students 2021 SKILL

• Programming languages: Python, C++, Java, Matlab

• Frameworks and Libraries: Pytorch, PyQt5, Flask, MQTT, Dlib, Faiss

• Models: Retina face, ArcFace, Faster RCNN, DNN Face Detector, Person Re-ID, attention, stepwise monotonic attention, LSTM, Transformer, Tacotron2, BERT, Sequence to Sequence (RNN, Bi-LSTM, GRU).

• Algorithms: Activation functions, Kalman filter, Adaptive threshold, Glove, tokenization, K-means clustering, PageRank

• Others: Jetson nano, Raspberry pi, Apache Hadoop, Hive, CVAT, Arduino. WORK EXPERIENCE

VinBigData Joint Stock Company Ha Noi-Ho Chi Minh city, Vietnam AI engineer intern - Vingroup AI engineer training program Sep 2021 – Jul 2022 I had 4 months in training courses and 6 months of internship. I accomplished 3 projects including:

• Visual Question Answering: I adopted bottom-up-attention network, whose feature extractor is Faster R-CNN object detector. Each word in the question is transformed into a vector using the 300-D GloVe word embeddings. The word embeddings are then passed through a one-layer LSTM network. I also replaced word embedding with BERT.

• Vietnamese Spelling Error Correction System: I used word augmentation to generate the Vietnamese spelling error data which is the target data training. I labeled correct and mistaken tokens by BartPho tokenizer. For the model, I researched word generation that I installed Sequence to Sequence (RNN, Bi-LSTM, GRU) combined attention and the Transformer. Moreover, I researched and implemented the Soft-masked BERT.

• Text to speech with subword embedding: I researched combining phoneme context with subword context using Tacotron2 model. I programmed the stepwise monotonic attention for extracting context. I implemented a tokenizer for Vietnamese using Huggingface tokenization and Vietnamese data and used that tokenizer to generate subword embedding which concatenated with BERT CLS token replication. I also used K-means clustering and cosine similarity to analyze the context of BERT CLS token and then I could synthesize the speech into 3 different styles. FPT Telecom Joint Stock Company Ho Chi Minh city, Vietnam Data scientist Jun – Oct 2021

I researched the Unknown Recognition by camera project. I researched replacing the backbone of Retina face with Efficient Net. I researched the ArcFace-Additive Angular Margin Loss for feature extraction. I installed Faiss to optimize the register and the adaptive threshold for label classification. I installed human detection and Person Re-ID to enhance the performance. Cloud Nine Solutions Company Ho Chi Minh city, Vietnam AI intern Jul – Oct 2020

I collaborated with another intern partner to implement the Facial Recognition Check-in. I used Dlib to detect faces in image, then I chose one closet face. After that, I aligned that face before extracting by 2 dense layers and I classified label by SoftMax. I built a video streaming by Flask to demonstrate the project. PERSONAL PROJECTS

Biometric-Based Attendance Tracking System with One/Fewshot Learning (thesis) Mar – Aug 2021

• Analyzed performance between Dlib and DNN for Face Detection.

• Implemented face tracking by Kalman filter to optimize the number of facial recognition processes.

• Built GUI by PyQt5.

• Built message streaming by Apache Kafka to transfer data between Jetson Nano and Google Cloud platform.

• Made the indexing module by Faiss for user register.

• Programmed the adaptive threshold for label classification. Face – Voice Attendance System Oct 2020 – Jan 2021

• Researched, implemented Dlib for Face Detection.

• Built 2 dense layers for facial feature extraction and Softmax for label classification.

• Researched deep speech for trigger word detection to trigger facial recognition.

• Built GUI by PyQt5.

Smart Parking Sep 2020

• Installed smart parking process by Arduino with Gate detect vehicles by HC-SR05 Ultrasonic Sensor

• Built website to demonstrate system

Support sandal/device for sightless people Dec 2015 – Mar 2016

• Designed mainboard by Eagle

• Designed box by Solidworks

• Programmed detect obstacles on Arduino using HC-SR05 Ultrasonic Sensor

Contact this candidate