Guangli Wu – Video Summarization – Best Researcher Award

Posted on by Leave a Comment on Guangli Wu – Video Summarization – Best Researcher Award

Guangli Wu – Video Summarization

prof Dr. Guangli Wu  distinguished academic and researcher in the field  Video summarization.  The existence of software vulnerabilities will cause serious network attacks and information leakage problems. Timely and accurate detection of vulnerabilities in software has become a research focus on the security field. Most existing work only considers instruction-level features, which to some extent overlooks certain syntax and semantic information in the assembly code segments, affecting the accuracy of the detection model. In this paper, we propose a binary code vulnerability detection model based on multi-level feature fusion. The model considers both word-level features and instruction-level features. In order to solve the problem that traditional text embedding methods cannot handle polysemy, this paper uses the Embeddings from Language Models (ELMo) model to obtain dynamic word vectors containing word semantics and other information. Considering the grammatical structure in the assembly code segment, the model randomly embeds the normalized assembly code segment to represent it. Then the model uses bidirectional Gated Recurrent Unit (GRU) to extract word-level sequence features and instruction-level sequence features respectively.

Eduvation

He pursued his academic journey with a solid foundation in computer science and technology, earning a Bachelor’s degree from Shandong Technology and Business University in 2003. Building upon this, he delved into the realm of Computer Application Technology, completing his Master’s degree at Northwest Minzu University in 2007. Driven by a passion for cultural diversity and linguistic exploration, he further expanded his expertise by attaining a doctoral degree in Chinese Minority Ethnic Languages and Literature from Northwest Minzu University in 2011. This educational trajectory reflects his commitment to a multidisciplinary approach, seamlessly blending computer technology with a profound understanding of language and culture.
Professional Profiles:

RESEARCH INTEREST

⚫ Video Summarization
⚫ Temporal Language Localization in videos
⚫ Botnet Detection
⚫ Binary Code Vulnerability Detection
⚫ Video Abnormal Event Detection
FUND PROJECTS
1. Natural Science Foundation of Gansu Province (17JR5RA161, 21JR7RA570)
2. Gansu University of Political Science and Law Major Scientific Research and Innovation Projects
(GZF2020XZDA03)
3. Young Doctoral Fund Project of Higher Education Institutions in Gansu Province (2022QB-123)
4. Gansu Province Higher Education Innovation Fund Project (2017A-068)
5. University-level Innovative Research Team of Gansu University of Political Science and Law
6. Longyuan Youth Innovation and Entrepreneurship Talent Project (2022QB-123)

MAIN SCIENTIFIC PUBLICATIONS

1. Guangli Wu,ShengTao Wang,Shipeng Xu. “Feature fusion over hyperbolic graph convolution networks for
video summarization.” IET Computer Vision,2023.
2. Guangli Wu,Tongjie Xu. “Video Moment Localization Network Based on Text Multi-semantic Clues
Guidance.” Advances in Electrical and Computer Engineering,2023,23(3):85-92.
3. Guangli Wu,Huili Tang. “Binary Code Vulnerability Detection Based on Multi-Level Feature Fusion.” IEEE
Access,2023,11: 63904-63915.
4. Guangli Wu,Shanshan Song,Leiting Li. “Video Summarization Generation Model Based on Transformer
and Deep Reinforcement Learning.” in 2023 8th International Conference on Computer and
Communication Systems (ICCCS). IEEE, 2023: 916-921.
5. Guangli Wu,Shengtao Wang,Liping Liu. “Fast Video Summary Generation Based On Low Rank Tensor
Decomposition.” IEEE Access,2021,9:127917-127926.
6. Guangli Wu,Zhenzhou Guo,Mianzhao Wang,Leiting Li and Chengxiang Wang. “Video Abnormal Event
Detection Based on CNN and Multiple Instance Learning.” in twelfth international conference on signal
processing systems. SPIE,2021:134-139.
7. Guangli Wu,Zhenzhou Guo,Leiting Li and Chengxiang Wang. “Video Abnormal Event Detection Based on
CNN and LSTM.” in 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP).
IEEE,2020: 334-338.
8. Guangli WU,Leiting LI,Zhenzhou GUO,Chengxiang WANG and Yanpeng, YAO. “Video summarization
Based on ListNet Scoring Mechanism.” in 2020 5th International Conference on Computer and
Communication Systems (ICCCS). IEEE,2020: 281-285.
9. Guangli WU,Liping LIU,Chen Zhang and Dengtai TAN. “Video Abnormal Event Detection Based on ELM.”
in 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP).IEEE,2019: 367-371

 

Tumlumbe Juliana Chengula – Computer Vision -Best Researcher Award

Posted on by Leave a Comment on Tumlumbe Juliana Chengula – Computer Vision -Best Researcher Award

Tumlumbe Juliana Chengula  – Computer Vision

Tumlumbe Juliana Chengula  a distinguished academic and researcher in the field of Computer Vision. He possesses proficiency in several programming languages, with a focus on Python. His expertise extends to utilizing various tools such as Tableau, QGIS, PyTorch, and Tensorflow, showcasing a well-rounded skill set in data science and machine learning. Additionally, he has earned certifications in Data Science Tools, SQL for Data Science, and Machine Learning with Python, all from IBM. Furthermore, he has completed the “Using Python for Research” certification from Harvard University, underscoring his commitment to continuous learning and staying at the forefront of relevant technologies in the field. These skills and honors collectively highlight his comprehensive knowledge and dedication to the dynamic and evolving realm of data science.

Eduvation

His master’s studies at Amirkabir University of Technology (AUT) in Tehran, Iran, from September 2018 to October 2021, he specialized in Electrical Engineering with a focus on Control. During this period, he maintained a GPA of 3.5/4, and his final project earned a perfect score of 4/4. Prior to his master’s degree, he completed his Bachelor’s in Power Electrical Engineering at Yazd University, Iran, from September 2014 to August 2018, achieving a GPA of 3.1/4.

Professional Profiles:

Employment Experience
As a Graduate Research Assistant at South Carolina State University since August 2022, she has been actively engaged in the collection, recording, and analysis of transportation data, utilizing proficient tools such as Python, Tableau, PowerBI, and QGIS. Her research focus involves the application of cutting-edge technologies, including Machine Learning, Deep Learning, and Artificial Intelligence, to address challenges within the transportation industry.
Over the course of her tenure, she has showcased her contributions by delivering six impactful presentations on her research in Machine Learning and Artificial Intelligence at seven distinguished transportation conferences. Furthermore, her commitment to scholarly dissemination is evident through the submission and acceptance of two peer-reviewed articles, which are slated for presentation at the prestigious 2024 Annual Transportation Research Board conference. These accomplishments underscore her dedication to advancing knowledge and providing innovative solutions to enhance the efficiency and effectiveness of the transportation sector.
Research Project Highlights
She has made notable contributions to the field of transportation through her research endeavors, addressing critical issues with cutting-edge technologies. One of her significant projects involves enhancing road safety through Ensemble Learning, specifically in detecting driver anomalies using vehicle inbuilt cameras. In another study, she employed Topic Modeling and Categorical Correlations to unveil patterns associated with autonomous vehicle disengagements, shedding light on crucial aspects of autonomous driving systems.
Furthermore, she delved into the realm of quantum computing to improve classification performance in traffic sign recognition, utilizing an optimized hybrid classical-quantum approach. Additionally, her research extends to the realm of sustainable urban mobility, where she has applied Explainable Artificial Intelligence to predict bike-sharing station capacity. These diverse projects showcase her proficiency in utilizing advanced technologies and methodologies to address multifaceted challenges within the transportation sector.
Publication

Improving road safety with ensemble learning: Detecting driver anomalies using vehicle inbuilt cameras

Machine Learning with Applications
2023-12 | Journal article
DOI: 10.1016/j.mlwa.2023.100510
CONTRIBUTORS: Tumlumbe Juliana Chengula; Judith Mwakalonge; Gurcan Comert; Saidi Siuhi