- Investigate NLP and ML techniques in medical concept annotation.
- Empirically compare the performance of latest NER and EL algorithms.
- Write and publish research papers in reputable journals or conferences.
Hello! I am Jiajun Zhang.
Clifford <- English Name
"EdgeTrier" <- Cyber alias
I have recently completed my PhD from Loughborough University and researched AI-related techniques with output explanation capability in defect detection, classification, analysis & retrieval across industrial and healthcare domains. I am interested in using technologies to improve our daily life and social community. Please feel free to find out more about me on this website.
大家好!我叫张家郡。
大家也可以叫我 "克里"。
"EdgeTrier" 是我的网名。
刚刚完成了我的博士,拉夫堡大学计算机科学学院,研究及开发了与人工智能相关的技术(同时,对模型输出进行解释)且应用于缺陷检测,分类,分析及检索等任务。我对各种各样的科技非常感兴趣,希望可以利用它们对生活和社会有所帮助。关于更多关于我的信息,请浏览我的网站。
Railston Co. Ltd. is the industrial partner, supporting my PhD research.
The aim of this project is:
Themis.AI is a research project that utilises ML models to predict a young person who needs early help/support.
Railston Co. Ltd. 是一家知名的科技咨询公司。公司提供了部分博士奖学金用于研发工业领域的缺陷检测和分析技术
项目包括
Themis.AI 是一项学术研究项目。此项目使用机械学习方法预测儿童和青少年的身心健康是否需要早期帮助或者干预。
Media officer is responsible for organising and leading the media team to manage social media and produce related media content.
Q&A Assistant is responsible for helping Chinese candidates answer their questions in student application and living.
传媒部部长主要负责管理并组织传媒部成员进行社交媒体上的管理和相关内容制作
疑问解答员主要负责为正在申请大学或者即将来英国的同学解答关于大学申请和生活等方向的疑问。
Research Topic: Using Deep Learning and Computer Vision Technologies to Detect and Analyse Defects on the Wind Turbine Blade Surfaces
Studentship: Railston & Co Ltd + Loughborough University
1st Year Contribution:
1. Image Enhanced Mask R-CNN: a proposed pipeline to detect the WTB defects and classify the defect types
2. Proposed new evaluation metrics for defect detection
3. Compared defect detection performance between our proposed pipeline and current state-of-the-art algorithms (YOLOv3, YOLOv4 and Mask R-CNN)
2nd Year Contribution:
1. Defect Characteristics: a new set of features for describing the WTB defects in common vision-based knowledge
2. AI Reasoning: a proposed Decision Tree-based framework to reason and explain the outputs of the AI models (generic to any AI models) by using Defect Characteristics
3. Forest Monkey Toolkit: a Python package to provide functionalities, including Defect Characteristics extraction, AI reasoning capability, AI model improvement suggestions, etc. Also, the research successfully applied the toolkit to other datasets with different types of defects
3rd Year Contribution:
1. Proposed an image retrieval framework, utilising the Defect Characteristics as features, to retrieve defects/irregular patterns from images by computing their similarities.
2. Developed a web-based toolkit for industry uses based on the Flask framework
3. Integrated all PhD research outcomes into the toolkit
4. Designed an AI model training and testing management system to maintain the operation efficiency
Courses:
Natural Language Processing
Data Mining
Data Analysis
Game Theory
Agent-Based System
Advanced Computer Security
Dissertation:
Title: Extension of Sherlock Source-code Plagiarism Detection Software - Internet Resource Detection Algorithm
Summary:
1. Designed & Developed a similarity measure method to compare the source codes with the internet resources (e.g. Google, Overflow, Github, etc.) by using Data Mining and NLP techniques
2. Integrated our method into the Sherlock source-code plagiarism detection software
Courses (Partial):
Machine Learning
Robot Programming
Software Engineering
Database
Data Structures & Algorithms
Human-Computer Interaction
2nd Year Team Project:
Title: Carnage - Mini Game Project - 1 vs 1 bomb pick and throw game
Summary:
1. Designed & Developed a strategy to let a robot player (with different difficulty levels) which can play against a real player by building route-planning methods (i.e. A* Search) and decision-making methods (policy-based)
2. Communicated and cooperated with teammates in the project designs, discussions and integrations
Final Year Project:
Title: Mixed Reality with Hololens - a Computer Vision Project
Summary:
1. Developed a physical environment simulation in the Hololens by using a physics engine (Unity) to simulate an object's physical actions and behaviours
2. Evaluated the physical actions and behaviours similarity between the virtual and real objects
Courses:
Mathematics
Further Mathematics
Physics
Information Communication & Technology (AS only)
Pre-A Level Courses: Mathematics, Physics, Chemistry and IELTS
研究课题: 利用深度学习和计算机视觉技术检测和分析风力发电机叶片表面的缺陷
奖学金: Railston & Co Ltd + 拉夫堡大学
第一年的贡献:
1. 提出并开发了Image Enhanced Mask R-CNN 模型为了检测风力发电机叶片的缺陷区域和分析缺陷类型
2. 提出了对于缺陷检测模型全新的评估方法
3. 将我们所提出的框架与现有成熟的算法(YOLOv3, YOLOv4 and Mask R-CNN)进行缺陷检测对比
第二年的贡献:
1. Defect Characteristics: 提出了一组缺陷特征, 其特征利用视觉常识解释了风力发电机叶面的缺陷
2. 提出并开发了基于决策树算法并利用Defect Characteristics数据的一个AI模型(通用于任意模型)输出推理框架。
3. Forest Monkey 工具包: 开发了一个Python包,此工具包可以提取图像的Defect Characteristics特征,执行AI输出推理,提供潜在的AI模型或数据相关的改进建议等;同时,研究成功地使用了此工具包针对不同类型的缺陷。
第三年的贡献:
1.提出了一种基于Defect Characteristics特征的图像检索框架,此框架可通过对比特征的相似度去检索任意类型的缺陷或者非正常区域。
2.为业界开发了一个基于Flask平台的网站
3. 将学术研究成果嵌入到网站里面
4. 设计了一套AI模型的训练和测试系统以提高效率
已读课程:
自然语言处理
数据挖掘
数据分析
博弈论
多智能体系統
高级计算机安全
毕业论文:
标题: Sherlock源代码抄袭检测软件的扩展——互联网资源检测算法
总结:
1. 通过利用数据挖掘和自然语言处理的技术,设计并开发一种基于网络资源(例如,谷歌,Github, Overflow等)的代码相似度算法。
2. 将开发的功能嵌入Sherlock代码查重软件
课程 (部分):
机器学习
机器人编程
软件工程
数据库
数据结构与算法
人机交互
大二团队项目:
标题: Carnage - 小游戏开发 - 1对1扔炸弹小游戏
总结:
1. 设计并开发了游戏中与真实玩家对抗的机器人策略,包含了A*算法路径寻找功能,基于政策的对抗策略功能等。
2. 在项目设计、开发上,与团队进行有效地交流及合作。
毕业设计:
标题: Hololens混合现实项目 - 计算机视觉方向
总结:
1. 开发一套用于HoloLens的物理拟真环境系统(基于Unity物理引擎)并模拟物体的物理运动行为和轨迹。
2. 评估并对比物体在虚拟和现实环境中物理轨迹的准确性。
Welcome to Jiajun Zhang (Clifford)’s Personal Website | Created by EdgeTrier | Thanks to bslthemes for the webpage theme design | Privacy Policy