HDR DSC: Collaborative Research: Creating and Integrating Data Science Corps to Improve the Quality of Life in Urban Areas

HDR DSC：协作研究：创建和整合数据科学团队以提高城市地区的生活质量

• 批准号: 1923982
• 负责人: Aryya Gangopadhyay
• 金额: $ 61.5万
• 依托单位: University of Maryland Baltimore County
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1923982&HistoricalAwards=false
• 关键词: HDR; DSC; Collaborative; Research; Creating

The goal of this project is to develop a team-based data science corps program for undergraduate students from Computer Science, Information Systems, and Business integrating both academic training as well as hands-on experience through real-world data science projects. This project is a collaborative effort with the University of Maryland Baltimore County as the coordinating as well as an implementing organization, and the University of Baltimore, Towson University, and Bowie State University as implementing organizations. This project focuses on the city of Baltimore as an exemplar for other cities in the US and across the globe. The project team will collaborate with a number of communities in the city of Baltimore to integrate real-world data science projects into classroom instruction in data science. The specific objectives of this project are as follows: (i) Develop the technical, analytical, modeling, and critical thinking skills that are key to success as a data science professional; (ii) Connect a cohort of students to communities, organizations, and projects that can benefit from the power of data science; (iii) Nurture and support innovative thinking in solving some of the key challenges facing the real world; (iv) Promote a better understanding of the power and pitfalls of data-driven discoveries to improve the quality of life in urban communities; (v) Increase the data science workforce capacity to support this critical area that is of growing importance in society; and finally, (vi) Evaluate the effect of the proposed data science corps on student learning. This project will create a core set of knowledge that will be valuable in developing solutions for real-world urban settings with the understanding that not all projects will require the application or use of every topic covered in the data science corps program. The core set of knowledge includes data collection and cleaning, data analysis using machine learning and deep learning techniques, data visualization including geospatial data and virtual reality, data privacy and security, and infrastructure for smart cities including IoT-based sensor networks. The proposed data science corps program will have two main phases: instructional phase (10 modules in total) and real-world team projects (5 modules in total). The project teams consist of students who have taken a course in at least one of the following areas: data collection and analysis, big data, machine learning including deep learning, smart cities, cybersecurity, geospatial data analysis and visualization, and virtual reality. Examples of team projects include: (i) developing community-based indicators that are compiled from open data portals and parametric and non-parametric statistical techniques to understand the relationship between urban sustainability and a range of factors including cleanliness and environment, crime and safety, business and economics, social and political, housing, health, and education; (ii) combining deep learning models such as convolutional neural networks (CNN) and long term short term memory recurrent neural networks (LSTM-RNN) to develop prediction models for derelict buildings that are likely to become vacant; (iii) combining sensor data and social media for automated information extraction, validation, and quality checks that can be beneficial to both citizens and emergency managers in crisis situations such as flash floods; (iv) developing smart streetlights that are networked LED systems that can be adjusted based on time of day and motion and can report outages back to central operations; and (v) developing augmented reality-based systems that leverage systems such as Microsoft HoloLens and mobile devices for building evacuation.NSF's Harnessing the Data Revolution Data Science Corps program focuses on building capacity for harnessing the data revolution at the local, state, national, and international levels to help unleash the power of data in the service of science and society. Projects in this program are being jointly funded by the NSF's Harnessing the Data Revolution Big Idea; the Directorate for Computer and Information Science and Engineering, Division of Information and Intelligent Systems; the Directorate for Education and Human Resources, Division of Undergraduate Education; the Directorate for Mathematical and Physical Sciences, Division of Mathematical Sciences; and the Directorate for Social, Behavioral and Economic Sciences, Office of Multidisciplinary Activities and Division of Behavioral and Cognitive Sciences.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该项目的目标是为计算机科学、信息系统和商科的本科生开发一个基于团队的数据科学团队项目，通过真实的数据科学项目整合学术培训和实践经验。该项目是由马里兰大学巴尔的摩县分校作为协调和实施组织，以及巴尔的摩大学、陶森大学和鲍伊州立大学作为实施组织的合作成果。 该项目重点关注巴尔的摩市作为美国和全球其他城市的典范。 该项目团队将与巴尔的摩市的多个社区合作，将现实世界的数据科学项目整合到数据科学的课堂教学中。该项目的具体目标如下： (i) 培养作为数据科学专业人员取得成功的关键的技术、分析、建模和批判性思维技能； (ii) 将一群学生与可以从数据科学的力量中受益的社区、组织和项目联系起来； (iii) 培养和支持创新思维，解决现实世界面临的一些关键挑战； (iv) 促进更好地理解数据驱动发现的力量和陷阱，以改善城市社区的生活质量； (v) 提高数据科学劳动力的能力，以支持这一在社会中日益重要的关键领域；最后，(vi) 评估拟议的数据科学团队对学生学习的影响。该项目将创建一套核心知识，这些知识对于开发现实城市环境的解决方案非常有价值，但我们要认识到，并非所有项目都需要应用或使用数据科学军团计划中涵盖的每个主题。核心知识包括数据收集和清理、使用机器学习和深度学习技术的数据分析、数据可视化（包括地理空间数据和虚拟现实）、数据隐私和安全以及智慧城市基础设施（包括基于物联网的传感器网络）。 拟议的数据科学军团计划将分为两个主要阶段：教学阶段（总共 10 个模块）和现实团队项目（总共 5 个模块）。项目团队由至少修读过以下领域之一课程的学生组成：数据收集和分析、大数据、机器学习（包括深度学习）、智慧城市、网络安全、地理空间数据分析和可视化以及虚拟现实。团队项目的例子包括：(i) 开发基于社区的指标，这些指标是根据开放数据门户以及参数和非参数统计技术编制的，以了解城市可持续性与一系列因素之间的关系，包括清洁和环境、犯罪和安全、商业和经济、社会和政治、住房、健康和教育； (ii) 结合卷积神经网络（CNN）和长期短期记忆递归神经网络（LSTM-RNN）等深度学习模型，开发可能空置的废弃建筑物的预测模型； (iii) 将传感器数据和社交媒体结合起来，进行自动信息提取、验证和质量检查，这对于山洪等危机情况下的公民和应急管理人员来说都是有益的； (iv) 开发智能路灯，即联网 LED 系统，可以根据一天中的时间和运动进行调整，并可以向中央运营部门报告断电情况； (v) 开发基于增强现实的系统，利用 Microsoft HoloLens 和移动设备等系统进行建筑物疏散。 NSF 的“利用数据革命数据科学队”计划侧重于建设地方、州、国家和国际层面利用数据革命的能力，以帮助释放数据的力量，为科学和社会服务。该计划中的项目由 NSF 的 Harnessing the Data Revolution Big Idea 联合资助；计算机与信息科学与工程局、信息与智能系统部；教育和人力资源局本科教育司；数学和物理科学理事会，数学科学部；该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Multi-modal Deep Learning Based Fusion Approach to Detect Illicit Retail Networks from Social Media

基于多模态深度学习的融合方法从社交媒体检测非法零售网络

• DOI: 10.1109/csci51800.2020.00047
• 发表时间: 2020
• 期刊: 2020 International Conference on Computational Science and Computational Intelligence (CSCI
• 作者: Paul Rupa, Anamika;Gangopadhyay, Aryya
• 通讯作者: Gangopadhyay, Aryya

DAHID: Domain Adaptive Host-based Intrusion Detection

• DOI: 10.1109/csr51186.2021.9527966
• 发表时间: 2021-07
• 期刊: 2021 IEEE International Conference on Cyber Security and Resilience (CSR)
• 作者: Oluwagbemiga Ajayi;A. Gangopadhyay

ARIS: A Real Time Edge Computed Accident Risk Inference System

• DOI: 10.1109/smartcomp52413.2021.00027
• 发表时间: 2021-08
• 期刊: 2021 IEEE International Conference on Smart Computing (SMARTCOMP)
• 作者: Pretom Roy Ovi;E. Dey;Nirmalya Roy;A. Gangopadhyay

Secure Federated Training: Detecting Compromised Nodes and Identifying the Type of Attacks

• DOI: 10.1109/icmla55696.2022.00183
• 发表时间: 2022-12
• 期刊: 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)
• 作者: Pretom Roy Ovi;A. Gangopadhyay;R. Erbacher;Carl E. Busart

A Comprehensive Study of Gradient Inversion Attacks in Federated Learning and Baseline Defense Strategies

• DOI: 10.1109/ciss56502.2023.10089719
• 发表时间: 2023-03
• 期刊: 2023 57th Annual Conference on Information Sciences and Systems (CISS)
• 作者: Pretom Roy Ovi;A. Gangopadhyay