Computing and Storage Infrastructure for Big Data Analytics

在一个数据以惊人的速度增长的世界里，对快速有效地分析大数据以发现有用信息的需求巨大。在约克大学的数据挖掘实验室中，我们正在进行NSERC支持的许多研究项目，以开发有效，高效和新颖的大数据挖掘解决方案。我们的大多数项目都涉及行业合作，其中大量数据用于开发行业实际问题的解决方案。这个RTI赠款将提供这些项目所需的计算支持。我们需要一个数据存储服务器，一个大内存服务器和一些工作站。这些设备将由从事项目工作的学生和博士后研究员使用。 这些项目包括（1）使用云计算在线挖掘大数据流，（2）从新兴类的数据流中进行半监督学习，（3）新颖的测地线和轮廓全局优化及其在机器学习中的应用，（4）下一代新闻媒体中决策标记的数据和可视化分析，（5）IBM平台解决方案在数据分析问题中的应用，（6）在线综合健康风险评估和推荐工具，（7）开发智能对话系统，（8）使用新闻文章的大数据预测强制迁移，（9）开发基于云的实时设施分析平台，以及（10）图形挖掘和探索算法。 我们的研究与加拿大工业界有着密切的合作，涵盖了与大数据相关的各种应用领域。我们将开发新颖、更有效的技术解决方案，将大数据转化为有益于企业的行动。我们相信这些应用将为我们的合作伙伴带来产品改进和新产品，并将为他们带来显著的全球竞争优势。

In a world where data are growing at extraordinary rates, there is a huge demand for fast and effective analysis of big data to discover useful information. In the Data Mining Lab at York University, we are working on a number of research projects supported by NSERC for developing effective, efficient, and novel solutions for mining big data. Most of our projects involve industry collaboration where high volumes of data are used to develop solutions to practical problems in industry. This RTI grant will provide computational support required by these projects. We request a data storage server, a big memory server, and a number of workstations. The equipment will be used by the students and postdoctoral fellows working on the projects. These projects include (1) Online mining of big data streams using cloud computing, (2) Semi-supervised learning from data streams with emerging classes, (3) Novel geodesic and contour global optimization and its application to machine learning, (4) Data and visual analytics for decision marking in next generation news media, (5) Application of IBM platform solutions for data analytics problems, (6) An online integrated health risk assessment and recommendation tool, (7) Developing smart conversational systems, (8) Predicting forced migration using big data of news articles, (9) Developing a cloud-based platform for real-time facility analytics, and (10) Graph Mining and Exploration Algorithms. Our research has strong collaborations with Canadian industry, and covers various application areas that are involved with big data. We will develop novel and more effective technological solutions that can turn big data into beneficial actions for business. We believe such applications will result in product enhancements and new products for our partners, and will bring them significant competitive advantages globally.