Damir Mirzanurov attended the 17th International Conference on Web-Age Information Management and presented the paper titled “An Effective Cluster Assignment Strategy for Large Time Series Data”.
The 17th International Conference on Web-Age Information Management (WAIM), held on June 3–5, 2016, in Nanchang, Jiangxi, China is a flagship conference in the Asia-Pacific region focusing on the research, development, and applications of Web information management.
The paper presented by Damir is focused on the problem of clustering time series data. “YADING is one of the most recent and efficient methods to cluster large-scale time series data, which mainly consists of sampling, clustering, and assigning steps. Given a set of processed time series entities, in the sampling step, YADING clusters are found by a density-based clustering method. Next, the left input data is assigned by computing the distance to the entities in the sampled data. Sorted Neighbors Graph data structure is used to prune the similarity computation of all possible pairs of entities. However, it does not guarantee to choose the sampled time series with lower density and therefore results in deterioration of accuracy.”- shared Damir, member of the Dainfos Lab of Innopolis Univerisity To resolve this issue, in the report they propose a strategy to order the SNG keys with respect to the density of clusters. The strategy improves the fast selection of time series entities with lower density and achieves high accuracy in terms of NMI. The paper is written in cooperation with Dr. Waqas Navaz, Prof. Jooyoung Lee and Prof.Qiang Qu.
Dainfos Lab invited Dr. Anders Skovsgaard from Denmark to give the talk dedicated to Scalable top-k spatio-temporal term querying.
Dr. Anders Skovsgaard is Softward Wizard and Partner at TrustSkills ApS in Aarhus, Denmark. He obtained his PhD in Computer Science from Aarhus University, working in the Data-Intensive Systems group/MADALGO primarily with Big Data algorithms. More specifically, scalable textual indexing and query processing of objects in space and time. He visited the Information and Data Management group at UCLA, Los Angeles in 2013/2014.He obtained his MSc in Computer Science from Aalborg University in 2009. Andres has worked several years in the industry and started a couple of spin-off companies related to his research.
About the talk:
With the rapidly increasing deployment of Internet-connected, location-aware mobile devices, very large and increasing amounts of geo-tagged and timestamped user-generated content, such as microblog posts, are being generated. We present indexing, update, and query processing techniques that are capable of providing the top-k terms seen in posts in a user-specified spatio-temporal range. The techniques enable interactive response times in the millisecond range in a realistic setting where the arrival rate of posts exceeds today’s average tweet arrival rate by a factor of 4-10. The techniques adaptively maintain the most frequent items at various spatial and temporal granularities. They extend existing frequent item counting techniques to maintain exact counts rather than approximations. An extensive empirical study with a large collection of geo-tagged tweets shows that the proposed techniques enable online aggregation and query processing at scale in realistic settings.
The working language is English. The talk will be held at the Innopolis University by the address: Innopolis city, 1 Universitetskaya St, room 108. The talk starts on September 11th at 15:00.
Dainfos Lab hosted 11 interns during this summer. The interns got deeper understanding of how scientific investigation works. The team of the Lab Qiang Qu, JooYoung Lee and Sadegh Nobari worked directly with all students sharing their experience in data analysis and problem solving with large amounts of diverse data. They provided hands-on experience that’s designed to fit career objectives of the interns, that complements their academic work and enhances their learning. Students got an ability to think creatively to solve complex problems. During the internship the members of the Lab got a great chance to work independently yet collaborate with management team.
The new Semester at Innopolis University began today (Aug.17). Congratulations to all new students who are beginning their program at our University in the Fall 2015 Semester! Qiang Qu gave a first lecture of Data Modeling and Databases of this semester. We are here to support you along the way!
Oleg Gusakov, System Architect from Cinarra Systems, Silicon Valley & Russian startup company and Emeritus Maven contributor, will talk about Maven – a project knowledge & build tool, which has a lot of buzz, and, sometimes, misconceptions about its utility and application, share his experience working on the software development process in global organizations. What is the difference between writing code delivering software products. For those know what SW development process and build systems are and want to deepen their understanding of the subject. While presenting Oleg Gusakov will also deviate into recommendation engines.
The talk will be held at the Innopolis University by the address: Innopolis city, 1 Universitetskaya St, room 108. The talk starts on August 12th at 15:00.
If you are enthusiasm in participating in research projects, and you’d like to collaborate with us, please feel free to contact Prof. Qiang Qu.
The Data Science and Information Systems (Dainfos) Lab of Innopolis University has several open positions for PhD students and postdocs in areas of database and data mining. Innopolis, based in Kazan, Russia, is a new, well-funded university founded on the international model and aiming to reach quickly the highest international ranks. Scholarships and benefits are on a par with the most attractive international offerings. We are accepting applications from enthusiastic students with M.S. degree. The working language is English. Please send an email to Prof. Qiang Qu with your CV if you are interested.
The position(s) are for the adaptive routing project (for details, please take a look at our research projects.)
Relevant topics include but not limited to:
1. mathematical modeling of transportation data
2. behavior analysis
3. trajectory data mining or management
4. routing on road networks
5. applications in spatial temporal graphs
6. incomplete graph data management
We provide competitive salary for a relatively long period, paid holidays, health insurance, etc.
1. Ph.D degree in computer science, statistics, or math
2. enthusiasm in research and guide beginners
3. Good in English writing
4. Better to have high quality publications in related areas
If you are interested, please contact Prof. Qiang Qu (email@example.com).