Sudeng Hu passed his defense

Sudeng Hu, a MCL member, has passed his defense on Oct 26, 2015. Congratulations!

His dissertation title is “Techniques for Compressed visual data quality assessment and advanced video coding”. Object quality assessment for compressed images and videos is critical to various image and video compression systems that are essential in the delivery and storage. In the thesis, an image quality metric (IQM) and a video quality metric (VQM) are proposed based on perceptually weighted distortion in term of the MSE. To capture the characteristics of HVS, for images, a spatial randomness map is proposed to measure the masking effect and a preprocessing scheme is proposed to simulate the processing that occurs in the initial part of human HVS. For the VQM, the dynamic linear system is employed to model the video signal and is used to capture the temporal randomness of the videos. The performance of the proposed IQM and VQM are validated on various image and video databases with various compression distortions. The experimental results show that the proposed IQM and VQM outperforms other benchmark quality metrics.

Sudeng gave a nice talk with clarity and smooth flow. The Committee was impressed by his high quality research work and results. When talking about his success in his research work, Sudeng shared his experience with us. He believes that 4 years of PhD life gives him many good memories to have in the rest of his life. He has been enjoying working and studying with our group members since the first day he joined the MCL lab. He also enjoyed conducting research here under the guidance of Prof. Kuo. Prof. Kuo and him had an interesting research topic with great challenges. They had hard time to conquer [...]

By |November 1st, 2015|News|Comments Off on Sudeng Hu passed his defense|

Entrepreneurship presentation by Hao Xu

The MCL has many alumni that has started their own successful businesses. In order to better prepare the students for the future challenges, MCL director Prof. C.-C. Jay Kuo initiates a monthly event to let one student study a company and present the company to the fellow lab mates. For this month, MCL Phd student, Hao Xu, studied Palantir, a private American software and services company, specializing in data analysis. Founded in 2004, Palantir’s original clients were federal agencies of the United States Intelligence Community. It has since expanded its customer base to serve state and local governments, as well as private companies in the financial and healthcare industries.
In Hao’s presentation, he introduced Palantir’s  two software projects, the Gotham and the Metropolis. Gotham is used by counter-terrorism analysts at offices in the United States Intelligence Community and United States Department of Defense, fraud investigators at the Recovery Accountability and Transparency Board, and cyber analysts at Information Warfare Monitor (responsible for the GhostNet and the Shadow Network investigation). Palantir Metropolis is used by hedge funds, banks, and financial services firms.

By |October 11th, 2015|News|Comments Off on Entrepreneurship presentation by Hao Xu|
  • Permalink Gallery

    MCL Research Paper selected as the Best Paper of an ACM SIGSPATIAL Workshop

MCL Research Paper selected as the Best Paper of an ACM SIGSPATIAL Workshop

The paper “Collaborative Group-Activity Recommendation in Location-Based Social Networks” by Sanjay Purushotham*, Junaith Shahabdeen, Lama Nachman, C.-C. JayKuo, published at the Geo Crowd 2014 workshop of the ACM SIGSPATIAL Conference has been selected by the workshop organizers as its Best Paper. In this paper, the authors are interested in examining the effectiveness of modeling group dynamics for ‘Group Recommendation’ in Location-Based Social Networks (LBSN). They proposed a novel hierarchical Bayesian model which jointly learns activities and group preferences by using topic models; and performs group recommendation using matrix factorization in a Collaborative Filtering framework. The model allows for group preference learning by capturing location semantics and user-group dynamics and. It also effectively handles data sparsity and cold start recommendation. A major advantage of the modeling framework is that the learned group preferences can be interpreted using latent topics. Empirical experiments on a large LBSN dataset (Gowalla) showed that this model provides more effective group recommendations than the state-of-the-art approaches. Those experiments revealed that the user preferences vary based on their groups, and users tend to exhibit a flair for novelty and exploration as part of a group. Furthermore, the results provide interesting insights into how the user and group preferences differ, and how the user’s behavior influences group’s decisions.

For more details, please refer to the paper at this link: http://dl.acm.org/citation.cfm?id=2676442

*Part of this work was done when Sanjay was interning at Intel Labs, Santa Clara, California.

By |September 27th, 2015|News|Comments Off on MCL Research Paper selected as the Best Paper of an ACM SIGSPATIAL Workshop|