Browsing by Author "Luo, Chen"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Camera-based positioning system using learning
    (2021-05-04) Shrivastava, Anshumali; Luo, Chen; Palem, Krishna; Moon, Yongshik; Noh, Soonhyun; Park, Daedong; Hong, Seongsoo; Rice University; Seoul National University R&DB Foundation; United States Patent and Trademark Office
    A device, system, and methods are described to perform machine-learning camera-based indoor mobile positioning. The indoor mobile positioning may utilize inexact computing, wherein a small decrease in accuracy is used to obtain significant computational efficiency. Hence, the positioning may be performed using a smaller memory overhead at a faster rate and with lower energy cost than previous implementations. The positioning may not involve any communication (or data transfer) with any other device or the cloud, providing privacy and security to the device. A hashing-based image matching algorithm may be used which is cheaper, both in energy and computation cost, over existing state-of-the-art matching techniques. This significant reduction allows end-to-end computation to be performed locally on the mobile device. The ability to run the complete algorithm on the mobile device may eliminate the need for the cloud, resulting in a privacy-preserving localization algorithm by design since network communication with other devices may not be required.
  • Thumbnail Image
    Item
    Mining Massive-Scale Time Series Data using Hashing
    (2017-05-09) Luo, Chen; Shrivastava, Anshumali
    Similarity search on time series is a frequent operation in large-scale data-driven applications. Sophisticated similarity measures are standard for time series matching, as they are usually misaligned. Dynamic Time Warping or DTW is the most widely used similarity measure for time series because it combines alignment and matching at the same time. However, the alignment makes DTW slow. To speed up the expensive similarity search with DTW, branch and bound based pruning strategies are adopted. However, branch and bound based pruning are only useful for very short queries (low dimensional time series), and the bounds are quite weak for longer queries. Due to the loose bounds branch and bound pruning strategy boils down to a brute-force search. To circumvent this issue, we design SSH (Sketch, Shingle, & Hashing), an efficient and approximate hashing scheme which is much faster than the state-of-the-art branch and bound searching technique: the UCR suite. SSH uses a novel combination of sketching, shingling and hashing techniques to produce (probabilistic) indexes which align (near perfectly) with DTW similarity measure. The generated indexes are then used to create hash buckets for sub-linear search. Empirical results on two large-scale benchmark time series data show that our proposed method prunes around 95% time series candidates and can be around 20 times faster than the state-of-the-art package (UCR suite) without any significant loss in accuracy.
  • Thumbnail Image
    Item
    Some Rare LSH Gems for Large-scale Machine Learning
    (2020-01-17) Luo, Chen; Shrivastava, Anshumali
    Locality Sensitive Hashing (LSH) is an algorithm for approximate nearest neighbor (ANN) search in high dimensional space. In this thesis, instead of using LSH as an ANN tool, we investigate the possibility of using LSH for addressing the computational and memory challenges in large scale machine learning tasks. We show some rare 'gems' of locality-sensitive hashing that can shed important lights on large scale learning system. We first show the power of LSH for high-speed anomaly detection. Anomaly detection is one of the frequent and important subroutines deployed in largescale data processing applications. Even being a well-studied topic, existing techniques for unsupervised anomaly detection require storing significant amounts of data, which is prohibitive from memory, latency and privacy perspectives, especially for small mobile devices which has ultralow memory budget and limited computational power. We Introduce ACE (Arrays of (locality-sensitive) Count Estimators) algorithm that can much faster than most state-of-the-art unsupervised anomaly detection algorithms with very low memory requirement. Secondly, we show a novel sampler view of LSH and propose to use LSH for scaling-up Split-Merge MCMC Inference. Split-Merge MCMC (Monte Carlo Markov Chain) is one of the essential and popular variants of MCMC for problems when an MCMC state consists of an unknown number of components. It is well known that state-of-the-art methods for split-merge MCMC do not scale well. Here, we leverage some unique properties of weighted MinHash, which is a popular LSH, to design a novel class of split-merge proposals which are significantly more informative than random sampling but at the same time efficient to compute. In the end, we show a practical usage of LSH for Indoor Navigation tasks. In this work, we developed the first camera based (privacy-preserving) indoor mobile positioning system, CaPSuLe, which does not involve any communication (or data transfer) with any other device or the cloud. The system only needs 78.9MB of memory and can localize a mobile device with $92.11\%$ accuracy with very fast speed. The ability to run the complete system on the mobile device eliminates the need for the cloud, making CaPSuLe a privacy-preserving localization algorithm by design as it does not require any communication.