The global e-commerce store needs to ensure compliance with various regulations at local, national, and international levels. One business use case is to identify face masks to avoid price gouging during times of high demand. In order to keep billions of items safe and legally compliant, it is important to ensure accurate classifications. Classification revisers aim to enhance classification accuracy by detecting and revising incorrect classifications. In this paper, we introduce this problem, along with appropriate online evaluation metrics for large-scale application scenarios. Our proposed method first learns neural network embedding from item textual features to define similar neighbors, and then simply uses these known classification results from k nearest neighbors to estimate an item’s class assignment. Our experiments demonstrate that it outperforms the state-of-the-art baseline approaches and its robustness to large scales. The proposed method can uniquely revise a significant number of classifications correctly, complementary to a multi-label classification system. The study indicates that our simple yet effective approach empowered by GPU computation is a viable solution of a commercial multi-label-classification revision problem.

The increased availability of large-scale trajectory data provides rich information for the study of urban dynamics. For example, New York City Taxi 8 Limousine Commission regularly releases source/destination information of taxi trips, where 173 million taxi trips released for Year 2013 [29]. Such a big dataset provides us potential new perspectives to address the traditional traffic problems. In this article, we study the travel time estimation problem. Instead of following the traditional route-based travel time estimation, we propose to simply use a large amount of taxi trips without using the intermediate trajectory points to estimate the travel time between source and destination. Our experiments show very promising results. The proposed big-data-driven approach significantly outperforms both state-of-the-art route-based method and online map services. Our study indicates that novel simple approaches could be empowered by big data and these approaches could serve as new baselines for some traditional computational problems.

Advances in sensor technology have enabled the collection of large-scale datasets. Such datasets can be extremely noisy and often contain a significant amount of outliers that result from sensor malfunction or human operation faults. In order to utilize such data for real-world applications, it is critical to detect outliers so that models built from these datasets will not be skewed by outliers. In this paper, we propose a new outlier detection method that utilizes the correlations in the data (e.g., taxi trip distance vs. trip time). Different from existing outlier detection methods, we build a robust regression model that explicitly models the outliers and detects outliers simultaneously with the model fitting. We validate our approach on real-world datasets against methods specifically designed for each dataset as well as the state of the art outlier detectors. Our outlier detection method achieves better performances, demonstrating the robustness and generality of our method. Last, we report interesting case studies on some outliers that result from atypical events.

We consider the problem of privately releasing a class of queries that we call hierarchical count-of-counts histograms . Count-of-counts histograms partition the rows of an input table into groups (e.g., group of people in the same household), and for every integer j report the number of groups of size j . Hierarchical count-of-counts queries report count-of-counts histograms at different granularities as per hierarchy defined on an attribute in the input data (e.g., geographical location of a household at the national, state and county levels). In this paper, we introduce this problem, along with appropriate error metrics and propose a differentially private solution that generates count-of-counts histograms that are consistent across all levels of the hierarchy.

With the advance of VLSI technology, the parameter shift due to device aging has increasingly impacts on the circuit yield and reliability. Because the aging effects may degrade circuit performance and cause circuit failure after a period of time, aging analysis is also required in the design flow to avoid reliability issues. Previous aging analysis approaches often have a trade-off between accuracy and simulation time. In order to improve the efficiency of aging analysis while keeping high accuracy, this paper proposes an incremental simulation technique based on delta circuit models. Since aging process is often a gradual change, incremental simulation technique is very effective to reduce the simulation time of each iteration with almost the same accuracy. Furthermore, a dynamic aging sampling technique is also proposed to further improve the efficiency of aging analysis with little accuracy loss. As demonstrated in the experiments, the proposed approach is indeed an effective way to reduce the aging analysis time while keeping estimation accuracy.

The increased availability of large-scale trajectory data provides rich information for the study of urban dynamics. For example, New York City Taxi & Limousine Commission regularly releases source/destination information of taxi trips, where 173 million taxi trips released for Year 2013 [1]. Such a big dataset provides us potential new perspectives to address the traditional traffic problems. In this paper, we study the travel time estimation problem. Instead of following the traditional route-based travel time estimation, we propose to simply use a large amount of taxi trips without using the intermediate trajectory points to estimate the travel time between source and destination. Our experiments show very promising results. The proposed big data-driven approach significantly outperforms both state-of-the-art route-based method and online map services. Our study indicates that novel simple approaches could be empowered by the big data and these approaches could serve as new baselines for some traditional computational problems.

The key to content-aware warping and cropping is adapting data to fit displays with various aspect ratios while preserving visually salient contents. Most previous studies achieve this objective by cropping insignificant contents near frame boundaries and consistently resizing frames through an optimization technique with various preservation constraints and fixed boundary conditions. These strategies significantly improve retargeting quality. However, warping under fixed boundary conditions may bound/limit the preservation of visually salient contents. Moreover, dynamic frame cropping and frame alignment may result in unnatural object/camera motions. In this paper, a floating boundary with volumetric warping and object-aware cropping is proposed to address these problems. In the proposed scheme, visually salient objects in the space-time domain are deformed as rigidly and as consistently as possible using information from matched objects and content-aware boundary constraints. The content-aware boundary constraints can retain visually salient contents in a fixed region with a desired resolution and aspect ratio, called critical region, during warping. Volumetric cropping with the fixed critical region is then performed to adjust stereoscopic videos to the desired aspect ratios. The strategies of warping and cropping using floating boundaries and spatiotemporal constraints enable our method to consistently preserve the temporal motions and spatial shapes of visually salient volumetric objects in the left and right videos as much as possible, thus leading to good content-aware retargeting. In addition, by considering shape, motion, and disparity preservation, the proposed scheme can be applied to various media, including images, stereoscopic images, videos, and stereoscopic videos. Qualitative and quantitative analyses of stereoscopic videos with diverse camera and considerable motions demonstrate a clear superiority of the proposed method over related methods in terms of retargeting quality.

Patents are very important intangible assets that protect firm technologies and maintain market competitiveness. Thus, patent evaluation is critical for firm business strategy and innovation management. Currently patent evaluation mostly relies on some meta information of patents, such as number of forward/backward citations and number of claims. In this paper, we propose to identify patent technological trends, which carries information about technology evolution and trajectories among patents, to enable more effective and precise patent evaluation. We explore features to capture both the value of trends and the quality of patents within a trend, and perform patent evaluation to validate the extracted trends and features using patents in the United States Patent and Trademark Office (USPTO) dataset. Experimental results demonstrate that the identified technological trends are able to capture patent value precisely. With the proposed trend related features extracted from our identified trends, we can improve patent evaluation performance significantly over the baseline using conventional features.