skip to main content

Title: LOCATER: Cleaning WiFi Connectivity Datasets for Semantic Localization
This paper explores the data cleaning challenges that arise in using WiFi connectivity data to locate users to semantic indoor locations such as buildings, regions, rooms. WiFi connectivity data consists of sporadic connections between devices and nearby WiFi access points (APs), each of which may cover a relatively large area within a building. Our system, entitled semantic LOCATion cleanER (LOCATER), postulates semantic localization as a series of data cleaning tasks - first, it treats the problem of determining the AP to which a device is connected between any two of its connection events as a missing value detection and repair problem. It then associates the device with the semantic subregion (e.g., a conference room in the region) by postulating it as a location disambiguation problem. LOCATER uses a bootstrapping semi-supervised learning method for coarse localization and a probabilistic method to achieve finer localization. The paper shows that LOCATER can achieve significantly high accuracy at both the coarse and fine levels.
Award ID(s):
2032525 2008993
Publication Date:
Journal Name:
Proceedings of the VLDB Endowment
Sponsoring Org:
National Science Foundation
More Like this
  1. Tag localization is crucial for many context-aware and automation applications in smart homes, retail stores, or warehouses. While custom localization technologies (e.g RFID) have the potential to support low-cost battery-free tag tracking, the cost and complexity of commissioning a space with beacons or readers has stifled adoption. In this paper, we explore how WiFi backscatter localization can be realized using the existing WiFi infrastructure already deployed for data applications. We present a new approach that leverages existing WiFi infrastructure to enable extremely low-power and accurate tag localization relative to a single scanning device. First, we adopt an ultra-low power tagmore »design in which the tag blindly modulates ongoing WiFi packets using On-Off Keying (OOK). Then, we utilize the underlying physical properties of multipath propagation to detect the passive wireless reflection from the tag in the presence of rich multipath propagations. Finally, we localize the tag from a single receiver by forming a triangle between the tag reflection and the LoS path between the two WiFi transceivers. We implement TagFi using a customized backscatter tag and off-the-shelf WiFi chipsets. Our empirical results in a cluttered office building demonstrate that TagFi achieves a median localization accuracy of 0.2m up to 8 meters range.« less
  2. Visual place recognition is essential for large-scale simultaneous localization and mapping (SLAM). Long-term robot operations across different time of the days, months, and seasons introduce new challenges from significant environment appearance variations. In this paper, we propose a novel method to learn a location representation that can integrate the semantic landmarks of a place with its holistic representation. To promote the robustness of our new model against the drastic appearance variations due to long-term visual changes, we formulate our objective to use non-squared ℓ2-norm distances, which leads to a difficult optimization problem that minimizes the ratio of the ℓ2,1-norms ofmore »matrices. To solve our objective, we derive a new efficient iterative algorithm, whose convergence is rigorously guaranteed by theory. In addition, because our solution is strictly orthogonal, the learned location representations can have better place recognition capabilities. We evaluate the proposed method using two large-scale benchmark data sets, the CMU-VL and Nordland data sets. Experimental results have validated the effectiveness of our new method in long-term visual place recognition applications.« less
  3. In this paper, we aimed to study the energy consumption problem in a collaborative activity monitoring system (CAMS) that consists of a compan- ion robot and a wearable device. First, we tested the energy consumption in different operation modes of the system. Based on that, we analyzed the effect of band- width on the time cost and energy consumption which allowed us to combine WiFi and Bluetooth together for data transmission to improve the performance of the system. Second, we preprocessed the image data on the wearable device to reduce the size of images before sending them to the robot,more »and analyzed the time and energy consumption cost by local computing and data transmission. Third, based on the bandwidth of WiFi and Bluetooth, the requirement of time and energy consumption, we proposed an optimization problem on image sizes in which the wearable device decides how to send the data to the robot to reduce the energy and time cost. The results showed that the relations between the bandwidth, time cost, image resolutions and energy consumption could be used to improve the performance of CAMS.« less
  4. Offloading cellular traffic to WiFi networks plays an important role in alleviating the increasing burden on cellular networks. However, excessive traffic offloading brings severe packet collisions into a WiFi network due to its contention-based medium access scheme, which significantly reduces the WiFi network’s throughput. In this paper, we propose DAO, a device-to-device (D2D) communications assisted traffic offloading scheme to improve the amount of traffic offloaded from cellular to WiFi in integrated cellular and WiFi networks. Specifically, in an integrated cellular-WiFi network, the cellular network exploits D2D communications in licensed cellular bands to aggregate traffic from cellular users before offloading itmore »to the WiFi network to reduce the number of contending users in WiFi access. The traffic offloading process in DAO is formulated as an optimization problem that jointly takes into account the activations of aggregation nodes (ANs) and the connections between ANs and offloading users to maximize the offloaded traffic while guaranteeing the long-term data rates required by the offloading users. Extensive simulation results reveal the significant performance gain achieved by DAO over the existing schemes.« less
  5. Bug tracking systems, which help to track the reported software bugs, have been widely used in software development and maintenance. In these systems, recognizing relevant source files among a large number of source files for a given bug report is a time-consuming and labor-intensive task for software developers. To tackle this problem, information retrieval methods have been widely used to capture either the textual similarities or the semantic similarities between bug reports and source files. However, these two types of similarities are usually considered separately and the historical bug fixings are largely ignored by the existing methods. In this paper,more »we propose a supervised topic modeling method (STMLOCATOR) for automatically locating the relevant source files for a given bug report. In particular, the proposed model is built upon three key observations. First, supervised modeling can effectively make use of the existing fixing histories. Second, certain words in bug reports tend to appear multiple times in their relevant source files. Third, longer source files tend to have more bugs. By integrating the above three observations, the proposed STMLOCATOR utilizes historical fixings in a supervised way and learns both the textual similarities and semantic similarities between bug reports and source files. We further consider a special type of bug reports with stack-traces in bug reports, and propose a variant of STMLOCATOR to tailor for such bug reports. Experimental evaluations on three real data sets demonstrate that the proposed STMLOCATOR can achieve up to 23.6% improvement in terms of prediction accuracy over its best competitors, and scales linearly with the size of the data. Moreover, the proposed variant further improves STMLOCATOR by up to 76.2% on those bug reports with stack-traces.« less