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.  more » « less
Award ID(s):
2032525 2008993
NSF-PAR ID:
10251139
Author(s) / Creator(s):
Date Published:
Journal Name:
Proceedings of the VLDB Endowment
ISSN:
2150-8097
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. 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 of 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. 
    more » « less
  2. null (Ed.)
    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, 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. 
    more » « less
  3. 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 it 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. 
    more » « less
  4. Vision-based localization approaches now underpin newly emerging navigation pipelines for myriad use cases, from robotics to assistive technologies. Compared to sensor-based solutions, vision-based localization does not require pre-installed sensor infrastructure, which is costly, time-consuming, and/or often infeasible at scale. Herein, we propose a novel vision-based localization pipeline for a specific use case: navigation support for end users with blindness and low vision. Given a query image taken by an end user on a mobile application, the pipeline leverages a visual place recognition (VPR) algorithm to find similar images in a reference image database of the target space. The geolocations of these similar images are utilized in a downstream task that employs a weighted-average method to estimate the end user’s location. Another downstream task utilizes the perspective-n-point (PnP) algorithm to estimate the end user’s direction by exploiting the 2D–3D point correspondences between the query image and the 3D environment, as extracted from matched images in the database. Additionally, this system implements Dijkstra’s algorithm to calculate a shortest path based on a navigable map that includes the trip origin and destination. The topometric map used for localization and navigation is built using a customized graphical user interface that projects a 3D reconstructed sparse map, built from a sequence of images, to the corresponding a priori 2D floor plan. Sequential images used for map construction can be collected in a pre-mapping step or scavenged through public databases/citizen science. The end-to-end system can be installed on any internet-accessible device with a camera that hosts a custom mobile application. For evaluation purposes, mapping and localization were tested in a complex hospital environment. The evaluation results demonstrate that our system can achieve localization with an average error of less than 1 m without knowledge of the camera’s intrinsic parameters, such as focal length. 
    more » « less
  5. Despite its importance for federated learning, continuous learning and many other applications, on-device training remains an open problem for EdgeAI. The problem stems from the large number of operations (e.g., floating point multiplications and additions) and memory consumption required during training by the back-propagation algorithm. Consequently, in this paper, we propose a new gradient filtering approach which enables on-device CNN model training. More precisely, our approach creates a special structure with fewer unique elements in the gradient map, thus significantly reducing the computational complexity and memory consumption of back propagation during training. Extensive experiments on image classification and semantic segmentation with multiple CNN models (e.g., MobileNet, DeepLabV3, UPerNet) and devices (e.g., Raspberry Pi and Jetson Nano) demonstrate the effectiveness and wide applicability of our approach. For example, compared to SOTA, we achieve up to 19× speedup and 77.1% memory savings on ImageNet classification with only 0.1% accuracy loss. Finally, our method is easy to implement and deploy; over 20× speedup and 90% energy savings have been observed compared to highly optimized baselines in MKLDNN and CUDNN on NVIDIA Jetson Nano. Consequently, our approach opens up a new direction of research with a huge potential for on-device training. 
    more » « less