Spotlight: Hot target discovery and localization with crowdsourced photos

Increasing attention has been paid to high-precision indoor localization in dense urban and indoor environments. Previous studies have shown single indoor localization methods based on WiFi fingerprints, surveillance cameras or Pedestrian Dead Reckoning (PDR) are restricted by low accuracy, limited tracking region, and accumulative error, etc., and some defects can be resolved with more labor costs or special scenes. However, requesting more additional information and extra user constraints is costly and rarely applicable. In this paper, a two-stage indoor localization system is presented, integrating WiFi fingerprints, the vision of surveillance cameras, and PDR (the system abbreviated as iWVP). A coarse location using WiFi fingerprints is done advanced, and then an accurate location by fusing data from surveillance cameras and the IMU sensors is obtained. iWVP uses a matching algorithm based on motion sequences to confirm the identity of pedestrians, enhancing output accuracy and avoiding corresponding drawbacks of each subsystem. The experimental results show that the iWVP achieves high accuracy with an average position error of 4.61 cm, which can effectively track pedestrians in multiple regions in complex and dynamic indoor environments.

Section: Localization Methods Based On Visionmentioning

confidence: 99%

“…However, PDR suffers from accumulative errors seriously, leading to nonnegligible deviation [19] . Computer vision is a promising solution for indoor localization [20][21][22][23][24] . Fusion indoor localization methods are presented to eliminate the above shortcomings.…”

Section: Introductionmentioning

confidence: 99%

From Coarse to Fine: Two-Stage Indoor Localization with Multisensor Fusion

Zhang

Bao

et al. 2023

“…Sampling-based methods have been proposed for data aggregation in relational databases [21] , sensor networks [22][23][24][25][26][27][28][29] , etc. In previous years, big data analytic systems have leveraged sampling for fast aggregation with error bounds [30][31][32][33][34] . These efforts inspire us to use samples and precomputed data summaries in answering top/bottom-k fraction queries approximately to achieve a good response and accuracy.…”

Section: Related Workmentioning

confidence: 99%

Efficient top/bottom-k fraction estimation in spatial databases using bounded main memory

Wang

Duan

Han

et al. 2022

Spatial databases store objects with their locations and certain types of attached items. A variety of modern applications have been developed by leveraging the utilization of locations and items in spatial objects, such as searching points of interest, hot topics, or users' attitude in specified spatial regions. In many scenarios, the high and low-frequency items in a spatial region are worth noticing, considering they represent the majority's interest or eccentric users' opinion. However, existing works have yet to identify such items in an interactive manner, despite the significance of the endeavor in decision-making systems. This study recognizes a novel type of analytical query, called top/bottom-k fraction query, to discover such items in spatial databases. To achieve fast query response, we propose a multilayered data summary that is spread out across the main memory and external memory. A memory-based estimation method for top/bottom-k fraction queries is proposed. To maximize the use of the main memory space, we design a data summary tuning method to dynamically allocate memory space among different spatial partitions. The proposed approach is evaluated with real-life datasets and synthetic datasets in terms of estimation accuracy. Evaluation results demonstrate the effectiveness of the proposed data summary and corresponding estimation and tuning algorithms.

“…In recent years, the emergence of Facebook, Twitter, Weibo, and other multimedia social networks have gradually become an integral part of people's lives [15,16] . The wide usage of online social media enables the possibility to intentionally incorporate the social information of users to enhance the recommendation system.…”

Section: Introductionmentioning

confidence: 99%

SGNR: A Social Graph Neural Network Based Interactive Recommendation Scheme for E-Commerce

Wang

et al. 2023

Interactive Recommendation (IR) formulates the recommendation as a multi-step decision-making process which can actively utilize the individuals' feedback in multiple steps and optimize the long-term user benefit of recommendation. Deep Reinforcement Learning (DRL) has witnessed great application in IR for ecommerce. However, user cold-start problem impairs the learning process of the DRL-based recommendation scheme. Moreover, most existing DRL-based recommendations ignore user relationships or only consider the single-hop social relationships, which cannot fully utilize the social network. The fact that those schemes can not capture the multiple-hop social relationships among users in IR will result in a sub-optimal recommendation. To address the above issues, this paper proposes a Social Graph Neural network-based interactive Recommendation scheme (SGNR), which is a multiple-hop social relationships enhanced DRL framework. Within this framework, the multiple-hop social relationships among users are extracted from the social network via the graph neural network which can sufficiently take advantage of the social network to provide more personalized recommendations and effectively alleviate the user cold-start problem. The experimental results on two real-world datasets demonstrate that the proposed SGNR outperforms other state-of-the-art DRL-based methods that fail to consider social relationships or only consider single-hop social relationships.