This article focuses on the accuracy and practicality of geomagnetic-based indoor localization in large-scale real-world sites. Previous studies often use continuous geomagnetic sequences for better discriminability but ignore that longer sequences, while more accurate, increase response times. Shorter sequences enhance practicality but sacrifice accuracy. Additionally, varying walking speeds can cause sequence variations along the same path, leading to ambiguity. To address these challenges, we propose a spatial-temporal constrained indoor localization model (STC-loc) that enables both accurate and practical localization using geomagnetic sequences collected at arbitrary walking speeds. Specifically, we first design a speed-oriented adaptive normalization module to tackle the walking speed heterogeneity problem. Then, to balance accuracy and practicality, we initially employ shorter sequences as input and a self-attention hierarchical structure to efficiently extract the temporal features for initial location estimation. Subsequently, we further apply an encoder-decoder-based refinement strategy, leveraging spatial contextual for continuous localization to ensure accuracy and robustness. Additionally, a slide-window-based two-phase system architecture optimizes processing efficiency and scalability. Experiments on three large-scale real-world sites have demonstrated the superiority of the proposed STC-loc, reducing the localization error by more than 43% with shorter geomagnetic sequences.

Employing low-cost inertial measurement units (IMUs) from off-the-shelf mobile devices, inertial odometry techniques can provide environment-independent position information, exhibiting great research and commercial value. However, the high noise level of low-cost inertial sensor readings still makes this challenging. To address this, we propose a deep inertial odometry method that employs hierarchical temporal features of IMU sequences. Specifically, the proposed method transforms inertial odometry problem into a seq2seq translation task by segmenting the overall inertial sequence into subsequences, which are referred to as raw sentences. Then an attention-based hierarchical structure is designed to extract and fuse multi-level temporal features, generating feature sequences with rich contextual information, which are referred to as source sentences. Finally, we utilize the state-of-the-art Transformer as a translator for estimating corresponding pose change sequences, which are referred to as target sentences, and integrate the estimation results into the trajectory. We have conducted extensive experiments on two public datasets: the small-scale OxIOD and the large-scale IDOL. The experimental results demonstrate that our method reduces the mean absolute trajectory error and relative trajectory error by at least 16.8% and 16.7%, respectively, on the OxIOD dataset, and by 48.4% and 58.1%, respectively, on the IDOL dataset compared to competing schemes.

Geomagnetism-based indoor localization has great social and commercial value due to its pervasiveness and indepen-dence from extra infrastructure. To improve the distinguishability of geomagnetic signals as location clues, geomagnetic sequences are usually taken as input. Although longer input sequence can provide higher localization accuracy, it suffers from high response time in practice. To address the above, we first utilize short geomagnetic sequences as input, alleviating high response time, and propose an efficient single position estimation model, taking advantage of modified transformer to estimate position for each independent short sequence. Noticing the temporal dependency and the spatial consistency constraint during continuous positioning, we further propose a joint position estimation model to capture the correlations among consecutive short sequences, achieving higher accuracy with multiple short sequences. We have conducted extensive experiments in two typical trial sites, a narrow office area and a spacious parking lot. Experimental results show that the proposed approach outperforms state-of-the-art competing schemes, and the localization error is reduced by more than 32% with shorter geomagnetic sequences.

Live streaming service usually delivers the content in mobile edge computing (MEC) to reduce the network latency and save the backhaul capacity. Considering the limited resources, it is necessary that MEC servers collaborate with each other and form an overlay to realize more efficient delivery. The critical challenge is how to optimize the topology among the servers and allocate the link capacity so that the cost will be lower with delay constraints. Previous approaches rarely consider server collaborations for live streaming service, and the scheduling delay is usually ignored in MEC, leading to suboptimal performances. In this paper, we propose a popularity‐guided overlay model which takes the scheduling delay into consideration and utilizes MEC collaboration to achieve efficient live streaming service. The links and servers are shared among all channel streams and each stream is pushed from cloud servers to MEC servers via the trees. Considering the optimization problem is NP‐hard, we propose an effective optimization framework called cost optimization for live streaming (COLS) to predict the channel popularity by a LSTM model with multiscale input data. Finally, we compute topology graph by greedy scheme and allocate the capacity with convex programming. Experimental results show that the proposed approach achieves higher prediction accuracy, reducing the capacity cost by more than 40% with an acceptable delay compared with state‐of‐the‐art schemes.

Indoor localization has attracted considerable attention lately, due to its large commercial and social values in smart cities. The existing indoor localization approaches mostly rely on fingerprint techniques, and many of those leverage either spatially discrete fingerprints or temporally consecutive ones for localization, which either suffers from large errors due to signal ambiguities or high time overhead with long sequences. To achieve high accuracy with low computational cost, we propose ST-Loc, a deep neural network that extracts features from multiple representations of a single signal sequence for localization, where each representation indicates a corresponding signal structure with underlying feature correlations. Taking geomagnetism as an example, we infer location features from two different representations, e.g., spatial and temporal. In spatial representation, a signal sequence is converted to a signal heatmap, where each pixel corresponds to a spatial location and the value indicates fingerprint. Temporal representation, on the other hand, is a signal sequence with ordered readings, which provides temporal correlations. Using these different representations, we employ convolutional and recurrent networks to extract location features and fuse them to generate more distinguishing features for localization. We have conducted extensive experiments in two different trial sites, a narrow office area and a spacious food plaza. Our experimental results show that ST- Loc achieves more than 43% average localization error reduction compared with state-of-the-art competing schemes in both trial sites. © 2019 IEEE.