Time-frequency analysis (TFA) and ridge separation of non-stationary signals have long been research topics in signal processing. They are mutually dependent: informative time frequency representations (TFRs) enable reliable ridge estimation, while accurate ridges refine TFRs by outlining component wise time-frequency (TF) trajectories. However, the uncertainty principle limits TF resolution and ridge discriminability, and existing ridge tracking or optimization-based methods rely on empirical tuning and degrade with weak or closely spaced components, highlighting the need for a more robust and unified solution. This letter proposes a unified network that jointly performs TFA and ridge separation. It features a knowledge guided short-time transform module for extracting discriminative TF features, coupled with an instance segmentation module with learnable queries that interacts with the extracted TF features to achieve ridge separation. This knowledge- and data-integrated framework enables fine-grained TFR construction and high accuracy ridge separation, while eliminating manual parameter tuning and enhancing adaptability. Finally, experiments on simulated and real-world data validate its effectiveness.

Dynamic community division is crucial for comprehending the interactive structure and mechanism between residents and space. Currently, there is insufficient research on dynamic community changes in travel networks regarding travel distance. This study utilizes residents’ travel trajectories to construct a multi-layer network based on travel purposes. The study establishes methods for identifying travel network communities and analyzing community evolution influence. Dynamic characteristics of travel network communities at different distances are extracted. Results show that within 3–7 km travel distance, different travel network communities exhibit continuous spatial aggregation, whereas beyond 11 km, heterogeneity is observed. Moreover, communities within 3-7 km experience drastic dynamic evolution, whereas beyond 7 km, they tend to stabilize, forming a large-scale and fixed travel mode. This study enriches the dynamic interaction research of functional space from the perspective of distance, and the experimental results provide an effective reference for urban planning and management.

The accuracy of on-grid frequency estimation methods suffers from the quantization error of discrete grids. In this article, a deep unfolded network for off-grid frequency estimation is proposed, dubbed OGFreq. In the OGFreq, there exist two kinds of variables. One is the batch-oriented dictionary for frequency-domain transform, and the other one is the instance-specific on-grid frequency and off-grid bias. As the dictionary is required to be universally applicable among all observed signals, network layers are designed and network weights are updated to approximate the transform bases in a data-driven way. Besides, instance-specific on-grid frequencies and off-grid biases are solved by unfolding the iterative soft-threshold algorithm (ISTA). In addition, the instance-specific hyperparameters for sparsity in ISTA are obtained by an encoder-decoder soft-threshold (EDS) module with the attention mechanism. In this way, the dictionary, on-grid frequency, and off-grid bias are learned in a unified data-driven framework. Numerical experiments show that the OGFreq obtains 4% lower false negative rate (FNR) when the SNR is 20 dB. Moreover, the computational complexity is one order of magnitude lower than the iteration-based off-grid frequency estimation methods. Finally, the robustness of the OGFreq is discussed when extended to the impulse noise and damped signals.

Graph theory effectively explains urban structures via street–street connectivity. However, systematic comparisons of street structures across cities remain challenging. This study employs graph convolutional networks (GCNs) to analyze street network structures. A two-branch GCN was used as the backbone to extract comparable features among street networks. The proposed approach was used to examine the structures of different urban road networks in a case study of polycentricity prediction across 298 Chinese cities. The model transformed approximately 4.5-million street segments into natural streets to create urban street graphs, which were subsequently analyzed to extract local and global embeddings. The extracted embeddings – with a portion labeled with a known urban polycentricity score – were used to predict the score for each city through a single-layer perceptron (SLP) model. Our results show consistency between the predicted polycentricity scores based on the derived street embeddings and those based on the population. Thus, the proposed GCN-based method can effectively predict the complexity and interconnection of street networks in different cities. This innovative integration of GCNs into urban studies demonstrates that deep learning techniques can analyze and comprehend the intricate patterns of street networks on a large scale.

Fast urbanization brings great challenges to sustainable development goals, such as excessive exploitation and population explosion. Classical cellular automata (CA) have been widely used to independently simulate the change of spatial features, i.e. land use, population, economic production, etc. However, most CA models rely on historical data as static driving factors to simulate future scenarios while ignoring the inter-wined influences among multiple features in the development process. To address this issue, this study proposes a spatial cooperative simulation (SCS) approach to simulate the land use, population, and economy changes. The SCS approach starts with a separate CA model to obtain the initial scenes of each feature. Then, the simulation results of each other two features are used as dynamically updated driving factors, rather than the static historical data, to capture the inter-wined influence of multiple features during the development process. This step is iteratively performed until the changes of each feature converge and the final simulation results will be reported. The simulation experiment in Greater Bay Area demonstrates that the SCS approach can well capture the simultaneous development process and outperforms baseline approaches. The SCS approach is capable of forecasting future development scenarios and facilitates spatial planning and infrastructure synergies.

As one of the supporting technologies of the Internet of Thing (IOT), the indoor positioning method has attracted much attention from industry. To meet a variety of different demands especially in the era of artificial intelligence (AI), it is of significance to develop an intelligent and low-cost indoor positioning method. One noteworthy application is found within the domain of smart city initiatives, where voice interaction represents a critical mode of human-machine communication. As a kind of voice, locality description appears in human daily communication, in which near relationship is used frequently and has much potential in positioning. Wi-Fi and pedestrian dead reckoning (PDR) positioning methods have attracted much attention because of the widely deployed infrastructures available in the smart-city related scenarios. In this study we proposed a near relationship enhanced multisourced data fusion method for voice-interactive indoor positioning. Our method begins with the establishment of a voice interaction framework, wherein voice inputs are transcribed into textual forms. Subsequently, these locality descriptions are classified based on the number of near relationships. Then, the characteristics and modeling of near relationship are discussed thoroughly. Moreover, a novel method base on Hidden Markov model (HMM) is developed to fuse data from multiple source. The transition probability distribution is modeled by displacement ranging. The emission probability consists of received signal strength indicator (RSSI) and near relationship. To facilitate more efficient computation, the near region and its related probability are preprocessed and stored in a database. By incorporating the information of near regions, searching of reference locations can be narrowed to generate a candidate set, which can further improve the efficiency of real-time computing. Specifically, the data revealed that in 80% of the test cases, our proposed method was capable of achieving a positioning accuracy of 1.95 m.

With the fast development of consumer-level RGB-D cameras, real-world indoor three-dimensional (3D) scene modeling and robotic applications are gaining more attention. However, indoor 3D scene modeling is still challenging because the structure of interior objects may be complex and the RGB-D data acquired by consumer-level sensors may have poor quality. There is a lot of research in this area. In this survey, we provide an overview of recent advances in indoor scene modeling methods, public indoor datasets and libraries which can facilitate experiments and evaluations, and some typical applications using RGB-D devices including indoor localization and emergency evacuation.