Mapping Module Research Articles

TF-TS: Track-to-Track association via track fusion and track segmentation in distributed multi-sensor systems

Track-to-track association (T2TA) aims at unifying batch numbers of tracks, reducing redundancy, and clarifying the situation. It is the precondition and foundation of track fusion, situation awareness, and traffic control. Existing methods based on statistical reasoning or fuzzy math bring some problems that are difficult to solve simultaneously, such as unreasonable assumptions, unsuitable models, uncertain thresholds, and long association times. In the light of the above problems, in this paper, we proposed a T2TA method via Track Fusion and Track Segmentation (TF-TS). The track fusion module fuses and extracts track features from several tracks to reduce the dependency on prior assumptions, motion models, and thresholds. The track segmentation mapping module transforms track tensors into association matrices directly to improve association efficiency. With four kinds of constraints, the association matrices inferred by TF-TS are close to the real one. TF-TS can reduce the dependence on the assumptions, motion models, and thresholds. It can also reduce the traversal calculation of tracks and increase the association efficiency. The global AIS tracks are used to train and test our model, and association results demonstrate that the proposed method can associate tracks in complex scenarios. Moreover, the efficiency is improved and the demand for the real-time association is satisfied.

KaTaGCN: Knowledge-Augmented and Time-Aware Graph Convolutional Network for efficient traffic forecasting

Dynamic spatio-temporal dependencies and temporal patterns in traffic series are critical factors affecting traffic forecasting accuracy. Due to the intrinsic challenges of incorporating explicit, logical knowledge into the implicit black-box learning process of neural networks, only a few methods effectively use prior knowledge to improve the learning of traffic forecasting. To tackle this problem, we introduce a new approach called Knowledge-augmented and Time-aware Graph Convolutional Network, namely KaTaGCN. At its core, we have created a knowledge-augmented module that boosts the diffusion weights between closely related adjacent nodes in graph learning. This is achieved by implementing a new loss function. Then, to learn the periodic implicit relationship between these timestamps and traffic signals, the weights and biases are chosen adaptively to be trained based on the timestamps of each sample. Finally, a gated spatio-temporal mapping module regresses high-dimensional embedded features from spatial and temporal dimensions. KaTaGCN is structured without any attention mechanisms or recurrent neural networks. Extensive experimental results on six real-world public traffic datasets demonstrate that KaTaGCN achieves an average improvement of 4.29% in forecasting performance compared with suboptimal results.

Fine-Grained Entity-Type Completion Based on Neighborhood-Attention and Cartesian–Polar Coordinates Mapping

Entities refer to things that exist objectively, and entity types are concepts abstracted from entities that have the same features or properties. However, the entity types in the knowledge graph are always incomplete. Currently, the main approach for predicting missing entity types is to learn structured representations of entities and types separately, which ignores neighborhood semantic knowledge of the entity. Therefore, this paper proposes the aggregation neighborhood semantics model for type completion (ANSTC), which extracts neighborhood triple features of target entities with two attentional mechanisms. Meanwhile, the spatial mapping module in ANSTC maps entities from Cartesian coordinate to Polar coordinate system, which can map similar vectors onto a concentric circle and then rotate the angle according to the fine-grained difference to achieve entity-to-type transformation. Moreover, we add semantic features from text to the entity representations to enrich semantics. Through experimental comparison on the FB15K and YAGO43K dataset, we get similar results to the baseline. We also construct person dataset in computer domain, and the values of MRR, Hit@1, Hit@3 and Hit@10 are improved compared with the ConnectE model. The experimental results demonstrate that our model can effectively predict the fine-grained entity types in the domain dataset, and achieve state-of-the-art performance.

Embedded Zero-Shot Image Classification Based on Bidirectional Feature Mapping

The zero-shot image classification technique aims to explore the semantic information shared between seen and unseen classes through visual features and auxiliary information and, based on this semantic information, to complete the knowledge migration from seen to unseen classes in order to complete the classification of unseen class images. Previous zero-shot work has either not extracted enough features to express the relationship between the sample classes or has only used a single feature mapping method, which cannot fully explore the information contained in the features and the connection between the visual–semantic features. To address the above problems, this paper proposes an embedded zero-shot image classification model based on bidirectional feature mapping (BFM). It mainly contains a feature space mapping module, which is dominated by a bidirectional feature mapping network and supplemented with a mapping network from visual to category label semantic feature space. Attention mechanisms based on attribute guidance and visual guidance are further introduced to weight the features to reduce the difference between visual and semantic features to alleviate the modal difference problem, and then the category calibration loss is utilized to assign a larger weight to the unseen class to alleviate the seen class bias problem. The BFM model proposed in this paper has been experimented on three public datasets CUB, SUN, and AWA2, and has achieved 71.9%, 62.8%, and 69.3% and 61.6%, 33.2%, and 66.6% accuracies under traditional and generalized zero-sample image classification settings, respectively. The experimental results verify the superiority of the BFM model in the field of zero-shot image classification.

Reentrancy vulnerability detection based on graph convolutional networks and expert patterns under subspace mapping

Smart contracts with automatic execution capability provide a vast development space for transactions in Blockchain. However, due to the vulnerabilities in smart contracts, Blockchain has suffered huge economic losses, which greatly undermines people’s trust in Blockchain and smart contracts. In this paper, we explore a vulnerability detection method based on graph neural networks and combine both contract source code and opcode. The structure of the method consists of four modules, i.e., preprocessing, subspace mapping, feature extraction, and detection modules. In the feature mapping module, we use a multi-subspace mapping approach to explore the impact of different subspace mappings on the detection method. For reentrancy vulnerability, we conducted extensive experiments. The experiments prove that our method achieves 95% accuracy and 94% F1-Score on average.

Misalignment-Resistant Deep Unfolding Network for multi-modal MRI super-resolution and reconstruction

Multi-modal Magnetic Resonance Imaging (MRI) super-resolution (SR) and reconstruction aims to obtain a high-quality target image from corresponding sparsely sampled signals under the guidance of a reference image. However, existing techniques typically assume that the input multi-modal MR images are well aligned, which is challenging to achieve in clinical practice. This naive assumption has made their algorithms vulnerable to misalignment scenarios. Moreover, they often neglect many non-local common characteristics within and between modalities. In this work, we proposed a MisAlignment-Resistant Deep Unfolding Network (MAR-DUN) embedded in the tailored gradient descent module (GDM) and proximal mapping module (PMM) for multi-modal MRI SR and reconstruction. In the GDM, we employ an adaptive step-size sub-network (ASS-Net) to enhance the texture representation capacity of the proposed MAR-DUN. Furthermore, in the PMM, we propose a cross-modality non-local module (CNLM) featuring the inverse deformation layer (IDL). The IDL aligns features between the target and reference images by adaptively learning their spatial transformations, thus enhancing the robustness of the proposed network and allowing the CNLM to further explore the cross-modality non-local characteristics. On the other hand, the proposed CNLM aims to establish both the intra-modality and inter-modality non-local dependencies for fully exploiting the correlations between the target and reference images. Extensive experimental results show that our proposed method consistently achieves state-of-the-art reconstruction performance in alignment and misalignment scenarios, demonstrating its significant promise for real-world applications.

Streamlining social media information retrieval for public health research with deep learning.

Social media-based public health research is crucial for epidemic surveillance, but most studies identify relevant corpora with keyword-matching. This study develops a system to streamline the process of curating colloquial medical dictionaries. We demonstrate the pipeline by curating a Unified Medical Language System (UMLS)-colloquial symptom dictionary from COVID-19-related tweets as proof of concept. COVID-19-related tweets from February 1, 2020, to April 30, 2022 were used. The pipeline includes three modules: a named entity recognition module to detect symptoms in tweets; an entity normalization module to aggregate detected entities; and a mapping module that iteratively maps entities to Unified Medical Language System concepts. A random 500 entity samples were drawn from the final dictionary for accuracy validation. Additionally, we conducted a symptom frequency distribution analysis to compare our dictionary to a pre-defined lexicon from previous research. We identified 498480 unique symptom entity expressions from the tweets. Pre-processing reduces the number to 18226. The final dictionary contains 38175 unique expressions of symptoms that can be mapped to 966 UMLS concepts (accuracy = 95%). Symptom distribution analysis found that our dictionary detects more symptoms and is effective at identifying psychiatric disorders like anxiety and depression, often missed by pre-defined lexicons. This study advances public health research by implementing a novel, systematic pipeline for curating symptom lexicons from social media data. The final lexicon's high accuracy, validated by medical professionals, underscores the potential of this methodology to reliably interpret, and categorize vast amounts of unstructured social media data into actionable medical insights across diverse linguistic and regional landscapes.

PFMNet: Prototype-based feature mapping network for few-shot domain adaptation in medical image segmentation

Lack of data is one of the biggest hurdles for rare disease research using deep learning. Due to the lack of rare-disease images and annotations, training a robust network for automatic rare-disease image segmentation is very challenging. To address this challenge, few-shot domain adaptation (FSDA) has emerged as a practical research direction, aiming to leverage a limited number of annotated images from a target domain to facilitate adaptation of models trained on other large datasets in a source domain. In this paper, we present a novel prototype-based feature mapping network (PFMNet) designed for FSDA in medical image segmentation. PFMNet adopts an encoder–decoder structure for segmentation, with the prototype-based feature mapping (PFM) module positioned at the bottom of the encoder–decoder structure. The PFM module transforms high-level features from the target domain into the source domain-like features that are more easily comprehensible by the decoder. By leveraging these source domain-like features, the decoder can effectively perform few-shot segmentation in the target domain and generate accurate segmentation masks. We evaluate the performance of PFMNet through experiments on three typical yet challenging few-shot medical image segmentation tasks: cross-center optic disc/cup segmentation, cross-center polyp segmentation, and cross-modality cardiac structure segmentation. We consider four different settings: 5-shot, 10-shot, 15-shot, and 20-shot. The experimental results substantiate the efficacy of our proposed approach for few-shot domain adaptation in medical image segmentation.

A comprehensive overview of core modules in visual SLAM framework

Visual Simultaneous Localization and Mapping (VSLAM) technology has become a key technology in autonomous driving and robot navigation. Relying on camera sensors, VSLAM can provide a richer and more precise perception means, and its advancement has accelerated in recent years. However, current review studies are often limited to in-depth analysis of a specific module and lack a comprehensive review of the entire VSLAM framework. The VSLAM system consists of five core components: (1) The camera sensor module is responsible for capturing visual information about the surrounding environment. (2) The front-end module uses image data to roughly estimate the camera’s position and orientation. (3) The back-end module optimizes and processes the pose information estimated by the front-end. (4) The loop detection module is used to correct accumulated errors in the system. (5) The mapping module is responsible for generating environmental maps. This review provides a systematic and comprehensive analysis of the SLAM framework by taking the core components of VSLAM as the entry point. Deep learning brings new development opportunities for VSLAM, but it still needs to solve the problems of data dependence, cost and real-time in practical application. We deeply explore the challenges of combining VSLAM with deep learning and feasible solutions. This review provides a valuable reference for the development of VSLAM. This will help push VSLAM technology to become smarter and more efficient. Thus, it can better meet the needs of future intelligent autonomous systems in multiple fields.

Reversible data hiding scheme using prediction neural network and adaptive modulation mapping

Reversible data hiding scheme using prediction neural network and adaptive modulation mapping

McmIQA: Multi-Module Collaborative Model for No-Reference Image Quality Assessment

No reference image quality assessment is a technique that uses computers to simulate the human visual system and automatically evaluate the perceived quality of images. In recent years, with the widespread success of deep learning in the field of computer vision, many end-to-end image quality assessment algorithms based on deep learning have emerged. However, unlike other computer vision tasks that focus on image content, an excellent image quality assessment model should simultaneously consider distortions in the image and comprehensively evaluate their relationships. Motivated by this, we propose a Multi-module Collaborative Model for Image Quality Assessment (McmIQA). The image quality assessment is divided into three subtasks: distortion perception, content recognition, and correlation mapping. And specific modules are constructed for each subtask: the distortion perception module, the content recognition module, and the correlation mapping module. Specifically, we apply two contrastive learning frameworks on two constructed datasets to train the distortion perception module and the content recognition module to extract two types of features from the image. Subsequently, using these extracted features as input, we employ a ranking loss to train the correlation mapping module to predict image quality on image quality assessment datasets. Extensive experiments conducted on seven relevant datasets demonstrated that the proposed method achieves state-of-the-art performance in both synthetic distortion and natural distortion image quality assessment tasks.

Object phase-valid region segmentation method for FPP-based three-dimensional measurement

In most existing studies based on fringe projector profilometry (FPP), the whole scenario is reconstructed, or the ideal experimental settings are established to segment the object easily. However, in real industrial scenarios, automated object detection and segmentation are essential to perform object-level measurement. To address the problem, a dual-wavelet feature interaction network (DWFI-Net) is developed in this paper to perform object phase-valid region segmentation, where both the background and shadow are removed. In our work, the modulation and wrapped phase maps are considered as inputs innovatively. The modulation maps provide abundant structures and textures, while the wrapped phase maps complement and enhance shadows and edges. An adaptive wavelet feature interaction (AWFI) module is presented to learn and fuse the features, where discrete wavelet transformation (DWT) is applied to decompose the features. An edge-aware discrete cosine transformation (EDCT) module is developed as a decoder, where the discrete cosine transformation (DCT) is applied to interpret the fused features. Qualitative and quantitative experiments are performed to verify the superiority of our DWFI-Net and its effectiveness on object-level three-dimensional measurement based on FPP.

Complexity enhancement and grid basin of attraction in a locally active memristor-based multi-cavity map

The complexity of memristive chaotic systems determines whether it is suitable for applications in different subjects. To enhance complexity both in performance and diversity, this article first proposes a discrete model of locally active memristor (LAM) and conceives a three-dimensional memristive multi-cavity map by coupling LAM with the existing sine and cosine modulation (SCM) map. This map is named LAM-SCM map and has numerous independent fixed points with different stabilities. Numerical simulations reveal the memristive parameters-relied lossless displacement and self-shift of multi-cavity attractors, indicating the dynamical effects of LAM on the existing SCM map. The initial-relied dynamics distributions are disclosed by grid basins of attraction, showing the emergence of initial-boosting coexistence. Besides, the performance comparisons verify the superiority of LAM-SCM map over the existing SCM map. Finally, a hardware platform has been developed on FPGA to implement the LAM-SCM map and the captured attractors validate the numerical results. On this basis, we devise a 32-bit pseudorandom number generator (PRNG) based on chaos and implement it on the FPGA-based hardware platform to obtain high-speed and reconfigurable pseudorandom numbers. The results show that the proposed map has enhanced chaos complexity and rich dynamics diversity, which ensures the availability of hardware PRNG.

Big Data Analysis and User Behavior Prediction of Social Networks Based on Artificial Neural Network

The prediction of user behavior in social networks is of great significance for understanding user dynamics, personalized recommendation, and information dissemination. With the development of artificial intelligence (AI) technology, especially the application of artificial neural networks in big data analysis, new solutions and technical means have been provided for the analysis of user behavior in social networks. This study constructs a social network user behavior prediction model based on artificial neural networks. The article first reviews related research, establishes a research framework, and then describes in detail the functional structure of the user behavior prediction system. The key data structure design is meticulously constructed and the model is built through steps such as data preprocessing module, 3D feature frame construction module, feature mapping module, and feature prediction module. In addition, the article also constructs a group behavior theme probability prediction model based on an improved encoder-decoder model, which further enhances the understanding of group behavior of users in social networks. Through comparative experiments, the model proposed in this paper demonstrates its effectiveness in predicting individual and group user behaviors. The experimental results show that the model can accurately predict the behavior patterns of users in social networks and is superior to existing methods in terms of prediction accuracy and computational efficiency. This research shows that artificial neural networks are a powerful tool for analyzing big data in social networks and for predicting user behavior. The success of the study verifies the effectiveness of the model, provides a new technical path for future analysis of user behavior in social networks, and is expected to be widely applied in areas such as personalized recommendation and information dissemination analysis.

Cross-modal texture transformer for thermal infrared reference-based super-resolution reconstruction

The Reference-based super-resolution(RefSR) methods add a reference image as an extra information source, which effectively resolves the issue of poor reconstruction accuracy resulting from the limited data in single-image super-resolution (SISR). However, the significant differences in thermal infrared and visible imaging mechanisms and image textures make it challenging to accomplish cross-modal texture matching and transfer. To address these issues, we propose a cross-modal texture transfer method for thermal infrared reference super-resolution reconstruction. First, we introduce a pre-trained feature encoder based on contrastive learning, which equips the encoder with the capability to match textures between thermal infrared and visible images. Next, to decrease computational complexity when matching features, we suggest a new sparse feature matching approach that regards areas of the image with abundant textures as suitable matching regions. Ultimately, we introduce a feature mapping module to identify differences in the distribution between infrared and visible images and to remap visible features to the infrared feature distribution. Extensive experiments demonstrate that our method effectively transfers textures from visible reference images to infrared images, resulting in superior visual effects and evaluation metrics.

Structure Mapping Generative Adversarial Network for Multi-View Information Mapping Pattern Mining.

Multi-view learning is dedicated to integrating information from different views and improving the generalization performance of models. However, in most current works, learning under different views has significant independency, overlooking common information mapping patterns that exist between these views. This paper proposes a Structure Mapping Generative adversarial network (SM-GAN) framework, which utilizes the consistency and complementarity of multi-view data from the innovative perspective of information mapping. Specifically, based on network-structured multi-view data, a structural information mapping model is proposed to capture hierarchical interaction patterns among views. Subsequently, three different types of graph convolutional operations are designed in SM-GAN based on the model. Compared with regular GAN, we add a structural information mapping module between the encoder and decoder wthin the generator, completing the structural information mapping from the micro-view to the macro-view. This paper conducted sufficient validation experiments using public imaging genetics data in Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. It is shown that SM-GAN outperforms baseline and advanced methods in multi-label classification and evolution prediction tasks.

Design and Study of a Two-Dimensional (2D) All-Optical Spatial Mapping Module.

Sequentially timed all-optical mapping photography is one of the main emerging ultra-fast detection technologies that can be widely applicable to ultra-fast detection at the picosecond level in fields such as materials and life sciences. We propose a new optical structure for an all-optical spatial mapping module that can control the optical field of two-dimensional imaging while improving spectral resolution and detector sensor utilization. The model of optical parameters based on geometrical optics theory for the given structure has been established, and the theoretical analysis of the inter-frame energy crosstalk caused by incident beam spot width, chromatic aberration, and main errors of the periscope array has been conducted. The optical design of the two-dimensional (2D) all-optical spatial mapping module was finally completed using ZEMAX OpticStudio 2018 software. The results show that our optical module can realize targets of 16 frames and 1.25 nm spectral resolution.

MRG-T: Mask-Relation-Guided Transformer for Remote Vision-Based Pedestrian Attribute Recognition in Aerial Imagery

Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), utilizing UAV platforms for visual surveillance has become very attractive, and a key part of this is remote vision-based pedestrian attribute recognition. Pedestrian Attribute Recognition (PAR) is dedicated to predicting multiple attribute labels of a single pedestrian image extracted from surveillance videos and aerial imagery, which presents significant challenges in the computer vision community due to factors such as poor imaging quality and substantial pose variations. Despite recent studies demonstrating impressive advancements in utilizing complicated architectures and exploring relations, most of them may fail to fully and systematically consider the inter-region, inter-attribute, and region-attribute mapping relations simultaneously and be stuck in the dilemma of information redundancy, leading to the degradation of recognition accuracy. To address the issues, we construct a novel Mask-Relation-Guided Transformer (MRG-T) framework that consists of three relation modeling modules to fully exploit spatial and semantic relations in the model learning process. Specifically, we first propose a Masked Region Relation Module (MRRM) to focus on precise spatial attention regions to extract more robust features with masked random patch training. To explore the semantic association of attributes, we further present a Masked Attribute Relation Module (MARM) to extract intrinsic and semantic inter-attribute relations with an attribute label masking strategy. Based on the cross-attention mechanism, we finally design a Region and Attribute Mapping Module (RAMM) to learn the cross-modal alignment between spatial regions and semantic attributes. We conduct comprehensive experiments on three public benchmarks such as PETA, PA-100K, and RAPv1, and conduct inference on a large-scale airborne person dataset named PRAI-1581. The extensive experimental results demonstrate the superior performance of our method compared to state-of-the-art approaches and validate the effectiveness of mask-relation-guided modeling in the remote vision-based PAR task.

LIFNS: Design of a novel Lidar-IMU fusion navigation system for AGVs in smart factories

Traditional Automated Guided Vehicle (AGV) robots commonly employ 2D plane navigation systems. However, with the expansion of AGV application scenarios and the increasing complexity of structures, the limitations of existing 2D navigation systems have become more pronounced, rendering them inadequate for addressing these challenges. To tackle this issue, this paper proposes a novel navigation system suitable for AGV robots composed of fused Lidar and Inertial Measurement Unit (IMU), named as Lidar-IMU Fusion Navigation System (LIFNS). LIFNS primarily comprises mapping, localization, and fused path planning modules. In the mapping module, a 3D point cloud map for precise 3D localization and a 2D grid map for path planning are constructed using multiple-line Lidar and IMU. For the localization module, a fusion localization approach is introduced, combining IMU data with Normal Distributions Transform (NDT) point cloud registration through Unscented Kalman Filtering (UKF). Finally, global path planning is executed using the A* algorithm on the grid map, while local path planning utilizes the Timed-Elastic Band (TEB) algorithm. The effectiveness and universality of LIFNS are validated through simulation experiments and real-world deployment tests. The experimental results demonstrate that LIFNS achieves centimeter-level accuracy in both mapping and localization, effectively alleviating the issues of low precision and significant limitations present in traditional AGV robots. This positions LIFNS with promising applications in enclosed settings such as smart factories, industrial parks, and healthcare facilities.

Meta learning-based few-shot intrusion detection for 5G-enabled industrial internet

AbstractWith the formation and popularization of the 5G-enabled industrial internet, cybersecurity risks are increasing, and the limited number of attack samples, such as zero-day, leaves a short response time for security protectors, making it substantially more difficult to protect industrial control systems from new types of malicious attacks. Traditional supervised intrusion detection models rely on a large number of samples for training and their performance needs to be improved. Therefore, there is an urgent need for few-shot intrusion detection. Aiming at the above problems, this paper proposes a detection model based on a meta-learning framework, which aims to effectively improve the accuracy and real-time performance of intrusion detection, and designs a meta-learning intrusion detection model containing a sample generation module, a feature mapping module and a feature metric module. Among them, the sample generation module introduces the residual block into the Natural GAN and proposes a new method to generate high-quality antagonistic samples—Res-Natural GAN, which is used to enhance the antagonism of the generated samples and the feature mining degree, to improve the accuracy of malicious traffic detection; the feature mapping module proposes a new attention mechanism, the multi-head fast attention mechanism, which is applied to the encoder structure of the transformer and combined with a parameter optimization algorithm based on particle swarm mutation to shorten the mapping time and improve the real-time performance of the model while mapping the features effectively; the feature metric module proposes a prototype structure based on a prototype storage update algorithm and combines it with a prototype network to achieve correct classification by measuring the Euclidean distance between the detected samples and the class of prototypes, and to shorten the inference time while ensuring the detection accuracy; finally, the three modules are combined to form a real-time meta-learning intrusion detection model. To evaluate the proposed model, five different types of experiments are conducted on multiple public datasets. The experimental results show that the model has higher detection accuracy than the traditional model for both few-shot and zero-shot malicious attacks, and is not only applicable to 5G-enabled industrial internet, but also generalized to different network environments and attack types.