Map Network Research Articles

Modified Structure of Deep Neural Network for Training Multi-Fidelity Data With Non-Common Input Variables

Abstract Multi-fidelity surrogate (MFS) modeling technology, which efficiently constructs surrogate models using low-fidelity (LF) and high-fidelity (HF) data, has been studied to enhance the predictive capability of engineering performances. In addition, several neural network (NN) structures for MFS modeling have been introduced, benefiting from recent developments in deep learning research. However, existing multi-fidelity (MF) NNs have been developed assuming identical sets of input variables for LF and HF data, a condition that is often not met in practical engineering systems. Therefore, this study proposes a new structure of composite NN designed for MF data with different input variables. The proposed network structure includes an input mapping network that connects the LF and HF data's input variables. Even when the physical relationship between these variables is unknown, the input mapping network can be concurrently trained during the process of training the whole network model. Customized loss functions and activation variables are suggested in this study to facilitate forward and backward propagation for the proposed NN structures when training MF data with different inputs. The effectiveness of the proposed method, in terms of prediction accuracy, is demonstrated through mathematical examples and practical engineering problems related to tire performances. The results confirm that the proposed method offers better accuracy than existing surrogate models in most problems. Moreover, the proposed method proves advantageous for surrogate modeling of nonlinear or discrete functions, a characteristic feature of NN-based methods.

Acute transitory head mislocalization – a novel syndrome of pathological embodiment in a patient with traumatic brain injury – a case study

ABSTRACT Feeling of body ownership is a complex process with different brain mechanisms involved in integrating the varied and multiple representations of the body . The ability to discriminate between one’s own and others’ body parts can be lost after brain damage. We report a unique case study of a patient with head injury who experienced a phenomenon where he felt that his head was positioned with another person standing next to him. We describe this as a form of pathological embodiment and call it the “head mislocalization” phenomenon. We report his clinical findings and using the methods of lesion mapping and lesion network mapping postulate the neural mechanisms for this symptom.

Machine learning-assisted acoustic emission monitoring for track formability prediction of laser powder bed fusion

Laser powder bed fusion (L-PBF) additive manufacturing offers many advantages in directly fabricating geometrically complex parts. To achieve the optimal L-PBF-built part quality, the laser process parameters should be tailored before building or real-time adjusted during building if necessary. Monitoring the formation quality of L-PBF-built metal tracks during the building process is a technical prerequisite. The work studies the acoustic emission (AE) monitoring and machine learning (ML) to predict the formation quality of as-built tracks. The AE signals from the L-PBF processes under different laser parameters are collected. A method of deep neural network-based denoising is employed to identify and eliminate the AE noise-hits. Signal segments of interest signals in the track melting-solidification stage are detected and extracted. The features for constructing the ML models are extracted by combining wavelet packet transform and self-organization map network. The random forest is used for formation quality prediction of the as-built tracks. The correlation between AE signals and as-built track quality is analyzed based on the similarity matrix of self-organization map. The results indicate that the as-built track quality can be monitored by AE technology and ML model. It contributes to that the L-PBF process stability and the as-built track quality reliability can be ensured by adjusting the process parameters in time during the L-PBF process.

Validation of four optimization evolutionary algorithms combined with artificial neural network (ANN) for landslide susceptibility mapping: A case study of Gilan, Iran

Landslides, the most significant geohazards in Iran, adversely affect the region's socioeconomic conditions and the environment. Landslide susceptibility mapping is crucial for proactive risk management, sustainable development, and protecting human lives, infrastructure, and the environment. It enables decision-makers to make informed choices, implement appropriate mitigation measures, and plan for potential landslide events, leading to safer and more resilient communities. Using a recommended subdivision methodology, this research has developed a landslide susceptibility map for a significant Gilan, Iran region. The production of the map involved utilizing an artificial neural network (ANN) model. This model incorporated sixteen causal components from several characteristics, including topographic and geomorphologic features, geological factors, land use patterns, hydrological aspects, and hydrogeological properties. Three hundred seventy instances were identified using multiple verified sources and analyzing aerial photographs to create the landslide inventory map. Examining and verifying the weights assigned to the causal elements were conducted per accepted mathematical standards, incorporating sensitivity analysis, earlier research, and empirical data on landslides. The area under the receiver operating characteristic curve (AUROC) was used to compare the various models. The study's findings indicated that the best swarm size value for COA-MLP11Cuckoo Optimization Algorithm (COA). is equal to 450, and the accuracy indices for this algorithm were 0.998 and 0.995 in training and testing datasets, respectively. Similarly, the AUC22Area under the curve (AUC). for the HS-MLP,33Harmony Search Algorithm (HS). SFS-MLP,44Stochastic Fractal Search (SFS). and TLBO-MLP55Teaching- Learning-Based Optiization (TLBO). were 0.997, 0.999, and 0.999 in training and 0.995, 0.996, and 0.995 in the testing dataset, respectively. Therefore, the use of optimization algorithms leads to an increase in the performance and accuracy of the neural network, and the high accuracy of the SFS-MLP model demonstrates the existence of a dependable criterion for delineating the susceptibility zones about forthcoming landslide occurrences. The model is a cost-effective and potentially indispensable tool for urban planners in growing cities and municipalities. Its effectiveness is demonstrated by comparisons with previous susceptibility analyses conducted in the region.

Lightweight Multilevel Feature-Fusion Network for Built-Up Area Mapping from Gaofen-2 Satellite Images

The timely, accurate acquisition of geographic spatial information such as the location, scope, and distribution of built-up areas is of great importance for urban planning, management, and decision-making. Due to the diversity of target features and the complexity of spatial layouts, the large-scale mapping of urban built-up areas using high-resolution (HR) satellite imagery still faces considerable challenges. To address this issue, this study adopted a block-based processing strategy and constructed a lightweight multilevel feature-fusion (FF) convolutional neural network for the feature representation and discrimination of built-up areas in HR images. The proposed network consists of three feature extraction modules composed of lightweight convolutions to extract features at different levels, which are further fused sequentially through two attention-based FF modules. Furthermore, to improve the problem of incorrect discrimination and severe jagged boundaries caused by block-based processing, a majority voting method based on a grid offset is adopted to achieve a refined extraction of built-up areas. The effectiveness of this method is evaluated using Gaofen-2 satellite image data covering Shenzhen, China. Compared with several state-of-the-art algorithms for detecting built-up areas, the proposed method achieves a higher detection accuracy and preserves better shape integrity and boundary smoothness in the extracted results.

A spatially adaptive regularization based three-dimensional reconstruction network for quantitative susceptibility mapping

Objective. Quantitative susceptibility mapping (QSM) is a new imaging technique for non-invasive characterization of the composition and microstructure of in vivo tissues, and it can be reconstructed from local field measurements by solving an ill-posed inverse problem. Even for deep learning networks, it is not an easy task to establish an accurate quantitative mapping between two physical quantities of different units, i.e. field shift in Hz and susceptibility value in ppm for QSM. Approach. In this paper, we propose a spatially adaptive regularization based three-dimensional reconstruction network SAQSM. A spatially adaptive module is specially designed and a set of them at different resolutions are inserted into the network decoder, playing a role of cross-modality based regularization constraint. Therefore, the exact information of both field and magnitude data is exploited to adjust the scale and shift of feature maps, and thus any information loss or deviation occurred in previous layers could be effectively corrected. The network encoding has a dynamic perceptual initialization, which enables the network to overcome receptive field intervals and also strengthens its ability to detect features of various sizes. Main results. Experimental results on the brain data of healthy volunteers, clinical hemorrhage and simulated phantom with calcification demonstrate that SAQSM can achieve more accurate reconstruction with less susceptibility artifacts, while perform well on the stability and generalization even for severe lesion areas. Significance. This proposed framework may provide a valuable paradigm to quantitative mapping or multimodal reconstruction.

A comprehensive automatic labeling and repair strategy for cracks and peeling conditions of literary murals in ancient buildings

To protect the historical and cultural heritage, the application of self-organizing mapping networks and genetic algorithms in the restoration of ancient architectural murals is studied. The results show that the average repair time for different types of mural paintings is less than 60 seconds, and the shortest repair time is only 17.81 seconds. The evaluation effect of the research model is good, and the comprehensive efficiency evaluation of the mural restoration work is improved by about 40.42%. The repair system has excellent performance, and the algorithm has high feasibility and effectiveness. The impact of restoring murals is substantial, and the extent of restoration is highly consequential for the restoration of ancient architectural murals.

Brand and addiction: A network analysis of scientific literature.

The paper conducts a network analysis of the fragmented literature on brand and addiction. A thematic map, thematic evolution, word cloud, co-citation analysis, and cooperation networks were utilized to identify brand addiction study trends and topics. The data show that marketing and psychiatry have interdisciplinary groupings and multidisciplinary publications. These groups reflect societal changes, particularly the shift from traditional to digital challenges. Fast food addiction is different from alcohol and cigarette addictions due to its ease and extensive marketing. The decline in internet and gambling addiction suggests a shift in priorities. This research helps researchers, policymakers, and practitioners in addiction prevention and intervention. The study also understands brand addiction and its effects on psychology, psychiatry, and management by providing insights into emerging topics, thematic maps and evolution of studies, collaboration opportunities, geographical distribution of studies, and more.

The spark of synchronization in heterogeneous networks of chaotic maps.

We investigate the emergence of synchronization in heterogeneous networks of chaotic maps. Our findings reveal that a small cluster of highly connected maps is responsible for triggering the spark of synchronization. After the spark, the synchronized cluster grows in size and progressively moves to less connected maps, eventually reaching a cluster that may remain synchronized over time. We explore how the shape of the network degree distribution affects the onset of synchronization and derive an expression based on the network construction that determines the expected time for a network to synchronize. Understanding how the network design affects the spark of synchronization is particularly important for the control and design of more robust systems that require some level of coherence between a subset of units for better functioning. Numerical simulations in finite-sized networks are consistent with this analysis.

Systems genetics analysis reveals the common genetic basis for pain sensitivity and cognitive function.

There is growing evidence of a strong correlation between pain sensitivity and cognitive function under both physiological and pathological conditions. However, the detailed mechanisms remain largely unknown. In the current study, we sought to explore candidate genes and common molecular mechanisms underlying pain sensitivity and cognitive function with a transcriptome-wide association study using recombinant inbred mice from the BXD family. The pain sensitivity determined by Hargreaves' paw withdrawal test and cognition-related phenotypes were systematically analyzed in 60 strains of BXD mice and correlated with hippocampus transcriptomes, followed by quantitative trait locus (QTL) mapping and systems genetics analysis. The pain sensitivity showed significant variability across the BXD strains and co-varies with cognitive traits. Pain sensitivity correlated hippocampual genes showed a significant involvement in cognition-related pathways, including glutamatergic synapse, and PI3K-Akt signaling pathway. Moreover, QTL mapping identified a genomic region on chromosome 4, potentially regulating the variation of pain sensitivity. Integrative analysis of expression QTL mapping, correlation analysis, and Bayesian network modeling identified Ring finger protein 20 (Rnf20) as the best candidate. Further pathway analysis indicated that Rnf20 may regulate the expression of pain sensitivity and cognitive function through the PI3K-Akt signaling pathway, particularly through interactions with genes Ppp2r2b, Ppp2r5c, Col9a3, Met, Rps6, Tnc, and Kras. Our study demonstrated that pain sensitivity is associated with genetic background and Rnf20-mediated PI3K-Akt signaling may involve in the regulation of pain sensitivity and cognitive functions.

A High-Capacity and High-Security Image Steganography Network Based on Chaotic Mapping and Generative Adversarial Networks

With the enhancement of information volume, people are not satisfied with transmitting only a single secret image at a time but chase to hide multiple secret images in a single picture; however, the large-capacity steganographic scale can easily lead to the degradation of the quality of the image, which attracts the attention of eavesdroppers. In this paper, we propose a Chaotic mapping-enHanced imAge Steganography nEtwork (CHASE), which pioneers to hide colour images in grey images and reduces the difference between the container image and the cover image through the image permutation method, so as to enhance the security of the steganography. The method demonstrates excellent steganalysis resistance in experiments and introduces Generative Adversarial Networks (GANs) to improve the image fidelity in large-capacity steganographic scales. The fusion of chaotic mapping and GAN optimisation enables the steganographic network to simultaneously balance security and image quality. The experimental results show that CHASE can keep the secret image with good invisibility under large-capacity steganographic scales, and at the same time, it can reveal the secret image with high fidelity, and its steganalysis-resistant capability is much better than other state-of-the-art methods.

Self-Supervised Self-Organizing Clustering Network: A Novel Unsupervised Representation Learning Method.

Deep learning-based clustering methods usually regard feature extraction and feature clustering as two independent steps. In this way, the features of all images need to be extracted before feature clustering, which consumes a lot of calculation. Inspired by the self-organizing map network, a self-supervised self-organizing clustering network ( [Formula: see text]OCNet) is proposed to jointly learn feature extraction and feature clustering, thus realizing a single-stage clustering method. In order to achieve joint learning, we propose a self-organizing clustering header (SOCH), which takes the weight of the self-organizing layer as the cluster centers, and the output of the self-organizing layer as the similarities between the feature and the cluster centers. In order to optimize our network, we first convert the similarities into probabilities which represents a soft cluster assignment, and then we obtain a target for self-supervised learning by transforming the soft cluster assignment into a hard cluster assignment, and finally we jointly optimize backbone and SOCH. By setting different feature dimensions, a Multilayer SOCHs strategy is further proposed by cascading SOCHs. This strategy achieves clustering features in multiple clustering spaces. [Formula: see text]OCNet is evaluated on widely used image classification benchmarks such as Canadian Institute For Advanced Research (CIFAR)-10, CIFAR-100, Self-Taught Learning (STL)-10, and Tiny ImageNet. Experimental results show that our method significant improvement over other related methods. The visualization of features and images shows that our method can achieve good clustering results.

Study of Digital Marketing in Tourism and Hospitality Industry: A Literature Search Using the Keyword Co-Occurrence Mapping Network

Digital marketing is essential to the travel and hospitality industries. These days, it's a helpful tool for creating digital brand names and attracting and retaining clients. It has been demonstrated that using digital technology to implement marketing strategies, such as influencer marketing, social media marketing, and search engine optimization, benefits businesses. Through the process of monitoring customer behavior and assessing their preferences, digital marketing allows businesses to offer personalized and engaging content that encourages online referrals. Digital technology must be included into a number of sectors, including operations, services, communications, revenue management, distribution, and marketing, for the industry to be stimulated and reinvigorated. Hotel businesses need to reevaluate their current economic models and embrace digital marketing as an essential tool if they are to expand. The aim of the current research is to search the keywords in the database dimensions and creating co-occurrence mapping using VOSviewer software. Finally, the importance of digital marketing in tourism and hospitality industry is researched using research database and presented using term co-occurrence mappings.

Lightweight improved residual network for efficient inverse tone mapping

Lightweight improved residual network for efficient inverse tone mapping

A Geoscience-Aware Network (GASlumNet) Combining UNet and ConvNeXt for Slum Mapping

Approximately 1 billion people worldwide currently inhabit slum areas. The UN Sustainable Development Goal (SDG 11.1) underscores the imperative of upgrading all slums by 2030 to ensure adequate housing for everyone. Geo-locations of slums help local governments with upgrading slums and alleviating urban poverty. Remote sensing (RS) technology, with its excellent Earth observation capabilities, can play an important role in slum mapping. Deep learning (DL)-based RS information extraction methods have attracted a lot of attention. Currently, DL-based slum mapping studies typically uses three optical bands to adapt to existing models, neglecting essential geo-scientific information, such as spectral and textural characteristics, which are beneficial for slum mapping. Inspired by the geoscience-aware DL paradigm, we propose the Geoscience-Aware Network for slum mapping (GASlumNet), aiming to improve slum mapping accuracies via incorporating the DL model with geoscientific prior knowledge. GASlumNet employs a two-stream architecture, combining ConvNeXt and UNet. One stream concentrates on optical feature representation, while the other emphasizes geo-scientific features. Further, the feature-level and decision-level fusion mechanisms are applied to optimize deep features and enhance model performance. We used Jilin-1 Spectrum 01 and Sentinel-2 images to perform experiments in Mumbai, India. The results demonstrate that GASlumNet achieves higher slum mapping accuracy than the comparison models, with an intersection over union (IoU) of 58.41%. Specifically, GASlumNet improves the IoU by 4.60~5.97% over the baseline models, i.e., UNet and ConvNeXt-UNet, which exclusively utilize optical bands. Furthermore, GASlumNet enhances the IoU by 10.97% compared to FuseNet, a model that combines optical bands and geo-scientific features. Our method presents a new technical solution to achieve accurate slum mapping, offering potential benefits for regional and global slum mapping and upgrading initiatives.

Multi-Frame Content-Aware Mapping Network for Standard-Dynamic-Range to High-Dynamic-Range Television Artifact Removal.

Recently, advancements in image sensor technology have paved the way for the proliferation of high-dynamic-range television (HDRTV). Consequently, there has been a surge in demand for the conversion of standard-dynamic-range television (SDRTV) to HDRTV, especially due to the dearth of native HDRTV content. However, since SDRTV often comes with video encoding artifacts, SDRTV to HDRTV conversion often amplifies these encoding artifacts, thereby reducing the visual quality of the output video. To solve this problem, this paper proposes a multi-frame content-aware mapping network (MCMN), aiming to improve the performance of conversion from low-quality SDRTV to high-quality HDRTV. Specifically, we utilize the temporal spatial characteristics of videos to design a content-aware temporal spatial alignment module for the initial alignment of video features. In the feature prior extraction stage, we innovatively propose a hybrid prior extraction module, including cross-temporal priors, local spatial priors, and global spatial prior extraction. Finally, we design a temporal spatial transformation module to generate an improved tone mapping result. From time to space, from local to global, our method makes full use of multi-frame information to perform inverse tone mapping of single-frame images, while it is also able to better repair coding artifacts.

TDKI-Net: A Joint q-t Space Learning Network for Diffusion-Time-Dependent Kurtosis Imaging.

Time-dependent diffusion magnetic resonance imaging (TDDMRI) is useful for the non-invasive characterization of tissue microstructure. These models require both densely sampled q-t space data for microstructural fitting, leading to very time-consuming acquisition protocols. To overcome this problem, we present a joint q-t space model-tDKI-Net to estimate diffusion-time dependent kurtosis and the transmembrane exchange, using downsampled q-t space data. The tDKI-Net is composed of several q-Encoders and a t-Encoder, designed based on the extragradient mechanism, each integrated with their respective mapping networks. In the tDKI-Net, two types of encoders along with their mapping networks are employed sequentially to generate kurtosis at individual diffusion times and to fit the transmembrane exchange time ( τm) using the time-dependent kurtosis according the Kärger's model. Meanwhile, we proposed a three-stage training strategy, including physics-informed self-supervised pretraining, DKI warm-up, and joint training, to match the network structure. Our results demonstrated that the proposed tDKI-Net could effectively accelerate tDKI scans, resulting in lower estimation error compared with other methods. Our proposed three-stage training strategy demonstrated superior results than those training from scratch, e.g., the normalized root mean square error (NRMSE) of τm decreased by up to 1.4%. We also investigated the training data size effects and found that although we used one-subject training, the network achieved lower NRMSEs for Kavg, K0 and τm (2.50%, 3.04%, 10.86%) than previous work that used three-subject training (3.8%, 9.5%, 12.1%). tDKI-Net can considerably reduce the scan time by 10.5- fold by joint downsampling the q-t space data without compromising the estimation accuracy.

Physics-Guided Neural Networks for Intraventricular Vector Flow Mapping.

Intraventricular vector flow mapping (iVFM) seeks to enhance and quantify color Doppler in cardiac imaging. In this study, we propose novel alternatives to the traditional iVFM optimization scheme by utilizing physics-informed neural networks (PINNs) and a physics-guided nnU-Net-based supervised approach. When evaluated on simulated color Doppler images derived from a patient-specific computational fluid dynamics model and in vivo Doppler acquisitions, both approaches demonstrate comparable reconstruction performance to the original iVFM algorithm. The efficiency of PINNs is boosted through dual-stage optimization and pre-optimized weights. On the other hand, the nnU-Net method excels in generalizability and real-time capabilities. Notably, nnU-Net shows superior robustness on sparse and truncated Doppler data while maintaining independence from explicit boundary conditions. Overall, our results highlight the effectiveness of these methods in reconstructing intraventricular vector blood flow. The study also suggests potential applications of PINNs in ultrafast color Doppler imaging and the incorporation of fluid dynamics equations to derive biomarkers for cardiovascular diseases based on blood flow.

Bayesian Joint Adaptation Network for Crop Mapping in the Absence of Mapping Year Ground-truth Samples

Bayesian Joint Adaptation Network for Crop Mapping in the Absence of Mapping Year Ground-truth Samples

An Evaluation of Convolutional Neural Networks for Lithological Mapping Based on Hyperspectral Images

An Evaluation of Convolutional Neural Networks for Lithological Mapping Based on Hyperspectral Images