Dimensional Network Research Articles

Restoration of magnetohydrodynamic-corrupted 12-lead electrocardiogram to enhance cardiac monitoring during magnetic resonance imaging

The Magnetohydrodynamic (MHD) effect on the bloodstream, induced by the static magnetic field of Magnetic Resonance Imaging (MRI) devices, distorts Electrocardiogram (ECG) components, and poses challenges to cardiac gating and monitoring during MRI examinations. Restoring ECG components from MHD-induced artifacts has always been a challenge, primarily due to the influence of numerous device-induced and physiological variables and the absence of paired ground truth clean ECG for validation. In this research, at first, we employ unpaired restoration of MHD-corrupted 12-lead ECG signals using one dimensional (1D) Cycle Generative Adversarial Networks (CycleGANs) for channel and patient orientation-specific restoration. Subsequently, a 1D-segmentation-based comprehensive restoration scheme is proposed based on the phase 1 outputs to simultaneously restore 12-channel ECG signals, irrespective of internal and external factors affecting ECG. By employing the proposed Magnetohydrodynamic Generative Adversarial Network (MHDGAN) and MHD-to-ECG Network (MHD2ECGNet) for unpaired and comprehensive restoration, we achieved an overall spectral correlation improvement of 92.56% and 77.64%, respectively. In R-peak detection, MHDGAN demonstrated an overall precision, recall, and F1-score of 98.14%, 94.12%, and 96.01%, respectively. The extracted heart rate (HR) and heart rate variability (HRV) from the restored waveforms closely match the ground truth, as confirmed through quantitative and qualitative assessments. The proposed framework has proven effective in restoring MHD-corrupted ECG waveforms, even in the absence of paired ground truth labels and amidst compounding distortions from multiple sources.

Visualizing the Influence of Social Networks on Recovery: A Mixed-Methods Social Identity Mapping Study with Recovering Adolescents

Background: Social recovery capital (SRC) refers to resources and supports gained through relationships and is vital to adolescent addiction recovery. Much is known about how substance use relates to social networks, but little is known about how other dimensions of social networks influence recovery (e.g., network size/exposure, degree of conflict). Methods: This mixed-methods study sampled 28 adolescents who received treatment for alcohol and other drug (AOD) use disorder (14–19 yrs.: 71% male; M = 17.32 yrs., SD = 1.33; White 82%): 20 were recovery high school (RHS) students. Adolescents completed a social identity map for addiction recovery (SIM-AR), survey, and interview. Qualitative data were content analyzed and the data from the SIM-AR were quantified. Results: On average, participants reported belonging to five distinct groups within their network (Range, 2–9; SD = 1.63; M = 27.89 people, SD = 20.09). Of their social network connections, 51% drank alcohol and 46% used other substances, on average. Larger networks involved more conflict (r = 0.57). Participants were more likely to spend more time with groups that had greater proportions of non-substance-using members. These linkages were stronger for RHS than for non-RHS students. Qualitative analyses revealed that youth reported their recovery-oriented groups as supportive, but some reported that their substance-using friends also supported their recovery. Discussion: SIM-AR was a useful measurement tool, and, through qualitative interviews, we identified unique aspects of youths’ social networks important for further examination. Research with recovering youth should examine SRC-related elements within their networks including relationship quality, belonging, and conflict, alongside the substance use behaviors of network members.

Multi-perspective option price forecasting combining parametric and non-parametric pricing models with a new dynamic ensemble framework

This article introduces a dynamic ensemble framework that integrates parametric and non-parametric pricing models. Within this framework, we propose a time-varying parametric pricing model optimized using artificial intelligence algorithms. Additionally, we construct a non-parametric pricing model using a 2-dimensional convolutional neural network (2D-CNN) to capture the interactions among options, enhancing the existing non-parametric pricing model. Validation using China's SSE 50 ETF options trading data reveals several key findings: Firstly, the dynamic integration method proposed in this study not only improves prediction accuracy but also enhances stability. Secondly, previous parametric pricing models do not effectively utilize their pricing performance, while our proposed time-varying parametric pricing model significantly enhances accuracy. Lastly, the 2D-CNN model, which considers interactions among options trades, proves to be reasonable and effective, outperforming common non-parametric pricing models. The dynamic ensemble framework proposed in this study effectively combines the strengths of both parametric and non-parametric pricing models. This research serves as an important reference for risk managers, institutional investors, and other stakeholders. Furthermore, it provides valuable research ideas for future scholars in the field.

Graphene-Based Hydrogels for Controlled Drug Delivery: Opportunities and Challenges

Abstract: Graphene is a remarkable substance that has revolutionized numerous disciplines, including electronics, materials science, condensed physics, quantum physics, energy systems, and many more. Its physical and chemical properties have been the subject of a great deal of research since its 2004 discovery. Because of its unique properties, it has swiftly become a contender worth investigating for biomedical uses by nano-bio researchers. Studies on graphene and related materials have attracted a great deal of interest from the biomedical community in the last decade, with a focus on their potential applications in cancer treatment, smart drug delivery, and gene therapy. Graphene oxide (GO) has many desirable properties, including a high adsorption capacity, a big surface area, biocompatibility, and colloidal stability. To get around the problems with traditional treatment methods, researchers have been working on new drug delivery systems that include biocompatible polymers as nanocomposite carriers, a three- -dimensional (3D) hydrogel network, and controlled medication release. In this review, we compiled the latest findings from graphene's biomedical uses, took a look at the latest innovations in graphene-based hydrogels for medication delivery, and offered some exciting predictions for the future of this material's function in this field.

A hybrid 1D CNN-BiLSTM model for epileptic seizure detection using multichannel EEG feature fusion

Epilepsy, a chronic non-communicable disease is characterized by repeated unprovoked seizures, which are transient episodes of abnormal electrical activity in the brain. While Electroencephalography (EEG) is considered as the gold standard for diagnosis in current clinical practice, manual inspection of EEG is time consuming and biased. This paper presents a novel hybrid 1D CNN-Bi LSTM feature fusion model for automatically detecting seizures. The proposed model leverages spatial features extracted by one dimensional convolutional neural network and temporal features extracted by bi directional long short-term memory network. Ictal and inter ictal data is first acquired from the long multichannel EEG record. The acquired data is segmented and labelled using small fixed windows. Signal features are then extracted from the segments concurrently by the parallel combination of CNN and Bi-LSTM. The spatial and temporal features thus captured are then fused to enhance classification accuracy of model. The approach is validated using benchmark CHB-MIT dataset and 5-fold cross validation which resulted in an average accuracy of 95.90%, with precision 94.78%, F1 score 95.95%. Notably model achieved average sensitivity of 97.18% with false positivity rate at 0.05/hr. The significantly lower false positivity and false negativity rates indicate that the proposed model is a promising tool for detecting seizures in epilepsy patients. The employed parallel path network benefits from memory function of Bi-LSTM and strong feature extraction capabilities of CNN. Moreover, eliminating the need for any domain transformation or additional preprocessing steps, model effectively reduces complexity and enhances efficiency, making it suitable for use by clinicians during the epilepsy diagnostic process.

Automated evaluation of hip abductor muscle quality and size in hip osteoarthritis: Localized muscle regions are strongly associated with overall muscle quality

Limited information exists regarding abductor muscle quality variation across its length and which locations are most representative of overall muscle quality. This is exacerbated by time-intensive processes for manual muscle segmentation, which limits feasibility of large cohort analyses. The purpose of this study was to develop an automated and localized analysis pipeline that accurately estimates hip abductor muscle quality and size in individuals with mild-to-moderate hip osteoarthritis (OA) and identifies regions of each muscle which provide best estimates of overall muscle quality.Forty-four participants (age 52.7 ± 16.1 years, BMI 23.7 ± 3.4 kg/m2, 14 males) with and without mild-to-moderate radiographic hip OA were recruited for this study. Unilateral hip magnetic resonance (MR) images were acquired on a 3.0 T MR scanner and included axial T1-weighted fast spin echo and 3D axial Iterative Decomposition of water and fat with Echo Asymmetry and Least-squares estimation (IDEAL-IQ) spoiled gradient-recalled echo (SPGR) with multi-peak fat spectrum modeling and single T2* correction. A three dimensional (3D) V-Net convolutional neural network was trained to automatically segment the gluteus medius (GMED), gluteus minimus (GMIN), and tensor fascia lata (TFL) on axial IDEAL-IQ. Agreement between manual and automatic segmentation and associations between axial fat fraction (FF) estimated from IDEAL-IQ and overall muscle FF were evaluated.Dice scores for automatic segmentation were 0.94, 0.87, and 0.91 for GMED, GMIN, and TFL, respectively. GMED, GMIN, and TFL volumetric and FF measures were strongly correlated (r: 0.92–0.99) between automatic and manual segmentations, where all values fell within the 95% limits of agreement of [−9.79 cm3, 17.43 cm3] and [−1.99%, 2.89%], respectively. Axial FF was significantly associated with overall FF with the strongest correlations at 50%, 50%, and 65% the length of the GMED, GMIN, and TFL muscles, respectively (r: 0.93–0.97). An automated and localized analysis can provide efficient and accurate estimates of hip abductor muscle quality and size across muscle length. Specific regions of the muscle may be used to estimate overall muscle quality in an abbreviated evaluation of muscle quality.

Improved stochastic configuration networks with vision patch fusion method for industrial image classification

This paper contributes to the advancement of stochastic configuration neural networks (SCN) in the field of visual applications. The proposed image classification randomized algorithm is an extension of deep stochastic configuration networks (DeepSCN), known as an improved SCN with vision patch fusion (Vi-SCN). Compared to existing two dimensional stochastic configuration networks (2DSCN) and DeepSCN, we have developed an incremental modeling method that employs a stochastic configuration patch fusion method. This method extracts randomly fused image features from three-channel high-resolution image data, improving the network's ability to extract features. Moreover, we have introduced a strategy for dynamically determining the depth structure of the network, enabling flexible adjustments to the network structure and the number of nodes in each layer based on the complexity of image recognition tasks. Through a series of comparisons on four image classification benchmark datasets, we assess the superior learning performance of our design compared to 2DSCN and DeepSCN. Furthermore, to evaluate the performance of Vi-SCN in practical visual application scenarios, we collect three industrial datasets with distinct characteristics. Vi-SCN demonstrate outstanding performance in all three tasks, showing its significant potential in image recognition.

Deep Learning for Automated Measurement of Total Cardiac Volume for Heart Transplantation Size Matching.

Total Cardiac Volume (TCV)-based size matching using Computed Tomography (CT) is a novel technique to compare donor and recipient heart size in pediatric heart transplant that may increase overall utilization of available grafts. TCV requires manual segmentation, which limits its widespread use due to time and specialized software and training needed for segmentation. This study aims to determine the accuracy of a Deep Learning (DL) approach using 3-dimensional Convolutional Neural Networks (3D-CNN) to calculate TCV, with the clinical aim of enabling fast and accurate TCV use at all transplant centers. Ground truth TCV was segmented on CT scans of subjects aged 0-30years, identified retrospectively. Ground truth segmentation masks were used to train and test a custom 3D-CNN model consisting of a DenseNet architecture in combination with residual blocks of ResNet architecture. The model was trained on a cohort of 270 subjects and a validation cohort of 44 subjects (36 normal, 8 heart disease retained for model testing). The average Dice similarity coefficient of the validation cohort was 0.94 ± 0.03 (range 0.84-0.97). The mean absolute percent error of TCV estimation was 5.5%. There is no significant association between model accuracy and subject age, weight, or height. DL-TCV was on average more accurate for normal hearts than those listed for transplant (mean absolute percent error 4.5 ± 3.9 vs. 10.5 ± 8.5, p = 0.08). A deep learning-based 3D-CNN model can provide accurate automatic measurement of TCV from CT images. This initial study is limited as a single-center study, though future multicenter studies may enable generalizable and more accurate TCV measurement by inclusion of more diverse cardiac pathology and increasing the training data.

Review of High Dimensional Neural Network Potentials

Over the past few years, machine learning potentials (MLPs) have been fully developed and can now be applied to a variety of large-scale atomic simulations. MLPs encompass a number of different machine learning algorithms, of which neural network potentials are the most dominant and representative, and have achieved great success. This review focuses on the second generation of neural network potentials, high-dimensional neural network potentials (HDNNPs). While HDNNP has accomplished noteworthy results in the implementation of ion diffusion, nuclear magnetic resonance parameters, defect formation, and thermal conductivity, it still encounters hurdles in the compilation of training datasets, transferability, accuracy constraints, and the management of multiple chemical species. In spite of this, HDNNP remains a highly promising methodology. Looking forward, we anticipate the development of more specialized software for HDNNP to augment research efficiency and lower the barrier to usage.

A New Model of the Limited Availability Group with Priorities for Multi-Service Networks

In this article, a new analytical model is proposed for a limited-availability group serving a mixture of multiservice BPP (Binomial, Poisson, Pascal) traffic. The model assumes that the different traffic classes belonging to this traffic mixture have priorities that affect their ability to be served. The model includes for the first time the possibility of handling priority traffic through a limited availability group and assumes the possibility of handling priority BPP traffic. The proposed model has been subjected to a number of investigations in which a number of different BPP traffic classes and a number of different priority arrangements have been considered. In this article, the authors present exemplary results of the numerical experiments that illustrate the possible applications of this model to analyze links in a multiservice network. The presented computational results were also compared with the results of simulation experiments, which confirmed the satisfactory accuracy of the proposed model. This allows the model to be easily applied in practice for modeling, analysis, and dimensioning of modern multiservice networks, such as cellular or elastic optical networks.

Study on the impact of social capital on the rural residents’ conscious interpersonal waste separation behavior: evidence from Jiangxi province, China

Guiding rural residents to implement interpersonal waste separation in their daily lives consciously is crucial for controlling solid waste pollution in developing countries. This paper utilizes survey data from Jiangxi Province which is one of the national pilot zones for ecological conservation in China to analyze the impact of the social capital that includes social networks, social trust, and social norms on the rural residents’ conscious interpersonal waste separation behavior. The empirical results indicate that social capital has a positive effect on the rural residents’ conscious interpersonal waste separation behavior, wherein the effects of social networks and social trust are significant. Among the three dimensions of social capital, social networks and social norms are substitutable, while social trust and social norms have a complementary effect on each other. Moreover, the ecological cognition and subjective norm play a significant mediating role in the relationship between social network, social trust, and social norms and the rural residents’ conscious interpersonal waste separation behavior, while the government policies plays a significant moderating effect.

Multichannel consecutive data cross-extraction with 1DCNN-attention for diagnosis of power transformer

Power transformer plays a critical role in grid infrastructure, and its diagnosis is paramount for maintaining stable operation. However, the current methods for transformer diagnosis focus on discrete dissolved gas analysis, neglecting deep feature extraction of multichannel consecutive data. The unutilized sequential data contains the significant temporal information reflecting the transformer condition. In light of this, the structure of multichannel consecutive data cross-extraction (MCDC) is proposed in this article in order to comprehensively exploit the intrinsic characteristic and evaluate the states of transformer. Moreover, for the better accommodation in scenario of transformer diagnosis, one dimensional convolution neural network attention (1DCNN-attention) mechanism is introduced and offers a more efficient solution given the simplified spatial complexity. Finally, the effectiveness of MCDC and the superior generalization ability, compared with other algorithms, are validated in experiments conducted on a dataset collected from real operation cases of power transformer. Additionally, the better stability of 1DCNN-attention has also been certified.

Average trapping time on horizontally divided 3-dimensional 3-level Sierpinski gasket network

An important characteristic of random wandering is the average trapping time, which is a hot issue in current research. The average trapping time is an important measure of the transmission efficiency of random wandering in a network. In this paper, we construct a 3-dimensional 3-level Sierpinski gasket network divided horizontally by the horizontal division plane P s , that is, the division coefficients s. We study the capture problem on the network and obtain an analytical expression for the average trapping time (ATT). Then, by adjusting the number of iterations and the values of the division coefficients, we obtained the relationship between ATT and them. As can be seen from our numerical simulation plots, ATT is affected by s. The larger s is, the more the self-similar structure of the three-dimensional residual network gradually transforms towards the structure of the two-dimensional complete Sierpinski gasket network. Meanwhile, the shorter ATT is, that is, the more efficient the transmission on the network.

Overcoming the strength-ductility tradeoff of a 3D-printed Al-Si alloy by equal channel angular pressing

The integration of additive manufacturing and severe plastic deformation has produced an Al-Si alloy with superior mechanical properties. The novel processing pathway effectively avoids strength-ductility trade-off, resulting in an elongation increase of three times while maintaining a comparable yield strength to that of the original condition. The implementation of an intermediate annealing heat treatment (HT) before the subsequent equal channel angular pressing (ECAP) processing resulted in the most favorable combinations of strength and ductility. The ECAP process transformed the ultrafine interconnected eutectic network into ultrafine particles. This process also led to the formation of a heterogeneous grain size and the transformation of the 3-dimensional network of aluminides (Al2Cu) and Si-enriched precipitates into particles with varying sizes, ranging from 4 nm to 500 nm. In contrast, the ECAP processing without an intermediate annealing heat treatment led to a maximum yield strength increment of 22%. Notably, this enhancement in strength was achieved while preserving comparable levels of elongation to those observed in the as-built material. Hence, achieving the optimal combination of yield strength and ductility ratio demands a careful balance between various strengthening mechanisms, including subgrains and precipitates.

Acoustic data detection in large-scale emergency vehicle sirens and road noise dataset

This paper presents a novel deep learning model called Self-Attention Layer within a Convolutional Neural Network (SACNN), specifically designed for detecting acoustic data in extensive datasets containing emergency vehicle sirens and road noise. SACNN leverages a combination of EfficientNet and One Dimensional Convolutional Neural Networks (1D_CNN) to improve the precision and efficiency of detection. The dataset comprises 3-second WAV-format audio files categorized into Emergency Vehicles (Ambulance and Firetruck sirens) and Traffic (plain traffic sounds), with each category having 200 sound files and their corresponding 200 spectrogram images per audio file. Experimental results demonstrate SACNN's superior performance across various metrics, including accuracy, precision, recall, and F1 score, while also achieving notable advancements in computational efficiency. The research addresses the need for more effective solutions in the domain of emergency vehicle siren and road noise detection by introducing SACNN as a cutting-edge solution. By integrating EfficientNet and 1D_CNN, SACNN surpasses existing models in accuracy and computational efficiency. Comparative analysis with EfficientNet and 1D_CNN using a large-scale dataset validates SACNN's superior performance, with an average accuracy, precision, recall, and F1 score of 1.00. Additionally, SACNN exhibits the highest computational efficiency, averaging 0.20883 s per sample. These findings highlight SACNN's efficacy in detecting and classifying emergency vehicle sirens and road noise in large-scale datasets, with implications for traffic management, public safety, and noise pollution monitoring. SACNN offers the potential for constructing real-time acoustic data detection systems.

Graphite surface modification by quasi-periodically structured diazonium monolayer

In this study, a novel functionalization protocol of highly oriented pyrolytic graphite (HOPG) was proposed, in which a two dimensional (2D) porous network formed by alkoxy-substituted dehydrobenzo[12]annulene (DBA-OC12) was served as a sacrificial template for electrografting of 3,5-terbutyl diazonium (3,5-TBD). The 2D DBA-OC12 porous network was synthesized by drop-casting of the corresponding precursor followed by a drying process. The structural and electrochemical properties of pristine as well as functionalized HOPG surfaces were investigated by means of cyclic voltammetry (CV) and scanning tunneling microscopy (STM).

Enhancing Stability and Efficiency of Inverted Inorganic Perovskite Solar Cells with In-Situ Interfacial Cross-Linked Modifier.

Inverted inorganic perovskite solar cells (PSCs) is potential as the top cells in tandem configurations, owing to the ideal bandgap, good thermal and light stability of inorganic perovskites. However, challenges such as mismatch of energy levels between charge transport layer and perovskite, significant non-radiative recombination caused by surface defects, and poor water stability have led to the urgent need for further improvement in the performance of inverted inorganic PSCs. Herein, the fabrication of efficient and stable CsPbI3-x Brx PSCs through surface treatment of (3-mercaptopropyl) trimethoxysilane (MPTS), is reported. The silane groups in MPTS can in situ crosslink in the presence of moisture to build a 3-dimensional (3D) network by Si-O-Si bonds, which forms a hydrophobic layer on perovskite surface to inhibit water invasion. Additionally, -SH can strongly interact with the undercoordinated Pb2+ at the perovskite surface, effectively minimizing interfacial charge recombination. Consequently, the efficiency of the inverted inorganic PSCs improves dramatically from 19.0% to 21.0% under 100mW cm-2 illumination with MPTS treatment. Remarkably, perovskite films with crosslinked MPTS exhibit superior stability when soaking in water. The optimized PSC maintains 91% of its initial efficiency after aging 1000 h in ambient atmosphere, and 86% in 800 h of operational stability testing.

EXPERIMENTING TIN DATA STRUCTURE FOR REPRESENTING PLANE SURFACE AND SUBSURFACE SPATIAL OBJECTS - PRELIMINARY WORK

Abstract. Understanding and analyzing complex spatial objects involves the integration of surface, terrain, and subsurface data into 3D spatial models. However, describing and efficiently analyzing the connections between these data model is particularly challenging. This study aims to generate TIN data structure that enable the 3D representation of surface terrain subsurface integration. Furthermore, to ensure accurate representation within a unified 3D model, spatial relationships between the TIN data model could be obtained. Consequently, three – dimensional Triangular Irregular Networks (3D TIN) mesh of spatial objects representations and indexing structures were created. The integration of spatial objects, encompassing surface, terrain, and subsurface elements, is realized through a unified model. This synergy is achieved by combining the distinct 2D and 3D topology structures of each component. The resulting comprehensive model captures the intricate relationships and interactions within the spatial environment. This study provides additional insight into the representation and analysis of surface, terrain, and subsurface management in 3D spatial models. Hence, better decision making, resource management, underground utility installations, and evaluation of spatial objects will be made possible in our future work.

Distance-Based Fractional Dimension of Certain Wheel Networks

Distance-Based Fractional Dimension of Certain Wheel Networks

High-spatial resolution ground-level ozone in Yunnan, China: A spatiotemporal estimation based on comparative analyses of machine learning models

Monitoring ground-level ozone concentrations is a critical aspect of atmospheric environmental studies. Given the existing limitations of satellite data products, especially the lack of ground-level ozone characterization, and the discontinuity of ground observations, there is a pressing need for high-precision models to simulate ground-level ozone to assess surface ozone pollution. In this study, we have compared several widely utilized ensemble learning and deep learning methods for ground-level ozone simulation. Furthermore, we have thoroughly contrasted the temporal and spatial generalization performances of the ensemble learning and deep learning models. The 3-Dimensional Convolutional Neural Network (3-D CNN) model has emerged as the optimal choice for evaluating the daily maximum 8-h average ozone in Yunnan Province. The model has good performance: a spatial resolution of 0.05° × 0.05° and strong predictive power, as indicated by a Coefficient of Determination (R2) of 0.83 and a Root Mean Square Error (RMSE) of 12.54 μg/m³ in sample-based 5-fold cross-validation (CV).In the final stage of our study, we applied the 3-D CNN model to generate a comprehensive daily maximum 8-h average ozone dataset for Yunnan Province for the year 2021. This application has furnished us with a crucial high-resolution and highly accurate dataset for further in-depth studies on the issue of ozone pollution in Yunnan Province.