Multiple Networks Research Articles

Citric acid/sucrose-modified pMDI for constructing high-performance straw particleboard based on multiple cross-linked networks

Polymeric diphenylmethane diisocyanate (pMDI) is an indispensable material used to produce straw particleboard. However, prolonged exposure to high concentrations of pMDI significantly increases the health risks to relevant professionals. Herein, we report a strategy for reducing safety hazards by partially replacing the pMDI with a bio-based adhesive. An adhesive with multiple cross-linked networks were synthesized using citric acid (CA), sucrose (SU), and pMDI first, and then applied to the preparation of straw particleboard. The amide and esterification reactions between the adhesives and rice straw particles form covalent bonds, enhancing boards adhesion and water resistance. Furthermore, acidic conditions provided by citric acid facilitate to convert SU into 5-hydroxymethyl furfural (5-HMF), which plays a positive role in straw adhesion. Adhesives made with 2.4 % pMDI, 8 %, and 4.8 % SU were used to bond particleboard, achieving internal bond strength, bending strength and elastic modulus of 0.57 MPa, 25.87 MPa, and 3.77 GPa, respectively, whose mechanical properties are comparable to the particleboard prepared with 4 % pMDI. The board showed superb mechanical performances, mould resistance, as well as water resistance. The CA/SU-modified pMDI adhesive system shows significant potential and promising application value in straw particleboard.

Multimorbidity in neurodegenerative diseases: a network analysis

ABSTRACT The socioeconomic costs of neurodegenerative diseases (NDs) are highly affected by comorbidities. This study aims to enhance our understanding of the prevalent complications of NDs through the lens of network analysis. A multimorbidity network (MN) was constructed based on a longitudinal EHR dataset of 93,647,498 diagnoses of 824,847 patients. The association between the conditions was measured by two metrics, i.e. Phi-correlation and Cosine Index (CI). Based on multiple network centrality measures, a fused ranking list of the prevalent multimorbidities was provided. Finally, class-level networks depicting the prevalence and strength of diseases in different classes were constructed. The general MN included 928 diseases and 337,253 associations. Considering a 99% confidence level, two networks of 575 relationships were constructed based on Phi-correlations (73 diseases) and CI (102 diseases). Five out of 19 ICD-9 categories did not appear in either of the networks. Also, ND’s immediate MNs for the top 50% of the significant associations included 42 relationships, whereas the Phi-correlation and CI networks included 36 and 34 diseases, respectively. Thirteen diseases were identified as the most notable multimorbidities based on various centrality measures. The analysis framework helps practitioners toward better resource allocations, more effective preventive screenings, and improved quality of life for ND patients and caregivers.

Investigation of Bird Sound Transformer Modeling and Recognition

Birds play a pivotal role in ecosystem and biodiversity research, and accurate bird identification contributes to the monitoring of biodiversity, understanding of ecosystem functionality, and development of effective conservation strategies. Current methods for bird sound recognition often involve processing bird songs into various acoustic features or fusion features for identification, which can result in information loss and complicate the recognition process. At the same time, the recognition method based on raw bird audio has not received widespread attention. Therefore, this study proposes a bird sound recognition method that utilizes multiple one-dimensional convolutional neural networks to directly learn feature representations from raw audio data, simplifying the feature extraction process. We also apply positional embedding convolution and multiple Transformer modules to enhance feature processing and improve accuracy. Additionally, we introduce a trainable weight array to control the importance of each Transformer module for better generalization of the model. Experimental results demonstrate our model’s effectiveness, with an accuracy rate of 99.58% for the public dataset Birds_data, as well as 98.77% for the Birdsonund1 dataset, and 99.03% for the UrbanSound8K environment sound dataset.

A novel reinforcement learning agent for rotating machinery fault diagnosis with data augmentation

The problem of data imbalance and limited sample poses a prominent challenge to fault diagnosis in industry, especially in rotating machinery fault diagnosis due to the constraints of sampling and labeling. Reinforcement learning is known for its auto-optimized learning ability but it is severely limited by the quality and quantity of data it is able to collect. This paper applies the Equilibrium Deep Q-Network (Equilibrium-DQN) based agent with the Variational Autoencoder with Wasserstein Generative Adversarial Network and Gradient Penalty (VAE-WGAN-GP) for rotating machinery fault diagnosis. The Equilibrium-DQN possesses the property of leveraging multiple target networks to improve training stability and accuracy. The VAE-WGAN-GP excels in resolving data scarcity problems in fault diagnosis, especially in enriching labeled data with more typical samples while keeping the original data features. Herein, a novel framework is presented that integrates both data augmentation techniques with reinforcement learning agent for fault diagnosis. The proposed framework improves the weakness of insufficient samples in fault diagnosis and reveals its potential in complex industrial applications. The experiments, both on the test bench dataset and on the real locomotive dataset, confirm the advantage of the proposed framework.

Generating Artistic Images Through Neural Style Transfer Using Machine Learning and Image Manipulation Techniques

Neural Style Transfer (NST) is a computational technique that merges the content of one image with the stylistic characteristics of another, creating visually appealing compositions. Leveraging deep learning and image processing, this method separates andcombines the content and style of input images using convolutional neural networks (CNNs). The content representation of an image is captured by the high-level features extracted from a pre-trained CNN, while its style is characterized by the statistical correlations of features at multiple network layers. It explores the fusion of machine learning and image processing techniques in NST. Initially introduced by Gatys et al., NST has gained popularity due to its ability to generate artistic renditions and novel visualizations. The process involves extracting content and style features from separate images and optimizing a generated image to minimize differences in content and style representations. In this work, explored into the underlying concepts and technical aspectsof NST. This proceedings discussed the utilization of pre-trained CNN models like VGG19 or ResNet for feature extraction and how optimization algorithms, such as gradient descent, iteratively refine the generated image to achieve a fusion of content and style. Additionally, This development has been examined the impact of hyper parameters and layer choices on the quality of stylized outputs.Mainly this technology focuses on reduction of total variation loss, which we incur during the style transfer.These proceedings has carried on work with VGG19, XCEPTION, EfficientnetB7. These findings show how Convolutional Neural Networks can learn deep image representations and show how they may be used for sophisticated image synthesis andmodification.

Multiple network embedding for anomaly detection in time series of graphs

The problem of anomaly detection in time series of graphs is considered, focusing on two related inference tasks: the detection of anomalous graphs within a time series and the detection of temporally anomalous vertices. These tasks are approached via the adaptation of multiple adjacency spectral embedding (MASE), a statistically principled method for joint graph inference. The effectiveness of the method is demonstrated for these inference tasks, and its performance is assessed based on the nature of detectable anomalies. Theoretical justification is provided, along with insights into its use. The approach identifies anomalous vertices beyond just large degree changes when applied to the Enron communication graph, a large-scale commercial search engine time series, and a larval Drosophila connectome.

A Next-Generation Combinatorial Genomic Strategy Scans Genomic Loci Governing Heat Stress Tolerance in Chickpea.

In the wake of rising earth temperature, chickpea crop production is haunted by the productivity crisis. Chickpea, a cool season legume manifests tolerance in several agro-physiological level, which is complex quantitative in nature, and regulated by multiple genes and genetic networks. Understanding the molecular genetic basis of this tolerance and identifying key regulators can leverage chickpea breeding against heat stress. This study employed a genomics-assisted breeding strategy utilizing multi-locus GWAS to identify 10 key genomic regions linked to traits contributing to heat stress tolerance in chickpea. These loci subsequently delineated few key candidates and hub regulatory genes, such as RAD23b, CIPK25, AAE19, CK1 and WRKY40, through integrated genomics, transcriptomics and interactive analyses. The differential transcript accumulation of these identified candidates in contrasting chickpea accessions suggests their potential role in heat stress tolerance. Differential ROS accumulation along with their scavengers' transcript abundance aligning with the expression of identified candidates in the contrasting chickpea accessions persuade their regulatory significance. Additionally, their functional significance is ascertained by heterologous expression and subsequent heat stress screening. The high confidence genomic loci and the superior genes and natural alleles delineated here has great potential for swift genomic interventions to enhance heat resilience and yield stability in chickpea.

A Lightweight Method for Breast Cancer Detection Using Thermography Images with Optimized CNN Feature and Efficient Classification.

Breast cancer is a prominent cause of death among women worldwide. Infrared thermography, due to its cost-effectiveness and non-ionizing radiation, has emerged as a promising tool for early breast cancer diagnosis. This article presents a hybrid model approach for breast cancer detection using thermography images, designed to process and classify these images into healthy or cancerous categories, thus supporting disease diagnosis. Multiple pre-trained convolutional neural networks are employed for image feature extraction, and feature filter methods are proposed for feature selection, with diverse classifiers utilized for image classification. Evaluating the DRM-IR test set revealed that the combination of ResNet34, Chi-square ( ) filter, and SVM classifier demonstrated superior performance, achieving the highest accuracy at . Furthermore, the highest accuracy improvement obtained was when using the SVM classifier and Chi-square filter compared to regular convolutional neural networks. The results confirmed that the proposed method, with its high accuracy and lightweight model, outperforms state-of-the-art breast cancer detection from thermography image methods, making it a good choice for computer-aided diagnosis.

Highly sensitive and structure stable polyvinyl alcohol hydrogel sensor with tailored free water fraction and multiple networks by reinforcement of conductive nanocellulose.

The wearable composite hydrogel sensors with high stretchability have attracted much attention in recent years, while the traditional hydrogels have weak molecular (chain) interaction and contain a lot of free water, leading to poor mechanical properties, unstable environmental tolerance and sensing ability. Herein, a novel ice crystal extrusion-crosslinking strategy is used to obtain polyvinyl alcohol (PVA) hydrogel with conductive nanocellulose-poly (3,4-ethylenedioxythiophene) (CNC-PEDOT) as skeleton network, sodium alginate (SA) and Ca2+ as tough segment of multi-bonding network. This strategy synergistically enhanced the interaction of hydrogen bonds and calcium (Ca2+) ion chelation within the hydrogel, building highly sensitive and stable multiple tough-elastic networks. Therefore, the optimal hydrogel sensor (PVA/SA-CP45) shows good structural stability, robust mechanical performance, excellent compress (Sensitivity=68.7), stretching sensitivity (Gauge factor=4.16), ultra-wide application range (-105-60°C), fast response/relaxation time and outstanding dynamic durability with 6000 stretching-releasing cycles. Especially, it can give good sensing performance for omnidirectional monitoring of human motion and weak signals. Moreover, it was also designed into multifunctional sensing systems for gait guidance of model training and real-time monitoring ammonia gas for food preservation and public environmental safety, demonstrating great potential in flexible sensors devices for health monitoring.

Community Detection for Heterogeneous Multiple Social Networks

Community Detection for Heterogeneous Multiple Social Networks

A Probabilistic Descent Ensemble for Malware Prediction Using Deep Learning

INTRODUCTION: Introducing a Probabilistic Descent Ensemble (PDE) approach for enhancing malware prediction through deep learning leverages the power of multiple neural network models with distinct architectures and training strategies to achieve superior accuracy while minimizing false positives. OBJECTIVES: Combining Stochastic Gradient Descent (SGD) with early stopping is a potent approach to optimising deep learning model training. Early stopping, a vital component, monitors a validation metric and halts training if it stops improving or degrades, guarding against overfitting. METHODS: This synergy between SGD and early stopping creates a dynamic framework for achieving optimal model performance adaptable to diverse tasks and datasets, with potential benefits including reduced training time and enhanced generalization capabilities. RESULTS: The proposed work involves training a Gaussian NB classifier with SGD as the optimization algorithm. Gaussian NB is a probabilistic classifier that assumes the features follow a Gaussian (normal) distribution. SGD is an optimization algorithm that iteratively updates model parameters to minimize a loss function. CONCLUSION: The proposed work gives an accuracy of 99% in malware prediction and is free from overfitting and local minima.

Development of an evaluation method for addictive compounds based on electrical activity of human iPS cell-derived dopaminergic neurons using microelectrode array.

Addiction is known to occur through the consumption of substances such as pharmaceuticals, illicit drugs, food, alcohol and tobacco. These addictions can be viewed as drug addiction, resulting from the ingestion of chemical substances contained in them. Multiple neural networks, including the reward system, anti-reward/stress system and central immune system in the brain, are believed to be involved in the onset of drug addiction. Although various compound evaluations using microelectrode array (MEA) as an in vitro testing methods to evaluate neural activities have been conducted, methods for assessing addiction have not been established. In this study, we aimed to develop an in vitro method for assessing the addiction of compounds, as an alternative to animal experiments, using human iPS cell-derived dopaminergic neurons with MEA measurements. MEA data before and after chronic exposure revealed specific changes in addictive compounds compared to non-addictive compounds, demonstrating the ability to estimate addiction of compound. Additionally, conducting gene expression analysis on cultured samples after the tests revealed changes in the expression levels of various receptors (nicotine, dopamine and GABA) due to chronic administration of addictive compounds, suggesting the potential interpretation of these expression changes as addiction-like responses in MEA measurements. The addiction assessment method using MEA measurements in human iPS cell-derived dopaminergic neurons conducted in this study proves effective in evaluating addiction of compounds on human neural networks.

Multiple Heterogeneous Networks Representation With Latent Space for Synthetic Lethality Prediction.

Computational synthetic lethality (SL) method has become a promising strategy to identify SL gene pairs for targeted cancer therapy and cancer medicine development. Feature representation for integrating various biological networks is crutial to improve the identification performance. However, previous feature representation, such as matrix factorization and graph neural network, projects gene features onto latent variables by keeping a specific geometric metric. There is a lack of models of gene representational latent space with considerating multiple dimentionalities correlation and preserving latent geometric structures in both sample and feature spaces. Therefore, we propose a novel method to model gene Latent Space using matrix Tri-Factorization (LSTF) to obtain gene representation with embedding variables resulting from the potential interpretation of synthetic lethality. Meanwhile, manifold subspace regularization is applied to the tri-factorization to capture the geometrical manifold structure in the latent space with gene PPI functional and GO semantic embeddings. Then, SL gene pairs are identified by the reconstruction of the associations with gene representations in the latent space. The experimental results illustrate that LSTF is superior to other state-of-the-art methods. Case study demonstrate the effectiveness of the predicted SL associations.

An integrated approach combining experimental, informatics and energetic methods for solid form derisking of PF-06282999

The landscapes of observed and predicted three-dimensional crystal packing arrangements of small-molecule drug candidates can be complex. The possible appearance of a more thermodynamically stable solid form during drug development has led to the digital workflow of informatics-based risk assessments, named a Solid Form Health Check. Herein, we describe the use of a combined approach consisting of experiments, informatics together with energetic calculations in analysis of four competing polymorphs of PF-06282999, a myeloperoxidase (MPO) inhibitor with conformational flexibility and multiple plausible hydrogen bond networks. This combined approach offered a comprehensive understanding of the solid form structure, properties, and performance, ensuring robust solid form derisking and selection.

Alternations voxel-wise interhemispheric and intrahemipheric functional connectivity dynamics in internet gaming disorder

BackgroundCurrently, numerous studies have indicated that individuals with internet gaming disorder (IGDs) have aberrant functional connection patterns between multiple brain regions and networks. However, temporal variability in the intra- and interhemispheric dynamic functional connectivity in IGDs remains unknown. MethodsThis study investigated resting-state functional magnetic resonance data from 55 IGDs and 50 demographically matched healthy controls (HCs). Functional connectivity density (FCD) combined with sliding window analysis is employed to calculate the temporal variability of global functional connectivity. The temporal variability of dynamic functional connectivity further quantified utilizing the standard deviations of global, intra-, and interhemispheric FCD. Finally, correlation analyses were performed between dynamic FCD varience (dFCD) in differential brain regions and clinical behaviors. ResultIGDs showed decreased intra- and interhemispheric dFCD variance in the visual attention network (precuneus and calcarine) and also demonstrated hemispheric-level dFCD variance abnormalities in the posterior cingulate cortex (PCC) compared to HCs. Moreover, abnormal global dFCD variability of the calcarine and ipsilateral dFCD variability of the PCC were negatively correlated with the severity of IGDs in the IGD group. ConclusionOur results demonstrate abberant intra- and interhemispheric dynamic functional connectivity in the visual attention network, which emphasizes the neurobiological basis for impaired concentration in IGDs.

Logistics Performance Index-driven in operational planning for logistics companies: A smart transportation approach

The responsibility of Logistics Companies (LCs) extends beyond simply handling logistical processes and choosing transportation routes; they focus on being competitive and efficient in their operations. In multiple origins and destinations networks, LCs attempt to select the most optimal routes from each point. To address this challenge and reduce the time needed to identify potential routes, a novel method has been developed in this research for LCs. In operational planning, additional factors need to be considered to increase efficiency, customer satisfaction, and competitiveness. To confront this issue, the study proposes a novel model and contributions, inspired by the LPI, to apply the transformative impact of smart ports, the integration of smart containers, the choices of clearing and forwarding agents and port operators, and time uncertainty in the multi-objective framework. Specifically, the mathematical model's objectives include cost, time, customer satisfaction, and environmental impact in the periodic multimodal network. An innovative customer satisfaction function is introduced by integrating the selection of smart containers and smart ports, emphasizing their impact on enhancing customer satisfaction, while addressing time uncertainty through a chance-constrained approach and coefficients of variation. The model is solved using goal programming, and the results show that smart ports and smart containers can majorly affect transportation time and customer satisfaction. Furthermore, comparing the results to other studies demonstrates its superiority in decision-making for LCs, particularly by including time uncertainty and the role of clearing and forwarding agents and port operators. Therefore, the model holds practical significance in lowering costs, enhancing customer satisfaction, and facilitating smart international logistics. This research offers insights that are not only useful for the LCs but also for other stakeholders in the transport industry.

VSPIM: SRAM Processing-in-Memory DNN Acceleration via Vector-Scalar Operations

Processing-in-Memory (PIM) has been widely explored for accelerating data-intensive machine learning computation that mainly consists of general-matrix-multiplication (GEMM), by mitigating the burden of data movements and exploiting the ultra-high memory parallelism. The two mainstreams of PIM, the analog- and digital-type, have both been exploited in accelerating machine learning workloads by numerous outstanding prior works. Currently, the digital-PIM is increasingly favored due to the broader computing support and the avoidance of errors caused by intrinsic non-idealities, e.g., process variation. Nevertheless, it still lacks further optimization considering the characteristics of the GEMM computation, including better efficient data layout and scheduling, and the ability to handle the sparsity of activations at the bit-level. To boost the performance and efficiency of digital SRAM PIM, we propose the architecture called VSPIM that performs the computation in a bit-serial fashion, with unique support of vector-scalar computing pattern. The novelties of the VSPIM can be concluded as follows: 1) support bit-serial based scalar-vector computing via ingenious parallel bit-broadcasting; 2) refine the GEMM mapping strategy and computing pattern to enhance performance and efficiency; 3) powered by the introduced scalar-vector operation, the bit-sparsity of activation is leveraged to halt unnecessary computation to maximize efficiency and throughput. Our comprehensive evaluation shows that, compared to the state-of-the-art SRAM-based digital-PIM design (Neural Cache), VSPIM can significantly boost the performance and energy efficiency by up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$8.87\times$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$4.81\times$</tex-math></inline-formula> respectively, with negligible area overhead, upon multiple representative neural networks.

Variation in Opioid Agonist Dosing in Clinical Trials by Race and Ethnicity

Racial and ethnic disparities in access to treatment and quality of treatment for opioid use disorder (OUD) have been identified in usual care settings. In contrast, disparities in treatment quality within clinical trials are relatively unexamined. To estimate racial and ethnic differences in the dose of opioid agonist treatment for OUD in the first 4 weeks of treatment in clinical trials. This cohort study performed analysis of the methadone and buprenorphine treatment arms of 3 trials conducted by the National Institute on Drug Abuse Clinical Trials Network between May 2006, and January 31, 2017, at multiple Clinical Trials Network sites across the US. Trial participants who were randomized to and initiated buprenorphine or methadone treatment and who identified as Hispanic, non-Hispanic Black, or non-Hispanic White were included in the present study. Data were analyzed from November 1, 2023, to August 5, 2024. Combined race and ethnicity as self-classified by the patient at trial enrollment. The maximum daily dose of buprenorphine or methadone received in each week for the first 4 weeks of treatment. The mean dose and the percentage of patients receiving a higher dose (buprenorphine ≥16 mg and methadone ≥60 mg) were compared across race and ethnicity groups. A total of 1748 patients (1263 who initiated buprenorphine and 485 who initiated methadone treatment) were included in the analysis (1168 [66.8%] male; median age, 33 [IQR, 26-45] years). Of these, 138 patients (7.9%) identified as Black, 273 (15.6%) as Hispanic, and 1337 (76.5%) as White. In week 4, Black patients received buprenorphine doses 2.5 (95% CI -4.6 to -0.5) mg lower and methadone doses 16.7 (95% CI, -30.7 to -2.7) mg lower compared with White patients, after standardizing by age and sex. In week 4, the percentage of patients receiving a higher dose of medication (buprenorphine ≥16 mg; methadone ≥60 mg) was 16.9 (95% CI, -31.9 to -1.9) points lower for Black patients compared with White patients. Hispanic and White patients received similar buprenorphine doses; Hispanic patients received lower methadone doses than White patients. In this cohort study of data from 3 clinical trials, White patients generally received higher doses of medication than Black patients. Future research is needed to understand the mechanisms of and interventions to reduce disparities in OUD treatment quality and how such disparities impact generalizability of trial results.

Physics-informed neural network for simulating magnetic field of permanent magnet

Abstract With the rapid development of deep learning, its application in physical field simulation has been widely concerned, and it has begun to lead a new model of meshless simulation. In this paper, research based on physics-informed neural networks is carried out to solve partial differential equations related to the physical laws of electromagnetism. Then the magnetic field simulation is realized. In this method, the governing equation and the boundary conditions containing physical information are embedded into the neural network loss function as constraints, and the backpropagation of neural networks is realized based on automatic differentiation to solve partial differential equations. The high-precision simulation of tile-shaped and rectangular permanent magnet magnetic fields of permanent magnet motors based on physical information neural network is studied, and the error is within 5%. We consider the simulation of magnetic field in two coordinate systems, and realize the joint training of multiple neural networks in multiple sub-domains and different media.

PPDistiller: Weakly-supervised 3D point cloud semantic segmentation framework via point-to-pixel distillation

Despite the significant growth in the availability of 3D light detection and ranging (LiDAR) point cloud data in recent years, annotation remains expensive and time-consuming. This has led to an increasing demand for weakly-supervised semantic segmentation (WSSS) methods in applications such as autonomous driving, mapping, and robotics. Existing approaches typically rely solely on LiDAR point cloud data for WSSS, which often results in lower segmentation accuracy due to the sparsity of point clouds. To address these challenges, we propose a novel architecture, PPDistiller, which employs multiple teacher networks from different modalities. Compared to other WSSS and multimodal approaches, PPDistiller achieves superior segmentation accuracy with fewer annotations. This is facilitated through the novel Mean Multi-Teacher Framework (MMT), which incorporates multiple modalities and teachers. To address the issue of lacking 2D labels, we propose the Distance-CAM Self-Training (DCAM-ST) module, which utilizes sparse 3D weak annotations to produce accurate 2D pixel-level annotations. To enable adaptive fusion of 2D and 3D data, we introduce the Attention Point to Pixel Fusion (APPF) module, facilitating bidirectional transfer of cross-modal knowledge. Additionally, to fully leverage the spatial semantic information in point cloud, we propose the Pyramid Semantic-context Neighbor Aggregation (PSNA) module, aiming to exploit spatial and semantic correlations to improve performance. Extensive experimentation on SemanticKITTI, ScribbleKITTI and nuScenes datasets demonstrates the superiority of our proposed method. Compared to state-of-the-art fusion and weakly-supervised methods, PPDistiller achieves the highest mean Intersection over Union (mIoU) scores under both fully-supervised and weakly-supervised settings.