Two-layer Network Research Articles

Quantification of Size-Binned Particulate Matter in Electronic Cigarette Aerosols Using Multi-Spectral Optical Sensing and Machine Learning

To monitor health risks associated with vaping, we introduce a multi-spectral optical sensor powered by machine learning for real-time characterization of electronic cigarette aerosols. The sensor can accurately measure the mass of particulate matter (PM) in specific particle size channels, providing essential information for estimating lung deposition of vaping aerosols. For the sensor’s input, wavelength-specific optical attenuation signals are acquired for three separate wavelengths in the ultraviolet, red, and near-infrared range, and the inhalation pressure is collected from a pressure sensor. The sensor’s outputs are PM mass in three size bins, specified as 100–300 nm, 300–600 nm, and 600–1000 nm. Reference measurements of electronic cigarette aerosols, obtained using a custom vaping machine and a scanning mobility particle sizer, provided the ground truth for size-binned PM mass. A lightweight two-layer feedforward neural network was trained using datasets acquired from a wide range of puffing conditions. The performance of the neural network was tested using unseen data collected using new combinations of puffing conditions. The model-predicted values matched closely with the ground truth, and the accuracy reached 81–87% for PM mass in three size bins. Given the sensor’s straightforward optical configuration and the direct collection of signals from undiluted vaping aerosols, the achieved accuracy is notably significant and sufficiently reliable for point-of-interest sensing of vaping aerosols. To the best of our knowledge, this work represents the first instance where machine learning has been applied to directly characterize high-concentration undiluted electronic cigarette aerosols. Our sensor holds great promise in tracking electronic cigarette users’ puff topography with quantification of size-binned PM mass, to support long-term personalized health and wellness.

The Reliability of a Class of Two-Layer Networks with Unreliable Edges

It is well known that networks are dynamic graphs, and the topology of a network can be described by a graph. Thus, the reliability of a network under edge failure is defined as the probability that its corresponding topological graph remains connected under the condition that the edges fail with independent probabilities. In this paper, the reliability of a class of two-layer networks is considered, where each layer is a complete graph and the edges joining different layers are one-to-one correspondingly connected. The edge failure probability is uniform in the same layer and distinct in different layers and between layers. The recursive formula for the reliability (reliability polynomial) of the two-layer network is obtained, and the corresponding algorithm is also given. Furthermore, the reliability of several networks is computed by Python, which verifies the correctness of the algorithm.

Two-layer network evolutionary game model applied to complex systems

Two-layer network evolutionary game model applied to complex systems

Risk sharing framework and systemic tolerance in Indian banks: Double layer network approach

Interconnectedness spreads systemic risk and is critical in enhancing banks’ systemic tolerance through interbank liquidity and lines of credit. Literature on systemic risk has not considered the importance of interconnectedness in providing liquidity to improve banks’ systemic tolerance. As a bank’s resistivity towards systemic disruption depends on its tolerance, the current article develops a model to measure the systemic tolerance of individual banks in a two-layer interbank network using ΔCoVaR. It estimates systemic tolerance distance through a risk-sharing framework and analyzes the significance of macroeconomic and bank-specific factors in explaining systemic tolerance. The results support that systemic tolerance values are higher during the down-cycle than the up-cycle, signaling the importance of interconnectedness in protecting against systemic crises. The empirics further substantiate that risk-sharing distance is lower, and structure is complex with clusters during economic down-cycle. This highlights that banks couple with each other during stressful environments and empirically validate the importance of interbank and lines of credit in enhancing systemic tolerance and, therefore, possess the regulator to develop a robust interbank market through regulatory guidelines.

Design and implementation of anti-mapping security access technology based on illegal scanning

Abstract In the current field of information security, illegal network scanning activities are prevalent, and such behaviors are usually aimed at detecting security vulnerabilities in network systems and preparing for future attack activities. This study proposes a secure access system based on anti-mapping technology, which aims to effectively block illegal scanning behaviors while ensuring that the normal access of legitimate users is not affected. The system integrates advanced behavioral analysis algorithms that utilize machine learning techniques for deep learning and pattern recognition of network traffic, and is able to accurately distinguish between normal user activities and malicious scanning attempts. At the core of the system is a set of dynamic adaptive identification mechanisms that update the detection algorithms in real time to adapt to emerging scanning techniques and attack strategies by continuously learning from changes in network traffic. In addition, the system employs role-based access control (RBAC) policies to enhance the protection of sensitive resources. The Secure Access Gateway is deployed at the boundary of the network to monitor and filter all ingress traffic, effectively intercepting unauthorized scanning activities by comprehensively evaluating the source, behavior and frequency of traffic. Experimental results show that the proposed two-layer network structure performs well in detecting common threats such as port scanning, DDoS attacks, and SQL injections, with an accuracy rate of over 95%. Especially for complex and covert APT (advanced persistent threat) attacks, the system can significantly reduce the false alarm rate and effectively improve the detection speed. However, when dealing with some highly customized malware, the system's recognition ability still needs to be improved, which indicates that future research needs to focus more on enhancing the ability to learn and adapt to unknown threats.

Saddle-to-saddle dynamics in diagonal linear networks*

Abstract In this paper we fully describe the trajectory of gradient flow over two-layer diagonal linear networks for the regression setting in the limit of vanishing initialisation. We show that the limiting flow successively jumps from a saddle of the training loss to another until reaching the minimum ℓ 1 -norm solution. We explicitly characterise the visited saddles as well as the jump times through a recursive algorithm reminiscent of the LARS algorithm used for computing the Lasso path. Starting from the zero vector, coordinates are successively activated until the minimum ℓ 1 -norm solution is recovered, revealing an incremental learning. Our proof leverages a convenient arc-length time-reparametrisation which enables to keep track of the transitions between the jumps. Our analysis requires negligible assumptions on the data, applies to both under and overparametrised settings and covers complex cases where there is no monotonicity of the number of active coordinates. We provide numerical experiments to support our findings.

Disinformation, Fakes and Propaganda Identifying Methods in Online Messages Based on NLP and Machine Learning Methods

A new method of propaganda analysis is proposed to identify signs and change the dynamics of the behaviour of coordinated groups based on machine learning at the processing disinformation stages. In the course of the work, two models were implemented to recognise propaganda in textual data - at the message level and the phrase level. Within the framework of solving the problem of analysis and recognition of text data, in particular, fake news on the Internet, an important component of NLP technology (natural language processing) is the classification of words in text data. In this context, classification is the assignment or assignment of textual data to one or more predefined categories or classes. For this purpose, the task of binary text classification was solved. Both models are built based on logistic regression, and in the process of data preparation and feature extraction, such methods as vectorisation using TF-IDF vectorisation (Term Frequency – Inverse Document Frequency), the BOW model (Bag-of-Words), POS marking (Part-Of-Speech), word embedding using the Word2Vec two-layer neural network, as well as manual feature extraction methods aimed at identifying specific methods of political propaganda in texts are used. The analogues of the project under development are analysed the subject area (the propaganda used in the media and the basis of its production methods) is studied. The software implementation is carried out in Python, using the seaborn, matplotlib, genism, spacy, NLTK (Natural Language Toolkit), NumPy, pandas, scikit-learn libraries. The model's score for propaganda recognition at the phrase level was obtained: 0.74, and at the message level: 0.99. The implementation of the results will significantly reduce the time required to make the most appropriate decision on the implementation of counter-disinformation measures concerning the identified coordinated groups of disinformation generation, fake news and propaganda. Different classification algorithms for detecting fake news and non-fakes or fakes identification accuracy from Internet resources ana social mass media are used as the decision tree (for non-fakes identification accuracy 0.98 and fakes identification accuracy 0.9903), the k-nearest neighbours (0.83/0.999), the random forest (0.991/0.933), the multilayer perceptron (0.9979/0.9945), the logistic regression (0.9965/0.9988), and the Bayes classifier (0.998/0.913). The logistic regression (0.9965) the multilayer perceptron (0.9979) and the Bayesian classifier (0.998) are more optimal for non-fakes news identification. The logistic regression (0.9988), the multilayer perceptron (0.9945), and k-nearest neighbours (0.999) are more optimal for identifying fake news identification.

Comparison of measurement of integrated relaxation pressure by esophageal manometry with analysis of swallowing sounds with artificial intelligence in patients with achalasia.

Esophageal motility disorders are mainly evaluated with high-resolution manometry (HRM) which is a time-consuming and uncomfortable procedure with potential adverse events. Acoustic characterization of the swallowing has the potential to be an alternative noninvasive procedure. We compared the findings on HRM and swallowing sounds in 43 patients who were referred for evaluation of dysphagia. The sound analysis was done with empirical mode decomposition method and with artificial intelligence (AI) and the estimated integrated relaxation pressure (IRP) from a two-layer neural network method was compared to measured IRP on HRM. The model then was tested in five patients. IRP was estimated with high accuracy using the model developed with two-layer neural network method. The analysis of acoustic properties of swallowing has the potential to be used for evaluation of esophageal motility disorders, this needs to be further evaluated in larger studies.

Classifying zircon: A machine-learning approach using zircon geochemistry

This study presented a novel, rapid, and accurate method for determining zircon origin via a comprehensive analysis of a dataset containing 27,818 zircon trace element sets. This method integrated back propagation neural networks with the AdaBoost algorithm. The optimal classifier characterized as a linear combination of a two-layer neural network model, comprised 100 base classifiers and 400 hidden neurons. It was rigorously trained over 1000 iterations, which resulted in an unbiased error rate of 8.31%. To facilitate practical application, the classifier was integrated into a macro-enabled Excel spreadsheet.

Self-powered flexible sensor network for continuous monitoring of crop micro-environment and growth states

Monitoring crops’ micro-environment and growth states is significant for developing smart agriculture. However, the traditional rigid and large-sized sensor systems cannot meet the demands of precision agriculture for multi-parameter and high-throughput monitoring. Here, we integrate a flexible sensor system with low-power communication techniques, designing a two-layer star topology sensor network based on BLE and NB-IoT protocol. The sensors are arranged on flexible substrates, allowing them to closely adhere to various parts of crops, such as stems and leaves. To ensure the accuracy of the sensors, they are evaluated and calibrated in the laboratory. A solar energy harvesting system is designed for the sensor network to make it self-powered and successfully measure temperature, humidity, illumination, and leaf angles stably, demonstrating the system’s feasibility. The deployment cost of the sensor network is significantly lower than that of traditional automatic weather stations, showcasing its potential for widespread application in farmlands.

Enhancing smart city IoT communication: A two-layer NOMA-based network with caching mechanisms and optimized resource allocation

With advancements in next-generation communication systems, large-scale Internet of Things device (IoTDs) deployments in smart cities face challenges like limited bandwidth, high latency, and network congestion. To address this, we propose a two-layer network architecture utilizing non-orthogonal multiple access (NOMA) and caching to enhance IoT communications’ performance, efficiency, and reliability. Our primary objective is to optimize resource allocation and solve the association problem in a two-layer network. We formulated a joint optimization problem to maximize system utility through device association, power, and bandwidth allocation, considering constraints like channel quality and interference. We decoupled the non-linear, non-convex problem using block coordinate descent (BCD) and inner approximation techniques to maximize the aggregated data rate in high-density IoT scenarios. This approach reduced computational complexity while proving the scheme’s theoretical and numerical convergence. To evaluate the proposed scheme, we compared its performance with an ideal backhauling approach, an exhaustive search (upper bound), and a Genetic algorithm-based heuristic. Our scheme outperformed the others, achieving 98.04% of the ideal backhauling and 99.60% of the upper bound. Statistical analysis confirmed its robustness and consistent performance across various conditions. The two-layer NOMA-based network with caching and optimized resource allocation significantly enhances IoT communication efficiency and resilience, offering a solid framework for future smart city deployments.

Network structure analysis based on embodied energy of the Australian economy

Energy and economic growth are closely linked and have negative impacts on the environment. Both environmental protection and economic development are significant global focal points of concern. Australian economic growth has slowed but energy consumption has increased. The relationship between economic growth and energy consumption has changed significantly. However, existing methods for accounting energy transfers between industries overlook the role of embodied energy, making them insufficient to fully capture the actual energy usage in both domestic and international trade. This study investigates the structural changes in embodied energy in the Australian economy. The paper integrates sectors as the section nodes for a network and constructs a two-layer network model to analyze energy flows both between and within nodes. The results show that the Australian embodied energy network exhibited significant variations in efficiency and interconnectedness over time, with a trend toward shorter, more interconnected paths from 2015 to 2019, enhancing overall network efficiency. The Australian embodied energy network currently faces significant funding constraints. The findings show that the Australian economic sectors have increased energy consumption in production without contributing to economic growth due to the concentration of resources within the network.

A two-layer regression network for robust and accurate domain adaptation

Naturally, classification models suffer from severe performance degradation when they are tested on datasets different from the ones used in training. Unsupervised domain adaptation helps to improve the generalizability of a pre-trained model by transferring knowledge from the labeled source domain (i.e., training dataset) to the unlabeled target domain (i.e., test dataset). The typical way of domain adaptation is to align the data distributions in embedding spaces between source and target domains. However, most existing works only enhance cross-domain consistency in the latent space disregarding the impact of source samples on the target classification task. Besides, discovering a subspace shared by two domains first and then training a transfer classifier separately hardly ensures that the obtained target features are suited for the classification model. To address these issues, in this work, we propose a two-layer regression network for domain adaptation (TRN-DA). TRN-DA learns class-wise domain invariant feature representations by jointly optimizing three tasks: supervised classification of source domain, unsupervised reconstruction of target domain, and alignment of cross-domain distributions. Furthermore, we introduce the concept of weight (importance) for source instances so that the resulting classifier can adapt well to the target domain. We formulate the domain adaptation problem as a unified optimization problem and solve it in an iterative way. Experimental results on different cross-domain image classification tasks demonstrate the encouraging performance of our TRN-DA compared to several recent state-of-the-art methods.

Genotype and Phenotype Association Analysis Based on Multi-omics Statistical Data

Background: When using clinical data for multi-omics analysis, there are issues such as the insufficient number of omics data types and relatively small sample size due to the protection of patients' privacy, the requirements of data management by various institutions, and the relatively large number of features of each omics data. This paper describes the analysis of multi-omics pathway relationships using statistical data in the absence of clinical data. Methods: We proposed a novel approach to exploit easily accessible statistics in public databases. This approach introduces phenotypic associations that are not included in the clinical data and uses these data to build a three-layer heterogeneous network. To simplify the analysis, we decomposed the three-layer network into double two-layer networks to predict the weights of the inter-layer associations. By adding a hyperparameter β, the weights of the two layers of the network were merged, and then k-fold cross-validation was used to evaluate the accuracy of this method. In calculating the weights of the two-layer networks, the RWR with fixed restart probability was combined with PBMDA and CIPHER to generate the PCRWR with biased weights and improved accuracy. Results: The area under the receiver operating characteristic curve was increased by approximately 7% in the case of the RWR with initial weights. Conclusion: Multi-omics statistical data were used to establish genotype and phenotype correlation networks for analysis, which was similar to the effect of clinical multi-omics analysis.

Designing Universally-Approximating Deep Neural Networks: A First-Order Optimization Approach.

Universal approximation capability, also referred to as universality, is an important property of deep neural networks, endowing them with the potency to accurately represent the underlying target function in learning tasks. In practice, the architecture of deep neural networks largely influences the performance of the models. However, most existing methodologies for designing neural architectures, such as the heuristic manual design or neural architecture search, ignore the universal approximation property, thus losing a potential safeguard about the performance. In this paper, we propose a unified framework to design the architectures of deep neural networks with a universality guarantee based on first-order optimization algorithms, where the forward pass is interpreted as the updates of an optimization algorithm. The (explicit or implicit) network is designed by replacing each gradient term in the algorithm with a learnable module similar to a two-layer network or its derivatives. Specifically, we explore the realm of width-bounded neural networks, a common practical scenario, showcasing their universality. Moreover, adding operations of normalization, downsampling, and upsampling does not hurt the universality. To the best of our knowledge, this is the first work that width-bounded networks with universal approximation guarantee can be designed in a principled way. Our framework can inspire a variety of neural architectures including some renowned structures such as ResNet and DenseNet, as well as novel innovations. The experimental results on image classification problems demonstrate that the newly inspired networks are competitive and surpass the baselines of ResNet, DenseNet, as well as the advanced ConvNeXt and ViT, testifying to the effectiveness of our framework.

Land Cover Classification of Remote Sensing Imagery with Hybrid Two-Layer Attention Network Architecture

In remote sensing image processing, when categorizing images from multiple remote sensing data sources, the deepening of the network hierarchy is prone to the problems of feature dispersion, as well as the loss of semantic information. In order to solve this problem, this paper proposes to integrate a parallel network architecture HDAM-Net algorithm with a hybrid dual attention mechanism Hybrid dual attention mechanism for forest land cover change. Firstly, we propose a fusion MCA + SAM (MS) attention mechanism to improve VIT network, which can capture the correlation information between features; secondly, we propose a multilayer residual cascade convolution (MSCRC) network model using Double Cross-Attention Module (DCAM) attention mechanism, which is able to efficiently utilize the spatial dependency between multiscale encoder features: the spatial dependency between multiscale encoder features. Finally, the dual-channel parallel architecture is utilized to solve the structural differences and realize the enhancement of forestry image classification differentiation and effective monitoring of forest cover changes. In order to compare the performance of HDAM-Net, mountain urban forest types are classified based on multiple remote sensing data sources, and the performance of the model is evaluated. The experimental results show that the overall accuracy of the algorithm proposed in this paper is 99.42%, while the Transformer (ViT) is 96.92%, which indicates that the proposed classifier is able to accurately determine the cover type.The HDAM-Net model emphasizes the effectiveness in terms of accurately classifying the land, as well as the forest types by using multiple remote sensing data sources for predicting the future trend of the forest ecosystem. In addition, the land utilization rate and land cover change can clearly show the forest cover change and support the data to predict the future trend of the forest ecosystem so that the forest resource survey can effectively monitor deforestation and evaluate forest restoration projects.

Mapping the inter-provincial pathways of resources and socio-economic impacts in China's just transition of coal power

In the sustainable transition of the power system, China's resource distribution characteristics lead to a distinct geographical separation between the main production and consumption areas of coal and coal power. This separation leads to the transmission of complex inter-regional social risks and responsibilities associated with the phase-out of coal power. Considering the inter-provincial transmission of coal and coal power, this paper constructs a novel two-layer network framework incorporating both coal mining and coal power. This method systematically assesses the contributions of coal power production and consumption to provincial employment and tax revenue, and identifies key paths of inter-provincial impact transmission for the first time. In terms of total contribution, coal mining contributes significantly more to employment and tax revenue (1.45 million jobs and 143 billion RMB) than coal power production (0.69 million jobs and 58.2 billion RMB). Spatially, employment and tax revenue related to coal power are concentrated in North China's production areas and the coastal consumption regions. Provinces like Shanxi, characterized by abundant resource reserves yet low consumption, are more exposed to socio-economic risks from other provinces reducing coal use, whereas economically developed provinces like Guangdong currently benefiting more from coal consumption, should assume corresponding responsibility in the future sustainable transition of power sector. Our analysis emphasizes the need for future policies to consider inter-provincial economic and social impacts, innovating horizontal risk compensation and shared responsibility mechanisms, to secure the interests of resource-based provinces in the just transition of China's coal power industry.

Hebbian spatial encoder with adaptive sparse connectivity

Biologically plausible neural networks have demonstrated efficiency in learning and recognizing patterns in data. This paper proposes a general online unsupervised algorithm for spatial data encoding using fast Hebbian learning. Inspired by the Hierarchical Temporal Memory (HTM) framework, we introduce the SpatialEncoder algorithm, which learns the spatial specialization of neurons’ receptive fields through Hebbian plasticity and k-WTA (k winners take all) inhibition. A key component of our model is a two-part synaptogenesis algorithm that enables the network to maintain a sparse connection matrix while adapting to non-stationary input data distributions. In the MNIST digit classification task, our model outperforms the HTM SpatialPooler in terms of classification accuracy and encoding stability. Compared to another baseline, a two-layer artificial neural network (ANN), our model achieves competitive classification accuracy with fewer iterations required for convergence. The proposed model offers a promising direction for future research on sparse neural networks with adaptive neural connectivity.

Artificial Intelligence (AI) and Nuclear Features from the Fine Needle Aspirated (FNA) Tissue Samples to Recognize Breast Cancer.

Breast cancer is one of the paramount causes of new cancer cases worldwide annually. It is a malignant neoplasm that develops in the breast cells. The early screening of this disease is essential to prevent its metastasis. A mammogram X-ray image is the most common screening tool practiced currently when this disease is suspected; all the breast lesions identified are not malignant. The invasive fine needle aspiration (FNA) of a breast mass sample is the secondary screening tool to clinically examine cancerous lesions. The visual image analysis of the stained aspirated sample imposes a challenge for the cytologist to identify the malignant cells accurately. The formulation of an artificial intelligence-based objective technique on top of the introspective assessment is essential to avoid misdiagnosis. This paper addresses several artificial intelligence (AI)-based techniques to diagnose breast cancer from the nuclear features of FNA samples. The Wisconsin Breast Cancer dataset (WBCD) from the UCI machine learning repository is applied for this investigation. Significant statistical parameters are measured to evaluate the performance of the proposed techniques. The best detection accuracy of 98.10% is achieved with a two-layer feed-forward neural network (FFNN). Finally, the developed algorithm's performance is compared with some state-of-the-art works in the literature.

Turbofan engine health status prediction with neural network pattern recognition and automated feature engineering

PurposeThis study aims to present the concept of aircraft turbofan engine health status prediction with artificial neural network (ANN) pattern recognition but augmented with automated features engineering (AFE).Design/methodology/approachThe main concept of engine health status prediction was based on three case studies and a validation process. The first two were performed on the engine health status parameters, namely, performance margin and specific fuel consumption margin. The third one was generated and created for the engine performance and safety data, specifically created for the final test. The final validation of the neural network pattern recognition was the validation of the proposed neural network architecture in comparison to the machine learning classification algorithms. All studies were conducted for ANN, which was a two-layer feedforward network architecture with pattern recognition. All case studies and tests were performed for both simple pattern recognition network and network augmented with automated feature engineering (AFE).FindingsThe greatest achievement of this elaboration is the presentation of how on the basis of the real-life engine operational data, the entire process of engine status prediction might be conducted with the application of the neural network pattern recognition process augmented with AFE.Practical implicationsThis research could be implemented into the engine maintenance strategy and planning. Engine health status prediction based on ANN augmented with AFE is an extremely strong tool in aircraft accident and incident prevention.Originality/valueAlthough turbofan engine health status prediction with ANN is not a novel approach, what is absolutely worth emphasizing is the fact that contrary to other publications this research was based on genuine, real engine performance operational data as well as AFE methodology, which makes the entire research very reliable. This is also the reason the prediction results reflect the effect of the real engine wear and deterioration process.