Three-layer Network Research Articles

Satellite Image Classification Using a Hybrid Manta Ray Foraging Optimization Neural Network

A semi supervised image classification method for satellite images is proposed in this paper. The satellite images contain enormous data that can be used in various applications. The analysis of the data is a tedious task due to the amount of data and the heterogeneity of the data. Thus, in this paper, a Radial Basis Function Neural Network (RBFNN) trained using Manta Ray Foraging Optimization algorithm (MRFO) is proposed. RBFNN is a three-layer network comprising of input, output, and hidden layers that can process large amounts. The trained network can discover hidden data patterns in unseen data. The learning algorithm and seed selection play a vital role in the performance of the network. The seed selection is done using the spectral indices to further improve the performance of the network. The manta ray foraging optimization algorithm is inspired by the intelligent behaviour of manta rays. It emulates three unique foraging behaviours namelys chain, cyclone, and somersault foraging. The satellite images contain enormous amount of data and thus require exploration in large search space. The spiral movement of the MRFO algorithm enables it to explore large search spaces effectively. The proposed method is applied on pre and post flooding Landsat 8 Operational Land Imager (OLI) images of New Brunswick area. The method was applied to identify and classify the land cover changes in the area induced by flooding. The images are classified using the proposed method and a change map is developed using post classification comparison. The change map shows that a large amount of agricultural area was washed away due to flooding. The measurement of the affected area in square kilometres is also performed for mitigation activities. The results show that post flooding the area covered by water is increased whereas the vegetated area is decreased. The performance of the proposed method is done with existing state-of-the-art methods.

Long Short-term Memory Applied on Amazon's Stock Prediction

More and more investors are paying attention to how to use data mining technology into stock investing decisions as a result of the introduction of big data and the quick expansion of financial markets. Machine learning can automatically apply complex mathematical calculations to big data repeatedly and faster. The machine model can analyze all the factors and indicators affecting stock price and achieve high efficiency. Based on the Amazon stock price published on Kaggle, this paper adopts the Long Short-term Memory (LSTM) method for model training. The Keras package in the Python program is used to normalize the data. The Sequence model in Keras establishes a two-layer LSTM network and a three-layer LSTM network to compare and analyze the fitting effect of the model on stock prices. By calculating RMSE and RMPE, the study found that the stock price prediction accuracy of two-layer LSTM is similar to that of three-layer LSTM. In terms of F-measure and Accuracy, the LSTM model of the three-layer network is significantly better than the LSTM model of the two-layer network layer. In general, the LSTM model can accurately predict stock price. Therefore, investors will know the upward or downward trend of stock prices in advance according to the prediction results of the model to make corresponding decisions.

LANDMARK DETECTION USING DEEP LEARNING

In many computer vision applications, finding landmarks is a crucial challenge. In this thesis, we suggest a unique convolutional neural network-based method for landmark detection (CNNs). On the PASCAL VOC and COCO datasets, our solution surpasses cutting-edge techniques. The landmark detection method we suggest using CNN is built on a three-layer deep network. The input image's features are extracted by the feature extraction layer, which is the first layer. The input image is categorised into one of the pre-established landmark categories in the second layer, which is a classification layer. A localization layer, which is the third layer, locates the landmarks in the input picture. Keywords—CNN,tensorflow_hub,streamlit, geolocation,landmark detection, classification

NOMA-Assisted Routing Algorithm Design for UAV Ad Hoc Relay Networks

Unmanned aerial vehicle (UAV) ad hoc networks can be deployed flexibly and rapidly without any infrastructure, so as to play an irreplaceable role in postdisaster relief. However, the dynamic topology and energy constraints of UAVs always bring new challenges to the design of effective network architectures and routing strategies. In this article, a three-layer UAV network architecture is constructed, and the UAV channel models for the different layers are discussed categorically. A greedy perimeter comprehensive evaluation routing (GCER) algorithm is designed on the basis of geographic routing greedy perimeter stateless routing (GPSR). By estimating the energy, link stability, and data throughput of the UAV neighboring nodes, the optimal next-hop UAV node is synthetically evaluated using the analytic hierarchy process (AHP). In particular, the use of nonorthogonal multiple access (NOMA) technology in ad hoc networks is considered, and a nonconvex optimization problem for maximizing the throughput estimation of UAV relay nodes based on NOMA is proposed to solve for the optimal allocation of UAV transmission power in routing. Numerical results show that the proposed GCER routing algorithm has significant advantages over GPSR in improving link stability. The use of NOMA access technology in UAV ad hoc networks has a significant increase in the throughput of the data links.

Research on calibration of a binocular stereo-vision imaging system based on the artificial neural network.

Camera calibration is a key problem for 3D reconstruction in computer vision. Existing calibration methods, such as traditional, active, and self-calibration, all need to solve the internal and external parameters of the imaging system to clarify the image-object mapping relationship. The artificial neural network, which is based on connectionist architecture, provides a novel idea for the calibration of nonlinear mapping vision systems. It can learn the image-object mapping relationship from some sample points without considering too many uncertain factors in the middle. This paper discusses the learning ability. A binocular stereo-vision mapping model is used as the learning model to explore the ability of image-object mapping for artificial neural networks. This paper constructs sample libraries by pixel and world coordinates of checkerboard corners, builds the artificial neural network, and, through the training samples and test samples prediction, verifies the learning performance of the network. Furthermore, by the laser scanning binocular vision device constructed in the authors' laboratory and trained-well network, the 3D point cloud reconstruction of a physical target is performed. The experimental results show that the artificial neural network can learn the image-object mapping relationship well and more effectively avoid the impact of lens distortion and achieve more accurate nonlinear mapping at the edge of the image. When the X and Y coordinates are in the range of 100mm and the Z coordinates are in the range of a 1000mm, the absolute error rarely exceeds 2.5mm, and the relative error is in the level of 10-3; for 1000mm distance measurement, the standard deviation does not exceed 1.5mm. Network parameter selection experiments show that, for image-object mapping, a three-layer network and increasing the number of hidden layer's nodes can improve the training time more significantly.

A Method to Optimize Routing Paths for City-Pair Airlines on Three-Layer Air Transport Networks

Air transportation is a huge, complex system with emergence and self-organization, which makes it important for it to be modelled. In this paper, to model the air transportation system with more accuracy, from physical facilities to traffic applications, three-layer networks, including the air route network, the city-pair airline network, and flight operation network, are built, where the air route network is regarded as the physical layer, and city-pair airline network and flight operation network are the application layers. Furthermore, a powerful tool, complex network theory, is applied to discuss the topology characteristics of the three-layer networks. Moreover, considering the path diversity of city-pair airlines, a simulated annealing-based framework is proposed to optimize the routing paths on an air route network for each city-pair airline, such that the traffic congestion of the air route network can be alleviated, where an elaborated method for perturbing solutions, named Selection after Remove (SAR), is adopted. Experimental results show that, compared with the default routing paths, the shortest routing paths, and the random routing paths, the proposed routing-path optimization strategy can reduce the maximum traffic flows of the air route network by 2.4%, 4.6%, and 4.8%, respectively, which shows that the proposed optimization method performs well in alleviating the traffic congestion of the air route network.

Diamond Message Set Groupcasting: From an Inner Bound for the DM Broadcast Channel to the Capacity Region of the Combination Network

Multiple groupcasting over the broadcast channel (BC) is studied in a special setting. In particular, an inner bound is obtained for the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -receiver discrete memoryless (DM) BC for the diamond message set which consists of four groupcast messages: one desired by all receivers, one by all but two receivers, and two more desired by all but each one of those two receivers. The inner bound is based on rate-splitting and superposition coding and is given in explicit form herein as a union over coding distributions of four-dimensional polytopes. This inner bound is then shown to be the capacity for a certain class of partially ordered DM BCs with order defined via the less noisy condition. When specialized to the so- called combination network, which is a class of three-layer (two-hop) broadcast networks parameterized by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2^{K}{-}1$ </tex-math></inline-formula> finite-and-arbitrary-capacity noiseless links from the source node in the first layer to as many nodes of the second layer, our top-down approach from the DM BC to the combination network yields an explicit inner bound as a single polytope via the identification of a single coding distribution. This inner bound consists of inequalities which are then identified to be within the class of generalized cut-set outer bounds recently obtained by Salimi et al for broadcast networks. We hence establish the capacity region of the general <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -user combination network for the diamond message set, and do so in explicit and structured form. Such a result implies a certain strength of our inner bound for the DM BC in that it (a) produces a hitherto unknown capacity region when specialized to the combination network and (b) may capture many combinatorial aspects of the capacity region of the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -receiver DM BC itself for the diamond message set. Moreover, we extend that inner bound by adding binning to it. As in the no-binning case, we provide the more general inner bound in explicit form.

Deep Learning Depends on Segregated Dendritic Compartments and Spike Frequency Adaptation

Deep learning mimics the function of the biological nervous system via adopting strategies motivated by neurophysiology. However, integrating biophysical characteristics to make deep learning more brain-like remains challenging. To investigate whether the more realistic simulated neurons could make deep learning more realistic from the biology perspective, we propose a three-layer multi-compartment deep learning network with spike frequency adaptation (SFA). We utilize the segregated apical dendrites in the hidden layer to implement the credit assignment and coordinate the distribution of information flow. The introduction of SFA serves as the teaching signal. The results show that the apical dendrites separate the feedforward and feedback signals and instruct the credit assignment problem. The apical dendrites diverse the firing types of target neurons and further decrease the firing rate of non-target neurons via switching their firing types from the tonic firing type to predominantly burst firing. Furthermore, the expression of SFA in the non-target neurons further amplifies the difference between the firing rate of target and non-target signals. This work provides new insight into a deep learning network with more biophysical neurons and is a meaningful supplementary for deep learning.

Predictive Model Techniques with Energy Efficiency for IoT-Based Data Transmission in Wireless Sensor Networks

Wireless sensor networks are limited by the vast majority of goods with limited resources. Power consumption, network longevity, throughput, routing, and network security are only a few of the research issues that have not yet been addressed in sensor networks based on the Internet of Things. Prior to becoming widely deployed, sensor networks built on the Internet of Things must overcome a variety of technological obstacles as well as general and specific hazards. In order to address the aforementioned problems, this research sought to improve rogue node detection, reduce packet latency/packet loss, increase throughput, and lengthen network lifetime. Wireless energy harvesting is suggested in the proposed three-layer cluster-based wireless sensor network routing protocol to extend the energy lifespan of the network. For the purpose of recognising and blacklisting risky sensor node behaviour, a three-tier clustering architecture with an integrated security mechanism is suggested. This clustering approach is cost-based, and the sink node selects the cluster and grid heads based on the cost function’s value. With its seemingly endless potential across a wide range of industries, including intelligent transportation, the Internet of Things (IoT) has gained prominence recently. To analyse the nodes and clustering strategies in IoT, the suggested method PSO is applied. A plethora of new services, programmes, electrical devices with integrated sensors, and protocols have been produced as a result of the Internet of Things’ explosive growth in popularity.

Research on the Construction Method of Remote Sensing Sensing Information Platform Based on Internet of Things

With the gradual rise and development of Internet of Things technology, the development of related industries has shown new vigor and vitality. From the definition and application of the Internet of Things and remote sensing monitoring, the application fields of the combination of the Internet of Things and remote sensing monitoring are given a specific description. On the basis of analyzing the research status and technology at home and abroad, using VS. NET method to build a three-layer network platform to realize the construction of the information platform, and verify the application of the information platform is better.

Photons guided by axons may enable backpropagation-based learning in the brain

Despite great advances in explaining synaptic plasticity and neuron function, a complete understanding of the brain’s learning algorithms is still missing. Artificial neural networks provide a powerful learning paradigm through the backpropagation algorithm which modifies synaptic weights by using feedback connections. Backpropagation requires extensive communication of information back through the layers of a network. This has been argued to be biologically implausible and it is not clear whether backpropagation can be realized in the brain. Here we suggest that biophotons guided by axons provide a potential channel for backward transmission of information in the brain. Biophotons have been experimentally shown to be produced in the brain, yet their purpose is not understood. We propose that biophotons can propagate from each post-synaptic neuron to its pre-synaptic one to carry the required information backward. To reflect the stochastic character of biophoton emissions, our model includes the stochastic backward transmission of teaching signals. We demonstrate that a three-layered network of neurons can learn the MNIST handwritten digit classification task using our proposed backpropagation-like algorithm with stochastic photonic feedback. We model realistic restrictions and show that our system still learns the task for low rates of biophoton emission, information-limited (one bit per photon) backward transmission, and in the presence of noise photons. Our results suggest a new functionality for biophotons and provide an alternate mechanism for backward transmission in the brain.

A novel non-linear neuron model based on multiplicative aggregation in quaternionic domain

The learning algorithm for a three-layered neural structure with novel non-linear quaternionic-valued multiplicative (QVM) neurons is proposed in this paper. The computing capability of non-linear aggregation in the cell body of biological neurons inspired the development of a non-linear neuron model. However, unlike linear neuron models, most non-linear neuron models are built on higher order aggregation, which is more mathematically complex and difficult to train. As a result, building non-linear neuron models with a simple structure is a difficult and time-consuming endeavor in the neurocomputing field. The concept of a QVM neuron model was influenced by the non-linear neuron model, which has a simple structure and the great computational ability. The suggested neuron’s linearity is determined by the weight and bias associated with each quaternionic-valued input. Non-commutative multiplication of all linearly connected quaternionic input-weight terms accommodates the non-linearity. To train three-layered networks with QVM neurons, the standard quaternionic-gradient-based backpropagation (QBP) algorithm is utilized. The computational and generalization capabilities of the QVM neuron are assessed through training and testing in the quaternionic domain utilizing benchmark problems, such as 3D and 4D chaotic time-series predictions, 3D geometrical transformations, and 3D face recognition. The training and testing outcomes are compared to conventional and root-power mean (RPM) neurons in quaternionic domain using training–testing MSEs, network topology (parameters), variance, and AIC as statistical measures. According to these findings, networks with QVM neurons have greater computational and generalization capabilities than networks with conventional and RPM neurons in quaternionic domain.

A basic identification of late auditory evoked potentials at infrasound frequencies: Support via neural network–based signal processing

Concerns about potential health risks from infrasound exposure require objective investigation methods for the perception of infrasound by humans. Neural-network methods were applied to identify weak infrasound evoked potentials and to investigate the efficacy of these techniques. Two simple networks – a fully connected three-layer feed-forward network and a two-layer autoencoder – were designed for the analysis of electroencephalography (EEG) data recorded in response to infrasound stimuli presented. Late auditory evoked potentials (LAEPs) were detected and correlation factors between the target and the output of the networks were determined to assess the differentiation ability of the two networks. Both networks were able to differentiate infrasound evoked potentials from noise but showed different performance levels with respect to a differentiation threshold. The results can be applied to objectively identify perception events by infrasound in humans.

Amplitude death in multiplex networks with competing attractive and repulsive interactions

Amplitude death (AD) phenomenon is one of the most striking and ubiquitous collective behaviors of coupled dynamical networks, in which all the dynamical units will cease their oscillations totally when the coupling occurs. Various appealing works have been devoted to the study of AD in the single-layer networks from theoretical and experimental perspectives in the last decades. However, it is still unclear under which conditions AD can be induced in the multiplex networks. In this work, we investigate the onset of AD of coupled systems connected via multiplex network architectures in the presence of competing attractive and repulsive intralayer and interlayer interactions. We first theoretically derive the critical condition of AD for a class of generalized multiplex network models. Then we apply it to calculate the stable AD regions for the case of a single-layer network of Stuart–Landau oscillators and observe that in the single-layer ring network, AD only can occur for small networks regardless of how to tune the proportion of repulsive coupling. Whereas, for the single-layer all-to-all network, AD always can appear, and the larger the network size or the proportion of repulsive coupling, the smaller the required coupling strength for AD is. Finally, we show in the three-layer multiplex network of Stuart–Landau oscillators that the stable AD regions can be concluded to four types based on the intralayer and interlayer network topologies. In particular, even if AD does not exist separately in each layer network, it can be reached by choosing appropriately interlayer interaction in the three-layer multiplex network. Our study sheds a new insight into the generation of AD phenomenon and gives a general framework to analyze the steady state behaviors of coupled systems in the multiplex networks.

Metabolite annotation from knowns to unknowns through knowledge-guided multi-layer metabolic networking

Liquid chromatography - mass spectrometry (LC-MS) based untargeted metabolomics allows to measure both known and unknown metabolites in the metabolome. However, unknown metabolite annotation is a major challenge in untargeted metabolomics. Here, we develop an approach, namely, knowledge-guided multi-layer network (KGMN), to enable global metabolite annotation from knowns to unknowns in untargeted metabolomics. The KGMN approach integrates three-layer networks, including knowledge-based metabolic reaction network, knowledge-guided MS/MS similarity network, and global peak correlation network. To demonstrate the principle, we apply KGMN in an in vitro enzymatic reaction system and different biological samples, with ~100–300 putative unknowns annotated in each data set. Among them, >80% unknown metabolites are corroborated with in silico MS/MS tools. Finally, we validate 5 metabolites that are absent in common MS/MS libraries through repository mining and synthesis of chemical standards. Together, the KGMN approach enables efficient unknown annotations, and substantially advances the discovery of recurrent unknown metabolites for common biological samples from model organisms, towards deciphering dark matter in untargeted metabolomics.

FGOR: Flow-Guided Opportunistic Routing for Intrabody Nanonetworks

The advancement of nano communication has opened the door for the development of intrabody medical application services. Flow-guided nano-communication networks have gained major attraction in recent years as an effective solution for intrabody sensing and actuation. This article builds a three-layer vertical network structure for intrabody nanonetworks, i.e., nano nodes, nano routers, and gateway, where data packets generated by nano nodes are relayed to the gateway through nano routers or other nodes. However, how to guarantee the data transmission through the way of multiple hops in such a scenario is an unsolved challenge. In order to improve the throughput and reduce the energy consumption of intrabody nanonetworks in a single-flow environment where the nano devices are restricted, a flow-guided opportunistic routing (FGOR) protocol is proposed. In FGOR, a relative position (RP) model is proposed to formulate the criterion for candidate relay selection (CRS) and enable the nodes’ direction awareness to the gateway. Moreover, the CRS criterion is redesigned through a mobility gradient (MG) model further derived from the RP model. The candidate nodes are prioritized based on node ID, available energy, and RP information of nodes to perform backoff forwarding for decreasing transmission redundancy. Simulation results show that the RP model improves the throughput and significantly extends the lifecycle of intrabody nanonetwork by reducing the energy consumption. Compared with the RP model, the MG model performs better in terms of delay and successful transmission rate, especially within the circulation environment of intrabody.

Optimal Allocation of Enterprise Resources Based on the Intelligent Algorithm from the Perspective of Multidimensional Dynamic Innovation.

Faced with the upsurge of digital technology, many small and medium-sized startups are aware of the opportunities and challenges it brings and are actively responding to digital transformation. Digital transformation is a type of strategic change with certain risks. On the one hand, this requires business leaders to have a sense of change, and on the other hand, it also requires certain resources to be invested. As a result, in the real world, not all small and medium-sized entrepreneurial firms have the ability or inclination to implement digital transformation. SMEs' digital transformation has become a key factor in promoting the national economy's transition from new and old kinetic energy and providing new prospects for development of small and medium firms. As a starting point, this study devises an index system for assessing the digital maturity of small and medium-sized businesses. Based on the AHP method in the multicriteria framework, a hierarchical structure is established for each index, a three-layer basic framework is established, and the weight of the evaluation index is calculated. Second, this work establishes a BP network model for digital transformation maturity assessment of startups based on AHP and establishes a three-layer BP network structure. This work aims to optimize BP network using the improved ISFLA algorithm. It improves the adaptive step size update formula in the SFLA algorithm by using the mutation operator and improves the evolution method of the worst individual of the frog to the simultaneous evolution of multiple poor individuals. The constructed ISFLA-BP algorithm is then used to evaluate the digital transformation maturity of small and medium-sized startups. Finally, systematic and comprehensive experiments are carried out to verify superiority as well as feasibility of the method.

Reading Wishes from the Lips: Cancer Patients' Need for Psycho-Oncological Support during Inpatient and Outpatient Treatment.

Background: Psycho-oncological support (PO) is an effective measure to reduce distress and improve the quality of life in patients with cancer. Currently, there are only a few studies investigating the (expressed) wish for PO. The aim of this study was to evaluate the number of patients who request PO and to identify predictors for the wish for PO. Methods: Data from 3063 cancer patients who had been diagnosed and treated at a Comprehensive Cancer Center between 2011 and 2019 were analyzed retrospectively. Potential predictors for the wish for PO were identified using logistic regression. As a novelty, a Back Propagation Neural Network (BPNN) was applied to establish a prediction model for the wish for PO. Results: In total, 1752 patients (57.19%) had a distress score above the cut-off and 14.59% expressed the wish for PO. Patients’ requests for pastoral care (OR = 13.1) and social services support (OR = 5.4) were the strongest predictors of the wish for PO. Patients of the female sex or who had a current psychiatric diagnosis, opioid treatment and malignant neoplasms of the skin and the hematopoietic system also predicted the wish for PO, while malignant neoplasms of digestive organs and older age negatively predicted the wish for PO. These nine significant predictors were used as input variables for the BPNN model. BPNN computations indicated that a three-layer network with eight neurons in the hidden layer is the most precise prediction model. Discussion: Our results suggest that the identification of predictors for the wish for PO might foster PO referrals and help cancer patients reduce barriers to expressing their wish for PO. Furthermore, the final BPNN prediction model demonstrates a high level of discrimination and might be easily implemented in the hospital information system.

Numerical prediction of microstructure and hardness for low carbon steel wire Arc additive manufacturing components

The objective of this research is to define an optimized strategy for wire arc additive manufacturing (WAAM) process with a numerical tool. In this paper, a three-dimensional scaled steel plate model (120 mm × 24 mm × 6 mm) is built for numerical simulations to replace the expensive physical WAAM experiments. A series of thermo-metallo-mechanical analyses is conducted by using ABAQUS CAE user subroutines in which, thermal, metallurgical and mechanical models for gas metal arc welding (GMAW) process are implemented. Groups of variables in WAAM process namely wire melting current, voltage and torch moving speeds, as well as interval layer cooling coefficients, are chosen as input parameters of the artificial neural network (ANN). The two targeted values are hardness and ultimate strength of the steel plate model, which are obtained by fully coupled thermo-metallo-mechanical simulations or by quick results from commercial software JmatPro, and by real measurements on the test samples of WAAM experimental plates. In this primary study, Taguchi algorithm is used for data preparations of the numerical experiments. The tests are fulfilled with Neural Networks (NN) tool in MATLAB. A typical three-layer feedforward network is used for general works. The developed models show good prediction capability for hardness and ultimate strength. The ANN algorithm presents high potential in bidirectional modeling to develop the WAAM strategy tool. It is possible to realize the inverse modeling from properties obtained by fractions of phase volume to WAAM processing parameters.

Study on Cascading Failure and Elasticity of UAV Swarm Communication Network

As an important new force in information warfare, the UAV swarm has attracted more and more attention from militarists and scholars of various countries. At present, large-scale and low-cost UAV swarms have been gradually applied to reconnaissance operations. The invulnerability and elasticity of its communication network are the key factors that determine whether the swarm can successfully complete the reconnaissance mission. The research object of this study is the UAV swarm communication network, which performs reconnaissance missions. The swarm network is extracted as a three-layer interdependent network model. We apply scale-free network theory and the new connection probability equation to establish three subnetworks. Then, a three-layer interdependent network is constructed by using the interlayer connection rules of the nodes with the largest degree. The classical M-L model is extended to an interdependent network. An interlayer load redistribution rule is proposed to simulate the cascading failure process of swarm networks. Then, we attack network nodes randomly and observe the invulnerability and elasticity of this network. The simulation results show that the performance of the interdependent network is better than that of the single-layer network due to the effect of the interdependent links. By analyzing the experimental results, some feasible suggestions are put forward to improve the invulnerability and elasticity of reconnaissance UAV swarm communication network.