Ladder Network Research Articles

Malware Traffic Classification Using Domain Adaptation and Ladder Network for Secure Industrial Internet of Things

Malware traffic classification (MTC) is a key technology for anomaly and intrusion detection in secure Industrial Internet of Things (IIoT). Traditional MTC methods based on port, payload, and statistic depend on the manual-designed features, which have low accuracy. Recently, deep-learning methods have attracted a significant attention due to their high accuracy in terms of classification. However, in practical application scenarios, deep-learning methods require a large amount of labeled samples for training, while the available labeled samples for training are very rare. Furthermore, the preparation of a large amount of labeled samples requires a lot of labor costs. To solve these problems, this article proposes three methods based on semisupervised learning (SSL), transfer learning (TL), and domain adaptive (DA), respectively. Our proposed methods use a large amount of unlabeled data collected in the Internet traffic, which can greatly improve the classification accuracy with few labeled samples. Then, we use the DA method to solve the mismatch problem between the source domain and the target domain in the TL process. The proposed method is not only applicable to the shallow network but also to the deep neural network structure, and can achieve better classification results. Experimental results show that our proposed methods can satisfy the requirement of MTC in the case of few labeled samples in IIoT. The source code for all the experiments is available at GitHub.The code of this article can be downloaded from GitHub link: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/yzjh/Keras-MTC-DA-Ladder</uri> .

Low-frequency development approximations to the transmissive Warburg diffusion impedance

A study of the behaviour of the low-frequency development approximations to the transmissive Warburg diffusion impedance in both the frequency and time domains is presented. Simple low-frequency electric circuits have been derived from the Weierstrass products expansion and the equivalent ladder networks based on Foster, Maxwell and Cauer series. An original comparative study of the different low-frequency approximated impedances, including the characteristic frequencies, and those of the transmissive Warburg element is reported. The galvanostatic small-signal dynamic responses involving current steps and ramps have been compared by using exact numerical solutions and the approximated solutions at low frequencies derived from the different electric circuits. This study allows the dynamic response of electrochemical energy devices, such as fuel cells or rechargeable batteries, to be physically interpreted on the basis of an only relaxation time by means of the charging/discharging process of a capacitor through one or two resistors.

Error Estimator for Cauer Ladder Network Representation

The Cauer ladder network (CLN) method enables to construct a reduced-based circuit model of analytical or numerical models, e.g., finite-element (FE) model, under quasistatic approximation. This article proposes an estimator that provides guaranteed upper bounds of the truncation error due to the CLN method. The error estimator is tested on an analytical model and an FE model to validate the approach.

Generating a Cauer Ladder Network Representation of Eddy Current Fields Using Scalar Potentials

Formulations in terms of scalar potentials are proposed to solve the static field problems occurring when computing the parameters of a Cauer ladder network representation of two-pole devices involving eddy-current effects. The curl equations are satisfied by efficiently generating vector potentials describing the known flux density and current density and introducing unknown scalar potentials to represent the electric and magnetic field intensities. The scalar potentials are approximated using nodal basis functions in the finite-element realization, thus leading to Poisson equations to be easily solved. A simple numerical example illustrates the method.

Nonlinear Model Order Reduction of Induction Motors Using Parameterized Cauer Ladder Network Method

In this study, we established the nonlinear model order reduction (MOR) of induction motors by parameterizing a multi-port Cauer ladder network (CLN). Appropriate parameters were selected to incorporate nonlinear magnetic characteristics. The parameterized multi-port CLN was applied to the transient analysis of a rotating induction motor. The proposed method reproduced the finite-element analysis results with various driving frequencies and slips. The parameterized multi-port CLN can effectively reduce the computation time for analyses requiring a large number of time steps.

Frequency-Domain Model Order Reduction of Electromagnetic Field in Induction Motor

A model order reduction (MOR) method for an induction motor using a Cauer ladder network (CLN) is developed in the frequency domain. A multiport frequency transformation between the stator and mover domains is derived by neglecting the spatial harmonic interactions. Even after neglecting the harmonic interactions, the reduced model provides a reasonably accurate frequency response, which is more accurate than that of the conventional approximated equivalent circuit.

Reduced Order Modeling Based on Multiport Cauer Ladder Network for Space Harmonics of Air-Gap Flux Density in Cage Induction Motor

This study investigated an efficient procedure for developing an accurate behavioral model of a cage induction motor (IM) based on the multiport Cauer ladder network (CLN). The CLN method was applied to a cage IM with semi-closed rotor slots as a model order reduction (MOR) technique, and a method for selecting the appropriate space harmonics (SHs) included in the air-gap flux density, which is necessary for a multiport CLN method for induction machines, was discussed. Then, the developed approach was applied to the transient analysis of the cage IM coupled with a control system, and its effectiveness in terms of computational accuracy and cost was investigated.

Resistive Ladder Network in Handle Bar Switch Assembly

Abstract: An switching interface of handle bar assembly LH-RH, where it comprise a switching network have a input terminal Coupled with an input voltage supply, an output terminal. The interface network comprises of series of resistance having a predertmined values,i.e each of switches present on handle bar LH as well as in RH are coupled in between input &amp; output terminal which are used to evaluate a particular voltage value band when it get connect with 12 V voltage DC source . The switching interface further comprising or include a controller which gets input from the output terminal of interface Network when any of the switch is closed.After evaluating the total resistance at output terminal across interface (When any of switch is pressed) comparing the output Voltage with the supplied one .we can evaluate the voltage Ratio which reprents which button is pressed.

Ladder Network Synthesis in Wide Frequency Range for Transformer Winding From its Driving-Point Admittance Data

Ladder network synthesis is very significant for winding fault diagnosis within transformer. To synthesize the network reversely based on the measurable frequency response analysis (FRA) data is the only applicable way. To date the iron core and non-tested winding, which result in the frequency-dependent network components and multiple ladders in some frequency ranges, are usually not considered in the reverse process and thus the synthesis precision is largely limited. This paper proposes to synthesize multiple ladder networks in different frequency regions to handle this problem. Firstly, the sensitivities and frequency-dependent features of network components are analyzed, based on which the topology and components of the networks in diverse frequency ranges are determined afterwards. Further, the network synthesis strategies in different frequency ranges are elaborately designed. Finally, the synthesis method is applied on a distribution transformer successfully, with the fact that the extracted network parameters meet all the constraints and its FRA curve matches well with the measured one. An intact method of multiple-network synthesis for transformer winding in wide frequency range, considering the iron core and non-tested winding, is offered in this paper.

Approach for Identification of Inter-Turn Fault Location in Transformer Windings Using Sweep Frequency Response Analysis

As inter-turn faults in transformer windings are the most severe, their delayed detection and localization may create extensive damage to the winding. Therefore, a new inter-turn fault localization methodology based on sweep frequency response analysis (SFRA) through calculation of Pre-fault Inter-Turn Fault Factor ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ITFF_pre</i> ) for all possible fault locations by estimating the values of series and shunt capacitance of the windings during healthy conditions is presented. For a faulty transformer, Post-fault Inter-Turn Fault Factor ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ITFF_post</i> ) is calculated by determining the value of equivalent capacitance using SFRA. The exact fault location in the faulty transformer is obtained by comparing the single calculated value of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ITFF_post</i> of the faulty transformer with the values stored in the lookup table. The efficacy of the suggested approach is verified by performing faults at various locations on the transformer model developed in the laboratory. Its authenticity is also verified on an existing 400 kVA, 11 kV/440 V distribution transformer installed in the real field. The results indicate that the suggested method is capable to identify inter-turn fault location with the minimum ladder network parameters. Finally, a relative assessment of the suggested approach with numerous other methods confirms the superiority in terms of inter-turn fault localization.

Development of Prototype Fractional Order Controller for a Grid-Tied Photovoltaic System

This paper presents design of a robust fractional order proportional-integral (FO-PI) prototype controller for a grid connected photovoltaic (PV) system. The robustness in face of parameter variation is handled by designing a suitable controller considering sensitivity function, gain margin and phase margin for both inner and outer control loops. As FO-PI controller is not yet available in physical form and due to complexity involved in grid-tied PV system, we propose an alternative way of hardware implementation of inner loop FO-PI controller by using fractor through RC ladder network. Firstly, an emulator circuit of the inner current loop comprising the FO-PI controller (including fractor and the proportional gain) along with the transfer function of inverter and filter is developed and the response is verified through a real-time simulator (OPAL-RT). Finally, the FO-PI part of the emulator circuit is interfaced with the PC target to form a hardware-in-loop (HIL) by employing OPAL-RT. The performance of the complete system is verified through OPAL-RT simulator. The result shows the improved robustness by the proposed control design method.

Capacitance Characteristics Behavior of 0.5 Order FC Using CFOA Based FC Multiplier

This paper presents a method for capacitance scaling of Fractional Capacitor (FC) which is implemented using Current Feedback Operational Amplifiers (CFOA) based Capacitance Multipliers (C Multipliers). The circuit facilitates the change in FC value without changing component values in R-C network used for FC modelling or fabricating a new FC. The performance of the proposed circuit is examined for non ideal effects of CFOA. Effective impedance of scaled FC is examined through MATLAB simulations. The functionality of the realized scalers is verified using SPICE simulations where the FC is modelled using domino RC ladder network. Simulation results for impedance magnitude and phase responses are presented for various scaling factors and are compared with theoretical counterparts. The circuit application of proposed FC scaler is demonstrated through implementation of fractional order lossy and lossless integrators; and may be extended to fractional order filters, oscillators, controllers etc.

Development of an on-chip configurable DAC module for monolithic active pixel sensor

This paper describes an on-chip configurable Digital to Analog Converter (DAC) module for monolithic active pixel sensor. The DAC module consists of four 10-bit voltage DACs, seven 8-bit current DACs, a bandgap circuit, and a configure interface. The voltage DAC is implemented with an R-2R resistor ladder network, and each LSB corresponds to 3 mV. The current DAC is in the current-steering type with a thermometer code. Each LSB of the current DAC corresponds to 10 nA. The bandgap circuit provides a stable, temperature-independent reference voltage of 1.25 V to the DACs. All the DACs can be accessed and configured with the configure interface. The DAC module covers 3074 µm × 400 µm, and the total power consumption is 46.2 mW. This paper will discuss the design and performance of this DAC module.

SDNN: Symmetric deep neural networks with lateral connections for recommender systems

The recommender system is the key approach to alleviate the data explosion problem. Recently, with the rapid development of deep learning, there are several researches of employing deep neural networks (DNNs) on recommender systems. Most of these methods tend to capture the complex mapping relations between user-item representation and matching score via DNNs. These methods are mainly a pyramid structure which maps relations into low-dimensional space and then predicts the result by logistic regression. However, partial relations may be linearly indivisible in low-dimensional space. As we know, data that are hard to be separated in low-dimensional space can become much easier after being mapped into a high-dimensional space. Hence, motivated by the ladder network, we propose a Symmetric Deep Neural Networks (SDNN) with lateral connections, which can learn relations in both high-dimensional and low-dimensional spaces simultaneously. Moreover, considering that deep neural network is very inefficient in catching low-rank relations between users and items, we further combine SDNN with an improved deep matrix factorization model into a unified framework, and name this new model DualCF. Extensive experiments on three benchmark datasets are conducted and the results verify the effectiveness of SDNN and DualCF over state-of-the-art models for implicit feedback prediction.

Band structures of edge magnetoplasmon crystals

A two-dimensional electron gas in a static external magnetic field exhibits two distinct collective excitation modes. The lower frequency mode propagates along the periphery of the domain almost freely with an extended lifetime, which is referred to as edge magnetoplasmons. Peculiar phenomena caused by a capacitive interaction between nearest-neighbor domains are known, such as the emergence of Tomonaga-Luttinger liquid and charge-density fractionalization. Meanwhile, the number of coupled domains investigated in the past has been limited to a small number. Here, we performed calculations using a continuum model of edge magnetoplasmons, the band structures of planar crystals composed of an arbitrary number of domains, including a chain, ladder, and honeycomb network, with the general interaction strength. We explain the band structures in terms of the fundamental collective modes of a molecule composed of two equivalent domains. These are the extended chiral propagation modes that yield a linear dispersion band and the standing wave modes localized in the coupled regions that cause a flat band. The chain's band structures resemble the miniband structures calculated from the Kronig-Penney model for the electron in a semiconductor superlattice. We point out that a geometrical deformation of the chain does not change the band structures as it can be expressed as a gauge degree of freedom that only causes a shift in the wave number.

Tailoring flat bands and topological phases in a multistrand Creutz network

We prove that, a suitable correlation between the system parameters can trigger topological phase transition and flat bands in a multi strand Creutz ladder network, when a staggered second neighbor interaction is included along the x axis. An appropriate change of basis maps such a finite N strand mesh into N or N 1 decoupled Su Schrieffer Heeger chains, depending onNeven or odd. A simple intuitive method, using a real space decimation scheme turns out to be very powerful in analytically extracting the flat bands, explaining their degeneracy or a lifting of the same. Our results are analytically exact, and may inspire experiments in photonics and ultracold atomic systems.

The comparative study of resolving parameters for a family of ladder networks

&lt;abstract&gt;&lt;p&gt;For a simple connected graph $ G = (V, E) $, a vertex $ x\in V $ distinguishes two elements (vertices or edges) $ x_1\in V, y_1 \in E $ if $ d(x, x_1)\neq d(x, y_1). $ A subset $ Q_m\subset V $ is a mixed metric generator for $ G, $ if every two distinct elements (vertices or edges) of $ G $ are distinguished by some vertex of $ Q_m. $ The minimum cardinality of a mixed metric generator for $ G $ is called the mixed metric dimension and denoted by $ dim_m(G). $ In this paper, we investigate the mixed metric dimension for different families of ladder networks. Among these families, we consider Möbius ladder, hexagonal Möbius ladder, triangular Möbius ladder network and conclude that all these families have constant-metric, edge metric and mixed metric dimension.&lt;/p&gt;&lt;/abstract&gt;

Assignment Computations Based on Cexp Average in Various Ladder Graphs

This study introduces the Cexp average assignments and investigates its properties using various ladder graphs. The ladder graphs can be found in every communication networks. Ladder networks are increasingly being used in everyday life for monitoring and environmental applications such as domestic, military, surveillance, industrial, medical applications, and traffic management. These datasets are afflicted by the average representation of the graph structure. It aids in the visualisation and comprehension of data analysis. The Cexp labeling is used in sensor networks, adhoc networks, and other applications. It also efficiently creates a communication network after using noise reduction methods to remove salt and pepper noise.

End-to-end Image Dehazing Based on Ladder Network and Cross Fusion

End-to-end Image Dehazing Based on Ladder Network and Cross Fusion

Semisupervised Adaptive Ladder Network for Remote Sensing Image Change Detection

Nowadays, due to the difficult acquisition of true labels, a semisupervised neural network has shown great potential for change detection (CD) in remote sensing images. However, most of the traditional semisupervised neural network detection frameworks are complex to train and require additional structural analysis, along with a fixed structure, lacking universality. In this article, a semisupervised adaptive ladder network (SSALN) for remote sensing image CD is proposed, which enables dual-input label-incremental architecture searching with a concise and variable structure. First, SSALN is suitable for CD from two remote sensing images of any type with the characteristic of minimal label dependency and automatic network structure adjustment. The network can generate more reliable pseudolabels through continuous iterations to help limited real labels exploit implicit information, identify the most effective network, and form the ascending network structure optimization. Second, the acquisition of pseudolabels is the fusion of semisupervised and unsupervised CD approaches, which ensures the multiperspective information supplement. Multiple CD maps are fused to generate labels for the next iteration, making the predicting more reliable. Finally, both homogenous images and heterogenous images are tested with experiments. Even if the detection object is switched, it can be well adaptive and compatible without manual modification of the network. Experimental results demonstrate that the proposed method can promote the flow of label information through structure searching and self-circulation in the ascending network optimization; thus, it has outstanding performance on tasks of remote sensing image CD.