Searcharxiv⌕ Search

arXiv subjects

Jinde Cao

Publications and source records attributed to Jinde Cao.

47 records · Page 3Linked to original sources
arXiv2022

Sensors Design for Large-Scale Boolean Networks via Pinning Observability

In this paper, a set of sensors is constructed via the pinning observability approach with the help of observability criteria given in [1] and [2], in order to make the given Boolean network (BN) be observable. Given the assumption that system states can be accessible, an efficient pinning control scheme is developed to generate an observable BN by adjusting the network structure rather than just to check system observability. Accordingly, the sensors are constructed, of which the form is consistent with that of state feedback controllers in the designed pinning control. Since this pinning control approach only utilizes node-to-node message communication instead of global state space information, the time complexity is dramatically reduced from $O(2^{2n})$ to $O(n^2+n2^d)$, where where $n$ and $d$ are respectively the node number of the considered BN and the largest in-degree of vertices in its network structure. Finally, we design the sensors for the reduced D. melanogaster segmentation polarity gene network and the T-cell receptor kinetics, respectively.

eess.SY↗
arXiv2022

A SOM-based Gradient-Free Deep Learning Method with Convergence Analysis

As gradient descent method in deep learning causes a series of questions, this paper proposes a novel gradient-free deep learning structure. By adding a new module into traditional Self-Organizing Map and introducing residual into the map, a Deep Valued Self-Organizing Map network is constructed. And analysis about the convergence performance of such a deep Valued Self-Organizing Map network is proved in this paper, which gives an inequality about the designed parameters with the dimension of inputs and the loss of prediction.

cs.LG↗
arXiv2021

Polynomial-Time Algorithms for Structurally Observable Graphs by Controlling Minimal Vertices

The aim of this paper is to characterize an important class of marked digraphs, called structurally observable graphs (SOGs), and to solve two minimum realization problems. To begin with, by exploring structural observability of large-scale Boolean networks (LSBNs), an underlying type of SOGs is provided based on a recent observability criterion of conjunctive BNs. Besides, SOGs are also proved to have important applicability to structural observability of general discrete-time systems. Further, two minimum realization strategies are considered to induce an SOG from an arbitrarily given digraph by marking and controlling the minimal vertices, respectively. It indicates that one can induce an observable system by means of adding the minimal sensors or modifying the adjacency relation of minimal vertices. Finally, the structural observability of finite-field networks, and the minimum pinned node theorem for Boolean networks are displayed as application and simulation. The most salient superiority is that the designed algorithms are polynomial time and avoid exhaustive brute-force searches. It means that our results can be applied to deal with the observability of large-scale systems (particularly, LSBNs), whose observability analysis and the minimum controlled node theorem are known as intractable problems.

eess.SY↗
arXiv2021

A RNNs-based Algorithm for Decentralized-partial-consensus Constrained Optimization

This technical note proposes the decentralized-partial-consensus optimization with inequality constraints, and a continuous-time algorithm based on multiple interconnected recurrent neural networks (RNNs) is derived to solve the obtained optimization problems. First, the partial-consensus matrix originating from Laplacian matrix is constructed to tackle the partial-consensus constraints. In addition, using the non-smooth analysis and Lyapunov-based technique, the convergence property about the designed algorithm is further guaranteed. Finally, the effectiveness of the obtained results is shown while several examples are presented.

math.OC↗
arXiv2021

A Directed Spanning Tree Adaptive Control Framework for Time-Varying Formations

In this paper, the time-varying formation and time-varying formation tracking problems are solved for linear multi-agent systems over digraphs without the knowledge of the eigenvalues of the Laplacian matrix associated to the digraph. The solution to these problems relies on a framework that generalizes the directed spanning tree adaptive method, which was originally limited to consensus problems. Necessary and sufficient conditions for the existence of solutions to the formation problems are derived. Asymptotic convergence of the formation errors is proved via graph theory and Lyapunov analysis.

eess.SY↗
arXiv2020

STCNet: Spatio-Temporal Cross Network for Industrial Smoke Detection

Industrial smoke emissions present a serious threat to natural ecosystems and human health. Prior works have shown that using computer vision techniques to identify smoke is a low cost and convenient method. However, industrial smoke detection is a challenging task because industrial emission particles are often decay rapidly outside the stacks or facilities and steam is very similar to smoke. To overcome these problems, a novel Spatio-Temporal Cross Network (STCNet) is proposed to recognize industrial smoke emissions. The proposed STCNet involves a spatial pathway to extract texture features and a temporal pathway to capture smoke motion information. We assume that spatial and temporal pathway could guide each other. For example, the spatial path can easily recognize the obvious interference such as trees and buildings, and the temporal path can highlight the obscure traces of smoke movement. If the two pathways could guide each other, it will be helpful for the smoke detection performance. In addition, we design an efficient and concise spatio-temporal dual pyramid architecture to ensure better fusion of multi-scale spatiotemporal information. Finally, extensive experiments on public dataset show that our STCNet achieves clear improvements on the challenging RISE industrial smoke detection dataset against the best competitors by 6.2%. The code will be available at: https://github.com/Caoyichao/STCNet.

cs.CV↗
arXiv2020

Stability Analysis of Quaternion-valued Neural Networks with Leakage Delay and Additive Time-varying Delays

In this paper, the stability analysis of quaternion-valued neural networks (QVNNs) with both leakage delay and additive time-varying delays is proposed. By employing the Lyapunov-Krasovskii functional method and fully considering the relationship between time-varying delays and upper bounds of delays, some sufficient criteria are derived based on reciprocally convex method and several inequality techniques. The stability criteria are established in two forms: quaternion-valued linear matrix inequalities (QVLMIs) and complex-valued linear matrix inequalities (CVLMIs), in which CVLMIs can be directly resolved by the Yalmip toolbox in MATLAB. Finally, an illustrative example is presented to demonstrate the validity of the theoretical results.

math.DS↗
arXiv2020

Pinning Stabilizer Design for Large-Scale Probabilistic Boolean Networks

This paper investigates the stabilization of probabilistic Boolean networks (PBNs) via a novel pinning control strategy based on network structure. In a PBN, the evolution equation of each gene switches among a collection of candidate Boolean functions with probability distributions that govern the activation frequency of each Boolean function. Owing to the stochasticity, the uniform state feedback controller, independent of switching signal, might be out of work, and in this case, the non-uniform state feedback controller is required. Subsequently, a criterion is derived to determine whether uniform controllers is applicable to achieve stabilization. It is worth pointing out that the pinning control designed in this paper is based on the network structure, which only requires local in-neighbors' information, rather than global information (state transition matrix). Moreover, this pinning control strategy reduces the computational complexity from $O(2^{2n})$ to $O(n2^α)$, and thus it has the ability to handle some large-scale networks, especially the networks with sparse connections. Finally, the mammalian cell-cycle encountering a mutated phenotype is modelled by a PBN to demonstrate the obtained results.

eess.SY↗
arXiv2020

A new approach to descriptors generation for image retrieval by analyzing activations of deep neural network layers

In this paper, we consider the problem of descriptors construction for the task of content-based image retrieval using deep neural networks. The idea of neural codes, based on fully connected layers activations, is extended by incorporating the information contained in convolutional layers. It is known that the total number of neurons in the convolutional part of the network is large and the majority of them have little influence on the final classification decision. Therefore, in the paper we propose a novel algorithm that allows us to extract the most significant neuron activations and utilize this information to construct effective descriptors. The descriptors consisting of values taken from both the fully connected and convolutional layers perfectly represent the whole image content. The images retrieved using these descriptors match semantically very well to the query image, and also they are similar in other secondary image characteristics, like background, textures or color distribution. These features of the proposed descriptors are verified experimentally based on the IMAGENET1M dataset using the VGG16 neural network.

cs.CV↗
arXiv2020

A Separation-Based Methodology to Consensus Tracking of Switched High-Order Nonlinear Multi-Agent Systems

This work investigates a reduced-complexity adaptive methodology to consensus tracking for a team of uncertain high-order nonlinear systems with switched (possibly asynchronous) dynamics. It is well known that high-order nonlinear systems are intrinsically challenging as feedback linearization and backstepping methods successfully developed for low-order systems fail to work. At the same time, even the adding-one power-integrator methodology, well explored for the single-agent high-order case, presents some complexity issues and is unsuited for distributed control. At the core of the proposed distributed methodology is a newly proposed definition for separable functions: this definition allows the formulation of a separation-based lemma to handle the high-order terms with reduced complexity in the control design. Complexity is reduced in a twofold sense: the control gain of each virtual control law does not have to be incorporated in the next virtual control law iteratively, thus leading to a simpler expression of the control laws; the order of the virtual control gains increases only proportionally (rather than exponentially) with the order of the systems, dramatically reducing high-gain issues.

cs.MA↗