Bio-inspired Network Research Articles

A bio-inspired visual collision detection network integrated with dynamic temporal variance feedback regulated by scalable functional countering jitter streaming

In pursuing artificial intelligence for efficient collision avoidance in robots, researchers draw inspiration from the locust’s visual looming-sensitive neural circuit to establish an efficient neural network for collision detection. However, existing bio-inspired collision detection neural networks encounter challenges posed by jitter streaming, a phenomenon commonly experienced, for example, when a ground robot moves across uneven terrain. Visual inputs from jitter streaming induce significant fluctuations in grey values, distracting existing bio-inspired networks from extracting visually looming features. To overcome this limitation, we derive inspiration from the potential of feedback loops to enable the brain to generate a coherent visual perception. We introduce a novel dynamic temporal variance feedback loop regulated by scalable functional into the traditional bio-inspired collision detection neural network. This feedback mechanism extracts dynamic temporal variance information from the output of higher-order neurons in the conventional network to assess the fluctuation level of local neural responses and regulate it by a scalable functional to differentiate variance induced by incoherent visual input. Then the regulated signal is reintegrated into the input through negative feedback loop to reduce the incoherence of the signal within the network. Numerical experiments substantiate the effectiveness of the proposed feedback loop in promoting collision detection against jitter streaming. This study extends the capabilities of bio-inspired collision detection neural networks to address jitter streaming challenges, offering a novel insight into the potential of feedback mechanisms in enhancing visual neural abilities.

Tracking and classification performances in the bio-inspired asymmetric and symmetric networks

Abstract Machine learning, deep learning and neural networks are extensively applied for the development of many fields. Though their technologies are improved greatly, they are often said to be opaque in terms of explainability. Their explainable neural functions will be essential to realization in the networks. In this paper, it is shown that the bio-inspired networks are useful for the explanation of tracking and classification of features. First, the asymmetric network with nonlinear functions is created based on the bio-inspired retinal network. They have orthogonal properties useful for the tracking of features compared with the conventional symmetric networks, which is also proposed on the biological functions. Next, the analysis for the independence of the subspaces between the Fourier bases and the asymmetric network bases is performed. It was that the asymmetric networks have better performances in the classification compared with the symmetric ones. Further, the layered asymmetric networks generate the higher dimensional orthogonal bases that improve the classification accuracies by the replacements of bases. Finally, we classified Reuters collections data applying the explainable processing steps, which consist of the linear discriminations and the sparse coding with nearest neighbor relation for classification.

A bio-inspired network with automatic brightness adaptation for pavement crack detection in different environments

A bio-inspired network with automatic brightness adaptation for pavement crack detection in different environments

Bioinspired polysiloxane/WS2 composites with stretchable and near-infrared light remote-controlled self-healing abilities for deployable deformation actuators

Despite tremendous advancement of actuators based on self-healing polymeric composites, inevitable trade-offs in maintaining sensitive stimuli response and mechanical and self-healing properties are still left in suspense. Inspired by the character of butterfly wings, herein, we proposed a brand-new strategy to design polysiloxane composites with bioinspired network structure, which consists of tannic acid modified photothermal reagent tungsten disulfide nanosheets as vein and self-healing polysiloxane elastomers with multiple dynamic bonds as embedded membrane. High dense hydrogen bonds between nanosheets and elastomers enable interfaces to enhance interfacial strength of composite. The elaborate bioinspired network was employed as an essential role to endow composites with conspicuous stretchability (1146%), and near-infrared light (NIR) remote-controlled self-healing efficiency (97%). Moreover, the composite with conspicuous bioinspired network structure is connected with low coefficient of thermal expansion film by hydrogen bonds gathered around the interface, which endows deployable deformation actuator with a remarkably fast NIR response (7.50 s) due to bioinspired heat conduction network pathway. This work offers a versatile bioinspired strategy for design of self-healing actuators with conspicuous responding deformation and mechanical properties that enables an application to a wide range of flexible and smart devices.

A biologically inspired architecture with switching units can learn to generalize across backgrounds

Humans and other animals navigate different environments effortlessly, their brains rapidly and accurately generalizing across contexts. Despite recent progress in deep learning, this flexibility remains a challenge for many artificial systems. Here, we show how a bio-inspired network motif can explicitly address this issue. We do this using a dataset of MNIST digits of varying transparency, set on one of two backgrounds of different statistics that define two contexts: a pixel-wise noise or a more naturalistic background from the CIFAR-10 dataset. After learning digit classification when both contexts are shown sequentially, we find that both shallow and deep networks have sharply decreased performance when returning to the first background — an instance of the catastrophic forgetting phenomenon known from continual learning. To overcome this, we propose the bottleneck-switching network or switching network for short. This is a bio-inspired architecture analogous to a well-studied network motif in the visual cortex, with additional “switching” units that are activated in the presence of a new background, assuming a priori a contextual signal to turn these units on or off. Intriguingly, only a few of these switching units are sufficient to enable the network to learn the new context without catastrophic forgetting through inhibition of redundant background features. Further, the bottleneck-switching network can generalize to novel contexts similar to contexts it has learned. Importantly, we find that — again as in the underlying biological network motif, recurrently connecting the switching units to network layers is advantageous for context generalization.

Routing a quantum state in a bio-inspired network

Routing a quantum state in a bio-inspired network

Bio-Inspired Network for Diagnosing Liver Steatosis in Ultrasound Images.

Using ultrasound imaging to diagnose liver steatosis is of great significance for preventing diseases such as cirrhosis and liver cancer. Accurate diagnosis under conditions of low quality, noise and poor resolutions is still a challenging task. Physiological studies have shown that the visual cortex of the biological visual system has selective attention neural mechanisms and feedback regulation of high features to low features. When processing visual information, these cortical regions selectively focus on more sensitive information and ignore unimportant details, which can effectively extract important features from visual information. Inspired by this, we propose a new diagnostic network for hepatic steatosis. In order to simulate the selection mechanism and feedback regulation of the visual cortex in the ventral pathway, it consists of a receptive field feature extraction module, parallel attention module and feedback connection. The receptive field feature extraction module corresponds to the inhibition of the non-classical receptive field of V1 neurons on the classical receptive field. It processes the input image to suppress the unimportant background texture. Two types of attention are adopted in the parallel attention module to process the same visual information and extract different important features for fusion, which improves the overall performance of the model. In addition, we construct a new dataset of fatty liver ultrasound images and validate the proposed model on this dataset. The experimental results show that the network has good performance in terms of sensitivity, specificity and accuracy for the diagnosis of fatty liver disease.

Edge of Chaos Is Sine Qua Non for Turing Instability

Diffusion-driven instabilities with pattern formation may occur in a network of identical, regularly-spaced, and resistively-coupled cells if and only if the uncoupled cell is poised on a locally-active and stable operating point in the Edge of Chaos domain. This manuscript presents the simplest ever-reported two-cell neural network, combining together only 7 two-terminal components, namely 2 batteries, 3 resistors, and 2 volatile NbOx memristive threshold switches from NaMLab, and subject to diffusion-driven instabilities with the concurrent emergence of Turing patterns. Very remarkably, this is the first time an homogeneous cellular medium, with no other dynamic element than 2 locally-active memristors, hence the attribute all-memristor coined to address it in this paper, is found to support complex phenomena. The destabilization of the homogeneous solution occurs in this second-order two-cell array if and only if the uncoupled cell circuit parameters are chosen from the Edge of Chaos domain. A deep circuit- and system-theoretic investigation, including linearization analysis and phase portrait investigation, provides a comprehensive picture for the local and global dynamics of the bio-inspired network, revealing how a theory-assisted approach may guide circuit design with inherently non-linear memristive devices.

Temporal Graphs and Temporal Network Characteristics for Bio-Inspired Networks during Optimization

Temporal network analysis and time evolution of network characteristics are powerful tools in describing the changing topology of dynamic networks. This paper uses such approaches to better visualize and provide analytical measures for the changes in performance that we observed in Voronoi-type spatial coverage, particularly for the example of time-evolving networks with a changing number of wireless sensors being deployed. Specifically, our analysis focuses on the role different combinations of impenetrable obstacles and environmental noise play in connectivity and overall network structure. It is shown how the use of (i) temporal network graphs, and (ii) network centrality and regularity measures illustrate the differences between various options developed for the balancing act of energy and time efficiency in network coverage. Last, we compare the outcome of these measures with the less abstract classification variables, such as percent area covered and cumulative distance traveled.

Stepwise slime mould growth as a template for urban design

The true slime mould, Physarum polycephalum, develops as a vascular network of protoplasm, connecting node-like sources of food in an effort to solve multi-objective transport problems. The organism first establishes a dense and continuous mesh, reinforcing optimal pathways over time through constructive feedbacks of protoplasmic streaming. Resolved vascular morphologies are the result of an evolutionarily-refined mechanism of computation, which can serve as a versatile biological model for network design at the urban scale. Existing digital Physarum models typically use positive reinforcement mechanisms to capture meshing and refinement behaviours simultaneously. While these automations generate accurate descriptions of sensory and constructive feedback, they limit stepwise design control, reducing flexibility and applicability. A model that decouples the two “phases” of Physarum behaviour would enable multistage control over network growth. Here we introduce such a system, first by producing a site-responsive mesh from a population of nutrient-attracted agents, and then by independently calculating from it a flexible, proximity-defined shortest-walk to produce a final network. We develop and map networks within existing urban environments that perform similarly to those biologically grown, establishing a versatile tool for bio-inspired urban network design.

Smart surgical control under RCM constraint using bio-inspired network

In this paper, we propose a control framework for intelligent surgical robots under the Remote Center of Motion (RCM). The goal of a surgical robot is to assist surgeons in performing complex surgeries. RCM constraint implies that the surgical tip attached to the end-effector of the surgical robot does not slide away from the point of the incision while performing surgery. Implementation of a control algorithm to comply with RCM constraints is a complicated task because of the nonlinear model of the surgical robots and stringent conditions of accuracy imposed by the patient’s safety. This paper proposes an optimization-driven approach to perform the surgical maneuver under RCM constraints. We then applied a bio-inspired optimization algorithm to solve the problem efficiently. For testing the performance of ZNNBAS, we used MATLAB to simulate a surgical procedure. A 7-DOF surgical robot (KUKA LBR IIWA 7) was used as a test bench for running the simulations. The simulation results show that the ZNNBAS is comparable with BAS, PSO, and GA and efficiently and robustly performed the task commanded maneuvers while enforcing the RCM constraints.

Influence of bio-inspired activity regulation through neural thresholds learning in the performance of neural networks

Studies on Kenyon Cells (KCs) in the olfactory system of locust have found evidence that some of them are more responsive towards stimuli than others. This variability suggests that there could be a heterogeneous neural threshold distribution among KCs. This work explores the hypothesis that the heterogeneity in neural thresholds could control the activity level of populations of neurons and facilitate the generation of sparse code to achieve a better representation of stimuli. In order to study this hypothesis, an artificial neural network that adapts many of the strategies observed in the locust olfactory system is proposed, including a new learning algorithm capable of finding the best neural threshold distribution to resolve a certain classification problem and a gain control term that keeps the activity level of the neurons in the hidden layer under a certain limit. The bio-inspired neural network gets the best results when the activity level in the hidden layer is low, for which neural thresholds are more important for a better performance than the connections between the neurons in different layers. Also, it was found that the separability of the internal representations of the different patterns in the classification problem improves when the thresholds are adjusted by the learning algorithm in order to control the activity level. Finally, the performance of this network was compared to SVMs and MLP when applied to resolve a complex classification task with data collected by electronic noses and affected by sensor drift, for which the bio-inspired network obtains very satisfactory results, reaching a performance similar or even better than SVMs and MLP.

Theoretical and experimental research on anisotropic and nonlinear mechanics of periodic network materials

Bio-inspired network materials composed of regularly aligned repeating filamentary microstructures exhibit promising application prospects in tissue engineering and bio-integrated devices due to the typical J-shaped mechanics curve precisely matched to the biological tissues. During the tensile process, an evident nonlinear mechanical anisotropy is induced by the drastic changes of microstructure geometries, which is of great concern in some particular requirements such as identifying the direction with the lowest or highest tensile stiffness and inducing alternate positive and negative or nearly zero Poisson's ratio. An efficient theoretical model for nonlinear anisotropic mechanics is developed in this paper by introduction of equilibrium and deformation compatibility conditions of presentative unit cell under finite uniaxial stretching along arbitrary directions, which is then verified by finite element analyses (FEA) and experiments both graphically and quantitatively. Through this model, the anisotropic mechanical responses of the periodic network materials are studied thoroughly and systematically based on the precise prediction of stress-strain relation, transverse-longitudinal strain relation and the deformed configuration. The effects of both the geometric parameters and the unit cell topology on the anisotropic mechanical responses are analyzed thereafter, which implies that the proposed model can play an instructive role in the design, optimization, and application of the periodic network materials.

Adaptive Orthogonal Characteristics of Bio-Inspired Neural Networks

Abstract In recent years, neural networks have attracted much attention in the machine learning and the deep learning technologies. Bio-inspired functions and intelligence are also expected to process efficiently and improve existing technologies. In the visual pathway, the prominent features consist of nonlinear characteristics of squaring and rectification functions observed in the retinal and visual cortex networks, respectively. Further, adaptation is an important feature to activate the biological systems, efficiently. Recently, to overcome short-comings of the deep learning techniques, orthogonality for the weights in the networks has been developed for the signal propagation and the efficient optimization of the learning. In this paper, bio-inspired asymmetric networks with nonlinear characteristics are proposed, which are derived from the retinal networks in the biological visual pathway. The asymmetric network proposed here was verified to detect the movement of the object, efficiently in our previous studies. This paper shows a new characteristic of the adaptive orthogonality in the asymmetric networks. First, it is shown that the asymmetric network with nonlinear characteristics is effective for generating orthogonality. Second, the proposed asymmetric network with Gabor filters is compared with the conventional energy model from the point of the orthogonality characteristics. Finally, the asymmetric networks with nonlinear characteristics can generate the extended orthogonal bases in independent subspaces, which are useful for classification and efficient learning.

4D Printing of Bioinspired Absorbable Left Atrial Appendage Occluders: A Proof-of-Concept Study.

The significant mismatch of mechanical properties between the implanted medical device and biological tissue is prone to cause wear and even perforation. In addition, the limited biocompatibility and nondegradability of commercial Nitinol-based occlusion devices can easily lead to other serious complications, such as allergy and corrosion. The present study aims to develop a 4D printed patient-specific absorbable left atrial appendage occluder (LAAO) that can match the deformation of left atrial appendage (LAA) tissue to reduce complications. The desirable bioinspired network is explored by iterative optimization to mimic the stress-strain curve of LAA tissue and LAAOs are designed based on the optimal network. In vitro degradation tests are carried out to evaluate the effects of degradation on mechanical properties. In addition, 48 weeks of long-term subcutaneous implantation of the occluder shows favorable biocompatibility, and the 20-cycle compression test demonstrates outstanding durability of LAAO. Besides, a rapid, complete, and remote-controlled 4D transformation process of LAAO is achieved under the trigger of the magnetic field. The deployment of the LAAO in an isolated swine heart initially exhibits its feasibility for transcatheter LAA occlusion. To the best of our knowledge, this is the first demonstration of the 4D printed LAA occlusion device. It is worth noting that the bioinspired design concept is not only applicable to occlusion devices, but also to many other implantable medical devices, which is conducive to reducing complications, and a broad range of appealing application prospects can be foreseen.

MirrorNet: Bio-Inspired Camouflaged Object Segmentation

Camouflaged objects are generally difficult to be detected in their natural environment even for human beings. In this paper, we propose a novel bio-inspired network, named the MirrorNet, that leverages both instance segmentation and mirror stream for the camouflaged object segmentation. Differently from existing networks for segmentation, our proposed network possesses two segmentation streams: the main stream and the mirror stream corresponding with the original image and its flipped image, respectively. The output from the mirror stream is then fused into the main stream's result for the final camouflage map to boost up the segmentation accuracy. Extensive experiments conducted on the public CAMO dataset demonstrate the effectiveness of our proposed network. Our proposed method achieves 89% in accuracy, outperforming the state-of-the-arts. Project Page: https://sites.google.com/view/ltnghia/research/camo

THz generation and frequency manipulation in AFM/HM interfaces

In this paper, we propose an approximate nonlinear theory of a spintronic terahertz-frequency oscillator based on antiferromagnet-heavy metal interfaces. We present a model of excitation of nonlinear oscillations of Neel vector in an antiferromagnet under the action of terahertz pulses of an electromagnetic field. We determine that, with increasing pumping pulse amplitude, the spin system response increases nonlinearly in the fundamental quasi-antiferromagnetic mode. Our results theoretically show that a spin-current flowing from a heavy metal due to the spin-Hall effect vary the frequencies of the output EM oscillations in a wide range, which could be detected by a standard pump-and-probe spectroscopy. Our study paves the way to laser-induced, electrically tunable, low-power, ultrafast AFM-based oscillator that operates without external magnetic fields at room temperature for telecommunication systems, bio-inspired networks and optical networks on chip. The nonlinear dynamics of the antiferromagnet-based emitters discussed here is of importance in terahertz-frequency spintronic technologies.

Designing ecologically-inspired robustness into a water distribution network

Eco-Industrial Parks (EIPs), network of industries that collaborate by utilizing each other’s byproducts and wastes, are highly desirable for both the industries themselves, their environment, and governments due to their economic, environmental, and social advantages. Previous work has shown that EIPs are not as successful as they could be in terms of mimicking the behavior of biological ecosystems, highlighting that more work needs to be done for EIPs to truly mimic their biological-counterparts. The Kalundborg EIP, located in Kalundborg, Denmark, is a well documented example of an EIP with long-term success. Using the water network within the Kalundborg EIP as a case study, two bio-inspired networks are selected from an optimization based on the ecosystem metric robustness. The bio-inspired solutions are compared with a traditionally cost-minimized solution to understand what bio-inspired design can offer when a network is disturbed. Disturbances such as connection breakages and industry shutdowns are tested, showing that the bio-inspired designs require minimal recovery costs – in stark contrast to the traditional network solution. The results show that the bio-inspired designs reduce the network’s dependence on a scarce import (freshwater) and have higher overall network resilience in the event of disturbances. The three network solutions are discussed from a ecological perspective, explaining differences from the standpoint of ecosystem characteristics. The analysis highlights the benefits of using ecology to understand the nature of and improve the design of industrial networks.

Introduction to the Special Section on Network Science in Biological and Bio-Inspired Systems

The papers in this special section examine network science in biological and bio-inspired systems. Networks exist widely in biological systems, including neuronal networks, protein-protein interaction networks, metabolic networks, gene regulatory networks, food web, microbiome, and local interactions in flocks. These biological systems have inspired several intelligent algorithms such as genetic algorithms, artificial neural networks, particle swarm optimization, population protocol, to name a few. As biological and bio-inspired systems are distributed and usually operate without central control, network science is an elegant and powerful framework to investigate their structure and functions. Indeed, network biology and networked bio-inspired systems have recently attracted significant attentions and become a promising interdisciplinary field. The papers in this section focus on the structure and functions of biological and bio-inspired networks.

Bio-Inspired Network Security for 5G-Enabled IoT Applications

Every IPv6-enabled device connected and communicating over the Internet forms the Internet of things (IoT) that is prevalent in society and is used in daily life. This IoT platform will quickly grow to be populated with billions or more objects by making every electrical appliance, car, and even items of furniture smart and connected. The 5th generation (5G) and beyond networks will further boost these IoT systems. The massive utilization of these systems over gigabits per second generates numerous issues. Owing to the huge complexity in large-scale deployment of IoT, data privacy and security are the most prominent challenges, especially for critical applications such as Industry 4.0, e-healthcare, and military. Threat agents persistently strive to find new vulnerabilities and exploit them. Therefore, including promising security measures to support the running systems, not to harm or collapse them, is essential. Nature-inspired algorithms have the capability to provide autonomous and sustainable defense and healing mechanisms. This paper first surveys the 5G network layer security for IoT applications and lists the network layer security vulnerabilities and requirements in wireless sensor networks, IoT, and 5G-enabled IoT. Second, a detailed literature review is conducted with the current network layer security methods and the bio-inspired techniques for IoT applications exchanging data packets over 5G. Finally, the bio-inspired algorithms are analyzed in the context of providing a secure network layer for IoT applications connected over 5G and beyond networks.