Bio-inspired Model Research Articles

Reversible kink instability drives ultrafast jumping in nematodes and soft robots.

Entomopathogenic nematodes (EPNs) exhibit a bending-elastic instability, or kink, before becoming airborne, a feature hypothesized but not proven to enhance jumping performance. Here, we provide the evidence that this kink is crucial for improving launch performance. We demonstrate that EPNs actively modulate their aspect ratio, forming a liquid-latched closed loop over a slow timescale O (1 s), then rapidly open it O (10 µs), achieving heights of 20 body lengths (BL) and generating ∼ 10 4 W/Kg of power. Using jumping nematodes, a bio-inspired Soft Jumping Model (SoftJM), and computational simulations, we explore the mechanisms and implications of this kink. EPNs control their takeoff direction by adjusting their head position and center of mass, a mechanism verified through phase maps of jump directions in simulations and SoftJM experiments. Our findings reveal that the reversible kink instability at the point of highest curvature on the ventral side enhances energy storage using the nematode's limited muscular force. We investigated the impact of aspect ratio on kink instability and jumping performance using SoftJM, and quantified EPN cuticle stiffness with AFM, comparing it with C. elegans . This led to a stiffness-modified SoftJM design with a carbon fiber backbone, achieving jumps of ∼25 BL. Our study reveals how harnessing kink instabilities, a typical failure mode, enables bidirectional jumps in soft robots on complex substrates like sand, offering a novel approach for designing limbless robots for controlled jumping, locomotion, and even planetary exploration.

A Bio-Inspired Retinal Model as a Prefiltering Step Applied to Letter and Number Recognition on Chilean Vehicle License Plates

This paper presents a novel use of a bio-inspired retina model as a scene preprocessing stage for the recognition of letters and numbers on Chilean vehicle license plates. The goal is to improve the effectiveness and ease of pattern recognition. Inspired by the responses of mammalian retinas, this retinal model reproduces both the natural adjustment of contrast and the enhancement of object contours by parvocellular cells. Among other contributions, this paper provides an in-depth exploration of the architecture, advantages, and limitations of the model; investigates the tuning parameters of the model; and evaluates its performance when integrating a convolutional neural network and a spiking neural network into an optical character recognition (OCR) algorithm, using 40 different genuine license plate images as a case study and for testing. The results obtained demonstrate the reduction of error rates in character recognition based on convolutional neural networks (CNNs), spiking neural networks (SNNs), and OCR. It is concluded that this bio-inspired retina model offers a wide spectrum of potential applications to further explore, including motion detection, pattern recognition, and improvement of dynamic range in images, among others.

Bio-inspired deep learning-personalized ensemble Alzheimer's diagnosis model for mental well-being

Most classification models for Alzheimer's Diagnosis (AD) do not have specific strategies for individual input samples, leading to the problem of easily overlooking personalized differences between samples. This research introduces a customized dynamically ensemble convolution neural network (PDECNN), which is able to build a specific integration strategy based on the distinctiveness of the sample. In this paper, we propose a personalized dynamic ensemble alzheimer's Diagnosis classification model. This model will dynamically modify the deteriorated brain areas of interest depending on various samples since it can adjust to variations in the degeneration of sample brain areas. In clinical problems, the PDECNN model has additional diagnostic importance since it can identify sample-specific degraded brain areas based on input samples. This model considers the variability of brain region degeneration levels between input samples, evaluates the degree of degeneration of specific brain regions using an attention mechanism, and selects and integrates brain region features based on the degree of degeneration. Furthermore, by redesigning the classification accuracy performance, we respectively improve it by 4 %, 11 %, and 8 %. Moreover, the degraded brain regions identified by the model show high consistency with the clinical manifestations of AD.

Nanoformulations in Pharmaceutical and Biomedical Applications: Green Perspectives.

This study provides a brief discussion of the major nanopharmaceuticals formulations as well as the impact of nanotechnology on the future of pharmaceuticals. Effective and eco-friendly strategies of biofabrication are also highlighted. Modern approaches to designing pharmaceutical nanoformulations (e.g., 3D printing, Phyto-Nanotechnology, Biomimetics/Bioinspiration, etc.) are outlined. This paper discusses the need to use natural resources for the "green" design of new nanoformulations with therapeutic efficiency. Nanopharmaceuticals research is still in its early stages, and the preparation of nanomaterials must be carefully considered. Therefore, safety and long-term effects of pharmaceutical nanoformulations must not be overlooked. The testing of nanopharmaceuticals represents an essential point in their further applications. Vegetal scaffolds obtained by decellularizing plant leaves represent a valuable, bioinspired model for nanopharmaceutical testing that avoids using animals. Nanoformulations are critical in various fields, especially in pharmacy, medicine, agriculture, and material science, due to their unique properties and advantages over conventional formulations that allows improved solubility, bioavailability, targeted drug delivery, controlled release, and reduced toxicity. Nanopharmaceuticals have transitioned from experimental stages to being a vital component of clinical practice, significantly improving outcomes in medical fields for cancer treatment, infectious diseases, neurological disorders, personalized medicine, and advanced diagnostics. Here are the key points highlighting their importance. The significant challenges, opportunities, and future directions are mentioned in the final section.

Biomimetic artificial islet model with vascularized microcapsule structures for durable glycemic control

Islet transplantation is a promising strategy for diabetes mellitus treatment as it can recapitulate endogenous insulin secretion and provide long-term glycemic control. Islet models constructed in biomaterial scaffolds that reproduce biological characteristics of native islets is a feasible option to circumvent the dilemma of donor shortage and the requirement of chronic immunosuppression. Herein, we developed bioinspired artificial microcapsule-based islet models with microvessels for glycemic control using microfluidic electrospray strategy. Microfluidic electrospray can generate uniform hydrogel microcapsules with core-shell structure for encapsulating islet cells. The cell-laden microcapsules enabled the efficient transportation of nutrient, oxygen, and insulin; as well as the incorporation with microvessels for prompting glucose responsiveness and molecular exchange. We demonstrated by in vivo experiments that the blood glucose, food intake, and body weight of diabetic mouse models were alleviated, and the glucose tolerance was promoted after the engraftment of islet microcapsules. We further demonstrated the improved functionality of transplanted islet model in insulin secretion, immune escape, and microcirculation using standard histological and molecular analysis. These results indicated that the microcapsules with microvessels are promising artificial islet models and are valuable for treating diabetes.

Accurate prediction of antibody function and structure using bio-inspired antibody language model.

In recent decades, antibodies have emerged as indispensable therapeutics for combating diseases, particularly viral infections. However, their development has been hindered by limited structural information and labor-intensive engineering processes. Fortunately, significant advancements in deep learning methods have facilitated the precise prediction of protein structure and function by leveraging co-evolution information from homologous proteins. Despite these advances, predicting the conformation of antibodies remains challenging due to their unique evolution and the high flexibility of their antigen-binding regions. Here, to address this challenge, we present the Bio-inspired Antibody Language Model (BALM). This model is trained on a vast dataset comprising 336 million 40% nonredundant unlabeled antibody sequences, capturing both unique and conserved properties specific to antibodies. Notably, BALM showcases exceptional performance across four antigen-binding prediction tasks. Moreover, we introduce BALMFold, an end-to-end method derived from BALM, capable of swiftly predicting full atomic antibody structures from individual sequences. Remarkably, BALMFold outperforms those well-established methods like AlphaFold2, IgFold, ESMFold and OmegaFold in the antibody benchmark, demonstrating significant potential to advance innovative engineering and streamline therapeutic antibody development by reducing the need for unnecessary trials. The BALMFold structure prediction server is freely available at https://beamlab-sh.com/models/BALMFold.

How AI originates from biology – and how it returns to it

The most popular types of artificial intelligence are inspired by different biological processes, such as the functioning of nervous systems or adaptive immunity. Here, I make a short dive into the history of AI to track how bio-inspired models of AI replace other models and discuss which model could be the next one.

Development of a bio-inspired wound model for debridement training

Wound debridement is commonplace in expediting wound healing in the clinic. Despite this, there are limited resources available for simulation training for practitioners prior to facing real-life patients. Typically, citrus peels or porcine skin are employed in a vain attempt to improve debridement proficiency, yet these fail to provide a realistic experience of the textures and consistencies of wounds. Therefore, there is a clear unmet need for a safe and effective tool that can facilitate hands-on learning under the instruction of an experienced debrider. To fill this niche, a life-like wound model was designed and developed, featuring leathery necrotic eschar, an intermediary sloughy layer, and a rough granulation tissue in the bottommost layer, all within a healthy skin base. The healthy tissue portion of the model was designed to exhibit similar mechanical properties to those found in human skin. Likewise, the sloughy layer was viscous enough to remain within the model under static conditions yet could be removed using any appropriate debriding tool synonymous with real slough. Mechanical testing of the necrotic eschar revealed brittle fracture behaviour, akin to what is observed in patients. Each layer of the wound model provided the visual and haptic feedback of how it would look and feel to debride a patient’s wound in the clinic, giving invaluable experience for potential trainees in a safe and effectual way. It is envisaged that these models can be developed in a personalised way to suit the individual needs of the user, such as incorporating underlying models of bone or tendon, while retaining the key elements of the wound, which make it successful. This model is proposed as an important step forward in bridging the gap between becoming a newly qualified debriding practitioner and encountering the first wound in the clinic, subsequently improving the confidence of the debrider and enhancing patient outcomes.

Micro Photosynthetic Power Cell Array for Energy Harvesting: Bio-Inspired Modeling, Testing and Verification

A micro-photosynthetic power cell (µPSC) generates electricity through the exploitation of living photosynthetic organisms through the principles of photosynthesis and respiration. Modeling such systems will enhance insights into the µPSC that can be employed to design real-time applications from µPSC. In this study, the bio-inspired electrical equivalent modeling of the array of µPSC is elucidated. The model is validated for array configurations of the micro-photosynthetic power cells. The developed arrayed model foresees the steady-state response at various electrical loadings. The polarization characteristics of the current-voltage (I-V) and current-power (I-P) characteristics of the array of µPSC in series and parallel, and their combinations in series and parallel connected µPSCs were validated with the experimental results. From this analysis, it is predicted that the arraying of the µPSC in the combination of series and parallel is the optimal array strategy to obtain the desired voltage and current from the µPSC such that it can be used to power real-time low and ultra-low power devices.

A bio-inspired model for robust navigation assistive devices

This paper proposes a new implementation and evaluation in a real-world environment of a bio-inspired predictive navigation model for mobility control, suitable especially for assistance of visually impaired people and autonomous mobile systems. This bio-inspired model relies on the interactions between formal models of three types of neurons identified in the mammals’ brain implied in navigation tasks, namely place cells, grid cells, and head direction cells, to construct a topological model of the environment under the form of a decentralized navigation graph. Previously tested in virtual environments, this model demonstrated a high tolerance to motion drift, making possible to map large environments without the need to correct it to handle such drifts, and robustness to environment changes. The presented implementation is based on a stereoscopic camera, and is evaluated on its possibilities to map and guide a person or an autonomous mobile robot in an unknown real environment. The evaluation results confirm the effectiveness of the proposed bio-inspired navigation model to build a path map, localize and guide a person through this path. The model predictions remain robust to environment changes, and allow to estimate traveled distances with an error rate below 3% over test paths, up to 100m. The tests performed on a robotic platform also demonstrated the pertinence of navigation data produced by this navigation model to guide an autonomous system. These results open the way toward efficient wearable assistive devices for visually impaired people independent navigation.

Assessing the negative impact of chlorantraniliprole, isoxaflutole, and simazine pesticides on phospholipid membrane models and tilapia gill tissues

The indiscriminate and, very often, incorrect use of pesticides in Brazil, as well as in other countries, results in severe levels of environmental pollution and intoxication of human life. Herein, we studied plasma membrane models (monolayer and bilayer) of the phospholipid Dioleoyl-sn-glycerol-3-phosphocholine (DOPC) using Langmuir films, and large (LUVs) and giant (GUVs) unilamellar vesicles, to determine the effect of the pesticides chlorantraniliprole (CLTP), isoxaflutole (ISF), and simazine (SMZ), used in sugarcane. CLTP affects the lipid organization of the bioinspired models of DOPC π-A isotherms, while ISF and SMZ pesticides significantly affect the LUVs and GUVs. Furthermore, the in vivo study of the gill tissue in fish in the presence of pesticides (2.0 × 10−10 mol/L for CLTP, 8.3 × 10−9 mol/L for ISF, and SMZ at 9.9 × 10−9 mol/L) was performed using optical and fluorescence images. This investigation was motivated by the gill lipid membranes, which are vital for regulating transporter activity through transmembrane proteins, crucial for maintaining ionic balance in fish gills. In this way, the presence of phospholipids in gills offers a model for understanding their effects on fish health. Histological results show that exposure to CLTP, ISF, and SMZ may interfere with vital gill functions, leading to respiratory disorders and osmoregulation dysfunction. The results indicate that exposure to pesticides caused severe morphological alterations in fish, which could be correlated with their impact on the bioinspired membrane models. Moreover, the effect does not depend on the exposure period (24h and 96h), showing that animals exposed to pesticides for a short period suffer irreparable damage to gill tissue. In summary, we can conclude that the harm caused by pesticides, both in membrane models and in fish gills, occurs due to contamination of the aquatic system with pesticides. Therefore, water quality is vital for the preservation of ecosystems.

Improved Set-point Tracking Control of an Unmanned Aerodynamic MIMO System Using Hybrid Neural Networks

Artificial neural networks (ANN), an Artificial Intelligence (AI) technique, are both bio-inspired and nature-inspired models that mimic the operations of the human brain and the central nervous system that is capable of learning. This paper is based on a system that optimizes the performance of an uncertain unmanned nonlinear Multi-Input Multi-Output (MIMO) aerodynamic plant called Twin Rotor MIMO System (TRMS). The pitch and yaw angles which are challenging to control and optimize in practice, are being used as the input to the Nonlinear Auto-Regressive with eXogenous (NARX) model, and eventually trained. The training features use the Matlab Deep Learning Toolbox. The NARX structure has its core in the neural networks’ architecture. Data is collected from the TRMS testbed which is used to train the network. ANN as a Hybrid intelligent control strategy of ANN in combination with Pattern Search and Genetic Algorithm, is then utilized to optimize the parameters of the neural networks. At the end it was validated, tested and the optimized system run in simulation and compared with other intelligent and conventional controllers, with the proposed controller outperforming them, giving a very fast tracking control, stable and optimal performance that satisfactorily met all our design requirements.

SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation

Large language Models (LLMs), though growing exceedingly powerful, comprises of orders of magnitude less neurons and synapses than the human brain. However, it requires significantly more power/energy to operate. In this work, we propose a novel bio-inspired spiking language model (LM) which aims to reduce the computational cost of conventional LMs by drawing motivation from the synaptic information flow in the brain. In this paper, we demonstrate a framework that leverages the average spiking rate of neurons at equilibrium to train a neuromorphic spiking LM using implicit differentiation technique, thereby overcoming the non-differentiability problem of spiking neural network (SNN) based algorithms without using any type of surrogate gradient. The steady-state convergence of the spiking neurons also allows us to design a spiking attention mechanism, which is critical in developing a scalable spiking LM. Moreover, the convergence of average spiking rate of neurons at equilibrium is utilized to develop a novel ANN-SNN knowledge distillation based technique wherein we use a pre-trained BERT model as “teacher” to train our “student” spiking architecture. While the primary architecture proposed in this paper is motivated by BERT, the technique can be potentially extended to different kinds of LLMs. Our work is the first one to demonstrate the performance of an operational spiking LM architecture on multiple different tasks in the GLUE benchmark. Our implementation source code is available at https://github.com/NeuroCompLab-psu/SpikingBERT.

Role of compliant mechanics and motor control in hopping - from human to robot

Compliant leg function found during bouncy gaits in humans and animals can be considered a role model for designing and controlling bioinspired robots and assistive devices. The human musculoskeletal design and control differ from distal to proximal joints in the leg. The specific mechanical properties of different leg parts could simplify motor control, e.g., by taking advantage of passive body dynamics. This control embodiment is complemented by neural reflex circuitries shaping human motor control. This study investigates the contribution of specific passive and active properties at different leg joint levels in human hopping at different hopping frequencies. We analyze the kinematics and kinetics of human leg joints to design and control a bioinspired hopping robot. In addition, this robot is used as a test rig to validate the identified concepts from human hopping. We found that the more distal the joint, the higher the possibility of benefit from passive compliant leg structures. A passive elastic element nicely describes the ankle joint function. In contrast, a more significant contribution to energy management using an active element (e.g., by feedback control) is predicted for the knee and hip joints. The ankle and knee joints are the key contributors to adjusting hopping frequency. Humans can speed up hopping by increasing ankle stiffness and tuning corresponding knee control parameters. We found that the force-modulated compliance (FMC) as an abstract reflex-based control beside a fixed spring can predict human knee torque-angle patterns at different frequencies. These developed bioinspired models for ankle and knee joints were applied to design and control the EPA-hopper-II robot. The experimental results support our biomechanical findings while indicating potential robot improvements. Based on the proposed model and the robot’s experimental results, passive compliant elements (e.g. tendons) have a larger capacity to contribute to the distal joint function compared to proximal joints. With the use of more compliant elements in the distal joint, a larger contribution to managing energy changes is observed in the upper joints.

An Asynchronous Spiking Neural Membrane System for Edge Detection.

Spiking neural membrane systems (SN P systems) are a class of bio-inspired models inspired by the activities and connectivity of neurons. Extensive studies have been made on SN P systems with synchronization-based communication, while further efforts are needed for the systems with rhythm-based communication. In this work, we design an asynchronous SN P system with resonant connections where all the enabled neurons in the same group connected by resonant connections should instantly produce spikes with the same rhythm. In the designed system, each of the three modules implements one type of the three operations associated with the edge detection of digital images, and they collaborate each other through the resonant connections. An algorithm called EDSNP for edge detection is proposed to simulate the working of the designed asynchronous SN P system. A quantitative analysis of EDSNP and the related methods for edge detection had been conducted to evaluate the performance of EDSNP. The performance of the EDSNP in processing the testing images is superior to the compared methods, based on the quantitative metrics of accuracy, error rate, mean square error, peak signal-to-noise ratio and true positive rate. The results indicate the potential of the temporal firing and the proper neuronal connections in the SN P system to achieve good performance in edge detection.

Energy-saving robust control of active suspension system based on bioinspired reference model

This paper proposes an energy-saving robust tracking control method for active suspension systems with a bio-inspired reference model and nonlinear extended state observer (NLESO). According to the principle of cheetah running biology, a bionic structure with nonlinear quasi-zero stiffness is designed, which also has ideal Sky-hook damping and vibration-absorbing mass. An NLESO is designed to estimate the total uncertain disturbance and the state of sprung mass in the suspension system, and then an energy-saving robust tracking controller is proposed. The controller consumes less control energy while isolating the vibration of the sprung mass, thus improving the riding comfort of vehicles and saving energy. The simulation results show that, compared with the reference control method, the vertical acceleration of the sprung mass is reduced by 80.68% and 92.42% respectively in the class C road and bump road conditions and the control energy is decreased by 31.71% and 30.50%, respectively. The control effect of the proposed controller for the active suspension system is verified.

A Bio-Inspired Probabilistic Neural Network Model for Noise-Resistant Collision Perception.

Bio-inspired models based on the lobula giant movement detector (LGMD) in the locust's visual brain have received extensive attention and application for collision perception in various scenarios. These models offer advantages such as low power consumption and high computational efficiency in visual processing. However, current LGMD-based computational models, typically organized as four-layered neural networks, often encounter challenges related to noisy signals, particularly in complex dynamic environments. Biological studies have unveiled the intrinsic stochastic nature of synaptic transmission, which can aid neural computation in mitigating noise. In alignment with these biological findings, this paper introduces a probabilistic LGMD (Prob-LGMD) model that incorporates a probability into the synaptic connections between multiple layers, thereby capturing the uncertainty in signal transmission, interaction, and integration among neurons. Comparative testing of the proposed Prob-LGMD model and two conventional LGMD models was conducted using a range of visual stimuli, including indoor structured scenes and complex outdoor scenes, all subject to artificial noise. Additionally, the model's performance was compared to standard engineering noise-filtering methods. The results clearly demonstrate that the proposed model outperforms all comparative methods, exhibiting a significant improvement in noise tolerance. This study showcases a straightforward yet effective approach to enhance collision perception in noisy environments.

Digital design of a spatial-pow-STDP learning block with high accuracy utilizing pow CORDIC for large-scale image classifier spatiotemporal SNN

The paramount concern of highly accurate energy-efficient computing in machines with significant cognitive capabilities aims to enhance the accuracy and efficiency of bio-inspired Spiking Neural Networks (SNNs). This paper addresses this main objective by introducing a novel spatial power spike-timing-dependent plasticity (Spatial-Pow-STDP) learning rule as a digital block with high accuracy in a bio-inspired SNN model. Motivated by the demand for precise and accelerated computation that reduces high-cost resources in neural network applications, this paper presents a methodology based on COordinate Rotation DIgital Computer (CORDIC) definitions. The proposed designs of CORDIC algorithms for exponential (Exp CORDIC), natural logarithm (Ln CORDIC), and arbitrary power function (Pow CORDIC) are meticulously detailed and evaluated to ensure optimal acceleration and accuracy, which respectively show average errors near 10–9, 10–6, and 10–5 with 4, 4, and 6 iterations. The engineered architectures for the Exp, Ln, and Pow CORDIC implementations are illustrated and assessed, showcasing the efficiency achieved through high frequency, leading to the introduction of a Spatial-Pow-STDP learning block design based on Pow CORDIC that facilitates efficient and accurate hardware computation with 6.93 × 10–3 average error with 9 iterations. The proposed learning mechanism integrates this structure into a large-scale spatiotemporal SNN consisting of three layers with reduced hyper-parameters, enabling unsupervised training in an event-based paradigm using excitatory and inhibitory synapses. As a result, the application of the developed methodology and equations in the computational SNN model for image classification reveals superior accuracy and convergence speed compared to existing spiking networks by achieving up to 97.5%, 97.6%, 93.4%, and 93% accuracy, respectively, when trained on the MNIST, EMNIST digits, EMNIST letters, and CIFAR10 datasets with 6, 2, 2, and 6 training epochs.

A spatiotemporal energy model based on spiking neurons for human motion perception.

Inspired by the motion processing pathway, this paper proposes a bio-inspired feedforward spiking network model based on Hodgkin-Huxley neurons for human motion perception. The proposed network mimics the mechanisms of direction selectivity found in simple and complex cells of the primary visual cortex. Simple cells' receptive fields are modeled using Gabor energy filters, while complex cells' receptive fields are constructed by integrating the responses of simple cells in an energy model. To generate the motion map, the spiking output of the network integrates motion information encoded by the responses of complex cells with various preferred directions. Simulation results demonstrate that the spiking neuron-based network effectively replicates the directional selectivity operation of the visual cortex when presented with a sequence of time-varying images. We evaluate the proposed model against state-of-the-art spiking neuron-based motion detection models using publicly available datasets. The results highlight the model's capability to extract motion energy from diverse video sequences, akin to human visual motion perception models. Additionally, we showcase the application of the proposed model in motion segmentation tasks and compare its performance with state-of-the-art motion-based segmentation models using challenging video segmentation benchmarks. The results indicate competitive performance. The motion maps generated by the proposed model can be utilized for action recognition in input videos.

Large-Scale Bio-Inspired FPGA Models for Path Planning.

The hippocampus provides significant inspiration for spatial navigation and memory in both humans and animals. Constructing large-scale spiking neural network (SNN) models based on the biological neural systems is an important approach to comprehend the computational principles and cognitive function of the hippocampus. Such models are usually implemented on neuromorphic computing platforms, which often have limited computing resources that constrain the achievable scale of the network. This work introduces a series of digital design methods to realize a Field-Programmable Gate Array (FPGA) friendly SNN model. The methods include FPGA-friendly nonlinear calculation modules and a fixed-point design algorithm. A brain-inspired large-scale SNN of ∼21 k place cells for path planning is mapped on FPGA. The results show that the path planning tasks in different environments are finished in real-time and the firing activities of place cells are successfully reproduced. With these methods, the achievable network size on one FPGA chip is increased by 1595 times with higher resource usage efficiency and faster computation speed compared to the state-of-the-art.