Search Results (35)

Spinal cord injury (SCI) remains one of the toughest obstacles in neuroscience and regenerative medicine due to both severe functional loss and limited healing ability. This article aims to provide a key integrative, mechanism-focused review of the molecular landscape of SCI and the new disruptive therapy technologies that are now evolving in the SCI arena. Our goal is to unify a fundamental pathophysiology of neuroinflammation, ferroptosis, glial scarring, and oxidative stress with the translation of precision treatment approaches driven by artificial intelligence (AI), CRISPR-mediated gene editing, and regenerative bioengineering. Drawing upon advances in single-cell omics, systems biology, and smart biomaterials, we will discuss the potential for reprogramming the spinal cord at multiple levels, from transcriptional programming to biomechanical scaffolds, to change the course from an irreversible degeneration toward a directed regenerative pathway. We will place special emphasis on using AI to improve diagnostic/prognostic and inferred responses, gene and cell therapies enabled by genomic editing, and bioelectronics capable of rehabilitating functional connectivity. Although many of the technologies described below are still in development, they are becoming increasingly disruptive capabilities of what it may mean to recover from an SCI. Instead of prescribing a particular therapeutic fix, we provide a future-looking synthesis of interrelated biological, computational, and bioengineering approaches that conjointly chart a course toward adaptive, personalized neuroregeneration. Our intent is to inspire a paradigm shift to resolve paralysis through precision recovery and to be grounded in a spirit of humility, rigor, and an interdisciplinary approach. Full article

Object segmentation, a key type of image segmentation, focuses on detecting and delineating individual objects within an image, essential for applications like robotic vision and augmented reality. Despite advancements in deep learning improving object segmentation, underwater object segmentation remains challenging due to unique underwater complexities such as turbulence diffusion, light absorption, noise, low contrast, uneven illumination, and intricate backgrounds. The scarcity of underwater datasets further complicates these challenges. The Segment Anything Model (SAM) has shown potential in addressing these issues, but its adaptation for underwater environments, AquaSAM, requires fine-tuning all parameters, demanding more labeled data and high computational costs. In this paper, we propose WaterSAM, an adapted model for underwater object segmentation. Inspired by Low-Rank Adaptation (LoRA), WaterSAM incorporates trainable rank decomposition matrices into the Transformer’s layers, specifically enhancing the image encoder. This approach significantly reduces the number of trainable parameters to 6.7% of SAM’s parameters, lowering computational costs. We validated WaterSAM on three underwater image datasets: COD10K, SUIM, and UIIS. Results demonstrate that WaterSAM significantly outperforms pre-trained SAM in underwater segmentation tasks, contributing to advancements in marine biology, underwater archaeology, and environmental monitoring. Full article

Atherosclerosis, a leading cause of cardiovascular disease, necessitates advanced and innovative modeling techniques to better understand and predict plaque dynamics. The present work presents two distinct hypothetical models inspired by different research fields: the logistic map from chaos theory and Markov models from stochastic processes. The logistic map effectively models the nonlinear progression and sudden changes in plaque stability, reflecting the chaotic nature of atherosclerotic events. In contrast, Markov models, including traditional Markov chains, spatial Markov models, and Markov random fields, provide a probabilistic framework to assess plaque stability and transitions. Spatial Markov models, visualized through heatmaps, highlight the spatial distribution of transition probabilities, emphasizing local interactions and dependencies. Markov random fields incorporate complex spatial interactions, inspired by advances in physics and computational biology, but present challenges in parameter estimation and computational complexity. While these hypothetical models offer promising insights, they require rigorous validation with real-world data to confirm their accuracy and applicability. This study underscores the importance of interdisciplinary approaches in developing theoretical models for atherosclerotic plaques. Full article

Swifts, a distinctive avian cohort, have garnered widespread attention owing to their exceptional flight agility. While their aerial prowess is well documented, the challenge swifts encounter while imbibing water introduces an intriguing complexity. The act of water uptake potentially disrupts their flight equilibrium, yet the mechanisms enabling these birds to maintain stability during this process remain enigmatic. In this study, we employed high-speed videography to observe swifts’ water-drinking behavior. Notably, we observed that the swift adopts a dynamic V-shaped wing configuration during water immersion with the ability to modulate the V-shaped angle, thereby potentially fine-tuning their balance. To delve deeper, we utilized a three-dimensional laser scanner to meticulously construct a virtual 3D model of swifts, followed by computational fluid dynamics simulations to quantitatively assess the mechanical conditions during foraging. Our model indicates that the adoption of V-shaped wings, with a variable wing angle ranging from 30 to 60 degrees, serves to minimize residual torque, effectively mitigating potential flight instability. These findings not only enhance our comprehension of swifts’ flight adaptability but also hold promise for inspiring innovative, highly maneuverable next-generation unmanned aerial vehicles. This research thus transcends avian biology, offering valuable insights for engineering and aeronautics. Full article

We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric space and augments the loss function with a cost proportional to the length of each neuron connection. This is inspired by the idea of minimum connection cost in evolutionary biology, but we are the first the combine this idea with training neural networks with gradient descent for interpretability. We demonstrate that BIMT discovers useful modular neural networks for many simple tasks, revealing compositional structures in symbolic formulas, interpretable decision boundaries and features for classification, and mathematical structure in algorithmic datasets. Qualitatively, BIMT-trained networks have modules readily identifiable by the naked eye, but regularly trained networks seem much more complicated. Quantitatively, we use Newman’s method to compute the modularity of network graphs; BIMT achieves the highest modularity for all our test problems. A promising and ambitious future direction is to apply the proposed method to understand large models for vision, language, and science. Full article

Smart manufacturing needs cognitive computing methods to make the relevant systems more intelligent and autonomous. In this respect, bio-inspired cognitive computing methods (i.e., biologicalization) can play a vital role. This article is written from this perspective. In particular, this article provides a general overview of the bio-inspired computing method called DNA-Based Computing (DBC), including its theory and applications. The main theme of DBC is the central dogma of molecular biology (once information of DNA/RNA has got into a protein, it cannot get out again), i.e., DNA to RNA (sequences of four types of nucleotides) and DNA/RNA to protein (sequence of twenty types of amino acids) are allowed, but not the reverse ones. Thus, DBC transfers few-element information (DNA/RAN-like) to many-element information (protein-like). This characteristic of DBC can help to solve cognitive problems (e.g., pattern recognition). DBC can take many forms; this article elucidates two main forms, denoted as DBC-1 and DBC-2. Using arbitrary numerical examples, we demonstrate that DBC-1 can solve various cognitive problems, e.g., “similarity indexing between seemingly different but inherently identical objects” and “recognizing regions of an image separated by a complex boundary.” In addition, using an arbitrary numerical example, we demonstrate that DBC-2 can solve the following cognitive problem: “pattern recognition when the relevant information is insufficient.” The remarkable thing is that smart manufacturing-based systems (e.g., digital twins and big data analytics) must solve the abovementioned problems to make the manufacturing enablers (e.g., machine tools and monitoring systems) more self-reliant and autonomous. Consequently, DBC can improve the cognitive problem-solving ability of smart manufacturing-relevant systems and enrich their biologicalization. Full article

Random pulse computing (RPC), the third paradigm along with digital and quantum computing, draws inspiration from biology, particularly the functioning of neurons. Here, we study information processing in random pulse computing circuits intended for the summation of numbers. Based on the information-theoretic merits of entropy budget and relative Kolmogorov–Sinai entropy, we investigate the prior art and propose new circuits: three deterministic adders with significantly improved output entropy and one exact nondeterministic adder that requires much less additional entropy than the previous art. All circuits are realized and tested experimentally, using quantum entropy sources and reconfigurable logic devices. Not only the proposed circuits yield a precise mathematical result and have output entropy near maximum, which satisfies the need for building a programmable random pulse computer, but also they provide affordable hardware options for generating additional entropy. Full article

The detection of intrusions in computer networks, known as Network-Intrusion-Detection Systems (NIDSs), is a critical field in network security. Researchers have explored various methods to design NIDSs with improved accuracy, prevention measures, and faster anomaly identification. Safeguarding computer systems by quickly identifying external intruders is crucial for seamless business continuity and data protection. Recently, bioinformatics techniques have been adopted in NIDSs’ design, enhancing their capabilities and strengthening network security. Moreover, researchers in computer science have found inspiration in molecular biology’s survival mechanisms. These nature-designed mechanisms offer promising solutions for network security challenges, outperforming traditional techniques and leading to better results. Integrating these nature-inspired approaches not only enriches computer science, but also enhances network security by leveraging the wisdom of nature’s evolution. As a result, we have proposed a novel Amino-acid-encoding mechanism that is bio-inspired, utilizing essential Amino acids to encode network transactions and generate structural properties from Amino acid sequences. This mechanism offers advantages over other methods in the literature by preserving the original data relationships, achieving high accuracy of up to 99%, transforming original features into a fixed number of numerical features using bio-inspired mechanisms, and employing deep machine learning methods to generate a trained model capable of efficiently detecting network attack transactions in real-time. Full article

Conventional processing of sensory input often relies on uniform sampling leading to redundant information and unnecessary resource consumption throughout the entire processing pipeline. Neuromorphic computing challenges these conventions by mimicking biology and employing distributed event-based hardware. Based on the task of lateral auditory sound source localization (SSL), we propose a generic approach to map biologically inspired neural networks to neuromorphic hardware. First, we model the neural mechanisms of SSL based on the interaural level difference (ILD). Afterward, we identify generic computational motifs within the model and transform them into spike-based components. A hardware-specific step then implements them on neuromorphic hardware. We exemplify our approach by mapping the neural SSL model onto two platforms, namely the IBM TrueNorth Neurosynaptic System and SpiNNaker. Both implementations have been tested on synthetic and real-world data in terms of neural tunings and readout characteristics. For synthetic stimuli, both implementations provide a perfect readout ($100\%$ accuracy). Preliminary real-world experiments yield accuracies of $78\%$ (TrueNorth) and $13\%$ (SpiNNaker), RMSEs of ${41}^{\circ }$ and ${39}^{\circ }$, and MAEs of ${18}^{\circ }$ and ${29}^{\circ }$, respectively. Overall, the proposed mapping approach allows for the successful implementation of the same SSL model on two different neuromorphic architectures paving the way toward more hardware-independent neural SSL. Full article

Bayesian imaging algorithms are becoming increasingly important in, e.g., astronomy, medicine and biology. Given that many of these algorithms compute iterative solutions to high-dimensional inverse problems, the efficiency and accuracy of the instrument response representation are of high importance for the imaging process. For efficiency reasons, point spread functions, which make up a large fraction of the response functions of telescopes and microscopes, are usually assumed to be spatially invariant in a given field of view and can thus be represented by a convolution. For many instruments, this assumption does not hold and degrades the accuracy of the instrument representation. Here, we discuss the application of butterfly transforms, which are linear neural network structures whose sizes scale sub-quadratically with the number of data points. Butterfly transforms are efficient by design, since they are inspired by the structure of the Cooley–Tukey fast Fourier transform. In this work, we combine them in several ways into butterfly networks, compare the different architectures with respect to their performance and identify a representation that is suitable for the efficient representation of a synthetic spatially variant point spread function up to a $1\%$ error. Furthermore, we show its application in a short synthetic example. Full article

The exploration of biologically relevant chemical space for the discovery of small bioactive molecules present in marine organisms has led not only to important advances in certain therapeutic areas, but also to a better understanding of many life processes. The still largely untapped reservoir of countless metabolites that play biological roles in marine invertebrates and microorganisms opens new avenues and poses new challenges for research. Computational technologies provide the means to (i) organize chemical and biological information in easily searchable and hyperlinked databases and knowledgebases; (ii) carry out cheminformatic analyses on natural products; (iii) mine microbial genomes for known and cryptic biosynthetic pathways; (iv) explore global networks that connect active compounds to their targets (often including enzymes); (v) solve structures of ligands, targets, and their respective complexes using X-ray crystallography and NMR techniques, thus enabling virtual screening and structure-based drug design; and (vi) build molecular models to simulate ligand binding and understand mechanisms of action in atomic detail. Marine natural products are viewed today not only as potential drugs, but also as an invaluable source of chemical inspiration for the development of novel chemotypes to be used in chemical biology and medicinal chemistry research. Full article

Bayesian imaging algorithms are becoming increasingly important in, e.g., astronomy, medicine and biology. Given that many of these algorithms compute iterative solutions to high-dimensional inverse problems, the efficiency and accuracy of the instrument response representation are of high importance for the imaging process. For this reason, point spread functions, which make up a large fraction of the response functions of telescopes and microscopes, are usually assumed to be spatially invariant in a given field of view and can thus be represented by a convolution. For many instruments, this assumption does not hold and degrades the accuracy of the instrument representation. Here, we discuss the application of butterfly transforms, which are linear neural network structures whose sizes scale subquadratically with the number of data points. Butterfly transforms are efficient by design, since they are inspired by the structure of the Cooley–Tukey Fast Fourier transform. In this work, we combine them in several ways into butterfly networks, compare the different architectures with respect to their performance and identify a representation that is suitable for the efficient respresentation of a synthetic spatially variant point spread function up to a $1\%$ error. Full article

The development of genomic technology for smart diagnosis and therapies for various diseases has lately been the most demanding area for computer-aided diagnostic and treatment research. Exponential breakthroughs in artificial intelligence and machine intelligence technologies could pave the way for identifying challenges afflicting the healthcare industry. Genomics is paving the way for predicting future illnesses, including cancer, Alzheimer’s disease, and diabetes. Machine learning advancements have expedited the pace of biomedical informatics research and inspired new branches of computational biology. Furthermore, knowing gene relationships has resulted in developing more accurate models that can effectively detect patterns in vast volumes of data, making classification models important in various domains. Recurrent Neural Network models have a memory that allows them to quickly remember knowledge from previous cycles and process genetic data. The present work focuses on type 2 diabetes prediction using gene sequences derived from genomic DNA fragments through automated feature selection and feature extraction procedures for matching gene patterns with training data. The suggested model was tested using tabular data to predict type 2 diabetes based on several parameters. The performance of neural networks incorporating Recurrent Neural Network (RNN) components, Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU) was tested in this research. The model’s efficiency is assessed using the evaluation metrics such as Sensitivity, Specificity, Accuracy, F1-Score, and Mathews Correlation Coefficient (MCC). The suggested technique predicted future illnesses with fair Accuracy. Furthermore, our research showed that the suggested model could be used in real-world scenarios and that input risk variables from an end-user Android application could be kept and evaluated on a secure remote server. Full article

The Schrödinger equation is one of the most important equations in physics and chemistry and can be solved in the simplest cases by computer numerical methods. Since the beginning of the 1970s, the computer began to be used to solve this equation in elementary quantum systems, and, in the most complex case, a ‘hydrogen-like’ system. Obtaining the solution means finding the wave function, which allows predicting the physical and chemical properties of the quantum system. However, when a quantum system is more complex than a ‘hydrogen-like’ system, we must be satisfied with an approximate solution of the equation. During the last decade, application of algorithms and principles of quantum computation in disciplines other than physics and chemistry, such as biology and artificial intelligence, has led to the search for alternative techniques with which to obtain approximate solutions of the Schrödinger equation. In this work, we review and illustrate the application of genetic algorithms, i.e., stochastic optimization procedures inspired by Darwinian evolution, in elementary quantum systems and in quantum models of artificial intelligence. In this last field, we illustrate with two ‘toy models’ how to solve the Schrödinger equation in an elementary model of a quantum neuron and in the synthesis of quantum circuits controlling the behavior of a Braitenberg vehicle. Full article

Mathematical biology has been an area of wide interest during the recent decades, as the modeling of complicated biological processes has enabled the creation of analytical and computational approaches to many different bio-inspired problems originating from different branches such as population dynamics, molecular dynamics in cells, neuronal and heart diseases, the cardiovascular system, genetics, etc [...] Full article