Biologically-inspired Algorithms Research Articles

Classification of Program Texts Represented as Markov Chains with Biology-Inspired Algorithms-Enhanced Extreme Learning Machines

The massive nature of modern university programming courses increases the burden on academic workers. The Digital Teaching Assistant (DTA) system addresses this issue by automating unique programming exercise generation and checking, and provides means for analyzing programs received from students by the end of semester. In this paper, we propose a machine learning-based approach to the classification of student programs represented as Markov chains. The proposed approach enables real-time student submissions analysis in the DTA system. We compare the performance of different multi-class classification algorithms, such as support vector machine (SVM), the k nearest neighbors (KNN) algorithm, random forest (RF), and extreme learning machine (ELM). ELM is a single-hidden layer feedforward network (SLFN) learning scheme that drastically speeds up the SLFN training process. This is achieved by randomly initializing weights of connections among input and hidden neurons, and explicitly computing weights of connections among hidden and output neurons. The experimental results show that ELM is the most computationally efficient algorithm among the considered ones. In addition, we apply biology-inspired algorithms to ELM input weights fine-tuning in order to further improve the generalization capabilities of this algorithm. The obtained results show that ELMs fine-tuned with biology-inspired algorithms achieve the best accuracy on test data in most of the considered problems.

Wearable energy efficient fitness tracker for sports person health monitoring application

Continuous evaluation of biological and physiological metrics of sports personalities, evaluating general health status, and alerting for life-saving treatments, is supposed to enhance efficiency and healthy performance. Wearable devices with acceptable form factors compact, flexibility, minimal power consumption, etc., are needed for continuous monitoring to avoid affecting everyday operations, thereby retaining functional effectiveness and consumer satisfaction. This research focuses on the acceleration tracker for particularizing the work. Acceleration data is typically collected on battery-powered sensors for activity detection, referring to an exchange between high-precision detection and energy-efficient processing. From a feature selection perspective, the paper explores this trade-off. It suggests an Energy-Efficient Behavior Recognition System with a comprehensive energy utilization model and the Multi-objective Algorithm of Particle Swarm Optimization (EEBRS-MPSO). Therefore, using Random Forest (RF) classifiers, the model and algorithm are tested to measure the precision of identification and obtain the task’s best performance with the lowest energy consumption, among other biologically-inspired algorithms. The findings indicate that energy consumption for data storage and data processing is minimized with magnitude relative to the raw data method by choosing suitable groups of attributes. Thus, the platform allows a scalable range of feature clusters that require the authors to provide an adequate power adjustment for given target use.

Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing Its Gradient Estimator Bias.

Equilibrium Propagation is a biologically-inspired algorithm that trains convergent recurrent neural networks with a local learning rule. This approach constitutes a major lead to allow learning-capable neuromophic systems and comes with strong theoretical guarantees. Equilibrium propagation operates in two phases, during which the network is let to evolve freely and then “nudged” toward a target; the weights of the network are then updated based solely on the states of the neurons that they connect. The weight updates of Equilibrium Propagation have been shown mathematically to approach those provided by Backpropagation Through Time (BPTT), the mainstream approach to train recurrent neural networks, when nudging is performed with infinitely small strength. In practice, however, the standard implementation of Equilibrium Propagation does not scale to visual tasks harder than MNIST. In this work, we show that a bias in the gradient estimate of equilibrium propagation, inherent in the use of finite nudging, is responsible for this phenomenon and that canceling it allows training deep convolutional neural networks. We show that this bias can be greatly reduced by using symmetric nudging (a positive nudging and a negative one). We also generalize Equilibrium Propagation to the case of cross-entropy loss (by opposition to squared error). As a result of these advances, we are able to achieve a test error of 11.7% on CIFAR-10, which approaches the one achieved by BPTT and provides a major improvement with respect to the standard Equilibrium Propagation that gives 86% test error. We also apply these techniques to train an architecture with unidirectional forward and backward connections, yielding a 13.2% test error. These results highlight equilibrium propagation as a compelling biologically-plausible approach to compute error gradients in deep neuromorphic systems.

Alternative Generation in Complex Decision Modelling Using a Firefly Algorithm Metaheuristic Approach

Decision-making in the “real world” can become dominated by inconsistent performance requirements and incompatible specifications that can be difficult to detect when supporting mathematical programming models are formulated. There are invariably unmodelled elements, not apparent during model construction, which can greatly impact the acceptability of the model's solutions. Consequently, it can frequently prove beneficial to construct a set of options that provide dissimilar approaches to such problems. These alternatives should possess near-optimal objective measures with respect to all known objectives, but be maximally different from each other in terms of their decision variables. The approach for creating maximally different sets of solutions is referred to as modelling-to-generate-alternatives (MGA). This article provides an efficient biologically-inspired algorithm that can generate sets of maximally different alternatives by employing the Firefly Algorithm metaheuristic. The computational efficacy of this MGA approach is demonstrated on a commonly-tested benchmark problem.

A Computational Theory for the Emergence of Grammatical Categories in Cortical Dynamics.

A general agreement in psycholinguistics claims that syntax and meaning are unified precisely and very quickly during online sentence processing. Although several theories have advanced arguments regarding the neurocomputational bases of this phenomenon, we argue that these theories could potentially benefit by including neurophysiological data concerning cortical dynamics constraints in brain tissue. In addition, some theories promote the integration of complex optimization methods in neural tissue. In this paper we attempt to fill these gaps introducing a computational model inspired in the dynamics of cortical tissue. In our modeling approach, proximal afferent dendrites produce stochastic cellular activations, while distal dendritic branches–on the other hand–contribute independently to somatic depolarization by means of dendritic spikes, and finally, prediction failures produce massive firing events preventing formation of sparse distributed representations. The model presented in this paper combines semantic and coarse-grained syntactic constraints for each word in a sentence context until grammatically related word function discrimination emerges spontaneously by the sole correlation of lexical information from different sources without applying complex optimization methods. By means of support vector machine techniques, we show that the sparse activation features returned by our approach are well suited—bootstrapping from the features returned by Word Embedding mechanisms—to accomplish grammatical function classification of individual words in a sentence. In this way we develop a biologically guided computational explanation for linguistically relevant unification processes in cortex which connects psycholinguistics to neurobiological accounts of language. We also claim that the computational hypotheses established in this research could foster future work on biologically-inspired learning algorithms for natural language processing applications.

Success History-Based Position Adaptation in Fuzzy-Controlled Ensemble of Biology-Inspired Algorithms

In this study, a new modification of the meta-heuristic approach called Co-Operation of Biology-Related Algorithms (COBRA) is proposed. Originally the COBRA approach was based on a fuzzy logic controller and used for solving real-parameter optimization problems. The basic idea consists of a cooperative work of six well-known biology-inspired algorithms, referred to as components. However, it was established that the search efficiency of COBRA depends on its ability to keep the exploitation and exploration balance when solving optimization problems. The new modification of the COBRA approach is based on other method for generating potential solutions. This method keeps a historical memory of successful positions found by individuals to lead them in different directions and therefore to improve the exploitation and exploration capabilities. The proposed technique was applied to the COBRA components and to its basic steps. The newly proposed meta-heuristic as well as other modifications of the COBRA approach and components were evaluated on three sets of various benchmark problems. The experimental results obtained by all algorithms with the same computational effort are presented and compared. It was concluded that the proposed modification outperformed other algorithms used in comparison. Therefore, its usefulness and workability were demonstrated.

A minimal biologically-inspired algorithm for robots foraging energy in uncertain environments

This work details the design and simulation results of a bioinspired minimalist algorithm based on C. elegans, using autonomous agents to forage for attractant energy sources. The robotic agents are energy-constrained and depend on the energy they forage to recharge their batteries, which is significant as the foraging task is one of the canonical testbeds for cooperative robotics.The algorithm consists of 6 input parameters which were simulated and optimised in 9 unbounded environments of varying difficulty levels, containing attractant sources which robots would then have to forage from to maintain energy levels and survive the entirety of the simulation.The robots running the algorithm were then optimised using Evolutionary Algorithms and the best solutions in all 9 environments were categorised with the use of clustering techniques. The clustering results highlighted the different strategies which emerged. Ultimately across the 9 environments, 6 different strategies have been identified. The results demonstrate the applicability of the proposed algorithm to localise attractant sources and harvest energy in different scenarios using the same core algorithm.

Ensemble of the nature-inspired algorithms with success-history based position adaptation

Previously, a meta-heuristic approach called Co-Operation of Biology Related Algorithms, or COBRA for short, based on a fuzzy logic controller for solving real-valued optimization problems was introduced and described. The basic idea of the originally proposed approach consists in a cooperative work of six well-known biology-inspired algorithms (components) with similar schemes. Furthermore, the fuzzy logic controller determines which biology-inspired algorithms should be included in the co-operative work and their population sizes at a given moment for solving optimization problems using the COBRA approach. In this study a new modification of the COBRA approach based on an alternative way of generating potential solutions is proposed. The stated technique uses a historical memory of successful positions found by individuals to guide them in different directions and thus to improve their exploration and exploitation abilities. The proposed method was applied to the components of the COBRA approach and to its basic procedures. The modified meta-heuristic as well as other variants of the COBRA algorithm and components (with and without the proposed modification) were evaluated on three sets of low- and high-dimensional benchmark problems. The experimental results obtained by all algorithms are presented and compared. It was concluded that the fuzzy-controlled COBRA with success-history based position adaptation allows better solutions to be found than the other mentioned biology-inspired algorithms with the same computational effort. Thus, the usefulness of the proposed position adaptation technique was demonstrated.

Cooperative ant colony optimization for a hierarchical scheduling problem

An important part of modern integrated decision support systems in any area is scheduling. At the same time, domain knowledge can be extremely complex and includes numerous restrictions and process rules, which makes the corresponding optimization problem highly complicated. This paper is based on a hierarchical problem structure where the top-level problem is the travelling salesman problem, and the nested resource-constrained project scheduling problem is replaced by the simulation model. Cooperative ant colony optimization as well as other biology-inspired algorithms were evaluated on a set of generated problems, and the obtained experimental results are presented here.

Consistent estimation of rotational optical flow in real environments using a biologically-inspired vision algorithm on embedded hardware

Insects are able to freely navigate through ever-changing environments using predominantly visual inputs, while possessing very minimal processing power compared to humans. Not only are they able to move at high velocities and accelerations, but they are also able to achieve extraordinary levels of obstacle avoidance. We begin to emulate this biological behaviour in a robotic application by first modelling how these visual pathways react to separable degrees of freedom within the motion field, specifically rotation in this case. We have developed upon an existing biologically-inspired algorithm based on the visual pathway of the hoverfly, and statistically compare results to current state-of-the-art algorithms, all the while performing this on computationally-constrained embedded hardware. We have shown that, using a complex, highly-elaborated representation of the hoverfly visual pathway, rotation optical flow estimations can be achieved with a high level of accuracy, at a level of consistency previously unseen in dense-flow algorithms, and they can be achieved at 100 frames per second on an embedded system. This work forms a fundamental basis to understanding one of the two separable components of insect egomotion (rotation and translation), allowing for consistently accurate rotational velocity estimation, providing a building block towards understanding the translational component of insect vision and the application of biologically-inspired egomotion estimation in autonomous vehicles.

A Biology Inspired Algorithm to Mitigate the Local Minima Problem and Improve the Classification in Neural Networks

A Biology Inspired Algorithm to Mitigate the Local Minima Problem and Improve the Classification in Neural Networks

Bio-Inspired Presentation Attack Detection for Face Biometrics.

Today, face biometric systems are becoming widely accepted as a standard method for identity authentication in many security settings. For example, their deployment in automated border control gates plays a crucial role in accurate document authentication and reduced traveler flow rates in congested border zones. The proliferation of such systems is further spurred by the advent of portable devices. On the one hand, modern smartphone and tablet cameras have in-built user authentication applications while on the other hand, their displays are being consistently exploited for face spoofing. Similar to biometric systems of other physiological biometric identifiers, face biometric systems have their own unique set of potential vulnerabilities. In this work, these vulnerabilities (presentation attacks) are being explored via a biologically-inspired presentation attack detection model which is termed “BIOPAD.” Our model employs Gabor features in a feedforward hierarchical structure of layers that progressively process and train from visual information of people's faces, along with their presentation attacks, in the visible and near-infrared spectral regions. BIOPAD's performance is directly compared with other popular biologically-inspired layered models such as the “Hierarchical Model And X” (HMAX) that applies similar handcrafted features, and Convolutional Neural Networks (CNN) that discover low-level features through stochastic descent training. BIOPAD shows superior performance to both HMAX and CNN in all of the three presentation attack databases examined and these results were consistent in two different classifiers (Support Vector Machine and k-nearest neighbor). In certain cases, our findings have shown that BIOPAD can produce authentication rates with 99% accuracy. Finally, we further introduce a new presentation attack database with visible and near-infrared information for direct comparisons. Overall, BIOPAD's operation, which is to fuse information from different spectral bands at both feature and score levels for the purpose of face presentation attack detection, has never been attempted before with a biologically-inspired algorithm. Obtained detection rates are promising and confirm that near-infrared visual information significantly assists in overcoming presentation attacks.

Success-history based biology-inspired algorithms for global trajectory optimization

Biology-inspired algorithms are computationally efficient for real-parameter optimization. However, the search efficiency of such algorithms depends significantly on their ability in keeping the balance between exploration and exploitation when solving complex multimodal problems. A new technique for generating potential solutions in biology-inspired algorithms is proposed. The stated technique uses a historical memory of successful positions found by individuals to guide them in different directions, thereby improving their exploration and exploitation abilities. Thus, this paper describes the application of modified biology-inspired algorithms, namely the Firefly Algorithm, the Cuckoo Search Algorithm and the Bat Algorithm to global trajectory optimization problems. The problems are provided by the European Space Agency and represent trajectories of several well-known spacecraft, such as Cassini and Messenger. Firstly, modified versions of the listed heuristics as well as their original variants were evaluated on a set of various test functions. Then their performance was evaluated on two global trajectory optimization problems: Cassini-1 and Messenger. The experimental results obtained by them are presented and compared. It was established that success-history based position adaptation allows better solutions to be found with the same computational effort while solving complex real-world problems. Thus, the usefulness of the proposed position adaptation technique was demonstrated.

A Biologically-Inspired Metaheuristic Approach for the Simultaneous Generation of Alternatives

Decision-making in the “real world” involves complex problems that tend to be riddled with competing performance objectives and possess requirements which are very difficult to incorporate into any underlying decision support models. There are invariably unmodelled elements, not apparent during model construction, which can greatly impact the acceptability of the model's solutions. Consequently, it is preferable to generate numerous dissimilar alternatives that provide disparate perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known objectives, but be maximally different from each other in terms of their decision variables. This maximally different solution creation approach is referred to as modelling-to-generate-alternatives (MGA). This article provides an efficient biologically-inspired algorithm that simultaneously generates multiple, maximally different alternatives by employing the Firefly Algorithm metaheuristic. The effectiveness of this algorithm is demonstrated on an engineering optimization benchmark test problem

Region growing for image segmentation using an extended PCNN model

Pulse-coupled neural network (PCNN) is a biologically-inspired algorithm suited for image processing. However, determining a set of parameters involved in the alteration of the neural behaviour remains a prevalent research for further application. To apply the model into image segmentation, this study proposes an extended PCNN model by using a strategy of the decision tree, and establishes links between the parameters and image characteristics. Particularly, the adjustable threshold term, interacted with the estimation of the global neural threshold, enables the proposed model to obtain the better results with the use of the fuzzy set theory. Through iterative computation, the proposed model can be considered as a region growing approach for multilevel image segmentation, thus named as an extended PCNN model. Finally, experiments on synthetic and natural images demonstrate the efficiency of the proposed model. Moreover, comparisons with some existing PCNN-based models, and recently graph-based methods, normalised cuts, show that the proposed model can extract regions with more similarity.

Model turbine heat rate by fast learning network with tuning based on ameliorated krill herd algorithm

The krill herd (KH) is an innovative biologically-inspired algorithm. To improve the solution quality and to quicken the global convergence speed of KH, an ameliorated krill herd algorithm (A-KH) is proposed to solve the aforementioned problems and test it by classical benchmark functions, which is one of the major contributions of this paper. Compared with other several state-of-art optimization algorithms (biogeography-based optimization, particle swarm optimization, artificial bee colony and krill herd algorithm), A-KH shows better search performance. There is, furthermore, another contribution that the A-KH is adopted to adjust the parameters of the fast learning network (FLN) so as to build the turbine heat rate model of a 600MW supercritical steam and obtain a high-precision prediction model. Experimental results show that, compared with other several turbine heat rate models, the tuned FLN model by A-KH has better regression precision and generalization capability.

The Effects of Auditory Contrast Tuning upon Speech Intelligibility.

We have previously identified neurons tuned to spectral contrast of wideband sounds in auditory cortex of awake marmoset monkeys. Because additive noise alters the spectral contrast of speech, contrast-tuned neurons, if present in human auditory cortex, may aid in extracting speech from noise. Given that this cortical function may be underdeveloped in individuals with sensorineural hearing loss, incorporating biologically-inspired algorithms into external signal processing devices could provide speech enhancement benefits to cochlear implantees. In this study we first constructed a computational signal processing algorithm to mimic auditory cortex contrast tuning. We then manipulated the shape of contrast channels and evaluated the intelligibility of reconstructed noisy speech using a metric to predict cochlear implant user perception. Candidate speech enhancement strategies were then tested in cochlear implantees with a hearing-in-noise test. Accentuation of intermediate contrast values or all contrast values improved computed intelligibility. Cochlear implant subjects showed significant improvement in noisy speech intelligibility with a contrast shaping procedure.

Autonomous and distributed mobility management in mobile core networks

The 5th generation mobile and wireless communication systems are expected to accommodate exploding traffic, increasing number of devices, and heterogeneous applications driven by proliferation of IoT and M2M technologies. However, the centralized mobility management architecture in a current mobile core network would face critical problems such as excessive concentration of load on specific servers and considerable increase in C-plane overhead. To solve the problems we first consider a novel architecture of distributed mobility management in C-plane in the mobile core network, which employs virtualized mobility management entity called ADMMEs (Autonomous Distributed Mobility Management Entity) in this paper. In addition, to assign an appropriate ADMME to a UE in accordance with mobility characteristics of the UE and a management policy, we propose an autonomous and adaptive ADMME selection scheme. We adopt a biologically-inspired algorithm, called attractor selection, to accomplish adaptive selection taking into account multiple objectives. Through simulation experiments, we confirmed our proposal could accomplish more than 63 % performance improvement comparing to the current method from viewpoints of delay, load balancing, and C-plane overhead under a dynamic mobility scenario.

Environmental decision-making under uncertainty using a biologically-inspired simulation-optimisation algorithm for generating alternative perspectives

In solving many environmental policy formulation applications, it is generally preferable to formulate several quantifiably good alternatives that provide multiple, disparate approaches to the problem. This is because environmental decision-making typically involves complex problems that are riddled with incompatible performance objectives and possess competing design requirements which are very difficult - if not impossible - to quantify and capture at the time when supporting decision models must be constructed. By generating a set of maximally different solutions, it is hoped that some of the dissimilar alternatives can provide very different perspectives that may serve to satisfy the unmodelled objectives. This maximally different solution creation approach is referred to as modelling to generate-alternatives (MGA). This paper provides a biologically-inspired metaheuristic simulation-optimisation MGA method that can efficiently create multiple solution alternatives to environmental problems containing significant stochastic uncertainties that satisfy required system performance criteria and yet are maximally different in their decision spaces. The efficacy of this stochastic MGA approach for environmental policy formulation is demonstrated using a municipal solid waste case study. It is shown that this new computationally efficient algorithmic approach can simultaneously produce the desired number of maximally different solution alternatives in a single computational run of the procedure.

A bio-inspired evolutionary algorithm: allostatic optimisation

Over the last decade, several bio-inspired algorithms have emerged for solving complex optimisation problems. Since the performance of these algorithms present a suboptimal behaviour, a tremendous amount of research has been devoted to find new and better optimisation methods. On the other hand, allostasis is a medical term recently coined which explains how the configuration of the internal state IS in different organs allows reaching stability when an unbalance condition is presented. In this paper, a novel biologically-inspired algorithm called allostatic optimisation AO is proposed for solving optimisation problems. In AO, individuals emulate the IS of different organs. In the approach, each individual is improved by using numerical operators based on the biological principles of the allostasis mechanism. The proposed method has been compared to other well-known optimisation algorithms. The results show good performance of the proposed method when searching for a global optimum of several benchmark functions.