Biologically inspired computing

SubstanceNet is a modular bio-inspired cognitive architecture where each module corresponds to a specic brain structure (V1→V4 visual cortex, hippocampus, reexive consciousness). Unlike standard neural networks optimized for benchmarks, SubstanceNet serves as a computational platform for numerical verication of neuroscience hypotheses. According to the author's prior work, the emergence parameter κ ≈ 1 is a universal signature of criticality in physical and biological systems [2]; meta-analysis of seven systems, p = 0.518). Here we show that an architecture built on neurobiological principles naturally enters this regime. Results of seven experiments: 73.2% MNIST recognition without network parameter optimization (at matched spatial resolution of 3 × 3, standard average pooling yields 67.9%a +5.4% gain from biological V1+V2 features); an emergent velocity tuning curve reproducing primate electrophysiology; Hebbian maturation with a sensitive period eect; emergence parameter κ = 0.993 ± 0.010 (He-II (quantum liquid) reference: 0.989 ± 0.007), conrmed by an independent neuronal avalanche metric (α =-1.498 vs cortical-1.5). All results reproducible in ∼65 seconds.

The rapid advancement of artificial intelligence systems exhibiting increasingly sophisticated cognitive capabilities has generated urgent scientific, philosophical, and ethical questions regarding the assessment of consciousness-relevant properties in artificial systems. Despite substantial theoretical progress in consciousness science—including Global Workspace Theory, Integrated Information Theory, Higher-Order Theories, Attention Schema Theory, and Predictive Processing frameworks—no validated, comprehensive assessment instrument has been developed for systematically evaluating consciousness indicators across diverse AI architectures. This dissertation addresses this critical methodological gap through a sequential mixed-methods research program comprising four integrated phases.
Phase 1 employed systematic literature synthesis and a modified Delphi technique with 36 expert panelists representing consciousness science, artificial intelligence, philosophy of mind, and cognitive neuroscience. Through four iterative rounds achieving strong consensus (Kendall's W = .67, p < .001), researchers identified 58 consciousness indicators organized into 15 dimensions across five theoretical domains. Phase 2 developed three complementary assessment protocols—the Architectural Assessment Protocol, Computational Analysis Protocol, and Behavioral Assessment Battery—with pilot testing establishing preliminary reliability (mean ICC = .85). Phase 3 applied the framework to 52 diverse AI systems spanning transformer, recurrent, convolutional, hybrid, and specialized architectures, generating comprehensive consciousness indicator profiles. Phase 4 conducted rigorous psychometric validation, demonstrating excellent internal consistency (α = .94), a well-fitting five-factor structure (CFI = .94, RMSEA = .04), and strong criterion validity through convergence with expert judgments (r = .68–.79).
Results revealed that transformer-based systems scored significantly higher on Global Workspace, Attention Schema, and Predictive Processing domains compared to recurrent and convolutional architectures (η² = .31–.48), while model scale showed moderate positive correlations with all domain scores (r = .41–.52). The resulting Multi-Dimensional Assessment Framework for Artificial Intelligence Consciousness Indicators (MDAF-AICI) provides researchers, developers, and policymakers with a theoretically grounded, psychometrically validated instrument for systematic consciousness indicator assessment. This framework advances the scientific study of machine consciousness while offering practical tools for ethical AI governance, contributing to responsible development of increasingly sophisticated artificial intelligence systems.

Keywords: artificial intelligence consciousness, consciousness assessment, machine consciousness, consciousness indicators, integrated information theory, global workspace theory, AI ethics

This paper proposes EPyNet, a deep learning architecture designed for energy reduced audio emotion recognition.In the domain of audio based emotion recognition, where discerning emotional cues from audio input is crucial, the integration of artificial intelligence techniques has sparked a transformative shift in accuracy and performance.Deep learning, renowned for its ability to decipher intricate patterns, spearheads this evolution. However, the energy efficiency of deep learning models, particularly in resource-constrained environments, remains a pressing concern. Convolutional operations serve as the cornerstone of deep learning systems. However, their extensive computational demands leading to energy-inefficient computations render them as not ideal for deployment in scenarios with limited resources. Addressing these challenges, researchers came up with one-dimensional convolutional neural network (1D CNN) array convolutions, offering an alternative to traditional two-dimensional CNNs, with reduced resource requirements. However, this array-based operation reduced the resource requirement, but the energy-consumption impact was not studied. To bridge this gap, we introduce EPyNet, a deep learning architecture crafted for energy efficiency with a particular emphasis on neuron reduction. Focusing on the task of audio emotion recognition, We evaluate EPyNet on five public audio corpora-RAVDESS, TESS, EMO-DB, CREMA-D, and SAVEE.We propose three versions of EPyNet, a lightweight neural network designed for efficient emotion recognition, each optimized for different trade-offs between accuracy and energy efficiency. Experimental results demonstrated that the 0.06M EPyNet reduced energy consumed by 76.5% while improving accuracy by 5% on RAVDESS, 25% on TESS, and 9.75% on SAVEE. The 0.2M and 0.9M models reduced energy consumed by 64.9% and 70.3%, respectively. Additionally, we compared our Proposed 0.06M system with the MobileNet models on the CIFAR-10 dataset and achieved significant improvements. The proposed system reduces energy by 86.2% and memory by 95.7% compared to MobileNet, with a slightly lower accuracy of 0.8%. Compared to MobileNetV2, it improves accuracy by 99.2% and reduces memory by 93.8%. When compared to MobileNetV3, it achieves 57.2% energy reduction, 85.1% memory reduction, and a 24.9% accuracy improvement. We further test the scalability and robustness of the proposed solution on different data dimensions and frameworks.

Swarm intelligence of honey bees had motivated many bioinspired based optimisation techniques. The Bees Algorithm (BA) was created specifically by mimicking the foraging behavior of foraging bees in searching for food sources. During the searching, the original BA ignores the possibilities of the recruits being lost during the flying. The BA algorithm can become closer to the nature foraging behavior of bees by taking account of this phenomenon. This paper proposes an enhanced BA which adds a neighbourhood search parameter which we called as the Local Search Manoeuvres (LSM) recruitment factor. The parameter controls the possibilities of a bee extends its neighbourhood searching area in certain direction. The aim of LSM recruitment is to decrease the number of searching iteration in solving optimization problems that have high dimensions. The experiment results on several benchmark functions show that the BA with LSM performs better compared to the one with basic recruitment.

This article presents a conceptual analogy between the mathematical curiosity of Kaprekar's constant (6174) and the emergence of consciousness. It posits that the iterative process of reaching this constant serves as a model for how the brain's vast, parallel processing converges into a singular, stable state of awareness.

The Kaprekar routine, which involves repeatedly rearranging a four-digit number's digits into descending and ascending orders and subtracting them, is framed as a deterministic, self-organizing system. The initial number represents raw, unprocessed sensory and cognitive data. The iterative algorithm mirrors the brain's process of differentiation and integration, as described in frameworks like Global Workspace Theory (GWT) and Integrated Information Theory (IIT). The inevitable convergence on the fixed-point attractor, 6174, is analogous to achieving a stable, unified conscious state.

The analogy extends to states of unconsciousness and pathology. The exception of "repdigits" (e.g., 3333), which collapse to zero, models the low informational complexity of deep sleep or coma. Cyclical patterns found with other digit lengths are compared to recurring mental states like rumination or mood disorders.

Finally, the article critiques its own analogy by addressing the "hard problem of consciousness." It concludes that the Kaprekar routine is a purely syntactic process, manipulating symbols without semantic understanding, much like the scenario in Searle's Chinese Room argument. While the model effectively illustrates the dynamics of achieving a stable conscious state (the "easy problems"), it cannot explain subjective experience, or qualia. The analogy thus serves as a conceptual tool to clarify the limits of functionalist explanations of the mind.

This is, in fact, the wonder of emergence: how lower organisms, acting as a whole and without centralized control, can outperform a single, more developed organism. The extracellular and material activity of slime molds, the cooperative behavior of ant colonies, and the synchronized movements of birds baffle the human eye. Humanity stands dethroned, yearning to reclaim its privilege as the sole arbiter and architect of worlds.

This paper attempts to use GSO algorithm to tune a PID controller that can be used to control a satellite using reaction wheels. These have a higher order transfer function and the controller will be more difficult to tune due to this. To do this, a satellite is chosen which controls its attitude using reactions wheels. An axis is chosen and the reaction wheel along this axis is taken into consideration. A PID controller is then attached to this system. PID (Proportional-Integral-Derivative) are one of the most popular controllers used due to their broad applications and easy to design nature. The PID controller is tuned using Glowworm Swarm Optimization (GSO) algorithm and then the system is checked against a step input. The optimization of the controller is done by minimizing the time weighed absolute error cost function.

Learning new tasks accumulatively without forgetting remains a critical challenge in continual learning. Generative experience replay addresses this challenge by synthesizing pseudo-data points for past learned tasks and later replaying them for concurrent training along with the new tasks' data. Generative replay is the best strategy for continual learning under a strict class-incremental setting when certain constraints need to be met: (i) constant model size, (ii) no pre-training dataset, and (iii) no memory buffer for storing past tasks' data. Inspired by the biological nervous system mechanisms, we introduce a time-aware regularization method to dynamically fine-tune the three training objective terms used for generative replay: supervised learning, latent regularization, and data reconstruction. Experimental results on major benchmarks indicate that our method pushes the limit of brain-inspired continual learners under such strict settings, improves memory retention, and increases the average performance over continually arriving tasks.

The bird mating optimizer is a new metaheuristic algorithm that was originally proposed to solve continuous optimization problems with a very promising performance. However, the algorithm has not yet been applied for solving combinatorial optimization problems. Thus, the formulation may not be able to generate a discrete feasible solution. Many continuous algorithms used random-key representation to represent the discrete solution using real numbers or a discrete variant of the algorithm is used to deal with the discrete solution of the problem. However, there is no evidence which methodology is better for solving combinatorial optimization problems. Therefore, this work proposes two variants of bird mating optimizer (random-key bird mating optimizer and the discrete bird mating optimizer), to identify which one is more efficient in solving combinatorial optimization problems. In the first one, we use a random-key encoding scheme, whilst, in the later one, we use crossover (multi-parent) and mutation operators to combine the components of the selected parents to generate new broods. The performance of these algorithms is tested on the travelling salesman problem and berth allocation problem, and are compared with the results of two well-known optimization algorithms: Genetic Algorithm and Particle Swarm Optimization. Experimental results show that the discrete bird mating optimizer is more efficient than the others on all tested benchmark instances. Indeed, it is able to attain the best-known results in some of the BAP benchmark instances. These indicate the applicability and the effectiveness of the proposed discrete bird mating optimizer in solving combinatorial optimization problems. INDEX TERMS Heuristics, bird mating optimizer, berth allocation problem, travelling salesman problem, random-key, combinatorial optimization, metaheuristics.

Big Data is an important topic for discussion and research. It has gained this importance due to the meaningful value that could be extracted from these data. The application of Big Data in the modern business allows enterprises to take faster and smarter decisions, achieving a real competitive advantage. However, a lot of Big Data projects provide disappointing results that don&#39;t address the decision-makers&#39; needs due to many reasons. The main reason for this failure can be summarized in neglecting the study of the decision-making aspect of these projects. In light of this challenge, this study proposes the integration of decision aspect into Big Data as a solution. Therefore, this article presents three main contributions: 1) Clarify the definition of Big Data; 2) Presents BD-Da model, a conceptual model describes the levels that should be considered to develop a Big Data project aiming to solve a problem that calls a decision; 3) Describes a particular, logical, requireme...

A swarm of autonomous drones with self-coordination and environment adaptation can offer a robust, scalable and flexible manner to localize objects in an unexplored, dangerous or unstructured environment. We design a novel coordination algorithm combining three biologically-inspired processes: stigmergy, flocking and evolution. Stigmergy, a form of coordination exhibited by social insects, is exploited to attract drones in areas with potential targets. Flocking enables efficient cooperation between flock mates upon target detection, while keeping an effective scan. The two mechanisms can interoperate if their structural parameters are correctly tuned for a given scenario. Differential evolution adapts the swarm coordination according to environmental conditions. The performance of the proposed algorithm is examined with synthetic and real-world scenarios.

 Firefly Algorithm is a recently developed meta-heuristic algorithm, which is inspired by the flashing behaviour of Firefly. Initially, Firefly algorithm was used to solve the optimization problems of continuous search domain. Further, many researchers have successfully implemented this algorithm in several discrete optimization problems. Although the firefly algorithm behaves like another meta-heuristic method (i.e. Particle Swarm Optimization particle), however, the firefly is robust than that. Due to the presence of an exponential term in its movement equation, firefly algorithm is capable to search optimum value more efficiently than others. This study is, mainly, focused to show the strength of the firefly algorithm to solve the complex problems and to explore the possible research area on the structural engineering field. This study shows about the robustness of the firefly algorithm on the basis of recently published papers that was used to solve the size, shape and topology ...

This paper presents a transmission expansion algorithm based on ant colony optimization. It was developed and tested on a model for the Nordic area. The main focus of this work was to build a transmission expansion planning tool able to cope with the new challenge of large wind power integration. Thus, the optimization uses hourly time steps to include wind and load variations. Nevertheless, the overall simulation time to find good solutions is quite fast using heuristic information. The ant colony optimization method proved to be flexible and delivered reasonable results for the calculated scenario of wind power integration for 2030.

In this paper, we propose a new system for enhanced viewing of electronic text. It is named "Magnifying And Simplifying System for Text EXTension (MaSSTExt)". This system for displaying text has the operational feeling like a map system displayed on a web browser. No link buttons are used for changing the other pages in this system because it is made by using Ajax. So, it allows us to display huge text files in only one window or seamlessly display/not-display from index to body or annotation data. Using this system, footnotes, references, tables and figures on the text can be located at optimal positions. Comparing simultaneously two different texts is easy to read. Understanding a whole text with both a bird's-eye view in its totality and a detailed view can be easy. Simulation software "MaSSTExt" of our prototype system is introduced and the effectiveness of our research is shown.

IFIP was founded in 1960 under the auspices of UNESCO, following the First World Computer Congress held in Paris the previous year. An umbrella organization for societies working in information processing, IFIP's aim is two-fold: to support information processing within its member countries and to encourage technology transfer to developing nations. As its mission statement clearly states, IFIP's mission is to be the leading, truly international, apolitical organization which encourages and assists in the development, exploitation and application of information technology for the benefit of all people. IFIP is a non-profitmaking organization, run almost solely by 2500 volunteers. It operates through a number of technical committees, which organize events and publications. IFIP's events range from an international congress to local seminars, but the most important are: • The IFIP World Computer Congress, held every second year; • Open conferences; • Working conferences. The flagship event is the IFIP World Computer Congress, at which both invited and contributed papers are presented. Contributed papers are rigorously refereed and the rejection rate is high.

In this paper, we will examine numerous optimization approaches in the field of computer science engineering in depth, shedding light on their applications, strengths, and weaknesses. Optimization algorithms are important tools in computer science engineering, with applications spanning from machine learning to computer vision, data mining, robotics, and more. In principle, optimization algorithms strive to locate the best possible solution among a group of possibilities while taking certain objectives and restrictions into account. They are the foundation of problem-solving approaches, providing a systematic and efficient approach to dealing with multiple difficulties. The efficiency and efficacy of each algorithm vary from one another, and each algorithm has advantages and limits that rely on the applications they are used with. We intend to provide a comprehensive view of optimization algorithms. We will cover their many types, delving into their real-world applications and painstakingly analyzing their strengths and weaknesses. In addition, we will investigate the complexities of each algorithm, giving light on the specific characteristics and settings in which they shine. This work seeks to serve as a basic resource for computer science engineering academics and practitioners, developing a deeper understanding of optimization algorithms and stimulating more inquiry in this dynamic field.

Over the past few decades, the studies on algorithms inspired by nature have shown that these methods can be efficiently used to eliminate most of the difficulties of classical methods. Nature inspired algorithms are widely used to solve optimization problems with complex nature. Various research works are carried out and algorithms are presented based on that during last few decades. Recently, some new algorithms inspired from nature are proposed to further improve the solutions obtained by the algorithms presented before. In this paper, a survey of five recently introduced Nature inspired algorithms is carried out. They include Firefly algorithm (FA), Cuckoo Search (CS), and Bat Inspired Algorithm (BA). Each of these algorithms are introduced and applied on various numerical optimization functions by various authors. We have tried to review and study the papers published by the authors and present a conclusion of this survey based on the results obtained.

Biological organisms learn from interactions with their environment throughout their lifetime. For artificial systems to successfully act and adapt in the real world, it is desirable to similarly be able to learn on a continual basis. This challenge is known as lifelong learning, and remains to a large extent unsolved. In this perspective article, we identify a set of key capabilities that artificial systems will need to achieve lifelong learning. We describe a number of biological mechanisms, both neuronal and non-neuronal, that help explain how organisms solve these challenges, and present examples of biologically inspired models and biologically plausible mechanisms that have been applied to artificial intelligence systems in the quest towards development of lifelong learning machines. We discuss opportunities to further our understanding and advance the state of the art in lifelong learning, aiming to bridge the gap between natural and artificial intelligence.

The paper reviews and introduces the state-of-the-art nature-inspired metaheuristic algorithms in optimization, including Firefly algorithm, PSO algorithms and ABC algorithm. By implementing these algorithms in Matlab, we will use worked examples to show how each algorithm works. Firefly algorithm is one of the evolutionary optimization algorithms, and is inspired by the flashing behaviour of fireflies in nature. There are many noisy non-linear mathematical optimization problems that can be effectively solved by Metaheuristic Algorithms. Mathematical optimization or programming is the study of such planning and design problems using mathematical tools. Nowadays, computer simulations become an indispensable tool for solving such optimization problems with various efficient search algorithms. Nature-inspired algorithms are among the most powerful algorithms for optimization. Firefly algorithm is one of the new metaheuristic algorithms for optimization problems. The algorithm is inspired by the flashing behaviour of fireflies. A Firefly Algorithm (FA) is a recent nature inspired optimization algorithm, which simulates the flash pattern and characteristics of fireflies. It is a powerful swarm intelligence algorithm inspired by the flash phenomenon of the fireflies. In this context, three types of metaheuristics called Artificial bee Colony algorithm, Particle Swarm Optimization (PSO) and Firefly algorithms were devised to find optimal solutions of noisy non-linear continuous mathematical models. A series of computational experiments using each algorithm were conducted. The stimulation result of this experiment were analyzed and compared to the best solutions found so The Firefly algorithm in each noisy non linear optimization function seems to perform better and efficient.

Cloud computing has been considered as the new computing paradigm that would offer computer resources over the Internet as service. With the widespread use of cloud, computing would become another utility similar to electricity, water, gas and telephony where the customer would be paying only for the services consumed contrary to the current practice of paying a monthly or annual fixed charge irrespective of use. For cloud computing to become accepted by everybody, several issues need to be resolved. One of the most important issues to be addressed is cloud security. Trust management is one of the important components of cloud security that requires special attention. In this paper, the authors propose the concept that honey bee algorithm which has been developed to solve complex optimization problems can be successfully used to address this issue. The authors have taken a closer look at the optimization problems that had been solved using the honey bee algorithm and the similarity between these problems and the cloud computing environment. Thus concluding that the honey bee algorithm could be successfully used to solve the trust management issue in cloud computing.

Lifelong learning capabilities are crucial for artificial autonomous agents operating on real-world data, which is typically non-stationary and temporally correlated. In this work, we demonstrate that dynamically grown networks outperform static networks in incremental learning scenarios, even when bounded by the same amount of memory in both cases. Learning is unsupervised in our models, a condition that additionally makes training more challenging whilst increasing the realism of the study, since humans are able to learn without dense manual annotation. Our results on artificial neural networks reinforce that structural plasticity constitutes effective prevention against catastrophic forgetting in non-stationary environments, as well as empirically supporting the importance of neurogenesis in the mammalian brain.

Bom in Ireland and brought up in Glasgow, Scotland. James Arthur came to New York in 1871. Trained in mechanics and gearcutting, he pursued a career in the manufacture and repair of machinery, during the course of which he founded a number of successful businesses and received patents on a variety of mechanical devices. His mechanical interests evolved early into a lifelong passion for horology, the science of measuring time, and he both made some remarkable clocks and assembled an important collection of old and rare timepieces. Early in this century James Arthur became associated with the American Museum of Natural History, and began to expand his interest in time to evolutionary time, and his interest in mechanisms to that most precise and delicate mechanism of them all. the human brain. The ultimate expression of his fascination with evolution and the brain was James Arthur's bequest to the American Museum permitting the establishment of the James Arthur Lectures on the Evolution of the Human Brain. The first James Arthur Lecture was delivered on March 15. 1932. two years after Mr. Arthur's death, and the series has since continued annually, without interruption.

We propose a new method for unsupervised continual knowledge consolidation in generative models that relies on the partitioning of Variational Autoencoder’s latent space. Acquiring knowledge about new data samples without forgetting previous ones is a critical problem of continual learning. Currently proposed methods achieve this goal by extending the existing model while constraining its behavior not to degrade on the past data, which does not exploit the full potential of relations within the entire training dataset. In this work, we identify this limitation and posit the goal of continual learning as a knowledge accumulation task. We solve it by continuously re-aligning latent space partitions that we call bands which are representations of samples seen in different tasks, driven by the similarity of the information they contain. In addition, we introduce a simple yet effective method for controlled forgetting of past data that improves the quality of reconstructions encoded in l...

Nature is the best tutor and its designs and strengths are extremely massive and strange that it gives inspiration to researches to imitate nature to solve hard and complex problems in computer sciences. Bio Inspired computing has come up as a new era in computation covering wide range of applications. This paper gives overview of most predominant and successful classes of bio inspired optimization methods involving evolutionary and swarm based algorithms inspired by natural evolution and collective behavior in animals respectively.

The research outlined in this paper aims the development of a methodology to arrive at critical path calculations in construction networks using Ant Colony Optimization (ACO) algorithms. Ant Colony Optimization is a population-based, artificial multiagent, general-search technique for the solution of difficult combinatorial problems. The method's theoretical roots are based on the behaviour of real ant colonies and the collective trail-laying and trail-following of its members in searching for optimal solutions in traversing multiple paths. In essence, ACO is inspired by the foraging behaviour of natural ant colonies which optimize their path from an origin (ant nest) to a destination (food source) by taking advantage of knowledge acquired by other ants that previously traversed the possible paths. In computer implementations of the ACO algorithms, artificial ants are both agents and solution-construction procedures that stochastically build solutions by considering (1) artificial pheromone trails which change dynamically at run time to reflect the agents' acquired search experience, and (2) heuristic information on the problem/network being solved. The paper outlines the fundamental mathematical background of the ACO method and a suggested possible implementation strategy for solving for longest (critical) paths in construction schedule networks.

Evolutionary algorithms rarely deal with ontogenetic, non-inherited alteration of genetic information because they are based on a direct genotype-phenotype mapping. In contrast, several processes have been discovered in nature which alter genetic information encoded in DNA before it is translated into amino-acid chains. Ontogenetically altered genetic information is not inherited but extensively used in regulation and development of phenotypes, giving organisms the ability to, in a sense, re-program their genotypes according to environmental cues. An example of post-transcriptional alteration of gene-encoding sequences is the process of RNA Editing. Here we introduce a novel Agent-based model of genotype editing and a computational study of its evolutionary performance in static and dynamic environments. This model builds on our previous Genetic Algorithm with Editing, but presents a fundamentally novel architecture in which coding and non-coding genetic components are allowed to co...

Safety-critical systems used in applications that demand high levels of dependability, efficiency, and fault-tolerance often use sequential logic circuits in its design and implementation. The safety-critical digital system typically uses latches, flip-flops, and other memory elements, which are prone to the effects of natural faults and single event upsets (SEUs) caused by radiation-induced effects. The faults can lead to subsystem failures due to the continuous advancement in the realization of the small size transistor. To design a reliable digital-based system, it is essential to develop new faulttolerance approaches that are integrated into the design of sequential logic circuits. This work proposes a novel fault-tolerant approach based on the redundancy of sequential logic circuit, which consists of a variety of design components, D flip-flop storage elements linked to a fault injection unit, a duplicate modular redundancy, and data monitoring units with a switching circuit. The experimental simulation results using a five-state Markov chain analysis model prove that the proposed fault-tolerant system can achieve 0.99999998 for reliability of the fault detection coverage (C) which equal to 0.99999. Finally, we believe that using this new approach of fault-tolerance and redundancy would improve the dependability and reliability of next generation safety-critical applications.

The stability of synchronized states ͑frequency locked states͒ in networks of phase oscillators is investigated for several network topologies. It is shown that for some topologies there is more than one stable synchronized state according to the sign of coupling strength between oscillators. It is also shown that in some cases the synchronized state corresponds to zero order parameter.

A robotic swarm can perform various tasks. However, a human is required to task the swarm. Human control over the swarm can be enabled through a set of influential agents which can be either leaders or predators. In the presence of multiple tasks, the swarm may need to split into sub-swarms to accomplish the task and regroup as a swarm to execute larger tasks. The response of the swarm in the presence of influential agents depends on the swarm dynamics. A precise measure of influence using leaders or predators or a combination of leaders and predators to achieve the mission is not adequately studied. In this paper, we analyze the effect of using only leaders, only predators and a combination of leaders and predators on three swarm models namely, shepherding model, Couzin's model and a physicomimetic models while they perform foraging tasks and carry out Monte-Carlo simulations to evaluate the performance of the influential agents on different swarms. We also propose a novel way to split a swarm into smaller sub-swarms using influential agents. Our results show that the predator based swarm splitting and steering to a task based on shepherding model performs far better than any other combination of leaders and predators. This result is consistent even when the number of agents is increased to 500.