Muhammad Haris Abid (16469824), Rehan Ashraf (5047298), Toqeer Mahmood (4994945) et al. · Figshare · 2023
<div><p>Artificial intelligence (AI) development across the health sector has recently been the most crucial. Early medical information, identification, diagnosis, classification, then analysis, along with viable remedies, are always beneficial developments. Precise and consistent image classification has critical in diagnosing and tactical decisions for healthcare. The core issue with image classification has become the semantic gap. Conventional machine learning algorithms for classification rely mainly on low-level but rather high-level characteristics, employ some handmade features to close the gap, but force intense feature extraction as well as classification approaches. Deep learning is a powerful tool with considerable advances in recent years, with deep convolution neural networks (CNNs) succeeding in image classification. The main goal is to bridge the semantic gap and enhance the classification performance of multi-modal medical images based on the deep learning-based model ResNet50. The data set included 28378 multi-modal medical images to train and validate the model. Overall accuracy, precision, recall, and F1-score evaluation parameters have been calculated. The proposed model classifies medical images more accurately than other state-of-the-art methods. The intended research experiment attained an accuracy level of 98.61%. The suggested study directly benefits the health service.</p></div>
Cited by 0Open access
Ankita Sharma (3183054), Shalli Rani (19658599), Maha Driss (19658602) · Figshare · 2024
<div><p>In response to the rapidly evolving threat landscape in network security, this paper proposes an Evolutionary Machine Learning Algorithm designed for robust intrusion detection. We specifically address challenges such as adaptability to new threats and scalability across diverse network environments. Our approach is validated using two distinct datasets: BoT-IoT, reflecting a range of IoT-specific attacks, and UNSW-NB15, offering a broader context of network intrusion scenarios using GA based hybrid DT-SVM. This selection facilitates a comprehensive evaluation of the algorithm’s effectiveness across varying attack vectors. Performance metrics including accuracy, recall, and false positive rates are meticulously chosen to demonstrate the algorithm’s capability to accurately identify and adapt to both known and novel threats, thereby substantiating the algorithm’s potential as a scalable and adaptable security solution. This study aims to advance the development of intrusion detection systems that are not only reactive but also preemptively adaptive to emerging cyber threats.” During the feature selection step, a GA is used to discover and preserve the most relevant characteristics from the dataset by using evolutionary principles. Through the use of this technology based on genetic algorithms, the subset of features is optimised, enabling the subsequent classification model to focus on the most relevant components of network data. In order to accomplish this, DT-SVM classification and GA-driven feature selection are integrated in an effort to strike a balance between efficiency and accuracy. The system has been purposefully designed to efficiently handle data streams in real-time, ensuring that intrusions are promptly and precisely detected. The empirical results corroborate the study’s assertion that the IDS outperforms traditional methodologies.</p></div>
Cited by 0Open access
Paul Bloomfield · Oxford University Press eBooks · 2023
Abstract A naturalistic theory of moral realism, based on ancient Greek eudaimonism, is presented using concepts from biological and evolutionary theory. The general empirical claim is that each species evolves traits which promote flourishing in those individual members who develop them. Using biological analogies, Plato (Repub 352d–354c) and Aristotle (NE 1097b21–1098a20) gave their ergon arguments defending the functional excellence of the virtues and their central role in making human lives flourish. A new version of these arguments is based on a contemporary understanding of biological function and individual fitness, and a definition of “eudaimonia” constructed from this naturalistic basis. Human beings will live as well as possible by developing the virtues, for these traits allow us to act as well as possible regardless of the individual circumstances. Many standard objections are resolved, including Enoch’s “just too different” objection, Millgram’s Pollyanna objection, Copp and Sobel’s objection from relativism, and Watson’s gangster objection.
Cited by 13
Max Generation Number · 2011
� Choose initial population � Evaluate the fitness of each individual in the population � Repeat �Select best-ranking individuals to reproduce �Breed new generation through crossover and mutation(genetic operations) and give birth to offspring �Evaluate the individual fitness&apos;s of the offspring �Replace worst ranked part of population with offspring � Until &lt;some stopping criteria are satisfied&gt; � Tells when algorithm will stop � Selection is important � The better SC selection, the better algorithm results
Cited by 0
Denis M. Walsh · The British Journal for the Philosophy of Science · 1996
According to historical theories of biological function, a trait's function is determined by natural selection in the past. I argue that, in addition to historical functions, ahistorical functions ought to be recognized. I propose a theory of biological function which accommodates both. The function of a trait is the way it contributes to fitness and fitness can only be determined relative to a selective regime. Therefore, the function of a trait can only be specified relative to a selective regime. Apart from its desirable pluralism, only this view of relational function can support the function/accident and function/malfunction distinctions commonly thought to be part of the concept of function. Furthermore, only relational function correctly characterizes the explanatory consequences of function attributions in evolutionary biology.
Cited by 127
Yujia Ge (2827352), Bin Xu (10691) · Figshare · 2016
Cited by 0Open access
Hana Ali-Pacha, A. Hadj Brahim, Laurent Pascal · Indonesian Journal of Electrical Engineering and Computer Science · 2025
<p>In the dynamic field of artificial intelligence, genetic algorithms (GAs) offer a powerful approach to solving complex problems by mimicking biological mechanisms such as mutation, crossover, and natural selection. Their efficiency relies primarily on the fitness function, which evaluates the quality of candidate solutions and guides the evolutionary process toward an optimal outcome. A well-designed fitness function not only enhances convergence speed but also reduces the risk of stagnation and improves algorithmic accuracy. This paper explores the fundamental role of fitness functions in optimization, machine learning, multi-objective optimization, and cryptography, highlighting their impact on the performance of GAs. We propose a novel fitness function that incorporates the influence of crossover, mutation, and inversion rates on solution quality. This approach, which diverges from conventional models, demonstrates improved convergence behavior and adaptability across different problem domains. The proposed method enhances GA performance not only in secure data encryption but also in general optimization and learning tasks, making it a valuable contribution for both researchers and practitioners, which can open new avenues for research in the development of more robust evolutionary strategies that can adapt effectively to the specific characteristics and challenges of each problem domain.</p>
Cited by 0Open access
2014
This paper is made available online in accordance with publisher policies. Please scroll down to view the document itself. Please refer to the repository record for this item and our policy information available from the repository home page for further information. To see the final version of this paper please visit the publisher’s website. Access to the published version may require a subscription.
Cited by 0
Ajmeera Kiran (16819294), Ch Nagaraju (18251572), J. Chinna Babu (16819291) et al. · Figshare · 2024
<div><p>A shell and tube heat exchanger (STHE) for heat recovery applications was studied to discover the intricacies of its optimization. To optimize performance, a hybrid optimization methodology was developed by combining the Neural Fitting Tool (NFTool), Particle Swarm Optimization (PSO), and Grey Relational Analysis (GRE). STHE heat exchangers were analyzed systematically using the Taguchi method to analyze the critical elements related to a particular response. To clarify the complex relationship between the heat exchanger efficiency and operational parameters, grey relational grades (GRGs) are first computed. A forecast of the grey relation coefficients was then conducted using NFTool to provide more insight into the complex dynamics. An optimized parameter with a grey coefficient was created after applying PSO analysis, resulting in a higher grey coefficient and improved performance of the heat exchanger. A major and far-reaching application of this study was based on heat recovery. A detailed comparison was conducted between the estimated values and the experimental results as a result of the hybrid optimization algorithm. In the current study, the results demonstrate that the proposed counter-flow shell and tube strategy is effective for optimizing performance.</p></div>
Cited by 0Open access
Martin A. Trefzer, Andy M. Tyrrell · Natural computing series · 2015
Cited by 0
John F. McGrew · PsycEXTRA Dataset · 2003
Cited by 0
Sandra D. Mitchell · Biology & Philosophy · 1995
Cited by 101
James V Stone (378781) · Figshare · 2015
<p>The response of the network to a given input vector <b>x</b> is y = <b>w</b> · <b>x</b>. Given a desired (target) output <i>d</i>, the solid curve shows how the fitness penalty <i>D</i> for an incorrect response increases sharply (to unity) if the magnitude of the difference <i>e</i> = <i>y</i> − <i>d</i> is greater than 0.1 (i.e., if <i>e</i><sup>2</sup> > 0.01). For comparison, the quadratic error function <i>e</i><sup>2</sup> = (<i>y</i> − <i>d</i>)<sup>2</sup>, which is minimised during learning, is shown as a dashed curve. The range of <i>e</i>-values shown are typical for the simulations reported here. See <a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.0030147#s2" target="_blank">Methods</a> section for details.</p>
Cited by 0Open access
B. Venkatesh (17202747), Ajmeera Kiran (16819294), Mudassir Khan (14439377) et al. · Figshare · 2024
<div><p>In this study, shell and heat exchangers are optimized using an integrated optimization framework. In this research, A structured Design of Experiments (DOE) comprising 16 trials was first conducted to systematically determine the essential parameters, including mass flow rates (mh, mc), temperatures (T1, t1, T2, t2), and heat transfer coefficients (€, TR, U). By identifying the first four principal components, PCA was able to determine 87.7% of the variance, thereby reducing the dimensionality of the problem. Performance-related aspects of the system are the focus of this approach. Key outcomes (€, TR, U) were predicted by 99% R-squared using the RSM models. Multiple factors, such as the mass flow rate and inlet temperature, were considered during the design process. The maximizing efficiency, thermal resistance, and utility were achieved by considering these factors. By using genetic algorithms, Pareto front solutions that meet the requirements of decision-makers can be found. The combination of the shell and tube heat exchangers produced better results than expected. Engineering and designers can gain practical insight into the mass flow rate, temperature, and key responses (€, TR, U) if they quantify improvements in these factors. Despite the importance of this study, it has several potential limitations, including specific experimental conditions and the need to validate it in other situations as well. Future research could investigate other factors that influence system performance. A holistic optimization framework can improve the design and engineering of heat exchangers in the future. As a result of the study, a foundation for innovative advancements in the field has been laid with tangible improvements. The study exceeded expectations by optimizing shell and heat exchanger systems using an integrated approach, thereby contributing significantly to the advancement of the field.</p></div>
Cited by 0Open access
Ziwei Wu (11386352), Kuangang Fan (17468338), Ping Yi (389595) · Figshare · 2025
<div> Electromagnetic levitation technology has several advantages, such as no friction, safety, and reliability. Electromagnetic levitation control, as the core of electromagnetic levitation technology, has attracted people’s attention. The use of other traditional control algorithms frequently results in a decline in the system’s anti-disturbance and tracking performance due to the highly nonlinear, stochastic uncertainty, and time delay characteristics of electromagnetic levitation systems. This work takes the single point electromagnetic levitation ball system as the research object to address the above-mentioned issues. A control method combining an improved whale optimization algorithm with robust sliding mode control and adaptive linear active disturbance rejection (IWOA-SMC-ALADRC) is proposed to achieve stable control of a single point electromagnetic levitation ball. Firstly, a nonlinear model of the electromagnetic levitation ball system was established; Secondly, robust sliding mode control is combined with linear active disturbance rejection control, and an adaptive parameter tuning strategy is introduced for the PD module in LADRC; Meanwhile, an improved whale optimization algorithm was proposed to address the issue of excessive adjustable parameters in the controller; In addition, the stability and convergence of the control algorithm were proven using the Lyapunov equation; Finally, in order to verify the effectiveness of the control method, PID, LADRC, CS-LADRC, and I-LADRC were introduced for simulation analysis and experimental verification. The results indicate that IWOA-SMC-ALADRC has better anti-disturbance and tracking performance. </div>
Cited by 0Open access
Kejia Liu (5699651), Yiping Teng (21464646), Fang Liu (13271) · Figshare · 2025
<div> The fast developments in artificial intelligence together with evolutionary algorithms have not solved all the difficulties that Gene Expression Programming (GEP) encounters when maintaining population diversity and preventing premature convergence. Its restrictions block GEP from successfully handling high-dimensional along with complex optimization problems. This research develops Dynamic Gene Expression Programming (DGEP) as an algorithm to control genetic operators dynamically thus achieving improved global search with increased population diversity. The approach operates with two unique operators which include Adaptive Regeneration Operator (DGEP-R) and Dynamically Adjusted Mutation Operator (DGEP-M) to preserve diversity while maintaining exploration-exploitation balance during evolutionary search. An extensive evaluation of DGEP occurred through symbolic regression problem tests. The study employed traditional benchmark functions and conducted evaluations versus baselines Standard GEP, NMO-SARA, and MS-GEP-A to assess fitness outcomes, R² values, population diversification, and the avoidance of local optima. All key metric evaluations showed that DGEP beat standard GEP along with alternative improved variants. DGEP produced the optimal results for 8 benchmark functions that produced 15.7% better R² scores along with 2.3 × larger population diversity. The escape rate from local optima within DGEP reached 35% higher than what standard GEP could achieve. The DGEP model serves to enhance GEP performance through the effective maintenance of diversity and improved global search functions. The results indicate that adaptive genetic methods strengthen evolutionary procedures for solving complex problems effectively. </div>
Cited by 0Open access
J. Martikainen, S. J. Ovaska · 2008
any way imply IEEE endorsement of any of Helsinki University of Technology&apos;s products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to
Cited by 0
William B. White, Scott L. Hooper · Encyclopedia of Computational Neuroscience · 2015
Cited by 1
Guocai Chen (577157), Michael J. Cairelli (577158), Halil Kilicoglu (65631) et al. · Figshare · 2015
<p>Each contributory gene's expression in the current time point is magnified by its weight of interaction with the target gene. The sum of these contributions determines the expression level of the target gene at the subsequent time point. <i>t</i> indicates the time point in the microarray dataset, <i>n</i> is the number of genes in the pathway, is the weight of the interaction between gene <i>i</i> and gene <i>j</i>, is the gene expression value in the microarray set for gene <i>i</i> at time point <i>t</i>.</p>
Cited by 0Open access
Ruoxue Xiang (22838184), Xiang Liu (119470), Min Tian (438923) et al. · Figshare · 2025
This figure illustrates the overall computational process of the fitness function.
Cited by 0Open access