The problem of mapping application tasks is one of key issues in 3D Network on chip (3D NoC) design. A novel Logistic function based adaptive genetic algorithm (LFAGA) is proposed for energy-aware mapping of homogeneo...
详细信息
The problem of mapping application tasks is one of key issues in 3D Network on chip (3D NoC) design. A novel Logistic function based adaptive genetic algorithm (LFAGA) is proposed for energy-aware mapping of homogeneous 3D NoC. We formulate the mapping problem and show the Standard genetic algorithm (SGA). The LFAGA is presented in detail with the goal of obtaining higher convergence speed while preventing the premature convergence. Experimental results indicate that the proposed LFAGA is more efficient than previously proposed Chaos-genetic mapping algorithm (CGMAP). In the experiments, a randomly generated task graph of size 27 is mapped to a 3D NoC of size $\boldsymbol{3}\times \boldsymbol{3}\times \boldsymbol{3},\mathbf{t}$ he convergence speed of LFAGA is 2.55 times faster than CGMAP in the best condition. When the task size increases to 64 and the 3D NoC size extends to $\boldsymbol{4}\times \boldsymbol{4}\times \boldsymbol{4}$ , LFAGA is 2.31 times faster compared to CGMAP. For the NoC sizes in the range from $\boldsymbol{3}\times \boldsymbol{3}\times \boldsymbol{2}$ to $\boldsymbol{4}\times \boldsymbol{4}\times \boldsymbol{4}$ , solutions obtained by the LFAGA are consistently better than the CGMAP. For example, in the experiment of size $\boldsymbol{4}\times \boldsymbol{4}\times \boldsymbol{4}$ , the improvement of final result reaches 30.0% in term of energy consumption. For a real application of size $3\times 4\times 2$ , 18.6% of energy saving can be achieved and the convergence speed is 1.58 times faster than that of the CGMAP.
The growing complexity of modern network systems has increased the need for efficient multi-objective routing (MOR) algorithms. However, existing MOR methods face significant challenges, particularly in terms of compu...
详细信息
The growing complexity of modern network systems has increased the need for efficient multi-objective routing (MOR) algorithms. However, existing MOR methods face significant challenges, particularly in terms of computation time, which becomes problematic in networks with short-lived tasks where rapid decision-making is essential. The Non-dominated Sorting genetic Algorithm II (NSGA-II) offers a promising approach to addressing these challenges. Nevertheless, directly applying NSGA-II in dynamic network environments, where states frequently change, is impractical. This paper presents GAMR, an enhanced non-dominated sorting genetic Algorithm II-based dynamic multi-objective QoS routing algorithm, which leverages QoS metrics for its multi-objective function. Introducing novel initialization and crossover strategies, our approach efficiently identifies optimal solutions within a brief runtime. Implemented within a Software-defined Network controller for routing, GAMR outperforms existing multi-objective algorithms, exhibiting notable improvements in performance indicators. Specifically, enhancements range from 3.4% to 22.8% on the Hypervolume metric and from 33% to 86% on the Inverted Generational Distance metric. In terms of network metrics, experimental results demonstrate significant reductions in forwarding delay and packet loss rate to 41.25 ms and 3.9%, respectively, even under challenging network configurations with only 2 servers and up to 100 requests.
Robotic therapy has demonstrated significant potential in upper limb rehabilitation, particularly for patients with unilateral motor function disorders resulting from stroke. Dual-robot systems introduce innovative ap...
详细信息
This study explores the development of polypropylene (PP) compound recipes using analytical models (AM) combined with genetic algorithms (GAs). A talcum-filled PP compound, commonly utilised in injection moulding for ...
详细信息
This study explores the development of polypropylene (PP) compound recipes using analytical models (AM) combined with genetic algorithms (GAs). A talcum-filled PP compound, commonly utilised in injection moulding for packaging applications, served as a reference material, with shear viscosity, tensile modulus, and impact strength selected as target properties for replication. The AM were adapted and fitted to a dataset of 52 compounds, achieving high predictive accuracy for shear viscosity and tensile modulus, while impact strength proved more challenging due to its inherent variability. Three recipes were generated using GA under predefined material constraints. Recipe 1 aimed to replicate all three target properties, achieving a balanced compromise with maximum deviations of 13.14% for tensile modulus and 12.37% for impact strength while closely matching shear viscosity (maximum 9.8% deviation). Recipes 2 and 3, focused solely on matching shear viscosity and impact strength, demonstrated exceptional accuracy for shear viscosity, with Recipe 2 achieving near-perfect alignment (2.5% deviation). However, neither recipe approached the tensile modulus target due to material limitations. The findings demonstrate the effectiveness of combining AM with GA for designing alternative formulations, emphasising the importance of realistic targets and material constraints. This methodology is highly adaptable, allowing for the inclusion of additional optimisation criteria such as cost or sustainability. Future work will explore broader material sets and properties, extending the framework's applicability to technical polymers and diverse industrial applications.
The classical highlight model is primarily applicable for solving acoustic scattering problems of targets with simple geometries. To extend its application to the acoustic scattering of underwater vehicles with comple...
详细信息
Solar energy is an alternative to conventional fossil fuels, and maximising the energy collected through solar cell design improvements is worthwhile. genetic algorithms (GAs) have been historically useful in pursuing...
详细信息
Solar energy is an alternative to conventional fossil fuels, and maximising the energy collected through solar cell design improvements is worthwhile. genetic algorithms (GAs) have been historically useful in pursuing design improvements in solar cell architecture and manufacturing, particularly in combination with cell modelling software. This study demonstrates solar cell structural optimisation using PC3D software in combination with a genetic algorithm (GA) to maximise solar cell power conversion efficiency. PC3D is an Excel-based tool for modelling solar cells. The cell models examined here are: Passivated-Emitter Rear Contact (PERC), Interdigitated Back Contact (IBC), Aluminium-Back Surface Field (Al-BSF), and Passivated-Emitter Rear Locally Diffused (PERL). These are all silicon PV cells with varying structural features that significantly alter the performance of each cell. Absolute efficiency improvements of 2% for PERC, 1.6% for Al-BSF, 0.9% for IBC, and 0.5% for PERL cells are achieved. The main parameters impacting cell efficiency in this model are cell thickness and minority charge carrier lifetime, which feature a necessary trade-off between the higher absorption resulting from a thicker cell and the increased likelihood of charge collection arising from longer carrier lifetimes. These parameters are managed through other related values such as cell doping.
In this paper, we use a machine learning technique, specifically genetic algorithms, to reconstruct the functional form of f(Q) gravity in a model-independent manner. To achieve this, we use Hubble measurements derive...
详细信息
In this paper, we use a machine learning technique, specifically genetic algorithms, to reconstruct the functional form of f(Q) gravity in a model-independent manner. To achieve this, we use Hubble measurements derived from cosmic chronometers and radial baryon acoustic oscillations, including the latest Dark Energy Spectroscopic Instrument (DESI) BAO data. For the cosmic chronometers, we estimate the covariance matrix for 31 data points, considering both statistical and systematic errors. To the best of our knowledge, this is the first time that this estimation has been carried out, providing a robust and reliable foundation for reconstructing the functional form of f(Q) gravity. We reconstruct the Hubble parameter H(z) without assuming any specific dark energy model or a flat Universe, which allows us to derive f(Q) gravity without prior assumptions. In this reconstruction, we use the current value of H0 derived from genetic algorithms. The reconstructed f(Q) function aligns well with the ACDM model, suggesting only minor deviations at high redshift values that remain within the 1 sigma confidence region. Our approach is fully model-independent and does not rely on any a priori assumptions about the cosmological model, providing a powerful tool to describe the accelerated expansion of the Universe.
Recommender systems (RSs) are useful technology that can alleviate the problem of overload of information provided to users. In this research, we build a new RS, and we name it ETagMF. ETagMF is an Evolutionary-based ...
详细信息
Recommender systems (RSs) are useful technology that can alleviate the problem of overload of information provided to users. In this research, we build a new RS, and we name it ETagMF. ETagMF is an Evolutionary-based Tags-based Matrix Factorization (MF) model. Recently, researchers have introduced several MF-based approaches to improve the performance of the recommendation. MF is a multiplication of the items and user preference matrices in order to predict the unknown rating of items. ETagMF replaces the latent factors with the tags. It then uses genetic algorithms to predict the unknown rated items. It aims at improving accuracy, speeding up the recommendation process, increasing transparency and interaction. As far as we know, we have not found in the literature any similar work that applies the evolutionary algorithm and the tag-based MF techniques to predict values for the unknown items. Experimentally, we use Movielens dataset, and we show that ETagMF achieves good results. Furthermore, it outperforms the other competitive and similar state-of-the-art evolutionary-based collaborative filtering RSs. We compare ETagMF versus the Evolutionary Based Matrix Factorization (EMF) method done by Navgran using 500 latent factors for EMF and 500 tags for ETagMF. EMF is similar to ETagMF except that ETagMF uses tags and EMF uses latent factors. We show that ETagMF outperforms EMF, and it is 2.41 times faster than EMF and 12 times faster than the traditional MF method.
Compact genetic algorithms (cGAs) are condensed variants of classical genetic algorithms (GAs) that use a probability vector representation of the population instead of the complete population. cGAs have been shown to...
详细信息
Social media platforms frequently impose restrictive policies to moderate user content, prompting the emergence of creative evasion language strategies. This paper presents a multi-agent framework based on Large Langu...
详细信息
暂无评论