Efficient Optimization Research Articles

An efficient artificial neural network-based optimization techniques for the early prediction of coronary heart disease: comprehensive analysis

An efficient artificial neural network-based optimization techniques for the early prediction of coronary heart disease: comprehensive analysis

Synergism of Hydrogen-Induced Interstitial Effect and Gold-Induced Alloying Effect in PdAuH Metallene for Urea Electrosynthesis from Nitrate and Carbon Dioxide.

Urea is a common agricultural fertilizer and industrial raw material, but at present, the traditional industrial production of urea is energy-and pollution-intensive. Electrocatalytic coupling of CO2 and ubiquitous nitrogen sources to synthesize urea is considered as a promising alternative method but requiring high-performance catalysts to boost the C-N coupling electrocatalysis process. Herein, hydrogen-intercalated Pd-Au bimetallene (PdAuHene) was prepared by a three-step method and used for electrosynthesis of urea from NO3- and CO2, deriving an optimum urea Faradaic efficiency of 33.88% and yield rate of 6.68 mmol g-1 h-1 at an applied potential of -0.6 V vs RHE. Detailed material characterizations and electrochemical studies reveal that the metallene structure with ultrathin thickness could improve atomic utilization of precious metal atoms, and the introduction of Au and H atoms could adjust the electronic structure of Pd atoms, regulate the evolution pathway of key N-/C-intermediates, and promote the C-N coupling to form urea.

Analysis of the Impact of Enterprise Digital-Intelligent Transformation on Audit Fees

In todays digital era, enterprises are accelerating their digital-intelligent transformation processes to enhance competitiveness and operational efficiency. This paper employs theoretical analysis and case studies to examine the specific impact of digital-intelligent transformation on audit fees. The findings reveal that such transformation can reduce audit fees by improving information transparency, optimizing business processes, and mitigating audit risks. Using China Mobile and Haier Smart Home as examples, the study identifies three mechanisms through which different transformation measures affect audit fees: efficiency enhancement and burden reduction, quality improvement and empowerment, and precise risk prevention and control. These findings offer new insights into cost reduction and efficiency optimization for enterprises, helping to streamline cost structures and providing valuable guidance for the audit industrys transformation and upgrade in the digital-intelligent era.

Research on screening mechanism and efficiency optimization of segmented cross-screen

ABSTRACT In this work, the particle flow of wet coal particles in the segmented cross-screening process was simulated by DEM (discrete element method) with linear cohesion model. The screening mechanism of segmented cross-screening was investigated, and the simulation results were verified by experimental-scale cross-screen. Based on the Box-Behnken design (BBD) method, the effect of screen inclination (θ 1, θ 2, θ 3) on screening performance was investigated, and the optimized combination of screen inclination was used to further improve the screening efficiency. The results show that the segmented cross-screen structure significantly affects the screening effect, with the most pronounced impact observed in the screen inclination θ 3. The best combination of surface inclination is θ 1 = 10.39°, θ 2 = 17.64° and θ 3 = 23.97°, at which time the screening efficiency can reach 90.09%. This work contributes to the understanding of the cross-screening mechanism and provides the necessary reference for the optimal design of segmented cross-screens.

Adaptive Search Algorithms: A Comprehensive Overview and Emerging Optimization Trends

Adaptive search algorithms have emerged as pivotal tools for addressing complex, high-dimensional, and nonlinear challenges across various domains. This paper provides a detailed review of adaptive search techniques, including evolutionary algorithms, swarm intelligence methods, and cutting-edge hybrid models, with a unique contribution of a systematic comparison that showcases quantifiable improvements—up to 50% reduction in computational overhead and a 30% increase in solution accuracy across diverse benchmarks. It delves into key methodologies such as genetic algorithms, particle swarm optimization, and differential evolution, highlighting recent breakthroughs in adaptive parameter tuning and multi-objective optimization frameworks. The research emphasizes significant advancements in practical applications like machine learning, engineering design, and logistics, where these algorithms have improved the balance between exploration and exploitation for more optimal outcomes. Furthermore, emerging trends such as bio-inspired models and the integration of reinforcement learning and quantum-enhanced optimization are discussed, promising to reshape the adaptive search landscape by equipping it with sophisticated tools to manage the growing complexity of optimization challenges. This paper aims to map the current state and guide future directions of adaptive search algorithms, fostering the development of more robust, efficient, and adaptable optimization strategies essential for ongoing academic and practical innovations.

COBALT DOPED IRON BASED PEROVSKITE CATALYSTS FOR EFFICIENT REDUCTION OF NITRATE TO AMMONIA

Electrochemical nitrate reduction reaction (NO3RR) has received universal attention to synthesize value‐added ammonia, which requires high‐efficiency catalysts to reduce the reaction barrier. Herein, cobalt doped SrFeO3 nanofibers (SCFO) with abundant oxygen vacancies via electrospinning technique is proposed to convert nitrate to ammonia. Such catalyst achieves an optimum Faradaic efficiency of 81.5% and a high NH₃ yield of 16.1 mg h⁻¹ mg‐1cat. in a 0.1 M PBS + 0.1 M NaNO₃ solution at ‐0.9 V reversible hydrogen electrode (RHE). Moreover, the in‐situ electrochemical test and DFT calculations confirm the potential‐determining step (PDS) for SCFO is *NO‐*N with an energy barrier of only 1.28 eV.

Application of Reinforcement Learning Methods Combining Graph Neural Networks and Self-Attention Mechanisms in Supply Chain Route Optimization

Optimizing transportation routes to improve delivery efficiency and resource utilization in dynamic supply chain scenarios is a challenging task. Traditional route optimization methods often struggle with complex supply chain network structures and dynamic changes, which require a more efficient and flexible solution. This study proposes a method that integrates Graph Neural Networks (GNNs), self-attention mechanisms, and meta-reinforcement learning (Meta-RL) in order to address route optimization in supply chains. The goal is to develop a path planning method that excels in both static and dynamic environments. First, GNNs model the supply chain network, converting node and edge features into high-dimensional graph representations in order to capture local and global network information. Next, a Transformer-based strategy network captures global dependencies, optimizing path planning. Finally, Meta-RL enables rapid strategy adaptation to dynamic changes (e.g., new demand points or route disruptions) with minimal sample support. Experiments on multiple supply chain datasets show that our method improves path planning quality by about 7%, compared to traditional methods, achieving a path coverage of 92.29%. Ablation studies reveal that the on-time delivery rate improves by nearly 30% over the baseline model. These results demonstrate that the proposed method not only optimizes routes but also significantly enhances the overall efficiency and robustness of supply chain networks. This research provides an efficient route optimization framework applicable to complex supply chain management and other scheduling fields, offering new insights and technical solutions for future research and applications.

Transport resistance strikes back: unveiling its impact on fill factor losses in organic solar cells.

The fill factor (FF) is a critical parameter for solar cell efficiency, but its analytical description is challenging due to the interplay between recombination and charge extraction processes. A significant factor contributing to FF losses, beyond recombination, that has not received much attention is the influence of charge transport. In most state-of-the-art organic solar cells, the primary limitations of the FF do not just arise from non-radiative recombination, but also from low conductivity of the organic semiconductors. A closer look reveals that even in the highest efficiency cells, performance losses due to transport resistance are significant. This finding highlights the need for refined models to predict the FF accurately. 

Here, we extend the analytical model for transport resistance to a more general case by systematically incorporating energetic disorder. We introduce a straightforward set of equations to predict the FF of a solar cell, enabling the differentiation of losses attributed to recombination and transport resistance. Our analytical model is validated with a large set of experimental current-voltage and light intensity-dependent open-circuit voltage data for a wide range of temperatures. Based on our findings, we provide valuable insights into strategies for mitigating FF losses, guiding the development of more efficient solar cell designs and optimisation strategies.

Efficient Optimization of Magnetic Properties of Fe–4.5Si Alloy in Laser Powder Bed Fusion (LPBF)

Abstract Existing studies have successfully identified optimal process parameters to enhance relative density and mechanical properties. However, these optimizations often incur high experimental costs due to the need for repetitive experiments. This research introduces an efficient optimization framework using two design of experiment (DoE) methods and machine learning algorithms, aimed at optimizing the magnetic properties of Fe–4.5Si material. The framework consists of three steps: (1) identification of the process parameter region that ensures high relative density using cubic specimens, (2) development of surrogate models to predict magnetic properties, such as maximum relative permeability and core loss, using toroidal specimens, and (3) multi-objective optimization using the surrogate models and a multi-objective genetic algorithm (MOGA) to enhance magnetic properties. The results demonstrate that this method can efficiently optimize process parameters with a limited number of experiments. Furthermore, the versatility of this framework allows its application to other materials in the early stages of research, even without prior knowledge of specific materials.

Biosorption of Chromium and Nickel from Industrial Oil Mill Wastewater Using Groundnut Pod Waste Activated Carbon

Groundnut shell activated carbon was developed and characterized by chemical activation using phosphoric acid (H3PO4) for the uptake of Cr and Ni in a batch biosorption process. The purpose of this study was to reduce the spread of heavy metals in industrial oil mill wastewater. In this study characterization of activated carbon using, surface chemistry (FTI-IR), surface area (BET), surface morphology, and elemental identification (SEM/EDX) were all carried out, and the BET surface area was 689.41 m2/g for groundnut shell activated carbon. This study was also executed to determine the optimum biosorption efficiency parameters for Cr and Ni removal using Response Surface Methodology (RSM) to obtain maximum biosorption efficiency. The factors considered were temperature (25-55oC), adsorbent dosage (1-3 g) and contact time (1-2 hrs). Biosorption efficiency was the response. ANOVA analysis was carried out to analyse the most effective factor in experimental design response. The optimum conditions for removal of Cr and Ni were adsorbent dosage 0.40 g, contact time 1.1 hr and temperature 42.02 oC, which shows the maximum biosorption efficiency of 97.1% for Cr removal and 94.8% for Ni removal. Isotherm models analyses showed that the biosorption process was best fitted to Langmuir model and was physical. Results of the kinetic studies and thermodynamic parameters revealed that the biosorption process followed a pseudo-second-order, endothermic, and spontaneous in nature.

Wireless 5G Network in Edge Computing Based On MIMO with Federated Learning and Clustering Integrated Reinforcement Learning

Edge Computing (EC) is a revolutionary architecture that brings Cloud Computing (CC) services closer to data sources than ever before. This research proposed novel technique in edge computing network based on wireless 5G technology using MIMO_federated learning integrated with Reinforcement neural network. Here the aim is to enhance the resource allocation by Decentralized Federated learning in multiple user based MIMO (De_Fed_L- MIMO) networks. Then the energy efficiency and channel optimization of the network is carried out using K-means clustering integrated with Reinforcement learning (K-means_RL). Here the experimental analysis is carried out in terms of number of users of network as well as number of edge server by DoF of 92%, Spectral efficiency of 92%, Energy efficiency of 96%, Signal to noise ratio (SNR) of 85%, Coverage area of 92%, RL training accuracy of 95%, FL training accuracy of 98%.

Reducing Operational Costs in Sulselbar’s 150 kV System with Electromagnetic Field and Sine-Cosine Optimization

Dynamic economic dispatch (DED) is a crucial task in modern power systems, requiring efficient optimization to minimize generation costs while satisfying operational constraints. This study introduces a Hybrid Electromagnetic Field Optimization with Sine-Cosine Algorithm (EMFO-SCA) tailored to address the unique challenges of the Sulselbar 150 kV power system. Specifically, the algorithm is designed to handle non-linear cost functions, complex constraints, and dynamic load variations across a 24-hour scheduling period. EMFO-SCA achieves a balanced integration of global exploration (via Electromagnetic Field Optimization) and local exploitation (via the Sine-Cosine Algorithm), resulting in robust optimization performance. Applied to a system with seven active generator buses, EMFO-SCA demonstrates an average operational cost reduction of 0.27% compared to the Kho-Kho Algorithm (KKA). This improvement translates to measurable cost savings while maintaining strict adherence to generation limits, ramp rate constraints, and power balance at all intervals. For instance, during peak demand at 521.52 MW (hour 12), the method effectively minimizes costs without compromising operational reliability. The dual-phase design of EMFO-SCA enables faster convergence and higher accuracy than conventional methods, making it a scalable solution for real-world DED challenges. By optimizing power generation schedules dynamically and reliably, this study establishes EMFO-SCA as a significant advancement in energy system optimization, with clear potential for practical deployment in similar power systems.

Analysis and Design of Constant Current/Constant Voltage Output of Array Multitransmitter Inductive Power Transfer System

ABSTRACTWireless power transfer has been widely used in unmanned aerial vehicle (UAV) charging due to its convenient and flexible noncontact charging characteristics. The working area of the uncoupler inductive power transfer (IPT) system is limited, and ZVS is easily lost in phase‐shift modulation. This paper proposes a method for constant current (CC) /constant voltage (CV) output in an array multitransmitter IPT system based on HFP modulation in a wide working area. The HFP modulation method easily realizes the current phase synchronization of multiple transmitter coils, and the size can be adjusted. At the same time, an efficient optimization model for a multitransmitter IPT system based on HFP modulation is proposed. Finally, an experimental platform for the array multitransmitter IPT system is built to verify the effectiveness of the CC/CV output realization method and the efficiency optimization model for the multitransmitter IPT system. The maximum errors in charging current and voltage are less than 2.52% and 2.1%, respectively, and the peak efficiency of the IPT system reaches 87.3%.

Structure-Atropisomer Stability Relationship in Selective MCL-1 Inhibitors.

Atropisomersm is an emerging feature in recent drug candidates due to the increasing complexity of the targeted protein surfaces. The developability of the drug candidates requires that their atropisomer interconversion is either fast or very slow at ambient temperature therefore the understanding and predictability of the isomerization rate is of great importance. Through a series of selective MCL-1 inhibitors we studied how structural features influence the interconversion of atropisomers. Besides basic observations such as stability in solution, we also carried out NMR kinetics at varying temperatures and a quantum chemical assessment of the isomerization process. The results of our theoretical studies and experimental investigations matched nicely when it came to predicting the presence or absence of isomerization at ambient temperature. For certain compounds we also measured the rotational barrier that fitted nicely the predicted values. The better understanding of how structural elements impact atropisomer stability enables the more efficient optimization of this important feature.

Quality optimization of liquid silicon lenses based on sequential approximation optimization and radial basis function networks

This study introduces an innovative multi-objective optimization method based on sequential approximation optimization (SAO) and radial basis function (RBF) networks to enhance the injection molding process for liquid silicone optical lenses. The method successfully minimizes residual stress and volume shrinkage, thereby improving product quality and manufacturing efficiency. By replacing finite element reanalysis with the RBF network, it constructs an approximate functional relationship between process conditions and quality. The novelty lies in simplifying multi-objective optimization into a single-objective problem and utilizing Pareto boundary analysis for precise parameter tuning. This approach not only reduces trial-and-error costs and material waste but also significantly decreases carbon emissions, showcasing extensive potential for application in various manufacturing processes. Simulations varying key parameters—filling time, melt temperature, mold temperature, curing pressure, and curing time—revealed optimal conditions: filling time of 1.57s, melt temperature of 27.18 °C, mold temperature of 150 °C, curing time of 20.02s, and curing pressure of 28.79 MPa. Experiments were conducted to validate the numerical results, employing nondestructive testing methods to assess residual stress and volume shrinkage. The results demonstrated significant reductions in these values, affirming the method’s reliability and practicality. This innovative and efficient optimization approach provides a robust solution for enhancing injection molding processes while contributing to sustainability and cost efficiency.

Efficient Deployment of Peanut Leaf Disease Detection Models on Edge AI Devices

The intelligent transformation of crop leaf disease detection has driven the use of deep neural network algorithms to develop more accurate disease detection models. In resource-constrained environments, the deployment of crop leaf disease detection models on the cloud introduces challenges such as communication latency and privacy concerns. Edge AI devices offer lower communication latency and enhanced scalability. To achieve the efficient deployment of crop leaf disease detection models on edge AI devices, a dataset of 700 images depicting peanut leaf spot, scorch spot, and rust diseases was collected. The YOLOX-Tiny network was utilized to conduct deployment experiments with the peanut leaf disease detection model on the Jetson Nano B01. The experiments initially focused on three aspects of efficient deployment optimization: the fusion of rectified linear unit (ReLU) and convolution operations, the integration of Efficient Non-Maximum Suppression for TensorRT (EfficientNMS_TRT) to accelerate post-processing within the TensorRT model, and the conversion of model formats from number of samples, channels, height, width (NCHW) to number of samples, height, width, and channels (NHWC) in the TensorFlow Lite model. Additionally, experiments were conducted to compare the memory usage, power consumption, and inference latency between the two inference frameworks, as well as to evaluate the real-time video detection performance using DeepStream. The results demonstrate that the fusion of ReLU activation functions with convolution operations reduced the inference latency by 55.5% compared to the use of the Sigmoid linear unit (SiLU) activation alone. In the TensorRT model, the integration of the EfficientNMS_TRT module accelerated post-processing, leading to a reduction in the inference latency of 19.6% and an increase in the frames per second (FPS) of 20.4%. In the TensorFlow Lite model, conversion to the NHWC format decreased the model conversion time by 88.7% and reduced the inference latency by 32.3%. These three efficient deployment optimization methods effectively decreased the inference latency and enhanced the inference efficiency. Moreover, a comparison between the two frameworks revealed that TensorFlow Lite exhibited memory usage reductions of 15% to 20% and power consumption decreases of 15% to 25% compared to TensorRT. Additionally, TensorRT achieved inference latency reductions of 53.2% to 55.2% relative to TensorFlow Lite. Consequently, TensorRT is deemed suitable for tasks requiring strong real-time performance and low latency, whereas TensorFlow Lite is more appropriate for scenarios with constrained memory and power resources. Additionally, the integration of DeepStream and EfficientNMS_TRT was found to optimize memory and power utilization, thereby enhancing the speed of real-time video detection. A detection rate of 28.7 FPS was achieved at a resolution of 1280 × 720. These experiments validate the feasibility and advantages of deploying crop leaf disease detection models on edge AI devices.

Optimizing Bandwidth Allocation in Converged Networks Using Hybrid Deep Learning Model

The demand for high-speed network services and the increasing development of network traffic have led to the popularity of converged networks, which mix various services over a single infrastructure. However, because of the variety of application requirements and resource constraints, ensuring quality of service (QoS) in these networks is difficult. Conventional methods for allocating bandwidth are frequently static, reactive, and inefficient, which results in less-than-ideal network performance. We provide a unique deep learning method to optimize bandwidth allocation in convergent networks in order to overcome this. We create and use three deep learning models: Deep Q-Networks (DQN), Generative Adversarial Networks (GAN), and a special LSTM-based DQN model. We assess each model's performance using an extensive dataset. Our results show that the Novel DQN model performs better than the other models in terms of minimum packet loss, increased accuracy, decreased latency, throughput maximization, spectral efficiency optimization, bit error rate reduction, fairness assurance, and effective channel resource use. Better service quality is the outcome of these upgrades, which also significantly increase upload and download speeds. Our empirical studies demonstrate our methodology's usefulness in real-world scenarios and open the door to intelligent network management solutions that facilitate better QoS, efficient bandwidth allocation, and improved user experiences in converged networks.

Ultrasound-assisted deep eutectic solvent extraction of flavonol glycosides from Ginkgo biloba: Optimization of efficiency and mechanism

Ultrasound-assisted deep eutectic solvent extraction of flavonol glycosides from Ginkgo biloba: Optimization of efficiency and mechanism

Membrane transport engineering for efficient yeast biomanufacturing.

Yeast strains have been widely recognized as useful cell factories for biomanufacturing. To improve production efficiency, their biosynthetic pathways and regulatory strategies have been continuously optimized. However, commercial production using yeasts is still limited by low product yield and high production cost. Accumulating evidences have demonstrated the importance of metabolite transport processes in addressing these challenges. Engineering yeast membrane transporters for transporting precursors, substrates, intermediates, products and toxic inhibitors has been successful. In addition, membrane properties are also important for metabolite production. Here we propose membrane transport engineering (MTE) to integrate manipulation of both membrane transporters and membrane properties. We emphasize that systematic optimization of both transporters and membrane lipid bilayers benefits production efficiency. We also envision the potential of artificial intelligence and automation process in MTE for economic and sustainable bioproduction using yeast cell factories.

Optimization of Ignition Delay and Combustion Efficiency in Diesel-Biodiesel-Ethanol Blends for Compression Ignition Engine

Optimization of Ignition Delay and Combustion Efficiency in Diesel-Biodiesel-Ethanol Blends for Compression Ignition Engine