Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning paradigm.While this approach allows models to specialize in speci...Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning paradigm.While this approach allows models to specialize in specific tasks with reduced training costs,the substantial memory requirements during fine-tuning present a barrier to broader deployment.Parameter-Efficient Fine-Tuning(PEFT)techniques,such as Low-Rank Adaptation(LoRA),and parameter quantization methods have emerged as solutions to address these challenges by optimizing memory usage and computational efficiency.Among these,QLoRA,which combines PEFT and quantization,has demonstrated notable success in reducing memory footprints during fine-tuning,prompting the development of various QLoRA variants.Despite these advancements,the quantitative impact of key variables on the fine-tuning performance of quantized LLMs remains underexplored.This study presents a comprehensive analysis of these key variables,focusing on their influence across different layer types and depths within LLM architectures.Our investigation uncovers several critical findings:(1)Larger layers,such as MLP layers,can maintain performance despite reductions in adapter rank,while smaller layers,like self-attention layers,aremore sensitive to such changes;(2)The effectiveness of balancing factors depends more on specific values rather than layer type or depth;(3)In quantization-aware fine-tuning,larger layers can effectively utilize smaller adapters,whereas smaller layers struggle to do so.These insights suggest that layer type is a more significant determinant of fine-tuning success than layer depth when optimizing quantized LLMs.Moreover,for the same discount of trainable parameters,reducing the trainable parameters in a larger layer is more effective in preserving fine-tuning accuracy than in a smaller one.This study provides valuable guidance for more efficient fine-tuning strategies and opens avenues for further research into optimizing LLM fine-tuning in resource-constrained environments.展开更多
Configuring computational fluid dynamics(CFD)simulations typically demands extensive domain expertise,limiting broader access.Although large language models(LLMs)have advanced scientific computing,their use in automat...Configuring computational fluid dynamics(CFD)simulations typically demands extensive domain expertise,limiting broader access.Although large language models(LLMs)have advanced scientific computing,their use in automating CFD workflows is underdeveloped.We introduce a novel approach centered on domain-specific LLM adaptation.By fine-tuning Qwen2.5-7B-Instruct on NL2FOAM,our custom dataset of 28,716 natural language-to-OpenFOAM configuration pairs with chain-of-thought(CoT)annotations enables direct translation from natural language descriptions to executable CFD setups.A multi-agent system orchestrates the process,autonomously verifying inputs,generating configurations,running simulations,and correcting errors.Evaluation on a benchmark of 21 diverse flow cases demonstrates state-of-the-art performance,achieving 88.7%solution accuracy and 82.6%first-attempt success rate.This significantly outperforms larger general-purpose models such as Qwen2.5-72B-Instruct,DeepSeek-R1,and Llama3.3-70B-Instruct,while also requiring fewer correction iterations and maintaining high computational efficiency.The results highlight the critical role of domain-specific adaptation in deploying LLM assistants for complex engineering workflows.Our code and fine-tuned model have been deposited at https://github.com/YYgroup/AutoCFD.展开更多
A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehens...A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance,strengths,and weaknesses.This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies.In this research,50 studies on 25+LLMs,including GPT-3,GPT-4,Claude 3.5,DeepKet,and hybrid multimodal frameworks like ContextDET and GeoRSCLIP,are thoroughly reviewed.We propose LLM application taxonomy by grouping techniques by task focus—healthcare,chemistry,sentiment analysis,agent-based simulations,and multimodal integration.Advanced methods like parameter-efficient tuning(LoRA),quantumenhanced embeddings(DeepKet),retrieval-augmented generation(RAG),and safety-focused models(GalaxyGPT)are evaluated for dataset requirements,computational efficiency,and performance measures.Frameworks for ethical issues,data limited hallucinations,and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted.The investigation’s scope,mad,and methods are described,but the primary results are not.The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings performbetter for context-heavy applications.In medical text normalization,ChatGPT-4 outperforms previous models,while two multimodal frameworks,GeoRSCLIP,increase remote sensing.Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance,demonstrating the necessity for adaptive models in multiple domains.To discover the optimum domain-specific models,explain domain-specific fine-tuning,and present quantum andmultimodal LLMs to address scalability and cross-domain issues.The framework helps academics and practitioners identify,adapt,and innovate LLMs for different purposes.This work advances the field of efficient,interpretable,and ethical LLM application research.展开更多
In the rapidly evolving landscape of natural language processing(NLP)and sentiment analysis,improving the accuracy and efficiency of sentiment classification models is crucial.This paper investigates the performance o...In the rapidly evolving landscape of natural language processing(NLP)and sentiment analysis,improving the accuracy and efficiency of sentiment classification models is crucial.This paper investigates the performance of two advanced models,the Large Language Model(LLM)LLaMA model and NLP BERT model,in the context of airline review sentiment analysis.Through fine-tuning,domain adaptation,and the application of few-shot learning,the study addresses the subtleties of sentiment expressions in airline-related text data.Employing predictive modeling and comparative analysis,the research evaluates the effectiveness of Large Language Model Meta AI(LLaMA)and Bidirectional Encoder Representations from Transformers(BERT)in capturing sentiment intricacies.Fine-tuning,including domain adaptation,enhances the models'performance in sentiment classification tasks.Additionally,the study explores the potential of few-shot learning to improve model generalization using minimal annotated data for targeted sentiment analysis.By conducting experiments on a diverse airline review dataset,the research quantifies the impact of fine-tuning,domain adaptation,and few-shot learning on model performance,providing valuable insights for industries aiming to predict recommendations and enhance customer satisfaction through a deeper understanding of sentiment in user-generated content(UGC).This research contributes to refining sentiment analysis models,ultimately fostering improved customer satisfaction in the airline industry.展开更多
Aiming to solve the steering instability and hysteresis of agricultural robots in the process of movement,a fusion PID control method of particle swarm optimization(PSO)and genetic algorithm(GA)was proposed.The fusion...Aiming to solve the steering instability and hysteresis of agricultural robots in the process of movement,a fusion PID control method of particle swarm optimization(PSO)and genetic algorithm(GA)was proposed.The fusion algorithm took advantage of the fast optimization ability of PSO to optimize the population screening link of GA.The Simulink simulation results showed that the convergence of the fitness function of the fusion algorithm was accelerated,the system response adjustment time was reduced,and the overshoot was almost zero.Then the algorithm was applied to the steering test of agricultural robot in various scenes.After modeling the steering system of agricultural robot,the steering test results in the unloaded suspended state showed that the PID control based on fusion algorithm reduced the rise time,response adjustment time and overshoot of the system,and improved the response speed and stability of the system,compared with the artificial trial and error PID control and the PID control based on GA.The actual road steering test results showed that the PID control response rise time based on the fusion algorithm was the shortest,about 4.43 s.When the target pulse number was set to 100,the actual mean value in the steady-state regulation stage was about 102.9,which was the closest to the target value among the three control methods,and the overshoot was reduced at the same time.The steering test results under various scene states showed that the PID control based on the proposed fusion algorithm had good anti-interference ability,it can adapt to the changes of environment and load and improve the performance of the control system.It was effective in the steering control of agricultural robot.This method can provide a reference for the precise steering control of other robots.展开更多
We study the split common solution problem with multiple output sets for monotone operator equations in Hilbert spaces.To solve this problem,we propose two new parallel algorithms.We establish a weak convergence theor...We study the split common solution problem with multiple output sets for monotone operator equations in Hilbert spaces.To solve this problem,we propose two new parallel algorithms.We establish a weak convergence theorem for the first and a strong convergence theorem for the second.展开更多
Accurate prediction of flood events is important for flood control and risk management.Machine learning techniques contributed greatly to advances in flood predictions,and existing studies mainly focused on predicting...Accurate prediction of flood events is important for flood control and risk management.Machine learning techniques contributed greatly to advances in flood predictions,and existing studies mainly focused on predicting flood resource variables using single or hybrid machine learning techniques.However,class-based flood predictions have rarely been investigated,which can aid in quickly diagnosing comprehensive flood characteristics and proposing targeted management strategies.This study proposed a prediction approach of flood regime metrics and event classes coupling machine learning algorithms with clustering-deduced membership degrees.Five algorithms were adopted for this exploration.Results showed that the class membership degrees accurately determined event classes with class hit rates up to 100%,compared with the four classes clustered from nine regime metrics.The nonlinear algorithms(Multiple Linear Regression,Random Forest,and least squares-Support Vector Machine)outperformed the linear techniques(Multiple Linear Regression and Stepwise Regression)in predicting flood regime metrics.The proposed approach well predicted flood event classes with average class hit rates of 66.0%-85.4%and 47.2%-76.0%in calibration and validation periods,respectively,particularly for the slow and late flood events.The predictive capability of the proposed prediction approach for flood regime metrics and classes was considerably stronger than that of hydrological modeling approach.展开更多
This paper proposes an equivalent modeling method for photovoltaic(PV)power stations via a particle swarm optimization(PSO)K-means clustering(KMC)algorithm with passive filter parameter clustering to address the compl...This paper proposes an equivalent modeling method for photovoltaic(PV)power stations via a particle swarm optimization(PSO)K-means clustering(KMC)algorithm with passive filter parameter clustering to address the complexities,simulation time cost and convergence problems of detailed PV power station models.First,the amplitude–frequency curves of different filter parameters are analyzed.Based on the results,a grouping parameter set for characterizing the external filter characteristics is established.These parameters are further defined as clustering parameters.A single PV inverter model is then established as a prerequisite foundation.The proposed equivalent method combines the global search capability of PSO with the rapid convergence of KMC,effectively overcoming the tendency of KMC to become trapped in local optima.This approach enhances both clustering accuracy and numerical stability when determining equivalence for PV inverter units.Using the proposed clustering method,both a detailed PV power station model and an equivalent model are developed and compared.Simulation and hardwarein-loop(HIL)results based on the equivalent model verify that the equivalent method accurately represents the dynamic characteristics of PVpower stations and adapts well to different operating conditions.The proposed equivalent modeling method provides an effective analysis tool for future renewable energy integration research.展开更多
Existing feature selection methods for intrusion detection systems in the Industrial Internet of Things often suffer from local optimality and high computational complexity.These challenges hinder traditional IDS from...Existing feature selection methods for intrusion detection systems in the Industrial Internet of Things often suffer from local optimality and high computational complexity.These challenges hinder traditional IDS from effectively extracting features while maintaining detection accuracy.This paper proposes an industrial Internet ofThings intrusion detection feature selection algorithm based on an improved whale optimization algorithm(GSLDWOA).The aim is to address the problems that feature selection algorithms under high-dimensional data are prone to,such as local optimality,long detection time,and reduced accuracy.First,the initial population’s diversity is increased using the Gaussian Mutation mechanism.Then,Non-linear Shrinking Factor balances global exploration and local development,avoiding premature convergence.Lastly,Variable-step Levy Flight operator and Dynamic Differential Evolution strategy are introduced to improve the algorithm’s search efficiency and convergence accuracy in highdimensional feature space.Experiments on the NSL-KDD and WUSTL-IIoT-2021 datasets demonstrate that the feature subset selected by GSLDWOA significantly improves detection performance.Compared to the traditional WOA algorithm,the detection rate and F1-score increased by 3.68%and 4.12%.On the WUSTL-IIoT-2021 dataset,accuracy,recall,and F1-score all exceed 99.9%.展开更多
Frequency diverse array multiple-input multiple-output(FDA-MIMO)radar has gained considerable research attention due to its ability to effectively counter active repeater deception jamming in complex electromagnetic e...Frequency diverse array multiple-input multiple-output(FDA-MIMO)radar has gained considerable research attention due to its ability to effectively counter active repeater deception jamming in complex electromagnetic environments.The effectiveness of interference suppression by FDA-MIMO is limited by the inherent range-angle coupling issue in the FDA beampattern.Existing literature primarily focuses on control methods for FDA-MIMO radar beam direction under the assumption of static beampatterns,with insufficient exploration of techniques for managing nonstationary beam directions.To address this gap,this paper initially introduces the FDA-MIMO signal model and the calculation formula for the FDA-MIMO array output using the minimum variance distortionless response(MVDR)beamformer.Building on this,the problem of determining the optimal frequency offset for the FDA is rephrased as a convex optimization problem,which is then resolved using the cuckoo search(CS)algorithm.Simulations confirm the effectiveness of the proposed approach,showing that the frequency offsets obtained through the CS algorithm can create a dot-shaped beam direction at the target location while effectively suppressing interference signals within the mainlobe.展开更多
Welding deformation adversely affects the quality and precision of structural components,and traditional methods require significant material resources and time.Machine learning has demonstrated exceptional ac-curacy ...Welding deformation adversely affects the quality and precision of structural components,and traditional methods require significant material resources and time.Machine learning has demonstrated exceptional ac-curacy and efficiency in solving complex problems.Thus,the use of machine learning to predict welding de-formations is a novel approach.In this study,laser welding experiments were conducted on a TC4 titanium alloy to establish a welding deformation dataset.The deep neural network(DNN)and convolutional neural network(CNN)models were designed and constructed,with average prediction errors of 0.85 mm and 0.94 mm on the validation set,respectively.To further optimize the network parameters,a differential evolution algorithm was employed through mutation,crossover,and selection.The results indicated that after optimization,the pre-diction errors of the DNN and CNN models reduced to 0.75 mm and 0.85 mm,respectively.These represent accuracy improvements of 14.8%and 9.6%,respectively.The optimized models exhibited superior predictive performances for the validation set.展开更多
Impact craters are important for understanding the evolution of lunar geologic and surface erosion rates,among other functions.However,the morphological characteristics of these micro impact craters are not obvious an...Impact craters are important for understanding the evolution of lunar geologic and surface erosion rates,among other functions.However,the morphological characteristics of these micro impact craters are not obvious and they are numerous,resulting in low detection accuracy by deep learning models.Therefore,we proposed a new multi-scale fusion crater detection algorithm(MSF-CDA)based on the YOLO11 to improve the accuracy of lunar impact crater detection,especially for small craters with a diameter of<1 km.Using the images taken by the LROC(Lunar Reconnaissance Orbiter Camera)at the Chang’e-4(CE-4)landing area,we constructed three separate datasets for craters with diameters of 0-70 m,70-140 m,and>140 m.We then trained three submodels separately with these three datasets.Additionally,we designed a slicing-amplifying-slicing strategy to enhance the ability to extract features from small craters.To handle redundant predictions,we proposed a new Non-Maximum Suppression with Area Filtering method to fuse the results in overlapping targets within the multi-scale submodels.Finally,our new MSF-CDA method achieved high detection performance,with the Precision,Recall,and F1 score having values of 0.991,0.987,and 0.989,respectively,perfectly addressing the problems induced by the lesser features and sample imbalance of small craters.Our MSF-CDA can provide strong data support for more in-depth study of the geological evolution of the lunar surface and finer geological age estimations.This strategy can also be used to detect other small objects with lesser features and sample imbalance problems.We detected approximately 500,000 impact craters in an area of approximately 214 km2 around the CE-4 landing area.By statistically analyzing the new data,we updated the distribution function of the number and diameter of impact craters.Finally,we identified the most suitable lighting conditions for detecting impact crater targets by analyzing the effect of different lighting conditions on the detection accuracy.展开更多
The existing multi-objective wheel profile optimization methods mainly consist of three sub-modules:(1)wheel profile generation,(2)multi-body dynamics simulation,and(3)an optimization algorithm.For the first module,a ...The existing multi-objective wheel profile optimization methods mainly consist of three sub-modules:(1)wheel profile generation,(2)multi-body dynamics simulation,and(3)an optimization algorithm.For the first module,a comparably conservative rotary-scaling finetuning(RSFT)method,which introduces two design variables and an empirical formula,is proposed to fine-tune the traditional wheel profiles for improving their engineering applicability.For the second module,for the TRAXX locomotives serving on the Blankenburg–Rubeland line,an optimization function representing the relationship between the wheel profile and the wheel–rail wear number is established based on Kriging surrogate model(KSM).For the third module,a method combining the regression capability of KSM with the iterative computing power of particle swarm optimization(PSO)is proposed to quickly and reliably implement the task of optimizing wheel profiles.Finally,with the RSFT–KSM–PSO method,we propose two wear-resistant wheel profiles for the TRAXX locomotives serving on the Blankenburg–Rubeland line,namely S1002-S and S1002-M.The S1002-S profile minimizes the total wear number by 30%,while the S1002-M profile makes the wear distribution more uniform through a proper sacrifice of the tread wear number,and the total wear number is reduced by 21%.The quasi-static and hunting stability tests further demonstrate that the profile designed by the RSFT–KSM–PSO method is promising for practical engineering applications.展开更多
Mo_(2)C is an excellent electrocatalyst for hydrogen evolution reaction(HER).However,Mo_(2)C is a poor electrocatalyst for oxygen evolution reaction(OER).Herein,two different elements,namely Co and Fe,are incorporated...Mo_(2)C is an excellent electrocatalyst for hydrogen evolution reaction(HER).However,Mo_(2)C is a poor electrocatalyst for oxygen evolution reaction(OER).Herein,two different elements,namely Co and Fe,are incorporated in Mo_(2)C that,therefore,has a finely tuned electronic structure,which is not achievable by incorporation of any one of the metals.Consequently,the resulting electrocatalyst Co_(0.8)Fe_(0.2)-Mo_(2)C-80 displayed excellent OER catalytic performance,which is evidenced by a low overpotential of 214.0(and 246.5)mV to attain a current density of 10(and 50)mA cm^(-2),an ultralow Tafel slope of 38.4 mV dec^(-1),and longterm stability in alkaline medium.Theoretical data demonstrates that Co_(0.8)Fe_(0.2)-Mo_(2)C-80 requires the lowest overpotential(1.00 V)for OER and Co centers to be the active sites.The ultrahigh catalytic performance of the electrocatalyst is attributed to the excellent intrinsic catalytic activity due to high Brunauer-Emmett-Teller specific surface area,large electrochemically active surface area,small Tafel slope,and low chargetransfer resistance.展开更多
This paper develops a wheel profile fine-tuning system(WPFTS)that comprehensively considers the influence of wheel profile on wheel damage,vehicle stability,vehicle safety,and passenger comfort.WPFTS can recommend one...This paper develops a wheel profile fine-tuning system(WPFTS)that comprehensively considers the influence of wheel profile on wheel damage,vehicle stability,vehicle safety,and passenger comfort.WPFTS can recommend one or more optimized wheel profiles according to train operators’needs,e.g.,reducing wheel wear,mitigating the development of wheel out-of-roundness(OOR),improving the shape stability of the wheel profile.Specifically,WPFTS includes four modules:(I)a wheel profile generation module based on the rotary-scaling finetuning(RSFT)method;(II)a multi-objective generation module consisting of a rigid multi-body dynamics simulation(MBS)model,an analytical model,and a rigid–flexible MBS model,for generating 11 objectives related to wheel damage,vehicle stability,vehicle safety,and passenger comfort;(III)a weight assignment module consisting of an adaptive weight assignment strategy and a manual weight assignment strategy;and(IV)an optimization module based on radial basis function(RBF)and particle swarm optimization(PSO).Finally,three cases are introduced to show how WPTFS recommends a wheel profile according to train operators’needs.Among them,a wheel profile with high shape stability,a wheel profile for mitigating the development of wheel OOR,and a wheel profile considering hunting stability and derailment safety are developed,respectively.展开更多
Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning...Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.展开更多
During cerebral cortical cortex neurogenesis two major types of progenitors generate a variety of morphologically and functionally diverse projection neurons destined for the different cortical layers in non-gyrified ...During cerebral cortical cortex neurogenesis two major types of progenitors generate a variety of morphologically and functionally diverse projection neurons destined for the different cortical layers in non-gyrified mice. Radial glia cells （RGCs） undergo mitosis in the cortical ventricular zone and exhibit an apical-basal cell polarity, whereas non-polar intermediate progenitor cells （IPCs） divide basally in the subventricular zone （Franco and Muller, 2013; Taverna et al., 2014）.展开更多
As the realm of enterprise-level conversational AI continues to evolve, it becomes evident that while generalized Large Language Models (LLMs) like GPT-3.5 bring remarkable capabilities, they also bring forth formidab...As the realm of enterprise-level conversational AI continues to evolve, it becomes evident that while generalized Large Language Models (LLMs) like GPT-3.5 bring remarkable capabilities, they also bring forth formidable challenges. These models, honed on vast and diverse datasets, have undoubtedly pushed the boundaries of natural language understanding and generation. However, they often stumble when faced with the intricate demands of nuanced enterprise applications. This research advocates for a strategic paradigm shift, urging enterprises to embrace a fine-tuning approach as a means to optimize conversational AI. While generalized LLMs are linguistic marvels, their inability to cater to the specific needs of businesses across various industries poses a critical challenge. This strategic shift involves empowering enterprises to seamlessly integrate their own datasets into LLMs, a process that extends beyond linguistic enhancement. The core concept of this approach centers on customization, enabling businesses to fine-tune the AI’s functionality to fit precisely within their unique business landscapes. By immersing the LLM in industry-specific documents, customer interaction records, internal reports, and regulatory guidelines, the AI transcends its generic capabilities to become a sophisticated conversational partner aligned with the intricacies of the enterprise’s domain. The transformative potential of this fine-tuning approach cannot be overstated. It enables a transition from a universal AI solution to a highly customizable tool. The AI evolves from being a linguistic powerhouse to a contextually aware, industry-savvy assistant. As a result, it not only responds with linguistic accuracy but also with depth, relevance, and resonance, significantly elevating user experiences and operational efficiency. In the subsequent sections, this paper delves into the intricacies of fine-tuning, exploring the multifaceted challenges and abundant opportunities it presents. It addresses the technical intricacies of data integration, ethical considerations surrounding data usage, and the broader implications for the future of enterprise AI. The journey embarked upon in this research holds the potential to redefine the role of conversational AI in enterprises, ushering in an era where AI becomes a dynamic, deeply relevant, and highly effective tool, empowering businesses to excel in an ever-evolving digital landscape.展开更多
Background： Sperm DNA fragmentation（sDF） has been proved to be an important parameter in order to predict in vitro the potential fertility of a semen sample. Colloid centrifugation could be a suitable technique to ...Background： Sperm DNA fragmentation（sDF） has been proved to be an important parameter in order to predict in vitro the potential fertility of a semen sample. Colloid centrifugation could be a suitable technique to select those donkey sperm more resistant to DNA fragmentation after thawing. Previous studies have shown that to elucidate the latent damage of the DNA molecule, sDF should be assessed dynamically, where the rate of fragmentation between treatments indicates how resistant the DNA is to iatrogenic damage. The rate of fragmentation is calculated using the slope of a linear regression equation. However, it has not been studied if s DF dynamics fit this model. The objectives of this study were to evaluate the effect of different after-thawing centrifugation protocols on sperm DNA fragmentation and elucidate the most accurate mathematical model（linear regression, exponential or polynomial） for DNA fragmentation over time in frozen-thawed donkey semen.Results： After submitting post-thaw semen samples to no centrifugation（UDC）, sperm washing（SW） or single layer centrifugation（SLC） protocols, sD F values after 6 h of incubation were significantly lower in SLC samples than in SW or UDC.Coefficient of determination（R-2） values were significantly higher for a second order polynomial model than for linear or exponential. The highest values for acceleration of fragmentation（aSDF） were obtained for SW, fol owed by SLC and UDC.Conclusion： SLC after thawing seems to preserve longer DNA longevity in comparison to UDC and SW. Moreover,the fine-tuning of models has shown that sDF dynamics in frozen-thawed donkey semen fit a second order polynomial model, which implies that fragmentation rate is not constant and fragmentation acceleration must be taken into account to elucidate hidden damage in the DNA molecule.展开更多
Precisely estimating the state of health(SOH)of lithium-ion batteries is essential for battery management systems(BMS),as it plays a key role in ensuring the safe and reliable operation of battery systems.However,curr...Precisely estimating the state of health(SOH)of lithium-ion batteries is essential for battery management systems(BMS),as it plays a key role in ensuring the safe and reliable operation of battery systems.However,current SOH estimation methods often overlook the valuable temperature information that can effectively characterize battery aging during capacity degradation.Additionally,the Elman neural network,which is commonly employed for SOH estimation,exhibits several drawbacks,including slow training speed,a tendency to become trapped in local minima,and the initialization of weights and thresholds using pseudo-random numbers,leading to unstable model performance.To address these issues,this study addresses the challenge of precise and effective SOH detection by proposing a method for estimating the SOH of lithium-ion batteries based on differential thermal voltammetry(DTV)and an SSA-Elman neural network.Firstly,two health features(HFs)considering temperature factors and battery voltage are extracted fromthe differential thermal voltammetry curves and incremental capacity curves.Next,the Sparrow Search Algorithm(SSA)is employed to optimize the initial weights and thresholds of the Elman neural network,forming the SSA-Elman neural network model.To validate the performance,various neural networks,including the proposed SSA-Elman network,are tested using the Oxford battery aging dataset.The experimental results demonstrate that the method developed in this study achieves superior accuracy and robustness,with a mean absolute error(MAE)of less than 0.9%and a rootmean square error(RMSE)below 1.4%.展开更多
基金supported by the National Key R&D Program of China(No.2021YFB0301200)National Natural Science Foundation of China(No.62025208).
文摘Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning paradigm.While this approach allows models to specialize in specific tasks with reduced training costs,the substantial memory requirements during fine-tuning present a barrier to broader deployment.Parameter-Efficient Fine-Tuning(PEFT)techniques,such as Low-Rank Adaptation(LoRA),and parameter quantization methods have emerged as solutions to address these challenges by optimizing memory usage and computational efficiency.Among these,QLoRA,which combines PEFT and quantization,has demonstrated notable success in reducing memory footprints during fine-tuning,prompting the development of various QLoRA variants.Despite these advancements,the quantitative impact of key variables on the fine-tuning performance of quantized LLMs remains underexplored.This study presents a comprehensive analysis of these key variables,focusing on their influence across different layer types and depths within LLM architectures.Our investigation uncovers several critical findings:(1)Larger layers,such as MLP layers,can maintain performance despite reductions in adapter rank,while smaller layers,like self-attention layers,aremore sensitive to such changes;(2)The effectiveness of balancing factors depends more on specific values rather than layer type or depth;(3)In quantization-aware fine-tuning,larger layers can effectively utilize smaller adapters,whereas smaller layers struggle to do so.These insights suggest that layer type is a more significant determinant of fine-tuning success than layer depth when optimizing quantized LLMs.Moreover,for the same discount of trainable parameters,reducing the trainable parameters in a larger layer is more effective in preserving fine-tuning accuracy than in a smaller one.This study provides valuable guidance for more efficient fine-tuning strategies and opens avenues for further research into optimizing LLM fine-tuning in resource-constrained environments.
基金supported by the National Natural Science Foundation of China(Grant Nos.52306126,22350710788,12432010,11988102,92270203)the Xplore Prize.
文摘Configuring computational fluid dynamics(CFD)simulations typically demands extensive domain expertise,limiting broader access.Although large language models(LLMs)have advanced scientific computing,their use in automating CFD workflows is underdeveloped.We introduce a novel approach centered on domain-specific LLM adaptation.By fine-tuning Qwen2.5-7B-Instruct on NL2FOAM,our custom dataset of 28,716 natural language-to-OpenFOAM configuration pairs with chain-of-thought(CoT)annotations enables direct translation from natural language descriptions to executable CFD setups.A multi-agent system orchestrates the process,autonomously verifying inputs,generating configurations,running simulations,and correcting errors.Evaluation on a benchmark of 21 diverse flow cases demonstrates state-of-the-art performance,achieving 88.7%solution accuracy and 82.6%first-attempt success rate.This significantly outperforms larger general-purpose models such as Qwen2.5-72B-Instruct,DeepSeek-R1,and Llama3.3-70B-Instruct,while also requiring fewer correction iterations and maintaining high computational efficiency.The results highlight the critical role of domain-specific adaptation in deploying LLM assistants for complex engineering workflows.Our code and fine-tuned model have been deposited at https://github.com/YYgroup/AutoCFD.
文摘A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance,strengths,and weaknesses.This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies.In this research,50 studies on 25+LLMs,including GPT-3,GPT-4,Claude 3.5,DeepKet,and hybrid multimodal frameworks like ContextDET and GeoRSCLIP,are thoroughly reviewed.We propose LLM application taxonomy by grouping techniques by task focus—healthcare,chemistry,sentiment analysis,agent-based simulations,and multimodal integration.Advanced methods like parameter-efficient tuning(LoRA),quantumenhanced embeddings(DeepKet),retrieval-augmented generation(RAG),and safety-focused models(GalaxyGPT)are evaluated for dataset requirements,computational efficiency,and performance measures.Frameworks for ethical issues,data limited hallucinations,and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted.The investigation’s scope,mad,and methods are described,but the primary results are not.The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings performbetter for context-heavy applications.In medical text normalization,ChatGPT-4 outperforms previous models,while two multimodal frameworks,GeoRSCLIP,increase remote sensing.Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance,demonstrating the necessity for adaptive models in multiple domains.To discover the optimum domain-specific models,explain domain-specific fine-tuning,and present quantum andmultimodal LLMs to address scalability and cross-domain issues.The framework helps academics and practitioners identify,adapt,and innovate LLMs for different purposes.This work advances the field of efficient,interpretable,and ethical LLM application research.
文摘In the rapidly evolving landscape of natural language processing(NLP)and sentiment analysis,improving the accuracy and efficiency of sentiment classification models is crucial.This paper investigates the performance of two advanced models,the Large Language Model(LLM)LLaMA model and NLP BERT model,in the context of airline review sentiment analysis.Through fine-tuning,domain adaptation,and the application of few-shot learning,the study addresses the subtleties of sentiment expressions in airline-related text data.Employing predictive modeling and comparative analysis,the research evaluates the effectiveness of Large Language Model Meta AI(LLaMA)and Bidirectional Encoder Representations from Transformers(BERT)in capturing sentiment intricacies.Fine-tuning,including domain adaptation,enhances the models'performance in sentiment classification tasks.Additionally,the study explores the potential of few-shot learning to improve model generalization using minimal annotated data for targeted sentiment analysis.By conducting experiments on a diverse airline review dataset,the research quantifies the impact of fine-tuning,domain adaptation,and few-shot learning on model performance,providing valuable insights for industries aiming to predict recommendations and enhance customer satisfaction through a deeper understanding of sentiment in user-generated content(UGC).This research contributes to refining sentiment analysis models,ultimately fostering improved customer satisfaction in the airline industry.
文摘Aiming to solve the steering instability and hysteresis of agricultural robots in the process of movement,a fusion PID control method of particle swarm optimization(PSO)and genetic algorithm(GA)was proposed.The fusion algorithm took advantage of the fast optimization ability of PSO to optimize the population screening link of GA.The Simulink simulation results showed that the convergence of the fitness function of the fusion algorithm was accelerated,the system response adjustment time was reduced,and the overshoot was almost zero.Then the algorithm was applied to the steering test of agricultural robot in various scenes.After modeling the steering system of agricultural robot,the steering test results in the unloaded suspended state showed that the PID control based on fusion algorithm reduced the rise time,response adjustment time and overshoot of the system,and improved the response speed and stability of the system,compared with the artificial trial and error PID control and the PID control based on GA.The actual road steering test results showed that the PID control response rise time based on the fusion algorithm was the shortest,about 4.43 s.When the target pulse number was set to 100,the actual mean value in the steady-state regulation stage was about 102.9,which was the closest to the target value among the three control methods,and the overshoot was reduced at the same time.The steering test results under various scene states showed that the PID control based on the proposed fusion algorithm had good anti-interference ability,it can adapt to the changes of environment and load and improve the performance of the control system.It was effective in the steering control of agricultural robot.This method can provide a reference for the precise steering control of other robots.
基金supported by the Science and Technology Fund of TNU-Thai Nguyen University of Science.
文摘We study the split common solution problem with multiple output sets for monotone operator equations in Hilbert spaces.To solve this problem,we propose two new parallel algorithms.We establish a weak convergence theorem for the first and a strong convergence theorem for the second.
基金National Key Research and Development Program of China,No.2023YFC3006704National Natural Science Foundation of China,No.42171047CAS-CSIRO Partnership Joint Project of 2024,No.177GJHZ2023097MI。
文摘Accurate prediction of flood events is important for flood control and risk management.Machine learning techniques contributed greatly to advances in flood predictions,and existing studies mainly focused on predicting flood resource variables using single or hybrid machine learning techniques.However,class-based flood predictions have rarely been investigated,which can aid in quickly diagnosing comprehensive flood characteristics and proposing targeted management strategies.This study proposed a prediction approach of flood regime metrics and event classes coupling machine learning algorithms with clustering-deduced membership degrees.Five algorithms were adopted for this exploration.Results showed that the class membership degrees accurately determined event classes with class hit rates up to 100%,compared with the four classes clustered from nine regime metrics.The nonlinear algorithms(Multiple Linear Regression,Random Forest,and least squares-Support Vector Machine)outperformed the linear techniques(Multiple Linear Regression and Stepwise Regression)in predicting flood regime metrics.The proposed approach well predicted flood event classes with average class hit rates of 66.0%-85.4%and 47.2%-76.0%in calibration and validation periods,respectively,particularly for the slow and late flood events.The predictive capability of the proposed prediction approach for flood regime metrics and classes was considerably stronger than that of hydrological modeling approach.
基金supported by the Research Project of China Southern Power Grid(No.056200KK52222031).
文摘This paper proposes an equivalent modeling method for photovoltaic(PV)power stations via a particle swarm optimization(PSO)K-means clustering(KMC)algorithm with passive filter parameter clustering to address the complexities,simulation time cost and convergence problems of detailed PV power station models.First,the amplitude–frequency curves of different filter parameters are analyzed.Based on the results,a grouping parameter set for characterizing the external filter characteristics is established.These parameters are further defined as clustering parameters.A single PV inverter model is then established as a prerequisite foundation.The proposed equivalent method combines the global search capability of PSO with the rapid convergence of KMC,effectively overcoming the tendency of KMC to become trapped in local optima.This approach enhances both clustering accuracy and numerical stability when determining equivalence for PV inverter units.Using the proposed clustering method,both a detailed PV power station model and an equivalent model are developed and compared.Simulation and hardwarein-loop(HIL)results based on the equivalent model verify that the equivalent method accurately represents the dynamic characteristics of PVpower stations and adapts well to different operating conditions.The proposed equivalent modeling method provides an effective analysis tool for future renewable energy integration research.
基金supported by the Major Science and Technology Programs in Henan Province(No.241100210100)Henan Provincial Science and Technology Research Project(No.252102211085,No.252102211105)+3 种基金Endogenous Security Cloud Network Convergence R&D Center(No.602431011PQ1)The Special Project for Research and Development in Key Areas of Guangdong Province(No.2021ZDZX1098)The Stabilization Support Program of Science,Technology and Innovation Commission of Shenzhen Municipality(No.20231128083944001)The Key scientific research projects of Henan higher education institutions(No.24A520042).
文摘Existing feature selection methods for intrusion detection systems in the Industrial Internet of Things often suffer from local optimality and high computational complexity.These challenges hinder traditional IDS from effectively extracting features while maintaining detection accuracy.This paper proposes an industrial Internet ofThings intrusion detection feature selection algorithm based on an improved whale optimization algorithm(GSLDWOA).The aim is to address the problems that feature selection algorithms under high-dimensional data are prone to,such as local optimality,long detection time,and reduced accuracy.First,the initial population’s diversity is increased using the Gaussian Mutation mechanism.Then,Non-linear Shrinking Factor balances global exploration and local development,avoiding premature convergence.Lastly,Variable-step Levy Flight operator and Dynamic Differential Evolution strategy are introduced to improve the algorithm’s search efficiency and convergence accuracy in highdimensional feature space.Experiments on the NSL-KDD and WUSTL-IIoT-2021 datasets demonstrate that the feature subset selected by GSLDWOA significantly improves detection performance.Compared to the traditional WOA algorithm,the detection rate and F1-score increased by 3.68%and 4.12%.On the WUSTL-IIoT-2021 dataset,accuracy,recall,and F1-score all exceed 99.9%.
基金supported by the National Natural Science Foundation of China(61503408)。
文摘Frequency diverse array multiple-input multiple-output(FDA-MIMO)radar has gained considerable research attention due to its ability to effectively counter active repeater deception jamming in complex electromagnetic environments.The effectiveness of interference suppression by FDA-MIMO is limited by the inherent range-angle coupling issue in the FDA beampattern.Existing literature primarily focuses on control methods for FDA-MIMO radar beam direction under the assumption of static beampatterns,with insufficient exploration of techniques for managing nonstationary beam directions.To address this gap,this paper initially introduces the FDA-MIMO signal model and the calculation formula for the FDA-MIMO array output using the minimum variance distortionless response(MVDR)beamformer.Building on this,the problem of determining the optimal frequency offset for the FDA is rephrased as a convex optimization problem,which is then resolved using the cuckoo search(CS)algorithm.Simulations confirm the effectiveness of the proposed approach,showing that the frequency offsets obtained through the CS algorithm can create a dot-shaped beam direction at the target location while effectively suppressing interference signals within the mainlobe.
基金Supported by Defense Industrial Technology Development Program of China(Grant No.JCKY2021605B015).
文摘Welding deformation adversely affects the quality and precision of structural components,and traditional methods require significant material resources and time.Machine learning has demonstrated exceptional ac-curacy and efficiency in solving complex problems.Thus,the use of machine learning to predict welding de-formations is a novel approach.In this study,laser welding experiments were conducted on a TC4 titanium alloy to establish a welding deformation dataset.The deep neural network(DNN)and convolutional neural network(CNN)models were designed and constructed,with average prediction errors of 0.85 mm and 0.94 mm on the validation set,respectively.To further optimize the network parameters,a differential evolution algorithm was employed through mutation,crossover,and selection.The results indicated that after optimization,the pre-diction errors of the DNN and CNN models reduced to 0.75 mm and 0.85 mm,respectively.These represent accuracy improvements of 14.8%and 9.6%,respectively.The optimized models exhibited superior predictive performances for the validation set.
基金the National Key Research and Development Program of China (Grant No.2022YFF0711400)the National Space Science Data Center Youth Open Project (Grant No. NSSDC2302001)
文摘Impact craters are important for understanding the evolution of lunar geologic and surface erosion rates,among other functions.However,the morphological characteristics of these micro impact craters are not obvious and they are numerous,resulting in low detection accuracy by deep learning models.Therefore,we proposed a new multi-scale fusion crater detection algorithm(MSF-CDA)based on the YOLO11 to improve the accuracy of lunar impact crater detection,especially for small craters with a diameter of<1 km.Using the images taken by the LROC(Lunar Reconnaissance Orbiter Camera)at the Chang’e-4(CE-4)landing area,we constructed three separate datasets for craters with diameters of 0-70 m,70-140 m,and>140 m.We then trained three submodels separately with these three datasets.Additionally,we designed a slicing-amplifying-slicing strategy to enhance the ability to extract features from small craters.To handle redundant predictions,we proposed a new Non-Maximum Suppression with Area Filtering method to fuse the results in overlapping targets within the multi-scale submodels.Finally,our new MSF-CDA method achieved high detection performance,with the Precision,Recall,and F1 score having values of 0.991,0.987,and 0.989,respectively,perfectly addressing the problems induced by the lesser features and sample imbalance of small craters.Our MSF-CDA can provide strong data support for more in-depth study of the geological evolution of the lunar surface and finer geological age estimations.This strategy can also be used to detect other small objects with lesser features and sample imbalance problems.We detected approximately 500,000 impact craters in an area of approximately 214 km2 around the CE-4 landing area.By statistically analyzing the new data,we updated the distribution function of the number and diameter of impact craters.Finally,we identified the most suitable lighting conditions for detecting impact crater targets by analyzing the effect of different lighting conditions on the detection accuracy.
基金the Assets4Rail Project which is funded by the Shift2Rail Joint Undertaking under the EU’s H2020 program(Grant No.826250)the Open Research Fund of State Key Laboratory of Traction Power of Southwest Jiaotong University(Grant No.TPL2011)+1 种基金part of the experiment data concerning the railway line is supported by the DynoTRAIN Project,funded by European Commission(Grant No.234079)The first author is also supported by the China Scholarship Council(Grant No.201707000113).
文摘The existing multi-objective wheel profile optimization methods mainly consist of three sub-modules:(1)wheel profile generation,(2)multi-body dynamics simulation,and(3)an optimization algorithm.For the first module,a comparably conservative rotary-scaling finetuning(RSFT)method,which introduces two design variables and an empirical formula,is proposed to fine-tune the traditional wheel profiles for improving their engineering applicability.For the second module,for the TRAXX locomotives serving on the Blankenburg–Rubeland line,an optimization function representing the relationship between the wheel profile and the wheel–rail wear number is established based on Kriging surrogate model(KSM).For the third module,a method combining the regression capability of KSM with the iterative computing power of particle swarm optimization(PSO)is proposed to quickly and reliably implement the task of optimizing wheel profiles.Finally,with the RSFT–KSM–PSO method,we propose two wear-resistant wheel profiles for the TRAXX locomotives serving on the Blankenburg–Rubeland line,namely S1002-S and S1002-M.The S1002-S profile minimizes the total wear number by 30%,while the S1002-M profile makes the wear distribution more uniform through a proper sacrifice of the tread wear number,and the total wear number is reduced by 21%.The quasi-static and hunting stability tests further demonstrate that the profile designed by the RSFT–KSM–PSO method is promising for practical engineering applications.
基金financial support from the SERB-SURE under file number of SUR/2022/003129Jong Hyeok Park acknowledges the support of the National Research Foundation of Korea (NRF)funded by the Ministry of Science and ICT (RS-2023-00302697,RS-2023-00268523).
文摘Mo_(2)C is an excellent electrocatalyst for hydrogen evolution reaction(HER).However,Mo_(2)C is a poor electrocatalyst for oxygen evolution reaction(OER).Herein,two different elements,namely Co and Fe,are incorporated in Mo_(2)C that,therefore,has a finely tuned electronic structure,which is not achievable by incorporation of any one of the metals.Consequently,the resulting electrocatalyst Co_(0.8)Fe_(0.2)-Mo_(2)C-80 displayed excellent OER catalytic performance,which is evidenced by a low overpotential of 214.0(and 246.5)mV to attain a current density of 10(and 50)mA cm^(-2),an ultralow Tafel slope of 38.4 mV dec^(-1),and longterm stability in alkaline medium.Theoretical data demonstrates that Co_(0.8)Fe_(0.2)-Mo_(2)C-80 requires the lowest overpotential(1.00 V)for OER and Co centers to be the active sites.The ultrahigh catalytic performance of the electrocatalyst is attributed to the excellent intrinsic catalytic activity due to high Brunauer-Emmett-Teller specific surface area,large electrochemically active surface area,small Tafel slope,and low chargetransfer resistance.
基金This work was supported by China Scholarship Council(Grant No.201707000113).
文摘This paper develops a wheel profile fine-tuning system(WPFTS)that comprehensively considers the influence of wheel profile on wheel damage,vehicle stability,vehicle safety,and passenger comfort.WPFTS can recommend one or more optimized wheel profiles according to train operators’needs,e.g.,reducing wheel wear,mitigating the development of wheel out-of-roundness(OOR),improving the shape stability of the wheel profile.Specifically,WPFTS includes four modules:(I)a wheel profile generation module based on the rotary-scaling finetuning(RSFT)method;(II)a multi-objective generation module consisting of a rigid multi-body dynamics simulation(MBS)model,an analytical model,and a rigid–flexible MBS model,for generating 11 objectives related to wheel damage,vehicle stability,vehicle safety,and passenger comfort;(III)a weight assignment module consisting of an adaptive weight assignment strategy and a manual weight assignment strategy;and(IV)an optimization module based on radial basis function(RBF)and particle swarm optimization(PSO).Finally,three cases are introduced to show how WPTFS recommends a wheel profile according to train operators’needs.Among them,a wheel profile with high shape stability,a wheel profile for mitigating the development of wheel OOR,and a wheel profile considering hunting stability and derailment safety are developed,respectively.
基金This work is part of the research projects LaTe4PoliticES(PID2022-138099OBI00)funded by MICIU/AEI/10.13039/501100011033the European Regional Development Fund(ERDF)-A Way of Making Europe and LT-SWM(TED2021-131167B-I00)funded by MICIU/AEI/10.13039/501100011033the European Union NextGenerationEU/PRTR.Mr.Ronghao Pan is supported by the Programa Investigo grant,funded by the Region of Murcia,the Spanish Ministry of Labour and Social Economy and the European Union-NextGenerationEU under the“Plan de Recuperación,Transformación y Resiliencia(PRTR).”。
文摘Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.
文摘During cerebral cortical cortex neurogenesis two major types of progenitors generate a variety of morphologically and functionally diverse projection neurons destined for the different cortical layers in non-gyrified mice. Radial glia cells （RGCs） undergo mitosis in the cortical ventricular zone and exhibit an apical-basal cell polarity, whereas non-polar intermediate progenitor cells （IPCs） divide basally in the subventricular zone （Franco and Muller, 2013; Taverna et al., 2014）.
文摘As the realm of enterprise-level conversational AI continues to evolve, it becomes evident that while generalized Large Language Models (LLMs) like GPT-3.5 bring remarkable capabilities, they also bring forth formidable challenges. These models, honed on vast and diverse datasets, have undoubtedly pushed the boundaries of natural language understanding and generation. However, they often stumble when faced with the intricate demands of nuanced enterprise applications. This research advocates for a strategic paradigm shift, urging enterprises to embrace a fine-tuning approach as a means to optimize conversational AI. While generalized LLMs are linguistic marvels, their inability to cater to the specific needs of businesses across various industries poses a critical challenge. This strategic shift involves empowering enterprises to seamlessly integrate their own datasets into LLMs, a process that extends beyond linguistic enhancement. The core concept of this approach centers on customization, enabling businesses to fine-tune the AI’s functionality to fit precisely within their unique business landscapes. By immersing the LLM in industry-specific documents, customer interaction records, internal reports, and regulatory guidelines, the AI transcends its generic capabilities to become a sophisticated conversational partner aligned with the intricacies of the enterprise’s domain. The transformative potential of this fine-tuning approach cannot be overstated. It enables a transition from a universal AI solution to a highly customizable tool. The AI evolves from being a linguistic powerhouse to a contextually aware, industry-savvy assistant. As a result, it not only responds with linguistic accuracy but also with depth, relevance, and resonance, significantly elevating user experiences and operational efficiency. In the subsequent sections, this paper delves into the intricacies of fine-tuning, exploring the multifaceted challenges and abundant opportunities it presents. It addresses the technical intricacies of data integration, ethical considerations surrounding data usage, and the broader implications for the future of enterprise AI. The journey embarked upon in this research holds the potential to redefine the role of conversational AI in enterprises, ushering in an era where AI becomes a dynamic, deeply relevant, and highly effective tool, empowering businesses to excel in an ever-evolving digital landscape.
基金partially supported by grants RZ2009-00006-00-00(Instituto Nacional de Investigacion y Tecnología Agraria y Alimentaria,Ministerio de Ciencia e Innovación,Spain)AGL-2013-42726-R(Secretaria de Estado de Investigacion,Desarrollo e Innovacion,Ministerio de Economia y Competitividad,Spain)+1 种基金supported by a Ph.D.fellowship from the ceiA3(Andalucia,Spain)with funding provided by Banco Santander through its Global Division,Santander Universidadesfunded by the Swedish Foundation for Equine Research,Stockholm,Sweden(H14-47-008)
文摘Background： Sperm DNA fragmentation（sDF） has been proved to be an important parameter in order to predict in vitro the potential fertility of a semen sample. Colloid centrifugation could be a suitable technique to select those donkey sperm more resistant to DNA fragmentation after thawing. Previous studies have shown that to elucidate the latent damage of the DNA molecule, sDF should be assessed dynamically, where the rate of fragmentation between treatments indicates how resistant the DNA is to iatrogenic damage. The rate of fragmentation is calculated using the slope of a linear regression equation. However, it has not been studied if s DF dynamics fit this model. The objectives of this study were to evaluate the effect of different after-thawing centrifugation protocols on sperm DNA fragmentation and elucidate the most accurate mathematical model（linear regression, exponential or polynomial） for DNA fragmentation over time in frozen-thawed donkey semen.Results： After submitting post-thaw semen samples to no centrifugation（UDC）, sperm washing（SW） or single layer centrifugation（SLC） protocols, sD F values after 6 h of incubation were significantly lower in SLC samples than in SW or UDC.Coefficient of determination（R-2） values were significantly higher for a second order polynomial model than for linear or exponential. The highest values for acceleration of fragmentation（aSDF） were obtained for SW, fol owed by SLC and UDC.Conclusion： SLC after thawing seems to preserve longer DNA longevity in comparison to UDC and SW. Moreover,the fine-tuning of models has shown that sDF dynamics in frozen-thawed donkey semen fit a second order polynomial model, which implies that fragmentation rate is not constant and fragmentation acceleration must be taken into account to elucidate hidden damage in the DNA molecule.
基金supported by the National Natural Science Foundation of China(NSFC)under Grant(No.51677058).
文摘Precisely estimating the state of health(SOH)of lithium-ion batteries is essential for battery management systems(BMS),as it plays a key role in ensuring the safe and reliable operation of battery systems.However,current SOH estimation methods often overlook the valuable temperature information that can effectively characterize battery aging during capacity degradation.Additionally,the Elman neural network,which is commonly employed for SOH estimation,exhibits several drawbacks,including slow training speed,a tendency to become trapped in local minima,and the initialization of weights and thresholds using pseudo-random numbers,leading to unstable model performance.To address these issues,this study addresses the challenge of precise and effective SOH detection by proposing a method for estimating the SOH of lithium-ion batteries based on differential thermal voltammetry(DTV)and an SSA-Elman neural network.Firstly,two health features(HFs)considering temperature factors and battery voltage are extracted fromthe differential thermal voltammetry curves and incremental capacity curves.Next,the Sparrow Search Algorithm(SSA)is employed to optimize the initial weights and thresholds of the Elman neural network,forming the SSA-Elman neural network model.To validate the performance,various neural networks,including the proposed SSA-Elman network,are tested using the Oxford battery aging dataset.The experimental results demonstrate that the method developed in this study achieves superior accuracy and robustness,with a mean absolute error(MAE)of less than 0.9%and a rootmean square error(RMSE)below 1.4%.
