Enhancing Fire Detection Performance Based on Fine-Tuned YOLOv10

In recent years,early detection and warning of fires have posed a significant challenge to environmental protection and human safety.Deep learning models such as Faster R-CNN(Faster Region based Convolutional Neural Network),YOLO(You Only Look Once),and their variants have demonstrated superiority in quickly detecting objects from images and videos,creating new opportunities to enhance automatic and efficient fire detection.The YOLO model,especially newer versions like YOLOv10,stands out for its fast processing capability,making it suitable for low-latency applications.However,when applied to real-world datasets,the accuracy of fire prediction is still not high.This study improves the accuracy of YOLOv10 for real-time applications through model fine-tuning techniques and data augmentation.The core work of the research involves creating a diverse fire image dataset specifically suited for fire detection applications in buildings and factories,freezing the initial layers of the model to retain general features learned from the dataset by applying the Squeeze and Excitation attention mechanism and employing the Stochastic Gradient Descent(SGD)with a momentum optimization algorithm to enhance accuracy while ensuring real-time fire detection.Experimental results demonstrate the effectiveness of the proposed fire prediction approach,where the YOLOv10 small model exhibits the best balance compared to other YOLO family models such as nano,medium,and balanced.Additionally,the study provides an experimental evaluation to highlight the effectiveness of model fine-tuning compared to the YOLOv10 baseline,YOLOv8 and Faster R-CNN based on two criteria:accuracy and prediction time.

Classification of Conversational Sentences Using an Ensemble Pre-Trained Language Model with the Fine-Tuned Parameter

Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.

基于Fine-tune与DDC的变工况数控设备部件故障诊断

针对复杂工业环境下的数控设备部件故障诊断数据样本少、变工况诊断困难和准确率不高等问题,提出一种基于模型迁移的故障诊断方法。利用连续小波变换对不同工况下的原始振动数据进行预处理,建立二维时频数据集,并分为源域与目标域;利用源域数据集与CNN进行模型预训练;分别引入微调(Fine-tune)与深度域混淆(DDC)2种迁移学习方式改进模型;最终实现了基于Fine-tune与基于DDC的故障诊断模型的构建。以轴承与数控铣刀2种部件为例进行实验验证,结果证明:Fine-tune与DDC均可以有效提高数控设备部件的故障诊断准确率,其中Fine-tune的泛化能力强,而DDC训练耗时更短且在复杂环境下的性能更优。

Comparing Fine-Tuning, Zero and Few-Shot Strategies with Large Language Models in Hate Speech Detection in English

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.

Fine-tuning electronic structure of N-doped graphitic carbon-supported Co-and Fe-incorporated Mo_(2)C to achieve ultrahigh electrochemical water oxidation activity

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.

Optimizing Enterprise Conversational AI: Accelerating Response Accuracy with Custom Dataset Fine-Tuning

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.

深度卷积神经网络嵌套fine-tune的图像美感品质评价

针对使用卷积神经网络对图像美感品质研究中图像数据库过小的问题,使用fine-tune的迁移学习方法,分析卷积神经网络结构和图像内容对图像美感品质评价的影响。在按图像内容进行美感品质评价研究时,针对图像数据再次减小的问题,提出连续两次fine-tune的嵌套fine-tune方法,并在数据库Photo Quality上进行试验。试验结果表明,嵌套fine-tune方法得到的美感品质评价正确率比传统提取人工设计特征方法平均高出5.36%,比两种深度学习方法分别平均高出3.35%和2.33%,有效解决了卷积神经网络在图像美感品质研究中因图像数据库过小而带来的训练问题。

Toward fine-tuned metabolic networks in industrial microorganisms

There are numerous microorganisms in nature capable of synthesizing diverse useful compounds;however,these natural microorganisms are generally inefficient in the production of target products on an industrial scale,relative to either chemical synthesis or extraction methods.To achieve industrial production of useful compounds,these natural microorganisms must undergo a certain degree of mutation or effective fine-tuning strategies.This review describes how to achieve an ideal metabolic fine-tuned process,including static control strategies and dynamic control strategies.The static control strategies mainly focus on various matabolic engineering strategies,including protein engineering,upregulation/downregulation,and combinatrorial control of these metabolic engineering strategies,to enhance the flexibility of their application in fine-tuned metabolic metworks.Then,we focus on the dynamic control strategies for fine-tuned metabolic metworks.The design principles derived would guide us to construct microbial cell factories for various useful compounds.

基于模型微调的空中无人机小样本目标识别方法

空中无人机目标识别是现代军事、航空领域的迫切需求,由于目前无人机的功能和种类繁多,对于新机型很难采集大量的无人机样本用于训练目标识别模型;针对该问题,提出了一种基于模型微调的空中无人机小样本目标识别方法;方法以Faster R-CNN为基础架构,首先采用具有大量标记样本的常见机型数据预训练Faster R-CNN模型;然后将基础架构最后的分类层替换为余弦度量,构建联合新机型与常见机型的小样本平衡数据集以较小的学习率微调分类层;实验结果表明,在标记样本数量为5、10和50的情况下,基于模型微调的小样本目标识别模型的mAP分别为88.6%,89.2%和90.8%,能够满足空中无人机小样本目标识别任务需求,且优于其它小样本目标识别方法。

基于微调原型网络的小样本敏感信息识别方法

敏感信息识别主要是指识别互联网上涉及色情、毒品、邪教、暴力等类型的敏感信息,现有的敏感信息识别通常将其看作文本分类任务,但由于缺乏大规模的敏感信息标注数据,分类效果不佳。该文提出一种基于微调原型网络的小样本敏感信息识别方法,在小样本学习框架下,利用快速适应的微调原型网络来缓解元训练阶段通用新闻领域和元测试阶段敏感信息数据差异大的问题。首先,在元训练阶段,基于通用新闻领域的分类数据训练模型来学习通用知识,同时在训练过程中经过两阶段梯度更新,得到一组对新任务敏感的快速适应初始参数,然后在元测试阶段敏感文本数据集的新任务上,冻结模型部分参数并使用支持集进一步微调,使模型更好地泛化到敏感识别领域上。实验结果证明,相比当前最优的小样本分类模型,该文提出的快速适应微调策略的原型网络显著提升了敏感信息识别效果。

面向自动驾驶的大模型对齐技术:综述

随着Transformer注意力机制的出现,以GPT为代表的通用基础大模型实现了智能的“涌现”,给自动驾驶迈向更高级别发展带来了曙光。受限于传统从头预训练方式需要大规模、高质量、多样性自动驾驶数据和高昂训练成本的困扰“,大模型+对齐技术”范式衍生。对齐技术作为通用基础大模型与自动驾驶之间的纽带,通过微调或提示工程等定制化方式,可高效、专业地解决自动驾驶领域内的工程性问题。对齐技术已是大模型在垂直领域发展的研究热点,但缺乏系统研究成果。基于此,本文首先对自动驾驶发展与大模型技术进行概述,从而衍生出对齐技术。然后,分别从微调和提示工程两个角度进行综述,系统化梳理并剖析各分类技术的结构或性能特点,同时给出实际的应用案例。最后,基于现有研究提出了对齐技术的研究挑战与发展趋势,为促进自动驾驶迈向更高级别发展提供参考。

基于域间Mixup微调策略的跨被试运动想象脑电信号分类算法

为了缓解传统微调算法的灾难性遗忘问题,本文提出了一种基于域间Mixup微调策略的跨被试运动想象脑电信号分类算法Mix-Tuning。Mix-Tuning通过预训练、微调的二阶段训练方式,实现跨领域知识迁移。预训练阶段,Mix-Tuning使用源域数据初始化模型参数,挖掘源域数据潜在信息。微调阶段,Mix-Tuning通过域间Mixup,生成域间插值数据微调模型参数。域间Mixup数据增强策略引入源域数据潜在信息,缓解传统微调算法在样本稀疏场景下的灾难性遗忘问题,提高模型的泛化性能。Mix-Tuning被进一步应用于运动想象脑电信号分类任务,实现了跨被试正向知识迁移。Mix-Tuning在BMI数据集的运动想象任务达到了85.50%的平均分类准确率,相较于被试–依赖和被试–独立训练方式的预测准确率58.72%和84.01%,分别提高26.78%和1.49%。本文分析结果可为跨被试运动想象脑电信号分类算法提供参考。

自动飞行员复诵指令生成方法研究

为了提高效率,降低培训成本并推广使用计算机来取代管制模拟机中的飞行员席位,采用集成学习的策略来生成飞行员复诵指令。选用5个大规模预训练语言模型进行微调,并使用K折交叉验证来筛选出性能较好的4个模型作为基础模型来构建集成学习模型。所构建的集成学习模型在管制指令数据集上取得在本领域中的最优效果。在通用的ROUGE(recall-oriented understudy for gisting evaluation)评价标准中,取得R_(OUGE-1)=0.998,R_(OUGE-2)=0.995,R_(OUGE-L)=0.998的最新效果。其中,R_(OUGE-1)关注参考文本与生成文本之间单个单词的匹配度,R_(OUGE-2)则关注两个连续单词的匹配度,R_(OUGE-L)则关注最长公共子序列的匹配度。为了克服通用指标在本领域的局限性,更准确地评估模型性能,针对生成的复诵指令提出一套基于关键词的评价标准。该评价指标准基于管制文本分词后的结果计算各个关键词指标来评估模型的效果。在基于关键词的评价标准下,所构建模型取得整体准确率为0.987的最优效果,对航空器呼号的复诵准确率达到0.998。

以对比学习与时序递推提升摘要泛化性的方法

为了有效缓解基于交叉熵损失函数训练的传统文本摘要模型所面临的推理过程中性能下降、泛化性较低、生成过程中曝光偏差现象严重、生成的摘要与参考摘要文本相似度较低等问题,提出了一种新颖的训练方式,一方面,模型本身以beamsearch的方式生成候选集,以候选摘要的评估分数选取正负样本,在输出的候选集中以“argmax-贪心搜索概率值”和“标签概率值”构建2组对比损失函数;另一方面,设计作用于候选集句内的时序递推函数引导模型在输出每个单独的候选摘要时确保时序准确性,并缓解曝光偏差问题。实验表明,所提方法在CNN/DailyMail和Xsum公共数据集上的泛化性得到提升,Rouge与BertScore在CNN/DailyMail上达到47.54和88.51,在Xsum上达到了48.75和92.61。

融合大模型与图神经网络的电力设备缺陷诊断

电力系统中不同装置设备的缺陷评级和分析处理常受运维人员主观性影响,导致同一缺陷文本描述出现不同的严重程度评级。专业知识的差异也导致诊断分析差异和诊断效率不同。为提升缺陷诊断的准确性和效率,提出一种基于图神经网络的缺陷文本评级分类方法和大模型智能诊断分析助手。构建专业词典,使用自然语言处理算法规范化文本描述。通过统计方法,优化缺陷文本的语义表示。集成图注意力神经网络和RoBERTa模型对缺陷文本进行精确评级分类。基于大语言模型Qwen1.5-14B-Chat进行低秩适配(LoRA)微调训练得到电力设备诊断大模型Qwen-ElecDiag,结合检索增强生成技术开发设备缺陷诊断助手。此外,整理提供微调电力设备诊断大模型的指令数据集。对比实验结果表明,提出的基于图神经网络的缺陷评级分类方法在准确性上较最优基准模型BERT提升近8个百分点;诊断助手的电力知识以及缺陷诊断能力得到提升。通过提高缺陷评级的准确率并提供全面专业化诊断建议,不仅提高电力设备运维的智能化水平,也为其他垂直领域的智能运维提供新的解决方案。

迁移学习在机械设备故障诊断领域的进展研究

迁移学习是一种新兴的机器学习方法,通过运用已学习的知识对不同但相关领域问题进行求解,能够较为有效的解决模型泛化能力弱、样本数据不足等问题。针对迁移学习在机械设备故障诊断领域的应用方法进行了综述,总结了三类关于迁移学习的诊断预测方法,并对迁移学习在故障诊断领域的未来研究方向进行了探讨。

基于样本增量学习的遥感影像分类

深度学习模型在遥感影像分类中取得了显著的成绩。随着新的遥感数据不断被采集,基于深度学习的遥感影像分类模型在训练新数据、学习新知识时,对旧数据的识别性能会下降,即旧知识遗忘。为帮助遥感影像分类模型巩固旧知识和学习新知识,提出一种基于样本增量学习的遥感影像分类模型——增量协同学习知识模型(ICLKM)。该模型由两个知识网络组成,第一个网络通过知识蒸馏保留旧模型的输出,缓解知识遗忘问题;第二个网络将新数据的输出作为第一个网络的学习目标,通过维护双网络模型的一致性有效地学习新知识。最后两个网络共同学习,通过知识协同策略生成更精确的模型。在两个遥感数据集NWPU-RESISC45和AID上的实验结果表明,相较于微调训练(FT)方法,ICLKM的准确率分别提升了3.53和6.70个百分点。可见ICLKM能够有效解决遥感影像分类的知识遗忘问题,不断提高对已知遥感影像的识别准确率。

油气行业人工智能大模型应用研究现状及展望

阐述了大模型技术的概念,总结了大模型技术的国内外研究现状,综述了大模型在垂直领域的应用现状,梳理了油气行业大模型应用面临的挑战,并对油气行业大模型应用进行了展望。现有大模型可粗略分为3类,即大语言模型、视觉大模型和多模态大模型。油气行业大模型应用刚刚起步,部分油气企业基于开源大语言模型,利用微调、检索增强等方式发布大语言模型产品,部分学者尝试利用视觉/多模态基础模型研发面向油气业务的场景模型,还有少数学者构建地震资料处理解释、岩心分析等领域的预训练基础模型。油气行业大模型应用面临数据量和数据质量难以支撑大模型训练、研发投入成本高、难以实现算法自主可控等挑战。油气行业在应用大模型时应始终聚焦油气主营业务需求,以大模型应用为契机,加强数据全生命周期管理,提升数据治理能力,推动融合算力建设,加强“人工智能+能源”复合团队建设,推动大模型技术自主可控。

深度神经网络修复策略综述

随着智能信息时代的发展,深度神经网络在人类社会众多领域中的应用,尤其是在自动驾驶、军事国防等安全攸关系统中的部署,引起了学术界和工业界对神经网络模型可能表现出的错误行为的担忧.虽然神经网络验证和神经网络测试可以提供关于错误行为的定性或者定量结论,但这种事后分析并不能防止错误行为的发生,如何修复表现出错误行为的预训练神经网络模型依然是极具挑战性的问题.为此,深度神经网络修复这一领域应运而生,旨在消除有缺陷的神经网络产生的错误预测,使得神经网络满足特定的规约性质.目前为止,典型的神经网络修复范式有3种:重训练、无错误定位的微调和包含错误定位的微调.介绍深度神经网络的发展和神经网络修复的必要性;厘清相近概念;明确神经网络修复的挑战;详尽地调研目前已有的神经网络修复策略,并对内在联系与区别进行分析和比较;调研整理神经网络修复策略常用的评价指标和基准测试;展望未来神经网络修复领域研究中需要重点关注的可行方向.

波长可调的量子点纠缠光源(特邀)

可按需产生纠缠光子对的量子光源是光量子网络中的重要组成部分。半导体量子点可确定性地产生高纠缠保真度的光子对。基于量子点构建量子网络所需的量子中继单元时,需要多个发光波长一致的高质量纠缠光源。然而量子点形貌、组分和应力的不均一性严重限制了基于量子点的量子中继器的可扩展性。国内外研究团队发展了多种量子点生长后调节技术,成功调节量子点精细结构劈裂并通过联合多个调节自由度实现多维度的调节。本文综述了目前联合多个调节自由度实现发光波长和精细结构劈裂均能调控的实验方案,总结了不同方案的调节方法和研究现状,并介绍了将量子点与光学微腔相结合通过Purcell效应能进一步提升纠缠光源的性能。最后,对该领域的未来发展进行展望。