Support Vector Machine active learning for 3D model retrieval

In this paper, we present a novel Support Vector Machine active learning algorithm for effective 3D model retrieval using the concept of relevance feedback. The proposed method learns from the most informative objects which are marked by the user, and then creates a boundary separating the relevant models from irrelevant ones. What it needs is only a small number of 3D models labelled by the user. It can grasp the user＇s semantic knowledge rapidly and accurately. Experimental results showed that the proposed algorithm significantly improves the retrieval effectiveness. Compared with four state-of-the-art query refinement schemes for 3D model retrieval, it provides superior retrieval performance after no more than two rounds of relevance feedback.

A Stable and Energy-Efficient Routing Algorithm Based on Learning Automata Theory for MANET

The mobile Ad Hoc network(MANET)is a self-organizing and self-configuring wireless network,consisting of a set of mobile nodes.The design of efficient routing protocols for MANET has always been an active area of research.In existing routing algorithms,however,the current work does not scale well enough to ensure route stability when the mobility and distribution of nodes vary with time.In addition,each node in MANET has only limited initial energy,so energy conservation and balance must be taken into account.An efficient routing algorithm should not only be stable but also energy saving and balanced,within the dynamic network environment.To address the above problems,we propose a stable and energy-efficient routing algorithm,based on learning automata(LA)theory for MANET.First,we construct a new node stability measurement model and define an effective energy ratio function.On that basis,we give the node a weighted value,which is used as the iteration parameter for LA.Next,we construct an LA theory-based feedback mechanism for the MANET environment to optimize the selection of available routes and to prove the convergence of our algorithm.The experiments show that our proposed LA-based routing algorithm for MANET achieved the best performance in route survival time,energy consumption,energy balance,and acceptable per-formance in end-to-end delay and packet delivery ratio.

A Railway Fastener Inspection Method Based on Abnormal Sample Generation

Regular fastener detection is necessary to ensure the safety of railways.However,the number of abnormal fasteners is significantly lower than the number of normal fasteners in real railways.Existing supervised inspectionmethods have insufficient detection ability in cases of imbalanced samples.To solve this problem,we propose an approach based on deep convolutional neural networks(DCNNs),which consists of three stages:fastener localization,abnormal fastener sample generation based on saliency detection,and fastener state inspection.First,a lightweight YOLOv5s is designed to achieve fast and precise localization of fastener regions.Then,the foreground clip region of a fastener image is extracted by the designed fastener saliency detection network(F-SDNet),combined with data augmentation to generate a large number of abnormal fastener samples and balance the number of abnormal and normal samples.Finally,a fastener inspection model called Fastener ResNet-8 is constructed by being trained with the augmented fastener dataset.Results show the effectiveness of our proposed method in solving the problem of sample imbalance in fastener detection.Qualitative and quantitative comparisons show that the proposed F-SDNet outperforms other state-of-the-art methods in clip region extraction,reaching MAE and max F-measure of 0.0215 and 0.9635,respectively.In addition,the FPS of the fastener state inspection model reached 86.2,and the average accuracy reached 98.7%on 614 augmented fastener test sets and 99.9%on 7505 real fastener datasets.

Hyperparameter Optimization Based Deep Belief Network for Clean Buses Using Solar Energy Model

Renewable energy has become a solution to the world’s energy concerns in recent years.Photovoltaic(PV)technology is the fastest technique to convert solar radiation into electricity.Solar-powered buses,metros,and cars use PV technology.Such technologies are always evolving.Included in the parameters that need to be analysed and examined include PV capabilities,vehicle power requirements,utility patterns,acceleration and deceleration rates,and storage module type and capacity,among others.PVPG is intermit-tent and weather-dependent.Accurate forecasting and modelling of PV sys-tem output power are key to managing storage,delivery,and smart grids.With unparalleled data granularity,a data-driven system could better anticipate solar generation.Deep learning(DL)models have gained popularity due to their capacity to handle complex datasets and increase computing power.This article introduces the Galactic Swarm Optimization with Deep Belief Network(GSODBN-PPGF)model.The GSODBN-PPGF model predicts PV power production.The GSODBN-PPGF model normalises data using data scaling.DBN is used to forecast PV power output.The GSO algorithm boosts the DBN model’s predicted output.GSODBN-PPGF projected 0.002 after 40 h but observed 0.063.The GSODBN-PPGF model validation is compared to existing approaches.Simulations showed that the GSODBN-PPGF model outperformed recent techniques.It shows that the proposed model is better at forecasting than other models and can be used to predict the PV power output for the next day.

Impact of Artificial Intelligence on Corporate Leadership

Artificial Intelligence (AI) is transforming organizational dynamics, and revolutionizing corporate leadership practices. This research paper delves into the question of how AI influences corporate leadership, examining both its advantages and disadvantages. Positive impacts of AI are evident in communication, feedback systems, tracking mechanisms, and decision-making processes within organizations. AI-powered communication tools, as exemplified by Slack, facilitate seamless collaboration, transcending geographical barriers. Feedback systems, like Adobe’s Performance Management System, employ AI algorithms to provide personalized development opportunities, enhancing employee growth. AI-based tracking systems optimize resource allocation, as exemplified by studies like “AI-Based Tracking Systems: Enhancing Efficiency and Accountability.” Additionally, AI-powered decision support, demonstrated during the COVID-19 pandemic, showcases the capability to navigate complex challenges and maintain resilience. However, AI adoption poses challenges in human resources, potentially leading to job displacement and necessitating upskilling efforts. Managing AI errors becomes crucial, as illustrated by instances like Amazon’s biased recruiting tool. Data privacy concerns also arise, emphasizing the need for robust security measures. The proposed solution suggests leveraging Local Machine Learning Models (LLMs) to address data privacy issues. Approaches such as federated learning, on-device learning, differential privacy, and homomorphic encryption offer promising strategies. By exploring the evolving dynamics of AI and leadership, this research advocates for responsible AI adoption and proposes LLMs as a potential solution, fostering a balanced integration of AI benefits while mitigating associated risks in corporate settings.

智能遥感大模型研究进展与发展方向

AI大模型以其泛化性、通用性、高精度等优势,成为计算机视觉、自然语言处理等AI应用的基石,本文在分析AI大模型发展历程、价值、挑战的基础上,首先从数据、模型、下游任务3个层面阐述了其研究进展,数据层面从单模态向多模态发展,模型层面从小模型向大模型发展,下游任务层面从单任务向多任务发展;其次,探讨了遥感大模型3个重点发展方向,即多模态遥感大模型、可解释遥感大模型、人类反馈强化学习;再次,实现了“无标签数据集构建-自监督模型学习-下游迁移应用”遥感大模型构建思路,初步开展了技术试验,验证了遥感大模型的显著优势;最后,进行了总结与展望,呼吁以应用任务为导向,将理论方法、工程技术、应用迭代进行结合,实现遥感大模型的低成本训练、高效快速推理、轻量化部署及工程化落地应用。

A hierarchical enhanced data-driven battery pack capacity estimation framework for real-world operating conditions with fewer labeled data

Battery pack capacity estimation under real-world operating conditions is important for battery performance optimization and health management,contributing to the reliability and longevity of batterypowered systems.However,complex operating conditions,coupling cell-to-cell inconsistency,and limited labeled data pose great challenges to accurate and robust battery pack capacity estimation.To address these issues,this paper proposes a hierarchical data-driven framework aimed at enhancing the training of machine learning models with fewer labeled data.Unlike traditional data-driven methods that lack interpretability,the hierarchical data-driven framework unveils the“mechanism”of the black box inside the data-driven framework by splitting the final estimation target into cell-level and pack-level intermediate targets.A generalized feature matrix is devised without requiring all cell voltages,significantly reducing the computational cost and memory resources.The generated intermediate target labels and the corresponding features are hierarchically employed to enhance the training of two machine learning models,effectively alleviating the difficulty of learning the relationship from all features due to fewer labeled data and addressing the dilemma of requiring extensive labeled data for accurate estimation.Using only 10%of degradation data,the proposed framework outperforms the state-of-the-art battery pack capacity estimation methods,achieving mean absolute percentage errors of 0.608%,0.601%,and 1.128%for three battery packs whose degradation load profiles represent real-world operating conditions.Its high accuracy,adaptability,and robustness indicate the potential in different application scenarios,which is promising for reducing laborious and expensive aging experiments at the pack level and facilitating the development of battery technology.

A generalized deep neural network approach for improving resolution of fluorescence microscopy images

Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed,imaging resolution,and imagingflux.This paper proposes a deep neural network based on a generative adversarial network(GAN).The generator employs a U-Net-based network,which integrates Dense Net for the downsampling component.The proposed method has excellent properties,for example,the network model is trained with several different datasets of biological structures;the trained model can improve the imaging resolution of different microscopy imaging modalities such as confocal imaging and wide-field imaging;and the model demonstrates a generalized ability to improve the resolution of different biological structures even out of the datasets.In addition,experimental results showed that the method improved the resolution of caveolin-coated pits(CCPs)structures from 264 nm to 138 nm,a 1.91-fold increase,and nearly doubled the resolution of DNA molecules imaged while being transported through microfluidic channels.

基于建构性反馈的双循环对分课堂教学模式研究

随着教育数字化转型的推进,混合学习因能够结合线上线下教学优势、提供更灵活多样的学习体验、适应数字化转型的需求而受到高校课堂的青睐。然而,对于人数较多的通识课程或专业必修课程,大班式在线教学中容易出现师生和生生互动缺乏、学生社会存在感低、学习效果不佳等问题。为此,本研究提出了基于建构性反馈的双循环对分课堂教学模式,核心理念是在泛在学习环境与信息化工具的支撑下,以学习支架为引导,完成两轮相互迭代的循环:学生主体建构循环与师生生成性建构循环,最终指向以建构性反馈为基础的“教、学、评”一致性设计。针对该模式,本研究对华南地区某大学全校性公共必修课“现代教育技术”的165位本科二年级学生开展了为期16周的教学实验,结果表明,该教学模式对提高学生的社会存在感、学习动机和学习成绩具有积极的作用,可为教育数字化转型背景下开展混合学习提供参考。

大语言模型领域意图的精准性增强方法

目前通用大语言模型(如GPT)在专业领域问答应用中存在不稳定性和不真实性。针对这一现象,提出了一种在通用大语言模型上耦合领域知识的意图识别精准性增强方法(EIRDK),其中引入了三个具体策略:a)通过领域知识库对GPT输出结果进行打分过滤;b)训练领域知识词向量模型优化提示语句规范性;c)利用GPT的反馈结果提升领域词向量模型和GPT模型的一致性。实验分析显示,相比于标准的GPT模型,新方法在私有数据集上可以提升25%的意图理解准确性,在CMID数据集上可以提升12%的意图理解准确性。实验结果证明了EIRDK方法的有效性。

基于示教学习和视线跟踪的机器人遥操作系统设计

针对传统的机器人遥操作系统缺乏对任务的认知和操作者主观性判断的问题,课题组提出了一种基于示教学习与视线追踪的遥操作系统设计策略。首先运用高斯混合模型(Gaussian mixture model,GMM)和高斯混合回归(Gaussian mixture regression,GMR)对机器人的技能进行学习,实现人机技能转移;然后基于示教学习设计了一种人工势场法的虚拟夹具(virtual fixtures,VF),并设计了力反馈算法;最后使用网络摄像头对操作者的视觉意图进行判别,将意图识别结果和人工势场法应用于虚拟夹具力反馈算法中,并进行实验。研究结果表明:基于视觉意图判别的虚拟夹具力反馈遥操作系统能够对操作者的意图进行判别,有效解决了操作者的主观意图受传统虚拟夹具产生的反馈力限制的问题,增强了操作者在遥操作过程中的主观性,是遥操作控制系统中一种有效且实用的力反馈控制方案。研究结果可为高危场景下具有力觉临场感的机器人遥操作系统的实际应用提供参考。

CT-NET: A Novel Convolutional Transformer-Based Network for Short-Term Solar Energy Forecasting Using Climatic Information

Photovoltaic(PV)systems are environmentally friendly,generate green energy,and receive support from policies and organizations.However,weather fluctuations make large-scale PV power integration and management challenging despite the economic benefits.Existing PV forecasting techniques(sequential and convolutional neural networks(CNN))are sensitive to environmental conditions,reducing energy distribution system performance.To handle these issues,this article proposes an efficient,weather-resilient convolutional-transformer-based network(CT-NET)for accurate and efficient PV power forecasting.The network consists of three main modules.First,the acquired PV generation data are forwarded to the pre-processing module for data refinement.Next,to carry out data encoding,a CNNbased multi-head attention(MHA)module is developed in which a single MHA is used to decode the encoded data.The encoder module is mainly composed of 1D convolutional and MHA layers,which extract local as well as contextual features,while the decoder part includes MHA and feedforward layers to generate the final prediction.Finally,the performance of the proposed network is evaluated using standard error metrics,including the mean squared error(MSE),root mean squared error(RMSE),and mean absolute percentage error(MAPE).An ablation study and comparative analysis with several competitive state-of-the-art approaches revealed a lower error rate in terms of MSE(0.0471),RMSE(0.2167),and MAPE(0.6135)over publicly available benchmark data.In addition,it is demonstrated that our proposed model is less complex,with the lowest number of parameters(0.0135 M),size(0.106 MB),and inference time(2 ms/step),suggesting that it is easy to integrate into the smart grid.

一个智能用户接口Agent设计与实现

文章主要介绍了DOLTRI－Agent（distanceandopenlearningtrainingresourceinformationretrievalagent）系统中的用户接口Agent（NanDauserinterfaceagent，简称NDUIA）的设计和实现的关键技术．此系统扩展了memory－basedreasoning技术，采用了多个记忆模型和多个分析模型，通过对不同用户使用经验的分析，产生该用户专用的用户兴趣模型；同时，根据用户兴趣模型和特定场景的使用经验共同作用来提供主动的智能服务，包括信息导引、搜索结果的预处理、智能即时帮助和分类信息的修改等，从而实现软件与人的协作．

Channelmeasurements and models for 6G:current status and future outlook

With the commercialization of fifth generation networks worldwide,research into sixth generation(6G)networks has been launched to meet the demands for high data rates and low latency for future services.A wireless propagation channel is the transmission medium to transfer information between the transmitter and the receiver.Moreover,channel properties determine the ultimate performance limit of wireless communication systems.Thus,conducting channel research is a prerequisite to designing 6G wireless communication systems.In this paper,we first introduce several emerging technologies and applications for 6G,such as terahertz communication,industrial Internet of Things,space-air-ground integrated network,and machine learning,and point out the developing trends of 6G channel models.Then,we give a review of channel measurements and models for the technologies and applications.Finally,the outlook for 6G channel measurements and models is discussed.

网络教学资源库反馈系统模型构建与应用研究

大学生作为网络学习的主体,在访问网络教学资源库期间的学习行为被采集分析,利用分析结果制定学习流程和优化资源库内容,并最终经过评价分析模块反馈至网络资源库和网络教学中,这就构成了网络教学资源库反馈系统。该系统可以有效地控制学习进程,形成高质量的学习活动,为网络学习平台的建设以及网络学习资源的开发提供了依据。

基于MOOC的“数据库原理与应用”混合式教学改革与实践

MOOC是由远程教育发展起来的一种在线课堂教学模式,基于MOOC的混合式教学改革成为教学研究的热点之一。文章分析了"数据库原理与应用"课程教学中存在的问题,构建了一种基于MOOC的混合式教学改革思路,并在教学实践中选择不同专业的两个班级进行了阶段性实践检验。还探讨了教学实践中应注意的问题。教学实践表明,混合式教学模式是传统教学模式的有益补充,对于教学质量的改善具有积极的促进作用。

反馈对知觉类别学习的影响及其认知神经生理机制

知觉类别学习是一种人类对知觉刺激进行分类、习得类别的过程,反馈是进行知觉类别学习不可或缺的重要部分。研究者通过操纵反馈的不同特征,如反馈延迟(即时、延迟)、反馈性质(积极、消极)、反馈类型(丰富、简单)等,对反馈如何影响知觉类别学习进行了广泛的研究,并试图从神经生理学方面给出合理的解释。但是目前反馈对知觉类别学习影响的研究还存在许多不足,特别在反馈延迟时间的细化、延迟反馈时间临界点、无关因素掩蔽、反馈试次等影响方面的研究较少涉及,现有的反馈机制尚需进一步研究。

基于隐式反馈的个人信息检索技术及实现

回顾了已有的相关反馈技术，在此基础上提出了构造和调整用户兴趣模型的隐式反馈算法，给出了一个基于隐式反馈的InfoAgent的设计实现和实验结果。实验表明隐式反馈技术对提高检索精度有很大的帮助。

基于深度神经网络的嵌入式向量及话题模型

在对文档集合进行话题分析的过程中,为描述文档中单词间的依赖关系,提高话题分析的效果,提出一种基于反馈递归神经网络的嵌入式向量生成及话题模型。在将单词表示为One-hot向量后,采用递归神经网络将文档嵌入在低维的向量空间。在文档的嵌入式向量计算过程中,采用LSTM(long short-term memory)描述单词间的前向依赖关系,提出一种反馈神经网络用于描述单词间的后向依赖关系。在话题分析模型中,采用原文档和变异文档对作为正样本,采用原文档和随机文档对作为负样本进行模型的训练。实验结果表明,该方法时间和空间复杂度低,具有更好的话题分析效果。

基于无穷跳-扩散双因子交叉回馈模型的期权定价

为研究股市无穷跳跃和连续扩散行为特征,提出了一类能够捕捉无穷跳和扩散之间交互影响的动态跳-扩散双因子交叉回馈模型.借助Lévy过程条件特征函数、局部风险中性关系和贝叶斯学习技术,给出了动态跳-扩散随机过程的期权定价方法,并进行标准普尔500指数欧式期权标准化合约的实证研究,对比了有限跳-扩散及无穷跳-扩散模型定价差异.研究结果表明:以VG为基础的无穷跳-扩散全面优于Merton的有限跳-扩散双因子模型;跳-扩散交又回馈模型具有最小的期权定价误差;跳跃行为相比扩散波动具有更高的持续性、更强的杠杆作用和更高的风险市场价格.