Intelligent Risk-Identification Algorithm with Vision and 3D LiDAR Patterns at Damaged Buildings

Existingfirefighting robots are focused on simple storage orfire sup-pression outside buildings rather than detection or recognition.Utilizing a large number of robots using expensive equipment is challenging.This study aims to increase the efficiency of search and rescue operations and the safety offirefigh-ters by detecting and identifying the disaster site by recognizing collapsed areas,obstacles,and rescuers on-site.A fusion algorithm combining a camera and three-dimension light detection and ranging(3D LiDAR)is proposed to detect and loca-lize the interiors of disaster sites.The algorithm detects obstacles by analyzingfloor segmentation and edge patterns using a mask regional convolutional neural network(mask R-CNN)features model based on the visual data collected from a parallelly connected camera and 3D LiDAR.People as objects are detected using you only look once version 4(YOLOv4)in the image data to localize persons requiring rescue.The point cloud data based on 3D LiDAR cluster the objects using the density-based spatial clustering of applications with noise(DBSCAN)clustering algorithm and estimate the distance to the actual object using the center point of the clustering result.The proposed artificial intelligence(AI)algorithm was verified based on individual sensors using a sensor-mounted robot in an actual building to detectfloor surfaces,atypical obstacles,and persons requiring rescue.Accordingly,the fused AI algorithm was comparatively verified.

Identification of Mulberry Bacterial Blight Caused by Klebsiella oxytoca in Bazhong,Sichuan,China

To provide a scientific basis for controlling mulberry bacterial blight in Bazhong,Sichuan,China(BSC),this study aimed to isolate and purify pathogenic bacteria from diseased branches of mulberry trees in the region and to clarify their taxonomic status using morphological observation,physiological and biochemical detection,molecular-level identification,and the construction of a phylogenetic tree.A total of 218 bacterial strains were isolated from samples of diseased mulberry branches.Of these,7 strains were identified as pathogenic bacteria based on pathogenicity tests conducted in accordance with Koch’s postulates.Preliminary findings from the analysis of the 16S rRNA sequence indicated that the 7 pathogenic bacteria are members of Klebsiella spp.Morphological observation revealed that the pathogenic bacteria were oval-shaped and had capsules but no spores.They could secrete pectinase,cellulase,and protease and were able to utilize D-glucose,D-mannose,D-maltose,and D-Cellobiose.The 7 strains of pathogenic bacteria exhibited the highest homology with Klebsiella oxytoca.This study identifies Klebsiella oxytoca as the causative agent of mulberry bacterial blight in BSC,laying the foundation for the prevention and control of this pathogen and further investigation into its pathogenic mechanism.

Application of Transgenic Technology in Identification for Gene Function on Grasses

Perennial grasses have developed intricate mechanisms to adapt to diverse environments,enabling their resistance to various biotic and abiotic stressors.These mechanisms arise from strong natural selection that contributes to enhancing the adaptation of forage plants to various stress conditions.Methods such as antisense RNA technology,CRISPR/Cas9 screening,virus-induced gene silencing,and transgenic technology,are commonly utilized for investigating the stress response functionalities of grass genes in both warm-season and cool-season varieties.This review focuses on the functional identification of stress-resistance genes and regulatory elements in grasses.It synthesizes recent studies on mining functional genes,regulatory genes,and protein kinase-like signaling factors involved in stress responses in grasses.Additionally,the review outlines future research directions,providing theoretical support and references for further exploration of(i)molecular mechanisms underlying grass stress responses,(ii)cultivation and domestication of herbage,(iii)development of high-yield varieties resistant to stress,and(iv)mechanisms and breeding strategies for stress resistance in grasses.

Structural Modal Parameter Recognition and Related Damage Identification Methods under Environmental Excitations: A Review

Modal parameters can accurately characterize the structural dynamic properties and assess the physical state of the structure.Therefore,it is particularly significant to identify the structural modal parameters according to the monitoring data information in the structural health monitoring(SHM)system,so as to provide a scientific basis for structural damage identification and dynamic model modification.In view of this,this paper reviews methods for identifying structural modal parameters under environmental excitation and briefly describes how to identify structural damages based on the derived modal parameters.The paper primarily introduces data-driven modal parameter recognition methods(e.g.,time-domain,frequency-domain,and time-frequency-domain methods,etc.),briefly describes damage identification methods based on the variations of modal parameters(e.g.,natural frequency,modal shapes,and curvature modal shapes,etc.)and modal validation methods(e.g.,Stability Diagram and Modal Assurance Criterion,etc.).The current status of the application of artificial intelligence(AI)methods in the direction of modal parameter recognition and damage identification is further discussed.Based on the pre-vious analysis,the main development trends of structural modal parameter recognition and damage identification methods are given to provide scientific references for the optimized design and functional upgrading of SHM systems.

Hybrid Feature Extractions and CNN for Enhanced Periocular Identification During Covid-19

The global pandemic of novel coronavirus that started in 2019 has ser-iously affected daily lives and placed everyone in a panic condition.Widespread coronavirus led to the adoption of social distancing and people avoiding unneces-sary physical contact with each other.The present situation advocates the require-ment of a contactless biometric system that could be used in future authentication systems which makesfingerprint-based person identification ineffective.Periocu-lar biometric is the solution because it does not require physical contact and is able to identify people wearing face masks.However,the periocular biometric region is a small area,and extraction of the required feature is the point of con-cern.This paper has proposed adopted multiple features and emphasis on the periocular region.In the proposed approach,combination of local binary pattern(LBP),color histogram and features in frequency domain have been used with deep learning algorithms for classification.Hence,we extract three types of fea-tures for the classification of periocular regions for biometric.The LBP represents the textual features of the iris while the color histogram represents the frequencies of pixel values in the RGB channel.In order to extract the frequency domain fea-tures,the wavelet transformation is obtained.By learning from these features,a convolutional neural network(CNN)becomes able to discriminate the features and can provide better recognition results.The proposed approach achieved the highest accuracy rates with the lowest false person identification.

Cat Swarm with Fuzzy Cognitive Maps for Automated Soil Classification

Accurate soil prediction is a vital parameter involved to decide appro-priate crop,which is commonly carried out by the farmers.Designing an auto-mated soil prediction tool helps to considerably improve the efficacy of the farmers.At the same time,fuzzy logic(FL)approaches can be used for the design of predictive models,particularly,Fuzzy Cognitive Maps(FCMs)have involved the concept of uncertainty representation and cognitive mapping.In other words,the FCM is an integration of the recurrent neural network(RNN)and FL involved in the knowledge engineering phase.In this aspect,this paper introduces effective fuzzy cognitive maps with cat swarm optimization for automated soil classifica-tion(FCMCSO-ASC)technique.The goal of the FCMCSO-ASC technique is to identify and categorize seven different types of soil.To accomplish this,the FCMCSO-ASC technique incorporates local diagonal extrema pattern(LDEP)as a feature extractor for producing a collection of feature vectors.In addition,the FCMCSO model is applied for soil classification and the weight values of the FCM model are optimally adjusted by the use of CSO algorithm.For exam-ining the enhanced soil classification outcomes of the FCMCSO-ASC technique,a series of simulations were carried out on benchmark dataset and the experimen-tal outcomes reported the enhanced performance of the FCMCSO-ASC technique over the recent techniques with maximum accuracy of 96.84%.

人工智能赋能大学治理:多重效应与治理效能转化

当人工智能与大学治理相遇后,数字化不仅成为提升大学治理能力和治理水平现代化的客观要求,还成为推进大学治理创新和制度变迁的重要途径。根据大学制度的层级结构、治理结构的复杂性程度以及治理事项的数字化程度,建构制度嵌入下人工智能技术赋能大学治理的解释模型,并借此模型着重分析人工智能技术对大学治理影响的多重效应及其治理效能转化机制/过程。研究发现,在制度嵌入和人工智能技术的共同影响下,现代大学治理随着大学制度外显性的不断加强而愈显复杂,在此渐进过程中,人工智能技术的影响力和渗透力也就愈加微弱,由此产生了人工智能技术对大学治理影响的多重效应及其治理效能的不同转化和提升机制:大学治理结构的复杂性程度越低,大学制度的层级结构越低,治理领域可数字化的程度就越高,人工智能技术对大学治理的积极效应越显著,大学具体制度得以更迭的可能性越大,也就愈容易借助“技术—制度”协同机制将中国特色现代大学的制度优势转化为治理效能;大学治理结构的复杂化程度越高,大学制度的层级结构越高,治理领域可数字化的程度越低,人工智能技术对大学治理的抑制效应越明显,其所依靠的(部分)基本制度和基础制度被替代/更迭的速度越慢,而被同化的可能性越大,也就越容易走上模仿西方大学制度建设的路径依赖。为此,一方面,要注重人工智能技术对大学治理的积极效应,充分发挥人工智能技术对于大学常规性治理、(部分)决策性治理的积极作用,通过大学具体制度和基本制度的不断健全和完善,推动现代大学制度的标准化建设和精细化发展;另一方面,要警惕人工智能技术对大学治理带来的潜在危险,充分考虑现代大学的组织特性,避免过度技术化而导致大学治理中技术应用的无限拓展和无序泛化。

多元智能视角下地方高校“实践基地+创新社团”工程教育模式探究

以霍华德·加德纳多元智能理论为理论基础,以地方应用型高校学生工程教学实践创新能力培养为目标,提出了“实践基地+创新社团”工程教育模式。在该模式下,以项目目标为驱动力,实践基地平台的实验设备、实验项目等为学生创新活动提供优良的环境和机会,在教师的组织、协调和引导下,通过创新社团的形式组织大学生以小组合作的形式进行自主创新。“实践基地+创新社团”工程教育模式是对课堂教学的一种有效补充,也是大学生自主创新和协作能力培养的有效手段。

动态不确定因果图在中医诊断中的应用探讨

动态不确定因果图(DUCG)已成为中医药领域新兴的、先进的知识表示与推理模型。为更好地应用DUCG为中医临床提供诊断推理与决策支持,在归纳总结DUCG中医药领域研究与应用情况的基础上,分析现阶段DUCG在中医诊断中存在的主要问题,包括中医术语规范统一和中医药知识库质量问题、推理算法和模型建造的方法选择与设计问题、DUCG中医诊断模型的平台化和产品化问题等,并据此展开应用思路与方法探讨,提出应深挖DUCG的技术内涵,根据临床实际需求选择精准、高效的推理建模方法,建立符合中医药理论思想、具有中医特色的智能辅助诊断模型,加强DUCG协同研究平台及产品的开发应用。

^(18)F-FDOPA PET/CT定量分析提高早期帕金森病的诊断效能

目的探讨6-^(18)F氟-L-多巴(^(18)F-FDOPA)PET/CT半定量分析及人工智能平台对帕金森病(PD)的诊断价值。资料与方法回顾性分析2018年1月—2019年12月南京医科大学附属南京医院经临床确诊的56例PD患者,其中33例早期(Hoehn-YahrⅠ~Ⅱ级),23例晚期(Hoehn-YahrⅢ~Ⅳ级);选取本院体检中心同期健康对照者27例,行^(18)F-FDOPA PET/CT。于HERMES BRASS平台计算受试者纹状体各亚区与枕叶体积计数比(SORs),完成基于感兴趣区的脑半定量分析,观察早期和晚期PD患者纹状体各亚区不对称性。使用人工智能技术对PD组和健康对照组纹状体各亚区SORs行主成分分析,观察数据聚集度和组间区分度。结果与健康对照组相比,晚期PD患者尾状体、前壳核、后壳核和纹状体整体SORs显著降低(t=9.02~11.72,P<0.0001),对应的曲线下面积分别为0.952、0.973、0.995和0.982。早期PD患者纹状体各亚区不对称指数分别为尾状核(7.61±5.50)%、前壳核(11.43±8.97)%、后壳核(17.17±11.63)%、纹状体(10.65±7.46)%。PD组和健康对照组相比,主成分分析有显著区分度,PD组纹状体^(18)F-FDOPA摄取显著降低,早期PD患者对侧后壳核损失最显著,下降百分比为34%。结论平台半定量分析^(18)F-FDOPA PET/CT图像,为PD早期诊断和鉴别诊断提供客观半定量数值,纹状体特别是壳核的不对称性可能是PD早期诊断的重要参数。

Radio frequency fingerprint identification for Internet of Things:A survey

Radio frequency fingerprint(RFF)identification is a promising technique for identifying Internet of Things(IoT)devices.This paper presents a comprehensive survey on RFF identification,which covers various aspects ranging from related definitions to details of each stage in the identification process,namely signal preprocessing,RFF feature extraction,further processing,and RFF identification.Specifically,three main steps of preprocessing are summarized,including carrier frequency offset estimation,noise elimination,and channel cancellation.Besides,three kinds of RFFs are categorized,comprising I/Q signal-based,parameter-based,and transformation-based features.Meanwhile,feature fusion and feature dimension reduction are elaborated as two main further processing methods.Furthermore,a novel framework is established from the perspective of closed set and open set problems,and the related state-of-the-art methodologies are investigated,including approaches based on traditional machine learning,deep learning,and generative models.Additionally,we highlight the challenges faced by RFF identification and point out future research trends in this field.

Exploration of transferable deep learning-aided radio frequency fingerprint identification systems

Radio frequency fingerprint identification(RFFI)shows great potential as a means for authenticating wireless devices.As RFFI can be addressed as a classification problem,deep learning techniques are widely utilized in modern RFFI systems for their outstanding performance.RFFI is suitable for securing the legacy existing Internet of Things(IoT)networks since it does not require any modifications to the existing end-node hardware and communication protocols.However,most deep learning-based RFFI systems require the collection of a great number of labelled signals for training,which is time-consuming and not ideal,especially for the Io T end nodes that are already deployed and configured with long transmission intervals.Moreover,the long time required to train a neural network from scratch also limits rapid deployment on legacy Io T networks.To address the above issues,two transferable RFFI protocols are proposed in this paper leveraging the concept of transfer learning.More specifically,they rely on fine-tuning and distance metric learning,respectively,and only require only a small amount of signals from the legacy IoT network.As the dataset used for transfer is small,we propose to apply augmentation in the transfer process to generate more training signals to improve performance.A Lo Ra-RFFI testbed consisting of 40 commercial-off-the-shelf(COTS)Lo Ra IoT devices and a software-defined radio(SDR)receiver is built to experimentally evaluate the proposed approaches.The experimental results demonstrate that both the fine-tuning and distance metric learning-based RFFI approaches can be rapidly transferred to another Io T network with less than ten signals from each Lo Ra device.The classification accuracy is over 90%,and the augmentation technique can improve the accuracy by up to 20%.

The technology of radio frequency fingerprint identification based on deep learning for 5G application

User Equipment(UE)authentication holds paramount importance in upholding the security of wireless networks.A nascent technology,Radio Frequency Fingerprint Identification(RFFI),is gaining prominence as a means to bolster network security authentication.To expedite the integration of RFFI within fifth-generation(5G)networks,this research undertakes the creation of a comprehensive link-level simulation platform tailored for 5G scenarios.The devised platform emulates various device impairments,including an oscillator,IQ modulator,and power amplifier(PA)nonlinearities,alongside simulating channel distortions.Consequent to this,a plausibility analysis is executed,intertwining transmitter device impairments with 3rd Generation Partnership Project(3GPP)new radio(NR)protocols.Subsequently,an exhaustive exploration is conducted to assess the impact of transmitter impairments,deep neural networks(DNNs),and channel effects on RF fingerprinting performance.Notably,under a signal-to-noise ratio(SNR)of 15 d B,the deep learning approach demonstrates the capability to accurately classify 100 UEs with a commendable 91%accuracy rate.Through a multifaceted evaluation,it is ascertained that the Attention-based network architecture emerges as the optimal choice for the RFFI task,serving as the new benchmark model for RFFI applications.

Genome-Wide Discovery and Expression Profiling of the SWEET Sugar Transporter Gene Family in Woodland Strawberry (Fragaria vesca) under Developmental and Stress Conditions: Structural and Evolutionary Analysis

The SWEET(sugar will eventually be exported transporter)family proteins are a recently identified class of sugar transporters that are essential for various physiological processes.Although the functions of the SWEET proteins have been identified in a number of species,to date,there have been no reports of the functions of the SWEET genes in woodland strawberries(Fragaria vesca).In this study,we identified 15 genes that were highly homolo-gous to the A.thaliana AtSWEET genes and designated them as FvSWEET1–FvSWEET15.We then conducted a structural and evolutionary analysis of these 15 FvSWEET genes.The phylogenetic analysis enabled us to categor-ize the predicted 15 SWEET proteins into four distinct groups.We observed slight variations in the exon‒intron structures of these genes,while the motifs and domain structures remained highly conserved.Additionally,the developmental and biological stress expression profiles of the 15 FvSWEET genes were extracted and analyzed.Finally,WGCNA coexpression network analysis was run to search for possible interacting genes of FvSWEET genes.The results showed that the FvSWEET10 genes interacted with 20 other genes,playing roles in response to bacterial and fungal infections.The outcomes of this study provide insights into the further study of FvSWEET genes and may also aid in the functional characterization of the FvSWEET genes in woodland strawberries.

ChatGPT在思想政治教育中的应用价值及潜在风险

ChatGPT依靠精准、智能、多模态的自然语言生成能力与自然、高效、实时的深度人机交互技术,在思想政治教育中得到了广泛应用,这丰富了教育资源,提高了教育效率,改进了教学方法,增强了教育反馈,为精准思政、智能思政提供了强大支持。但是,ChatGPT在语料库、自然语言处理技术逻辑、算法及人工管理上的缺陷也给思想政治教育造成认知误导、价值冲突、知识权威幻觉、人机互动挑战的情感困惑等突出问题。在思想政治教育中应用ChatGPT需要遵循科学性、规范性、适度性、安全性等原则,加强对ChatGPT的监督和管理,以保障思想政治教育的质量和效果。

Genome-Wide Exploration of the Grape GLR Gene Family and Differential Responses of VvGLR3.1 and VvGLR3.2 to Low Temperature and Salt Stress

Grapes,one of the oldest tree species globally,are rich in vitamins.However,environmental conditions such as low temperature and soil salinization significantly affect grape yield and quality.The glutamate receptor(GLR)family,comprising highly conserved ligand-gated ion channels,regulates plant growth and development in response to stress.In this study,11 members of the VvGLR gene family in grapes were identified using whole-genome sequence analysis.Bioinformatic methods were employed to analyze the basic physical and chemical properties,phylogenetic trees,conserved domains,motifs,expression patterns,and evolutionary relationships.Phylogenetic and collinear analyses revealed that the VvGLRs were divided into three subgroups,showing the high conservation of the grape GLR family.These members exhibited 2 glutamate receptor binding regions(GABAb and GluR)and 3-4 transmembrane regions(M1,M2,M3,and M4).Real-time quantitative PCR analysis demonstrated the sensitivity of all VvGLRs to low temperature and salt stress.Subsequent localization studies in Nicotiana tabacum verified that VvGLR3.1 and VvGLR3.2 proteins were located on the cell membrane and cell nucleus.Additionally,yeast transformation experiments confirmed the functionality of VvGLR3.1 and VvGLR3.2 in response to low temperature and salt stress.Thesefindings highlight the significant role of the GLR family,a highly conserved group of ion channels,in enhancing grape stress resistance.This study offers new insights into the grape GLR gene family,providing fundamental knowledge for further functional analysis and breeding of stress-resistant grapevines.

面向5G专网资源数据的数智化校验体系研究

为了高效提升5G专网资源数据质量,完善5G专网资源数据校验方法,本文提出面向5G专网资源数据的数智化校验体系框架。该框架以校验规则库研究为基础,将数据质量指标分解为完整性、规范性和关联性指标,并将指标规则嵌入到平台,打造智能化校验模块,完善5G专网数据管理流程规范,协同数据处理平台形成数据管理闭环,最后提供一个原型设计思路。该数智化校验体系框架为后续5G专网资源数据质量相关研究提供了一个整体性思路,相关的技术思路和方法设计可为5G专网资源数据的数智化校验提供借鉴。

A Modified Principal Component Analysis Method for Honeycomb Sandwich Panel Debonding Recognition Based on Distributed Optical Fiber Sensing Signals

The safety and integrity requirements of aerospace composite structures necessitate real-time health monitoring throughout their service life.To this end,distributed optical fiber sensors utilizing back Rayleigh scattering have been extensively deployed in structural health monitoring due to their advantages,such as lightweight and ease of embedding.However,identifying the precise location of damage from the optical fiber signals remains a critical challenge.In this paper,a novel approach which namely Modified Sliding Window Principal Component Analysis(MSWPCA)was proposed to facilitate automatic damage identification and localization via distributed optical fiber sensors.The proposed method is able to extract signal characteristics interfered by measurement noise to improve the accuracy of damage detection.Specifically,we applied the MSWPCA method to monitor and analyze the debonding propagation process in honeycomb sandwich panel structures.Our findings demonstrate that the training model exhibits high precision in detecting the location and size of honeycomb debonding,thereby facilitating reliable and efficient online assessment of the structural health state.

基于YOLO算法的智能云预警系统的设计和应用

为了解决当前各类市政施工对通信光缆维护的威胁,本文提出了基于YOLO算法的智能云光缆施工预警系统,通过自动化引流视频上云、基于YOLO_v3算法目标识别技术识别挖掘机、主动触发预警三大功能实现光缆人防到机防的升级,有效提升维护效率。

基于人工智能技术对明中都石刻的整理归类

明中都石刻现存六百余件,是中国建筑雕刻艺术的巅峰,具有极高的历史价值、文化价值、艺术价值。明中都石刻多散落在凤阳县内,且多已消失、残损,严重影响了石刻的保护和修复工作。面对如此数量庞大且类型繁多的石刻,传统的手工整理分类方法显然不能满足当前的需要。利用人工智能技术对石刻图像进行预处理、提取特征、归类分析、建立特征库等步骤实现图像的自动识别和分类,为研究提供了更加丰富、精准的数据资料。