An attention-based prototypical network for forest fire smoke few-shot detection

Existing almost deep learning methods rely on a large amount of annotated data, so they are inappropriate for forest fire smoke detection with limited data. In this paper, a novel hybrid attention-based few-shot learning method, named Attention-Based Prototypical Network, is proposed for forest fire smoke detection. Specifically, feature extraction network, which consists of convolutional block attention module, could extract high-level and discriminative features and further decrease the false alarm rate resulting from suspected smoke areas. Moreover, we design a metalearning module to alleviate the overfitting issue caused by limited smoke images, and the meta-learning network enables achieving effective detection via comparing the distance between the class prototype of support images and the features of query images. A series of experiments on forest fire smoke datasets and miniImageNet dataset testify that the proposed method is superior to state-of-the-art few-shot learning approaches.

Prototypical Network Based on Manhattan Distance

Few-shot Learning algorithms can be effectively applied to fields where certain categories have only a small amount of data or a small amount of labeled data,such as medical images,terrorist surveillance,and so on.The Metric Learning in the Few-shot Learning algorithmis classified by measuring the similarity between the classified samples and the unclassified samples.This paper improves the Prototypical Network in the Metric Learning,and changes its core metric function to Manhattan distance.The Convolutional Neural Network of the embedded module is changed,and mechanisms such as average pooling and Dropout are added.Through comparative experiments,it is found that thismodel can converge in a small number of iterations(below 15,000 episodes),and its performance exceeds algorithms such asMAML.Research shows that replacingManhattan distance with Euclidean distance can effectively improve the classification effect of the Prototypical Network,and mechanisms such as average pooling and Dropout can also effectively improve the model.

Prototypicality Gradient and Similarity Measure: A Semiotic-Based Approach Dedicated to Ontology Personalization

This paper introduces a new approach dedicated to the Ontology Personalization. Inspired by works in Cognitive Psychology, our work is based on a process which aims at capturing the user-sensitive relevance of the categorization process, that is the one which is really perceived by the end-user. Practically, this process consists in decorating the Specialization/Generalization links (i.e. the is-a links) of the hierarchy of concepts with 2 gradients. The goal of the first gradient, called Conceptual Prototypicality Gradient, is to capture the user-sensitive relevance of the categorization process, that is the one which is perceived by the end-user. As this gradient is defined according to the three aspects of the semiotic triangle (i.e. intentional, extensional and expressional dimension), we call it Semiotic based Prototypicality Gradient. The objective of the second gradient, called Lexical Prototypicality Gradient, is to capture the user-sensitive relevance of the lexicalization process, i.e. the definition of a set of terms used to denote a concept. These gradients enrich the initial formal semantics of an ontology by adding a pragmatics defined according to a context of use which depends on parameters like culture, educational background and/or emotional context of the end-user. This paper also introduces a new similarity measure also defined in the context of a semiotic-based approach. The first originality of this measure, called SEMIOSEM, is to consider the three semiotic dimensions of the conceptualization underlying an ontology. Thus, SEMIOSEM aims at aggregating and improving existing extensional-based and intentional-based measures. The second originality of this measure is to be context-sensitive, and in particular user-sensitive. This makes SEMIOSEM more flexible, more robust and more close to the end-user’s judgment than the other similarity measures which are usually only based on one aspect of a conceptualization and never take the end-user’s perceptions and purposes into account.

An Integrated Control Framework for Torque Vectoring and Active Suspension System

Four-wheel independently driven electric vehicles(FWID-EV)endow a flexible and scalable control framework to improve vehicle performance.This paper integrates the torque vectoring and active suspension system(ASS)to enhance the vehicle’s longitudinal and vertical motion control performance.While the nonlinear characteristic of the tire model leads to a relatively heavier computational burden.To facilitate the controller design and ease the load,a half-vehicle dynamics system is built and simplified to the linear-time-varying(LTV)model.Then a model predictive controller is developed by formulating the objective function by comprehensively considering the safety,energy-saving and comfort requirements.The in-wheel motor efficiency and the power loss of tire slip are treated as optimization indices in this work to reduce energy consumption.Finally,the effectiveness of the proposed controller is verified through the rapid-control-prototype(RCP)test.The results demonstrate the enhancement of the energy-saving as well as comfort on the basis of vehicle stability.

异构并行计算下高维混合型数据聚类算法研究

高维数据维度增加,数据空间的体积呈指数增长,容易陷入“维数灾难”,导致聚类算法执行效率低,为此,提出异构并行计算下高维混合型数据聚类算法。构建高维混合型数据相异度矩阵,提取高维混合型数据的统计序列特征值,利用时间窗口进行特征优化。采用K⁃Prototypes聚类算法提取高维混合型数据的统计序列特征,评估数据与类中心的相异性,计算数据与类中心的欧氏距离,实现高维混合型数据聚类。采用异构并行计算技术进行高维混合型数据K⁃Prototypes聚类的并行化处理,合理分配CPU与GPU工作,达到CPU与GPU的工作负载平衡,提高K⁃Prototypes的聚类效率。实验结果表明,此算法对于高维混合型数据的聚类效果好、运行时间短、性能稳定。

Unknown DDoS Attack Detection with Fuzzy C-Means Clustering and Spatial Location Constraint Prototype Loss

Since its inception,the Internet has been rapidly evolving.With the advancement of science and technology and the explosive growth of the population,the demand for the Internet has been on the rise.Many applications in education,healthcare,entertainment,science,and more are being increasingly deployed based on the internet.Concurrently,malicious threats on the internet are on the rise as well.Distributed Denial of Service(DDoS)attacks are among the most common and dangerous threats on the internet today.The scale and complexity of DDoS attacks are constantly growing.Intrusion Detection Systems(IDS)have been deployed and have demonstrated their effectiveness in defense against those threats.In addition,the research of Machine Learning(ML)and Deep Learning(DL)in IDS has gained effective results and significant attention.However,one of the challenges when applying ML and DL techniques in intrusion detection is the identification of unknown attacks.These attacks,which are not encountered during the system’s training,can lead to misclassification with significant errors.In this research,we focused on addressing the issue of Unknown Attack Detection,combining two methods:Spatial Location Constraint Prototype Loss(SLCPL)and Fuzzy C-Means(FCM).With the proposed method,we achieved promising results compared to traditional methods.The proposed method demonstrates a very high accuracy of up to 99.8%with a low false positive rate for known attacks on the Intrusion Detection Evaluation Dataset(CICIDS2017)dataset.Particularly,the accuracy is also very high,reaching 99.7%,and the precision goes up to 99.9%for unknown DDoS attacks on the DDoS Evaluation Dataset(CICDDoS2019)dataset.The success of the proposed method is due to the combination of SLCPL,an advanced Open-Set Recognition(OSR)technique,and FCM,a traditional yet highly applicable clustering technique.This has yielded a novel method in the field of unknown attack detection.This further expands the trend of applying DL and ML techniques in the development of intrusion detection systems and cybersecurity.Finally,implementing the proposed method in real-world systems can enhance the security capabilities against increasingly complex threats on computer networks.

The Advertisement Translation Based on the Prototype Theory

Based on the Prototype Theory,the prototypical feature of advertisement is found to be the combination of three language functions:the informative function,the expressive function,and the vocative function.The advertisement translation means the adjustment of the informative function and the expressive function according to the differences between languages or cultures in order to maximize the vocative function.The faithful translation is the closest to the prototype of the source text but not necessarily the best translation.

Rapid Prototype Development Approach for Genetic Programming

Genetic Programming (GP) is an important approach to deal with complex problem analysis and modeling, and has been applied in a wide range of areas. The development of GP involves various aspects, including design of genetic operators, evolutionary controls and implementations of heuristic strategy, evaluations and other mechanisms. When designing genetic operators, it is necessary to consider the possible limitations of encoding methods of individuals. And when selecting evolutionary control strategies, it is also necessary to balance search efficiency and diversity based on representation characteristics as well as the problem itself. More importantly, all of these matters, among others, have to be implemented through tedious coding work. Therefore, GP development is both complex and time-consuming. To overcome some of these difficulties that hinder the enhancement of GP development efficiency, we explore the feasibility of mutual assistance among GP variants, and then propose a rapid GP prototyping development method based on πGrammatical Evolution (πGE). It is demonstrated through regression analysis experiments that not only is this method beneficial for the GP developers to get rid of some tedious implementations, but also enables them to concentrate on the essence of the referred problem, such as individual representation, decoding means and evaluation. Additionally, it provides new insights into the roles of individual delineations in phenotypes and semantic research of individuals.

Generating prototypical residential building geometry models using a new hybrid approach

Building prototyping has regularly been used in building performance analyses with statistically feasible models.The novelty of this research involves a new hybrid approach combining stratified sampling and k-means clustering to establish building geometry prototypes.The research focuses on residential buildings in Ningbo,China.Seventeen small residential districts(SRDs)containing 367 residential buildings were systemically selected for survey and data collection.The stratified sampling used building construction year as the main parameter to generate stratification.Floor numbers,shape coefficients,floor areas,and window-to-wall ratios were used as the four observations for k-means clustering.Based on this new approach,nine building geometry prototypes were identified and modelled.These statistically representative prototypes provide building geometrical information and characteristic-based evaluations for subsequent building performance analysis.

Semi-Supervised Clustering Algorithm Based on Deep Feature Mapping

Clustering analysis is one of the main concerns in data mining.A common approach to the clustering process is to bring together points that are close to each other and separate points that are away from each other.Therefore,measuring the distance between sample points is crucial to the effectiveness of clustering.Filtering features by label information and mea-suring the distance between samples by these features is a common supervised learning method to reconstruct distance metric.However,in many application scenarios,it is very expensive to obtain a large number of labeled samples.In this paper,to solve the clustering problem in the few supervised sample and high data dimensionality scenarios,a novel semi-supervised clustering algorithm is proposed by designing an improved prototype network that attempts to reconstruct the distance metric in the sample space with a small amount of pairwise supervised information,such as Must-Link and Cannot-Link,and then cluster the data in the new metric space.The core idea is to make the similar ones closer and the dissimilar ones further away through embedding mapping.Extensive experiments on both real-world and synthetic datasets show the effectiveness of this algorithm.Average clustering metrics on various datasets improved by 8%compared to the comparison algorithm.

A multi-purpose prototype test system for mechanical behavior of tunnel supporting structure: Development and application

A multi-purpose prototype test system is developed to study the mechanical behavior of tunnel sup-porting structure,including a modular counterforce device,a powerful loading equipment,an advanced intelligent management system and an efficient noncontact deformation measurement system.The functions of the prototype test system are adjustable size and shape of the modular counterforce structure,sufficient load reserve and accurate loading,multi-connection linkage intelligent management,and high-precision and continuously positioned noncontact deformation measurement.The modular counterforce structure is currently the largest in the world,with an outer diameter of 20.5 m,an inner diameter of 16.5 m and a height of 6 m.The case application proves that the prototype test system can reproduce the mechanical behavior of the tunnel lining during load-bearing,deformation and failure processes in detail.

Field trial measurement and channel modeling for reconfigurable intelligent surface

With the advantage of programmable electromagnetic properties,Reconfigurable Intelligent Surfaces(RISs)havedrawn wide attention from both industry and academia.RIS-assisted communication systems can promote hugewireless channel quality improvement and remarkable coverage enhancement.This paper proposes generalpathloss model,radiation pattern and mirror beam effect of 1-bit RIS at sub-6 GHz band.Field trails have beencarried out in outdoor and indoor deployment scenarios.The proposed model is validated through extensivesimulations and field-trial measurements.In addition,an optimized RIS phase-shit design process for the mirrorbeam elimination is proposed and validated with simulations.The proposed theoretical model and measurementresults can promote future research and application in RIS-assisted communications.

Numerical study of geyser events in rainstorm systems at different scales

Considering that we still do not fully understand the behavior of air pockets trapped in rainstorm systems and water flow changes inside pipes,the study of actual geysers presents many challenges.In this study,three-dimensional numerical models were developed to investigate the mechanisms of geyser events triggered by rapid filling flows at different scales.The results showed that,in the first stage of the water–air mixture of the prototype model,a large amount of air was released quickly,and the subsequent overflow lasted for a more extended period.The transport capacity of the downstream pipe,as a critical factor,significantly influenced the water–air interaction of the geyser.Restricting the outlet area and increasing the outlet pressure simultaneously resulted in a stronger geyser.The equivalent density of the water–air mixture increased as the scale decreased during the geyser event.

Development and preliminary results of a large-pixel two-layer LaBr_(3) Compton camera prototype

Lanthanum bromide(LaBr_(3))crystal has a high energy resolution and time resolution and has been used in Compton cameras(CCs)over the past few decades.However,LaBr_(3) crystal arrays are difficult to process because LaBr_(3) is easy to crack and break;thus,few LaBr_(3)-based CC prototypes have been built.In this study,we designed and fabricated a large-pixel LaBr_(3) CC prototype and evaluated its performance with regard to position,energy,and angular resolution.We used two 10×10 LaBr_(3) crystal arrays with a pixel size of 5 mm×5 mm,silicon photomultipliers(SiPMs),and corresponding decoding circuits to construct our prototype.Additionally,a framework based on a Voronoi diagram and a lookup table was developed for list-mode projection data acquisition.Monte Carlo(MC)simulations based on Geant4 and experiments were conducted to evaluate the performance of our CC prototype.The lateral position resolution was 5 mm,and the maximum deviation in the depth direction was 2.5 and 5 mm for the scatterer and absorber,respectively.The corresponding measured energy resolu-tions were 7.65%and 8.44%,respectively,at 511 keV.The experimental results of ^(137)Cs point-like sources were consistent with the MC simulation results with regard to the spatial positions and full widths at half maximum(FWHMs).The angular resolution of the fabricated prototype was approximately 6°when a point-like ^(137)Cs source was centrally placed at a distance of 5 cm from the scatterer.We proposed and investigated a large-pixel LaBr_(3) CC for the first time and verified its feasibility for use in accurate spatial positioning of radiative sources with a high angular resolution.The proposed CC can satisfy the requirements of radiative source imaging and positioning in the nuclear industry and medical applications.

Affinity-Engineered Flexible Scaffold toward Energy-Dense, Highly Reversible Na Metal Batteries

The practical deployment of metallic anodes in the energy-dense batteries is impeded by the thermodynamically unstable interphase in contact with the aprotic electrolyte,structural collapse of the substrates as well as their insufficient affinity toward the metallic deposits.Herein,the mechanical flexible,lightweight(1.2 mg cm^(−2))carbon nanofiber scaffold with the monodispersed,ultrafine Sn_(4)P_(3) nanoparticles encapsulation(Sn_(4)P_(3)NPs@CNF)is proposed as the deposition substrate toward the high-areal-capacity sodium loadings up to 4 mAh cm^(−2).First-principles calculations manifest that the alloy intermediates,namely the Na_(15)Sn_(4) and Na_(3)P matrix,exhibit the intimate Na affinity as the“sodiophilic”sites.Meanwhile,the porous CNF regulates the heterogeneous alloying process and confines the deposit propagation along the nanofiber orientation.With the precise control of pairing mode with the NaVPO4F cathode(8.7 mg cm^(−2)),the practical feasibility of the Sn_(4)P_(3) NPs@CNF anode(1^(*)Na excess)is demonstrated in 2 mAh single-layer pouch cell prototype,which achieves the 95.7%capacity retention for 150 cycles at various mechanical flexing states as well as balanced energy/power densities.

UAV-Aided Data and Energy Integrated Network: System Design and Prototype Development

Terminal devices deployed in outdoor environments are facing a thorny problem of power supply.Data and energy integrated network(DEIN)is a promising technology to solve the problem,which simultaneously transfers data and energy through radio frequency signals.State-of-the-art researches mostly focus on theoretical aspects.By contrast,we provide a complete design and implementation of a fully functioning DEIN system with the support of an unmanned aerial vehicle(UAV).The UAV can be dispatched to areas of interest to remotely recharge batteryless terminals,while collecting essential information from them.Then,the UAV uploads the information to remote base stations.Our system verifies the feasibility of the DEIN in practical applications.

Semantic Changes and Translation of Chinese Buzzwords of COVID-19 Pandemic

As a unique cultural product of the pandemic era,the COVID-19 pandemic buzzwords fully reflect the characteristics of the time.The paper applies the prototype theory to classify the semantic changes of the pandemic prevention buzzwords into two types:semantic evolution and semantic variation,and briefly discusses the implications of the prototype theory for translating the pandemic prevention propaganda slogans based on understanding the semantic changes to help people further understand the pandemic buzzwords as well as related social realities.

Simulation Analysis of Electromechanical Coupling for Unmanned Aerial Vehicle Cabin Door System

In order to study the dynamic response of the unmanned aerial vehicle cabin door opening and closing system under impact load conditions, considering the flexible treatment of mechanical components, and the system’s motion with different stiffness of energy-absorbing components, a rigid-flexible coupling model of the cabin door actuation system was established in LMS. Virtual. Motion. In Amesim, a control model of the motor was created. Through the Motion-Amesim co-simulation module, the dynamic module of the system was combined with the motor control module to complete the electromechanical coupling simulation and analyze the results. .

A Study on Second Language Vocabulary Acquisition Under the Categorization Theory

In cognitive linguistics,debates on the status and functions of categorization have been a heated issue.In semantics and second language acquisition,scholars have discussed and achieved vocabulary acquisition from different perspectives and academic levels.Vocabulary learning exerts a fundamental role in second language vocabulary acquisition(SLVA),and it is closely related to learners’cognitive competence.However,studies on second language vocabulary acquisition under the categorization theory in cognitive linguistics have received less attention from linguists when compared with other studies.This paper employs two representative dimensions,the basic-level effect and the prototype effect,under the categorization theory to further delve into the implications on second language vocabulary acquisition.This article first provides a comprehensive introduction to the nature and the approaches of the categorization theory,and then analyzes the relations and implications for second language vocabulary acquisition under the categorization theory from the perspective of the basic-level and the prototype effects.The research results showed that the basic-level effect on SLVA is mainly on the classification of word categories distinguished from the superordinate and subordinate categories,while the prototype effect is more on understanding the complexity and use of word meaning.

混合属性数据聚类初始点选择的改进

k-prototypes和模糊k-prototypes是处理数值属性和分类属性混合数据主要的聚类算法。但这两种聚类算法不足之处是对初值有明显的依赖。对初值选取方法进行了分析和研究,提出一种新的改进方法,可在一定程度上减少随机性。实际数据集仿真结果表明改进算法有更高的稳定性和较强的伸缩性。