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 ...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.展开更多
Next generation grid systems where the emphasis shifts to distributed global collaboration, a service-oriented approach and information layer issues exhibit a strong sense of automation. Requirements for these systems...Next generation grid systems where the emphasis shifts to distributed global collaboration, a service-oriented approach and information layer issues exhibit a strong sense of automation. Requirements for these systems resemble the self-organizing and the healing properties of natural ecosystems. Some key ecological concepts and mechanisms are introduced into the design for the third generation grid computing architectures by inspiration of this resemblance. Also, an Ecological Network-based Computing Environment (ENCE) platform is designed in this paper. Based on the ENCE platform, a grid-computing model of three-layered grid conceptual prototype that embeds the ENCE layers is presented from the viewpoint of implementation. The implementation model should be useful to the design of the third generation grid systems.展开更多
Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take ca...Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.展开更多
Scene graph prediction has emerged as a critical task in computer vision,focusing on transforming complex visual scenes into structured representations by identifying objects,their attributes,and the relationships amo...Scene graph prediction has emerged as a critical task in computer vision,focusing on transforming complex visual scenes into structured representations by identifying objects,their attributes,and the relationships among them.Extending this to 3D semantic scene graph(3DSSG)prediction introduces an additional layer of complexity because it requires the processing of point-cloud data to accurately capture the spatial and volumetric characteristics of a scene.A significant challenge in 3DSSG is the long-tailed distribution of object and relationship labels,causing certain classes to be severely underrepresented and suboptimal performance in these rare categories.To address this,we proposed a fusion prototypical network(FPN),which combines the strengths of conventional neural networks for 3DSSG with a Prototypical Network.The former are known for their ability to handle complex scene graph predictions while the latter excels in few-shot learning scenarios.By leveraging this fusion,our approach enhances the overall prediction accuracy and substantially improves the handling of underrepresented labels.Through extensive experiments using the 3DSSG dataset,we demonstrated that the FPN achieves state-of-the-art performance in 3D scene graph prediction as a single model and effectively mitigates the impact of the long-tailed distribution,providing a more balanced and comprehensive understanding of complex 3D environments.展开更多
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 learn...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.展开更多
Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for...Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.展开更多
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...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.展开更多
Background:Yanhusuo powder,also known as Xuanhusuo powder,is a long-standing Chinese herbal formula mainly used in the treatment of osteoarthritis.Although the clinical effectiveness of Yanhusuo powder has long been a...Background:Yanhusuo powder,also known as Xuanhusuo powder,is a long-standing Chinese herbal formula mainly used in the treatment of osteoarthritis.Although the clinical effectiveness of Yanhusuo powder has long been acknowledged,its mechanism of action and bioactive components remain unknown.Methods:A novel analytical method combining the use of ultra-performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry and ultra-performance liquid chromatography-triple quadrupole mass spectrometry was applied to profile the formula and absorbed prototype components in plasma after oral administration of Yanhusuo powder.Then,the absorbed constituents were subjected to network pharmacology to predict targets and pathways.AutoDock software was then used for molecular docking studies to screen for potential pharmacodynamic substances.Results:A total of 34 in vitro formula components and 20 in vivo prototype compounds from the various relevant species were successfully separated and identified for the first time.Compound-target-pathway analysis revealed that 20 absorbed constituents,42 target genes and 42 pathways are probably related to the efficacy of Yanhusuo powder against osteoarthritis.The efficacy of Yanhusuo powder mainly involves AKT1,fibronectin 1 and matrix metalloproteinase 9 targets and apoptosis,as well as PI3K-AKT and mitogen-activated protein kinases signaling pathways.According to the results of the molecular docking studies,it can be preliminarily judged that protopine,dehydrocorybulbine and angelicin may be the pharmacologically active substances of Yanhusuo powder.Conclusion:The results provide a scientific basis for understanding the bioactive compounds and the pharmacological mechanism of Yanhusuo powder.展开更多
In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract i...In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric space.To sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature extraction.Additionally,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the experiment.The loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric space.Experimental evaluations are conducted on small-sample datasets mini-ImageNet and CUB200-2011.The method in this paper can achieve higher classification accuracy.Specifically,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two datasets.Moreover,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.展开更多
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 i...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.展开更多
The traditional software development model commonly named “waterfall” is unable to cope with the increasing functionality and complexity of modern embedded systems. In addition, it is unable to support the ability f...The traditional software development model commonly named “waterfall” is unable to cope with the increasing functionality and complexity of modern embedded systems. In addition, it is unable to support the ability for businesses to quickly respond to new market opportunities due to changing requirements. As a response, the software development community developed the Agile Methodologies (e.g., extreme Programming, Scrum) which were also adopted by the Embedded System community. However, failures and bad experiences in applying Agile Methodologies to the development of embedded systems have not been reported in the literature. Therefore, this paper contributes a detailed account of our first-time experiences adopting an agile approach in the prototype development of a wireless environment data acquisition system in an academic environment. We successfully applied a subset of the extreme Programming (XP) methodology to our software development using the Python programming language, an experience that demonstrated its benefits in shaping the design of the software and also increasing productivity. We used an incremental development approach for the hardware components and adopted a “cumulative testing” approach. For the overall development process management, however, we concluded that the Promise/Commitment-Based Project Management (PB-PM/CBPM) was better suited. We discovered that software and hardware components of embedded systems are best developed in parallel or near-parallel. We learned that software components that pass automated tests may not survive in the tests against the hardware. Throughout this rapid prototyping effort, factors like team size and our availability as graduate students were major obstacles to fully apply the XP methodology.展开更多
针对小样本学习过程中样本数量不足导致的性能下降问题,基于原型网络(Prototype network,ProtoNet)的小样本学习方法通过实现查询样本与支持样本原型特征间的距离度量,从而达到很好的分类性能.然而,这种方法直接将支持集样本均值视为类...针对小样本学习过程中样本数量不足导致的性能下降问题,基于原型网络(Prototype network,ProtoNet)的小样本学习方法通过实现查询样本与支持样本原型特征间的距离度量,从而达到很好的分类性能.然而,这种方法直接将支持集样本均值视为类原型,在一定程度上加剧了对样本数量稀少情况下的敏感性.针对此问题,提出了基于自适应原型特征类矫正的小样本学习方法(Few-shot learning based on class rectification via adaptive prototype features,CRAPF),通过自适应生成原型特征来缓解方法对数据细微变化的过度响应,并同步实现类边界的精细化调整.首先,使用卷积神经网络构建自适应原型特征生成模块,该模块采用非线性映射获取更为稳健的原型特征,有助于减弱异常值对原型构建的影响;然后,通过对原型生成过程的优化,提升不同类间原型表示的区分度,进而强化原型特征对类别表征的整体效能;最后,在3个广泛使用的基准数据集上的实验结果显示,该方法提升了小样本学习任务的表现.展开更多
基金partly funded by Natural Science Foundation of China(No.61971102 and 62132004)Sichuan Science and Technology Program(No.22QYCX0168)the Municipal Government of Quzhou(Grant No.2021D003)。
文摘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.
基金Supported in part by the National Nature Science Foundation of China (No. 60474037 and 60004006) and Specialized Research Fund for the Doctoral Program of Higher Education from Educational Committee of China (No. 20030255009)
文摘Next generation grid systems where the emphasis shifts to distributed global collaboration, a service-oriented approach and information layer issues exhibit a strong sense of automation. Requirements for these systems resemble the self-organizing and the healing properties of natural ecosystems. Some key ecological concepts and mechanisms are introduced into the design for the third generation grid computing architectures by inspiration of this resemblance. Also, an Ecological Network-based Computing Environment (ENCE) platform is designed in this paper. Based on the ENCE platform, a grid-computing model of three-layered grid conceptual prototype that embeds the ENCE layers is presented from the viewpoint of implementation. The implementation model should be useful to the design of the third generation grid systems.
文摘Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.
基金supported by the Glocal University 30 Project Fund of Gyeongsang National University in 2025.
文摘Scene graph prediction has emerged as a critical task in computer vision,focusing on transforming complex visual scenes into structured representations by identifying objects,their attributes,and the relationships among them.Extending this to 3D semantic scene graph(3DSSG)prediction introduces an additional layer of complexity because it requires the processing of point-cloud data to accurately capture the spatial and volumetric characteristics of a scene.A significant challenge in 3DSSG is the long-tailed distribution of object and relationship labels,causing certain classes to be severely underrepresented and suboptimal performance in these rare categories.To address this,we proposed a fusion prototypical network(FPN),which combines the strengths of conventional neural networks for 3DSSG with a Prototypical Network.The former are known for their ability to handle complex scene graph predictions while the latter excels in few-shot learning scenarios.By leveraging this fusion,our approach enhances the overall prediction accuracy and substantially improves the handling of underrepresented labels.Through extensive experiments using the 3DSSG dataset,we demonstrated that the FPN achieves state-of-the-art performance in 3D scene graph prediction as a single model and effectively mitigates the impact of the long-tailed distribution,providing a more balanced and comprehensive understanding of complex 3D environments.
基金The work was supported by the National Key R&D Program of China(Grant No.2020YFC1511601)Fundamental Research Funds for the Central Universities(Grant No.2019SHFWLC01).
文摘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.
基金supported in part by the National Natural Science Foundation of China(No.12302252)。
文摘Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.
文摘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.
基金The work was supported by the National Natural Science Foundation of China(No.81373942)the Key Science and Technology Research Projects of Tibet Autonomous Region of China(No.XZ201801-GA-16).
文摘Background:Yanhusuo powder,also known as Xuanhusuo powder,is a long-standing Chinese herbal formula mainly used in the treatment of osteoarthritis.Although the clinical effectiveness of Yanhusuo powder has long been acknowledged,its mechanism of action and bioactive components remain unknown.Methods:A novel analytical method combining the use of ultra-performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry and ultra-performance liquid chromatography-triple quadrupole mass spectrometry was applied to profile the formula and absorbed prototype components in plasma after oral administration of Yanhusuo powder.Then,the absorbed constituents were subjected to network pharmacology to predict targets and pathways.AutoDock software was then used for molecular docking studies to screen for potential pharmacodynamic substances.Results:A total of 34 in vitro formula components and 20 in vivo prototype compounds from the various relevant species were successfully separated and identified for the first time.Compound-target-pathway analysis revealed that 20 absorbed constituents,42 target genes and 42 pathways are probably related to the efficacy of Yanhusuo powder against osteoarthritis.The efficacy of Yanhusuo powder mainly involves AKT1,fibronectin 1 and matrix metalloproteinase 9 targets and apoptosis,as well as PI3K-AKT and mitogen-activated protein kinases signaling pathways.According to the results of the molecular docking studies,it can be preliminarily judged that protopine,dehydrocorybulbine and angelicin may be the pharmacologically active substances of Yanhusuo powder.Conclusion:The results provide a scientific basis for understanding the bioactive compounds and the pharmacological mechanism of Yanhusuo powder.
基金the Scientific Research Foundation of Liaoning Provincial Department of Education(No.LJKZ0139)the Program for Liaoning Excellent Talents in University(No.LR15045).
文摘In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric space.To sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature extraction.Additionally,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the experiment.The loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric space.Experimental evaluations are conducted on small-sample datasets mini-ImageNet and CUB200-2011.The method in this paper can achieve higher classification accuracy.Specifically,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two datasets.Moreover,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.
基金This research was partly supported by the National Science and Technology Council,Taiwan with Grant Numbers 112-2221-E-992-045,112-2221-E-992-057-MY3 and 112-2622-8-992-009-TD1.
文摘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.
文摘The traditional software development model commonly named “waterfall” is unable to cope with the increasing functionality and complexity of modern embedded systems. In addition, it is unable to support the ability for businesses to quickly respond to new market opportunities due to changing requirements. As a response, the software development community developed the Agile Methodologies (e.g., extreme Programming, Scrum) which were also adopted by the Embedded System community. However, failures and bad experiences in applying Agile Methodologies to the development of embedded systems have not been reported in the literature. Therefore, this paper contributes a detailed account of our first-time experiences adopting an agile approach in the prototype development of a wireless environment data acquisition system in an academic environment. We successfully applied a subset of the extreme Programming (XP) methodology to our software development using the Python programming language, an experience that demonstrated its benefits in shaping the design of the software and also increasing productivity. We used an incremental development approach for the hardware components and adopted a “cumulative testing” approach. For the overall development process management, however, we concluded that the Promise/Commitment-Based Project Management (PB-PM/CBPM) was better suited. We discovered that software and hardware components of embedded systems are best developed in parallel or near-parallel. We learned that software components that pass automated tests may not survive in the tests against the hardware. Throughout this rapid prototyping effort, factors like team size and our availability as graduate students were major obstacles to fully apply the XP methodology.
文摘针对小样本学习过程中样本数量不足导致的性能下降问题,基于原型网络(Prototype network,ProtoNet)的小样本学习方法通过实现查询样本与支持样本原型特征间的距离度量,从而达到很好的分类性能.然而,这种方法直接将支持集样本均值视为类原型,在一定程度上加剧了对样本数量稀少情况下的敏感性.针对此问题,提出了基于自适应原型特征类矫正的小样本学习方法(Few-shot learning based on class rectification via adaptive prototype features,CRAPF),通过自适应生成原型特征来缓解方法对数据细微变化的过度响应,并同步实现类边界的精细化调整.首先,使用卷积神经网络构建自适应原型特征生成模块,该模块采用非线性映射获取更为稳健的原型特征,有助于减弱异常值对原型构建的影响;然后,通过对原型生成过程的优化,提升不同类间原型表示的区分度,进而强化原型特征对类别表征的整体效能;最后,在3个广泛使用的基准数据集上的实验结果显示,该方法提升了小样本学习任务的表现.
