检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Harrigan, Shane Coleman, Sonya Kerr, Dermot Yogarajah, Pratheepan Fang, Zheng Wu, Chengdong Ulster Univ Intelligent Syst Res Ctr Coleraine Londonderry North Ireland Northeastern Univ Fac Robot Sci & Engn Shenyang 110169 Peoples R China

ISBN: (纸本)9781509066315

Neural coding schemes are powerful tools used within neuroscience. This paper introduces three different neural coding scheme formations for event-based vision data which are designed to emulate the neural behaviour exhibited by neurons under stimuli. Presented are phase-of-firing and two sparse neural coding schemes. It is determined that machine learning approaches, i.e. Convolutional Neural Network combined with a Stacked Autoencoder network, produce powerful descriptors of the patterns within events. These coding schemes are deployed in an existing action recognition template and evaluated using two popular event-based data sets.

关键词： event-based vision convolutional neural network encoding scheme feature extraction object recognition

来源：评论

学校读者我要写书评

暂无评论

Benchmarking based search framework

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2019年第3期22卷 929-951页

作者： Xie, A. S. Zhejiang Univ Technol China Inst SMEs 18 Chaowang Rd Hangzhou 310014 Zhejiang Peoples R China

Most of the issues in science, engineering, and management can be turned into optimization problems by modeling. However, for most of which, the operations research methods based on rigid mathematical logic can do nothing, intelligent methods are helpful. Traditionally, the so-called intelligent methods, whose "intelligence" is mainly dependent on the probability rules of their operators. Thus there are always some probability equations or mathematical formulations that need to be updated. This paper proposed a new framework for intelligent optimization/search, which is based on artful organizing tactics rather than "intelligent" probability rules. Thus it needs no probability equations. In addition, it is helpful to balance the exploration and the exploitation, keep the population diversity and avoid useless and ineffective repetitious operations. The mentioned above had been proved by theoretical analyses and simulation experiments. Of course, any method has its disadvantages, the defects and the possible improvement measures of this framework were summarized in the conclusion part.

关键词： Optimization problems Intelligent optimization Optimization algorithm Evolutionary computation Swarm intelligence Artificial intelligence encoding scheme Benchmarking philosophy

来源：评论

学校读者我要写书评

暂无评论

StarZIP: Streaming Graph Compression Technique for Data Archiving

引用

IEEE ACCESS 2019年 7卷 38020-38034页

作者： Dolgorsuren, Batjargal Khan, Kifayat Ullah Rasel, Mostofa Kamal Lee, Young-Koo Kyung Hee Univ Dept Comp Sci & Engn Seoul 130701 South Korea Natl Univ Comp & Emerging Sci Dept Comp Sci Islamabad 75190 Pakistan

The size of a streaming graph is possibly unbounded, and it is updated by a continuous sequence of edges over time. Due to numerous types of real-world interactions, the nature of edge arrival in a streaming graph is dynamic and holds different types of temporal subgraphs, such as stars, bipartite forms, cliques, and chains. The most current techniques find such subgraphs in each snapshot of a dynamic graph and use a dictionary or hash-based summary to compress the graph before applying a stitching technique to demonstrate its temporal behavior. However, it remains difficult to discover those subgraph structures from the continuous stream of edges found in large and rapidly changing dynamic graphs. In this paper, we propose a streaming graph compression algorithm, StarZIP, that uses a new encoding scheme. Our motivational factor is real-world graphs that contain an overwhelmingly large number of stars and a few other structures. We have observed that all subgraph structures can be represented as star-shaped subgraphs. Moreover, the star-shaped representation can easily be arranged in the form of an inverted index, which enables the application of different inverted list encoding techniques for compression. Therefore, we shatter a graph into a uniform representation of stars to compress it. The evaluation of StarZIP on real-world datasets shows that our proposed system reduced the size of a highly dense graph to 60 times less than its original size. Moreover, the experimental results indicate that StarZIP compression is 4 times better than the stateof-the-art techniques.

关键词： encoding scheme graph compression streaming graph star structure

来源：评论

学校读者我要写书评

暂无评论

Parallelized Metaheuristic-Ensemble of Heterogeneous Feedforward Neural Networks for Regression Problems

引用

IEEE ACCESS 2019年 7卷 26909-26932页

作者： Musikawan, Pakarat Sunat, Khamron Kongsorot, Yanika Horata, Punyaphol Chiewchanwattana, Sirapat Khon Kaen Univ Fac Sci Dept Comp Sci Khon Kaen 40002 Thailand

A feedforward neural network ensemble trained through metaheuristic algorithms has been proposed by researchers to produce a group of optimal neural networks. This method, however, has proven to be very time-consuming during the optimization process. To overcome this limitation, we propose a metaheuristic-based learning algorithm for building an ensemble system, resulting in shorter training time. In our proposed method, a master-slave based metaheuristic algorithm is employed in the optimization process to produce a group of heterogeneous feedforward neural networks, in which the global search operations are executed on the master, and the tasks of objective evaluation are distributed to the slaves (workers). To reduce evaluation costs, the entire training dataset is randomly divided equally into several disjoint subsets. Each subset is randomly paired with another subset of the remainder and distributed to a worker for the objective evaluation. Following the optimization process, representative candidate solutions (individuals) from the entire population are selected to perform as the base components of the ensemble system. The performance of the proposed method has been compared with those of other state-of-the-art techniques in over 31 benchmark regression datasets taken from public repositories. The experimental results show that the proposed method not only reduces the computational time but also achieves significantly better prediction accuracy. Moreover, the proposed method achieved promising results in the application of a subset of the million song dataset, which identifies the release year of a song and predicts the buzz on Twitter.

关键词： Neural network with random weights feedforward neural network ensemble learning metaheuristic optimization hybrid learning encoding scheme master-slave model parallel computing

来源：评论

学校读者我要写书评

暂无评论

Design rule development for frequency-coded chipless radiofrequency identification with high capacity

引用

IET MICROWAVES ANTENNAS & PROPAGATION 2019年第8期13卷 1255-1261页

作者： Chen, Yen-Sheng Jiang, Tong-Yang Lai, Fei-Peng Natl Taipei Univ Technol Dept Elect Engn Taipei 10608 Taiwan

Recently, considerable attention has arisen over the frequency-coded chipless radiofrequency identification (RFID), but there is no general consensus on the system specification scheme including encoding techniques, resonators with narrowband and harmonic-rejected features, and a frequency spectrum used. The purpose of this study is to develop the design rules that improve the capacity and reliability of the chipless RFID. The proposed system development is cast into three phases. Phase one is to determine the encoding scheme that enhances robustness. The limitation of the conventional one-bit-per-resonator approach is identified, and frequency shift encoding is designed to be the kernel of the chipless RFID. Phase two is to determine the resolution of the frequency spectrum by analysing the radar cross-section for 37 resonators. Four resonators exhibit the narrowband and harmonic-rejected features, and thus they are recommended to be implemented in the chipless tag. Phase three is to determine the specification on the frequency spectrum. For a 21-bit example system, the frequency spectrum that meets the trade-off between the broadband complexity and the size of the tag is 2.0-5.0 GHz. The proposed design rules are validated by conducting simulation and measurement.

关键词： resonators radar cross-sections radiofrequency identification encoding design rule development frequency-coded chipless radiofrequency identification system specification scheme encoding techniques resonators narrowband rejected features harmonic-rejected features frequency spectrum chipless RFID encoding scheme frequency shift encoding chipless tag 21-bit example system one-bit-per-resonator frequency 2 0 GHz to 5 0 GHz

来源：评论

学校读者我要写书评

暂无评论

DRBox-v2: An Improved Detector With Rotatable Boxes for Target Detection in SAR Images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2019年第11期57卷 8333-8349页

作者： An, Quanzhi Pan, Zongxu Liu, Lei You, Hongjian Chinese Acad Sci Inst Elect Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Technol Geospatial Informat Proc & Applic Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 101408 Peoples R China

Convolutional neural network (CNN)-based methods have been successfully applied to SAR target detection. Different from prevalently used detection approaches with rectangle bounding box, rotatable bounding box (RBox)-based methods, such as DRBox-v1, can effectively reduce the interference of background pixels and locate the targets more finely for geospatial object detection. Although DRBox-v1 has achieved impressive detected performance, there still exist some remaining problems and room for improvement. In this paper, an improved RBox-based target detection framework is proposed to boost precision and recall rates of detection, and we refer to the method as DRBox-v2 and apply it to target detection in SAR images. The main improvements of DRBox-v2 as well as the contributions of this paper are fourfold. First, a multi-layer prior box generation strategy is designed for detecting small-scale targets. Since shallow layers lack strong sematic information, the feature pyramid network (FPN) module is applied. Second, a modified encoding scheme for RBox is proposed for more precisely estimating the position of RBox and orientation of targets. Third, a focal loss (FL) combined with hard negative mining (HNM) technique is proposed to mitigate the issue of the imbalance between positive and negative samples, which produces better results than solely employing either one. Fourth, comprehensive ablation studies are conducted to reveal the effect of each improvement on detected results. The results of the target detection on three data sets are illustrated and our method obtains 0.135, 0.081, 0.115 gains in average precision compared with three state-of-the-art methods, respectively.

关键词： Object detection Feature extraction Detectors Proposals Radar polarimetry Remote sensing encoding Deep convolutional neural network (CNN) encoding scheme feature pyramid network (FPN) focal loss (FL) prior box generation rotatable box target detection

来源：评论

学校读者我要写书评

暂无评论

A hybrid BGWO with KPCA for intrusion detection

引用

JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE 2020年第1期32卷 165-180页

作者： Velliangiri, S. CMR Inst Technol Dept Comp Sci & Engn Medchal Rd Hyderabad 501401 Telangana India

Intrusion detection is the primary model for giving security to the network. There are numerous issues with conventional intrusion detection models (for example, low detection ability against obscure arranges attack, high false caution rate, and inadequate investigation ability). The real challenging in design IDS with enhanced precision and diminished the training time. This paper come up with hybrid intrusion detection model by incorporating the kernel principal component analysis (KPCA) and binary grey wolf optimization (BGWO) with support vector machine (SVM). The curiosity of the paper is the headway of part parameters of the SVM classifier using the customized parameter assurance procedure. This proposed hybrid method streamlines the discipline factor (C) and kernel parameters (sigma) and the size of tube epsilon of SVM, like this enhancing the precision of the classifier and reduces the testing and training time.

关键词： Binary grey wolf optimization intrusion detection encoding scheme support vector machine and kernel principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Compression XML encoding scheme of Supporting Updating Data Completely

Compression XML Encoding Scheme of Supporting Updating Data ...

引用

International Workshop on Intelligent Communication and Social Networks

作者： Zhenxi Lei Zhou Zhou Xianfeng Liu Gaocai Wang Hunan Science and Technology Economy Trade Vocation College School of Software Central South University College of Mathematics and Computer Science Hunan Normal University School of Computer and Electronic Information Guangxi University

ISBN: (纸本)9781479909735

In order to update and query XML data effectively, a new XML encoding scheme named fraction and path encoding scheme (FAPE) is proposed. FAPE makes good use of the fraction characteristic that is unlimited fractions can be inserted between any two fractions. Besides, FAPE puts information of XML nodes into corresponding tables to avoid recording the same information. The experimental results show that FAPE saves storage space and improves efficiency of querying compared with other encoding scheme.

关键词： XML encoding scheme FAPE Fraction and path encoding scheme Efficiency of querying

来源：评论

学校读者我要写书评

暂无评论

Application of Constrained Multi-objective Evolutionary Algorithm in a Compressed-air Station Scheduling Problem 38

Application of Constrained Multi-objective Evolutionary Algo...

引用

38th Chinese Control Conference (CCC)

作者： Liu, Jianchang Yang, Yongkuan Tan, Shubin Wang, Honghai Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China

ISBN: (纸本)9789881563972

The compressor station is the utility that generates the compressed-air. This paper aims to present the formulation of the operation scheduling optimization problem for a compressor station, and apply a constrained multi-objective evolutionary algorithm, named CMOEA/D-CDP, to solve the problem. For this problem, it can be defined as one of the nonlinear 0-1 mixed integer multi-objective optimization problems due to the decision variables including continuous variables and 0-1 integer variables. In light of the relation between the unit commitment and rotational speed of a compressor station, a special encoding scheme which decreases the dimension of decision variables is proposed to change this nonlinear 0-1 mixed integer multi-objective optimization problem into a nonlinear continuous multi-objective optimization problem. The result obtained by CMOEA/D-CDP is a set of Pareto optimal solutions, which can help a decision maker select a specific preferred solution to guide the production under the different limits of objectives. Experimental results on two typical compressor stations indicate that the proposed encoding scheme shows apparent superiority compared to the normal encoding method.

关键词： Compressed-air station CMOEA/D-CDP Constrained multi-objective optimization encoding scheme Optimal scheduling of compressor station

来源：评论

学校读者我要写书评

暂无评论

An approach of top-k keyword querying for fuzzy XML

引用

COMPUTING 2018年第3期100卷 303-330页

作者： Ma, Zongmin Li, Ting Yan, Li Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 211106 Jiangsu Peoples R China Qilu Univ Technol Sch Informat Jinan 250353 Shandong Peoples R China

Keyword search on XML document has received wide attention. Many search semantics and algorithms have been proposed for XML keyword queries. But the existing approaches fall short in their abilities to support keyword queries over fuzzy XML documents. To overcome this limitation, in this paper, we discuss how to obtain and evaluate top-k smallest lowest common ancestor (SLCA) results of keyword queries on fuzzy XML documents. We define the fuzzy SLCA semantics on the fuzzy XML document, and then propose a novel encoding scheme to denote different types of nodes in fuzzy XML documents. After these, we propose two efficient algorithms to find k SLCA results with highest possibilities for a given keyword query on the fuzzy XML document. First one is an algorithm which can obtain the top-k SLCA results and their possibilities based on the stack technique. The second algorithm can obtain top-k SLCA results of keyword queries based on a set of SLCA's properties. Finally, we compare and evaluate the performances of the two algorithms.

关键词： SLCA Keyword query Fuzzy XML encoding scheme

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：