发布求助
文献互助 智能选刊 最新文献

Journal of Applied Computer Science Methods最新文献

筛选
英文 中文
Convergence Analysis of Inverse Iterative Neural Networks with L2 Penalty 具有L2惩罚的逆迭代神经网络的收敛性分析
Journal of Applied Computer Science Methods Pub Date : 2016-12-01 DOI: 10.1515/jacsm-2016-0006
Yanqing Wen, Jian Wang, Bing-jian Huang, J. Zurada
{"title":"Convergence Analysis of Inverse Iterative Neural Networks with L2 Penalty","authors":"Yanqing Wen, Jian Wang, Bing-jian Huang, J. Zurada","doi":"10.1515/jacsm-2016-0006","DOIUrl":"https://doi.org/10.1515/jacsm-2016-0006","url":null,"abstract":"Abstract The iterative inversion of neural networks has been used in solving problems of adaptive control due to its good performance of information processing. In this paper an iterative inversion neural network with L2 penalty term has been presented trained by using the classical gradient descent method. We mainly focus on the theoretical analysis of this proposed algorithm such as monotonicity of error function, boundedness of input sequences and weak (strong) convergence behavior. For bounded property of inputs, we rigorously proved that the feasible solutions of input are restricted in a measurable field. The weak convergence means that the gradient of error function with respect to input tends to zero as the iterations go to infinity while the strong convergence stands for the iterative sequence of input vectors convergence to a fixed optimal point.","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"66 1","pages":"85 - 98"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/jacsm-2016-0006","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66824982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Low-Cost Dynamic Constraint Checking for the JVM JVM的低成本动态约束检查
Journal of Applied Computer Science Methods Pub Date : 2016-12-01 DOI: 10.1515/jacsm-2016-0008
K. Grzanek
{"title":"Low-Cost Dynamic Constraint Checking for the JVM","authors":"K. Grzanek","doi":"10.1515/jacsm-2016-0008","DOIUrl":"https://doi.org/10.1515/jacsm-2016-0008","url":null,"abstract":"Abstract Using formal methods for software verification slowly becomes a standard in the industry. Overall it is a good idea to integrate as many checks as possible with the programming language. This is a major cause of the apparent success of strong typing in software, either performed on the compile time or dynamically, on runtime. Unfortunately, only some of the properties of software may be expressed in the type system of event the most sophisticated programming languages. Many of them must be performed dynamically. This paper presents a flexible library for the dynamically typed, functional programming language running in the JVM environment. This library offers its users a close to zero run-time overhead and strong mathematical background in category theory.","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"8 1","pages":"115 - 136"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/jacsm-2016-0008","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66824996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Monadic Printing Revisited 单元式印刷重访
Journal of Applied Computer Science Methods Pub Date : 2016-06-01 DOI: 10.1515/jacsm-2016-0005
K. Grzanek
{"title":"Monadic Printing Revisited","authors":"K. Grzanek","doi":"10.1515/jacsm-2016-0005","DOIUrl":"https://doi.org/10.1515/jacsm-2016-0005","url":null,"abstract":"Abstract Expressive and clear implementation of monadic printing requires an amount of work to define and design proper abstractions to rely upon when performing the actual programming works. Our previous realization of tree printing library left us with a sense of lack with respect to these considerations. This is why we decided to re-design and re-implement the library with core algorithms based upon new, effective and expressive text printing and concatenation routines. This paper presents the results of our work.","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"8 1","pages":"69 - 79"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66824924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The Internet of Things: Technological and Social Aspects 物联网:技术和社会方面
Journal of Applied Computer Science Methods Pub Date : 2016-06-01 DOI: 10.1515/jacsm-2016-0002
G. Sowa, A. Marchlewska
{"title":"The Internet of Things: Technological and Social Aspects","authors":"G. Sowa, A. Marchlewska","doi":"10.1515/jacsm-2016-0002","DOIUrl":"https://doi.org/10.1515/jacsm-2016-0002","url":null,"abstract":"Abstract The basic idea of is the Internet of Things is presence around us of a variety of things – such as RFID tags, sensors, actuators, mobile phones, etc. – which are able to interact with each other and cooperate with their neighbors to reach common goals. Semantic oriented IoT visions have also been proposed. The number of items involved in the future Internet is destined to become extremely high. Therefore, issues pertaining how to represent, store, interconnect, search, and organize information generated by the IoT will become very challenging. In this context, semantic technologies will play a key role. And creative approaches to visualizing data – humans are far better than computers at seeing patterns –frequently prove integral to the process of creating knowledge. From a privacy perspective, IoT is challenging because it operates in private settings, like homes, and presents an attack target that is harder to secure.","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"8 1","pages":"17 - 27"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/jacsm-2016-0002","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66824669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Resource Monitoring for Wireless Sensor Networks using ANFIS 基于ANFIS的无线传感器网络资源监控
Journal of Applied Computer Science Methods Pub Date : 2016-06-01 DOI: 10.1515/jacsm-2016-0004
Nagesha, S. Manvi
{"title":"Resource Monitoring for Wireless Sensor Networks using ANFIS","authors":"Nagesha, S. Manvi","doi":"10.1515/jacsm-2016-0004","DOIUrl":"https://doi.org/10.1515/jacsm-2016-0004","url":null,"abstract":"Abstract Wireless sensor networks (WSNs) are usually a resource constrained networks which have limited energy, bandwidth, processing power, memory etc. These networks are now part of Internet by the name Internet of Things (IoT). To get many services from WSNs, we may need to run many applications in the sensor nodes which consumes resources. Ideally, the resources availability of all sensor nodes should be known to the sink before it requests for any further service(s) from the sensor node(s). Hence, continuous monitoring of the resources of the sensor nodes by the sink is essential. The proposed work is a framework for monitoring certain important resources of sensor network using Adaptive-Neuro Fuzzy Inference System (ANFIS) and Constrained Application Protocol (CoAP). The ANFIS is trained with these resources consumption patterns. The input to ANFIS is the resources consumption levels and the output is the resources consumed levels that needs to be sent to the sink which may be individual or combinations of resources. The trained ANFIS generates the output periodically which determines resources consumption levels that needs to be sent to the sink. Also, ANFIS continuously learns using hybrid learning algorithm (which is basically a combination of back propagation and least squares method) and updates its parameters for better results. The CoAP protocol with its observe option is used to transport the resource monitoring data from the sensor nodes to the cluster head, then from the cluster head to the sink. The sensor nodes runs coap server, the cluster head runs both coap client and server and the sink runs coap client. The performance of the proposed work is compared with LoWPAN network management protocol (LNMP) and EmNets Network Management Protocol (EMP) in terms of bandwidth and energy overheads. It is observed that proposed work performs better when compared to the existing works.","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"8 1","pages":"41 - 67"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/jacsm-2016-0004","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66824768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Convergence Analysis of An Improved Extreme Learning Machine Based on Gradient Descent Method 一种改进的基于梯度下降法的极限学习机收敛性分析
Journal of Applied Computer Science Methods Pub Date : 2016-06-01 DOI: 10.1515/jacsm-2016-0001
Liu Yusong, Su Zhixun, Zhang Bingjie, Gong Xiaoling, Sang Zhaoyang
{"title":"Convergence Analysis of An Improved Extreme Learning Machine Based on Gradient Descent Method","authors":"Liu Yusong, Su Zhixun, Zhang Bingjie, Gong Xiaoling, Sang Zhaoyang","doi":"10.1515/jacsm-2016-0001","DOIUrl":"https://doi.org/10.1515/jacsm-2016-0001","url":null,"abstract":"Abstract Extreme learning machine (ELM) is an efficient algorithm, but it requires more hidden nodes than the BP algorithms to reach the matched performance. Recently, an efficient learning algorithm, the upper-layer-solution-unaware algorithm (USUA), is proposed for the single-hidden layer feed-forward neural network. It needs less number of hidden nodes and testing time than ELM. In this paper, we mainly give the theoretical analysis for USUA. Theoretical results show that the error function monotonously decreases in the training procedure, the gradient of the error function with respect to weights tends to zero (the weak convergence), and the weight sequence goes to a fixed point (the strong convergence) when the iterations approach positive infinity. An illustrated simulation has been implemented on the MNIST database of handwritten digits which effectively verifies the theoretical results..","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"57 1","pages":"15 - 5"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/jacsm-2016-0001","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66824609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Medical-Grade Network Security - Air-Gap Isolation and PossibleWeak Points 医疗级网络安全-气隙隔离和可能的弱点
Journal of Applied Computer Science Methods Pub Date : 2016-01-01 DOI: 10.34658/JACS.2016.24.3.7-19
Daniel Arendt
{"title":"Medical-Grade Network Security - Air-Gap Isolation and PossibleWeak Points","authors":"Daniel Arendt","doi":"10.34658/JACS.2016.24.3.7-19","DOIUrl":"https://doi.org/10.34658/JACS.2016.24.3.7-19","url":null,"abstract":"","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"54 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80755500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Selected Examples of Applications of New Graphics and Animation Technologies 新图形和动画技术应用的精选例子
Journal of Applied Computer Science Methods Pub Date : 2016-01-01 DOI: 10.1515/jacsm-2016-0003
Z. Filutowicz, K. Przybyszewski, J. Paszkowski
{"title":"Selected Examples of Applications of New Graphics and Animation Technologies","authors":"Z. Filutowicz, K. Przybyszewski, J. Paszkowski","doi":"10.1515/jacsm-2016-0003","DOIUrl":"https://doi.org/10.1515/jacsm-2016-0003","url":null,"abstract":"Abstract In recent years there has been a marked increase in the competitiveness of some very interesting (user) applications software within the field of computer graphics and animation. This paper presents an analysis of selected examples of the use of graphic applications software designed for professional use within various areas of human activity, and also focusses on the potential for further development of this software. Graphic applications software that makes use of motion capture, performance capture, time-lapse, morphing, Augmented Reality and the use of avatars in human-computer communication has become increasingly popular, cheap and simple.","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"8 1","pages":"29 - 40"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/jacsm-2016-0003","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66824679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Performance Analysis of Virtual Computer Network Based on Cisco Cloud Services Router 1000V in a Private Cloud Environment 私有云环境下基于Cisco云服务路由器1000V的虚拟计算机网络性能分析
Journal of Applied Computer Science Methods Pub Date : 2015-11-01 DOI: 10.1515/jacsm-2015-0013
Stanislaw Lota, M. Markowski
{"title":"Performance Analysis of Virtual Computer Network Based on Cisco Cloud Services Router 1000V in a Private Cloud Environment","authors":"Stanislaw Lota, M. Markowski","doi":"10.1515/jacsm-2015-0013","DOIUrl":"https://doi.org/10.1515/jacsm-2015-0013","url":null,"abstract":"Abstract Virtualization of physical network devices is a relatively new technology, that allows to improve the network organization and gives new possibilities for Software Defined Networking (SDN). Network virtualization is also commonly used for testing and debugging environments, before implementing new designs in production networks. Important aspect of network virtualization is selecting virtual platform and technology, that offer maximal performance with minimal physical resource utilization. This article presents a comparative analysis of performance of the virtual network created by the virtual CSR1000v and virtual machines running Windows 8.1 on two different virtual private cloud platforms: VMware vSphere 5.5 and Microsoft Hyper-V Server 2012 R2. In such prepared testbed we study the response time (delay) and throughput of virtual network devices.","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"7 1","pages":"117 - 132"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/jacsm-2015-0013","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66824595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Convergence Analysis of Multilayer Feedforward Networks Trained with Penalty Terms: A Review 用惩罚项训练的多层前馈网络的收敛性分析
Journal of Applied Computer Science Methods Pub Date : 2015-11-01 DOI: 10.1515/jacsm-2015-0011
Jian Wang, G. Yang, Shang-Wen Liu, J. Zurada
{"title":"Convergence Analysis of Multilayer Feedforward Networks Trained with Penalty Terms: A Review","authors":"Jian Wang, G. Yang, Shang-Wen Liu, J. Zurada","doi":"10.1515/jacsm-2015-0011","DOIUrl":"https://doi.org/10.1515/jacsm-2015-0011","url":null,"abstract":"Abstract Gradient descent method is one of the popular methods to train feedforward neural networks. Batch and incremental modes are the two most common methods to practically implement the gradient-based training for such networks. Furthermore, since generalization is an important property and quality criterion of a trained network, pruning algorithms with the addition of regularization terms have been widely used as an efficient way to achieve good generalization. In this paper, we review the convergence property and other performance aspects of recently researched training approaches based on different penalization terms. In addition, we show the smoothing approximation tricks when the penalty term is non-differentiable at origin.","PeriodicalId":89404,"journal":{"name":"Journal of Applied Computer Science Methods","volume":"7 1","pages":"103 - 89"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/jacsm-2015-0011","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66824544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书