Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963113
M. Chowdhury, M. K. Jahan, Silvia Shukla Karmokar, S. Mahmud
In this research paper we have introduced a new security system where user will set the password based on any colors and the system will be unlocked only with colors. Each color is a combination of Red, Green & Blue color. Any given color by the user consists of 16 bits Red, 16 bits green & 16 bit Blue color. So the total depth of any given color is 48 bits. The user can choose any random 4 to 6 colors as his/her password. Then the user will provide these passwords through RGB LEDs to the system. If the password matches, the system will be unlocked. For wrong password, alarm will be turned on. It's quite a bit impossible for the hacker/fraud to hack/break the system password as the value of any color lies between 0 to 2̂∧48(16 bits Red +16 bits Green+16 bits Blue). This security system can be used to prevent any unauthorized access to start/stop a computer or any machine.
{"title":"Color lock: 16 bit digital color based security system","authors":"M. Chowdhury, M. K. Jahan, Silvia Shukla Karmokar, S. Mahmud","doi":"10.1109/ICCCNT.2014.6963113","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963113","url":null,"abstract":"In this research paper we have introduced a new security system where user will set the password based on any colors and the system will be unlocked only with colors. Each color is a combination of Red, Green & Blue color. Any given color by the user consists of 16 bits Red, 16 bits green & 16 bit Blue color. So the total depth of any given color is 48 bits. The user can choose any random 4 to 6 colors as his/her password. Then the user will provide these passwords through RGB LEDs to the system. If the password matches, the system will be unlocked. For wrong password, alarm will be turned on. It's quite a bit impossible for the hacker/fraud to hack/break the system password as the value of any color lies between 0 to 2̂∧48(16 bits Red +16 bits Green+16 bits Blue). This security system can be used to prevent any unauthorized access to start/stop a computer or any machine.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128964624","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}
Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963103
He Lin, Mengyao Nie, LingYue Li
The concept of parallel equivalence operator arises from the equivalence operator and the pansystems series-parallel model, by which a family of arbitrary binary relations can be converted into equivalence relations. This paper presents the pansystems rough set based on parallel equivalence operator, which provides a new thought to process rough sets with non-equivalence relations(incomplete, uncertain, or vague information), as well as makes the rough set theory more practical in applications.
{"title":"The extension of the rough set theory based on parallel equivalence operator in pansystems","authors":"He Lin, Mengyao Nie, LingYue Li","doi":"10.1109/ICCCNT.2014.6963103","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963103","url":null,"abstract":"The concept of parallel equivalence operator arises from the equivalence operator and the pansystems series-parallel model, by which a family of arbitrary binary relations can be converted into equivalence relations. This paper presents the pansystems rough set based on parallel equivalence operator, which provides a new thought to process rough sets with non-equivalence relations(incomplete, uncertain, or vague information), as well as makes the rough set theory more practical in applications.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"25 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129856260","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}
Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963107
M. Kazemi, R. Azmi
The wireless network is become larger than past. So in the recent years the wireless with multiple sinks is more useful. The anonymity and privacy in this network is a challenge now. In this paper, we propose a new method for anonymity in multi sink wireless sensor network. In this method we use layer encryption to provide source and event privacy and we use a label switching routing method to provide sink anonymity in each cluster. A master sink that is a powerful base station is used to connect sinks to each other.
{"title":"Privacy preserving and anonymity in multi sinks wireless sensor networks with master sink","authors":"M. Kazemi, R. Azmi","doi":"10.1109/ICCCNT.2014.6963107","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963107","url":null,"abstract":"The wireless network is become larger than past. So in the recent years the wireless with multiple sinks is more useful. The anonymity and privacy in this network is a challenge now. In this paper, we propose a new method for anonymity in multi sink wireless sensor network. In this method we use layer encryption to provide source and event privacy and we use a label switching routing method to provide sink anonymity in each cluster. A master sink that is a powerful base station is used to connect sinks to each other.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122009152","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}
Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963105
Zhan Shi, Xiaoqin Zeng, Song Huang, Hui Li, Bing Hu, Xiaoyu Lei, Yi Wang
As a graphical language, the Business Process Modelling Notation (BPMN) plays an important role in enterprise information systems. BPMN is a standard notation for capturing business processes, while Business Process Execution Language (BPEL) provides a standard executable language for specifying business process compositions and interactions. This paper proposes a new method based on graph grammars to map from BPMN to BPEL codes. In the first place, the existing Edge-based Graph Grammar (EGG) is introduced, which is a context-sensitive grammar and a new formal method for simply specifying graph grammars. Secondly, some aspects of EGGs are extended to conveniently map from BPMN to BPEL. Finally, new mapping steps and a parsing algorithm are put forward, which achieve a goal of this paper.
{"title":"Transformation between BPMN and BPEL based on graph grammar","authors":"Zhan Shi, Xiaoqin Zeng, Song Huang, Hui Li, Bing Hu, Xiaoyu Lei, Yi Wang","doi":"10.1109/ICCCNT.2014.6963105","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963105","url":null,"abstract":"As a graphical language, the Business Process Modelling Notation (BPMN) plays an important role in enterprise information systems. BPMN is a standard notation for capturing business processes, while Business Process Execution Language (BPEL) provides a standard executable language for specifying business process compositions and interactions. This paper proposes a new method based on graph grammars to map from BPMN to BPEL codes. In the first place, the existing Edge-based Graph Grammar (EGG) is introduced, which is a context-sensitive grammar and a new formal method for simply specifying graph grammars. Secondly, some aspects of EGGs are extended to conveniently map from BPMN to BPEL. Finally, new mapping steps and a parsing algorithm are put forward, which achieve a goal of this paper.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122420158","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}
Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963100
Dong Zhao, M. Zhu, Ming Xu
Currently, enterprise WLAN is facing rapid growth of user scale and traffic load, as well as constantly emerging new features. However, traditional enterprise WLAN architecture suffers from poor flexibility and the lack of coordination between wireless access points (APs) and wired backbone. Inspired by the emerging idea of Software-Defined Networking (SDN), we proposed SDWLAN, an alternative architecture for enterprise WLAN. The salient features of SDWLAN are twofold. First, most of 802.11 AP functions are decoupled from scattered devices and centralized in a controller, leaving some simplified devices (i.e., wireless access switches, or WASes) manipulated by the controller through extended OpenFlow protocol. Second, the control of APs and wired backbone are consolidated to provide a unified network control platform. By reorganizing 802.11 AP's functional modules, SDWLAN can achieve remarkable flexibility. Benefiting from the extended OpenFlow protocol and the unified control platform, we proposed a client-unaware fast AP handoff mechanism in SDWLAN. Simulation results demonstrated that AP handoff operation in SDWLAN leads to negligible throughput fluctuation of on-going connection compared to traditional architecture with 802.11 standard handoff mechanism. Furthermore, SDWLAN requires no modification to existing 802.11 clients, which make our solution practical.
{"title":"SDWLAN: A flexible architecture of enterprise WLAN for client-unaware fast AP handoff","authors":"Dong Zhao, M. Zhu, Ming Xu","doi":"10.1109/ICCCNT.2014.6963100","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963100","url":null,"abstract":"Currently, enterprise WLAN is facing rapid growth of user scale and traffic load, as well as constantly emerging new features. However, traditional enterprise WLAN architecture suffers from poor flexibility and the lack of coordination between wireless access points (APs) and wired backbone. Inspired by the emerging idea of Software-Defined Networking (SDN), we proposed SDWLAN, an alternative architecture for enterprise WLAN. The salient features of SDWLAN are twofold. First, most of 802.11 AP functions are decoupled from scattered devices and centralized in a controller, leaving some simplified devices (i.e., wireless access switches, or WASes) manipulated by the controller through extended OpenFlow protocol. Second, the control of APs and wired backbone are consolidated to provide a unified network control platform. By reorganizing 802.11 AP's functional modules, SDWLAN can achieve remarkable flexibility. Benefiting from the extended OpenFlow protocol and the unified control platform, we proposed a client-unaware fast AP handoff mechanism in SDWLAN. Simulation results demonstrated that AP handoff operation in SDWLAN leads to negligible throughput fluctuation of on-going connection compared to traditional architecture with 802.11 standard handoff mechanism. Furthermore, SDWLAN requires no modification to existing 802.11 clients, which make our solution practical.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125735975","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}
Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963091
P. Das, Utpal Bhatacharjee
This paper proposes a new approach of noise reduction based on the analysis of MFCC feature space using self-organizing map network. Here the U-matrix plot of the feature space is analyzed in presence of white noise at different signal to noise ratio. Based on the observation, boundary neurons separating clusters are identified in the feature space. For each such neuron in the boundary, its 2-D feature vector is extracted from the U-matrix and hit matrix. This collection of feature vectors based on the boundary neurons are eliminated from the original feature space. Thus the new feature space obtained is used to perform the tasks of visualization and speaker verification. Experiments were carried out by combining synthetic white noise with real world data sets.
{"title":"Robust speaker verification using self organizing map","authors":"P. Das, Utpal Bhatacharjee","doi":"10.1109/ICCCNT.2014.6963091","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963091","url":null,"abstract":"This paper proposes a new approach of noise reduction based on the analysis of MFCC feature space using self-organizing map network. Here the U-matrix plot of the feature space is analyzed in presence of white noise at different signal to noise ratio. Based on the observation, boundary neurons separating clusters are identified in the feature space. For each such neuron in the boundary, its 2-D feature vector is extracted from the U-matrix and hit matrix. This collection of feature vectors based on the boundary neurons are eliminated from the original feature space. Thus the new feature space obtained is used to perform the tasks of visualization and speaker verification. Experiments were carried out by combining synthetic white noise with real world data sets.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115098966","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}
Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963141
P. Murugeswari, A. P. Kabilan, M. Vaishnavi, C. Divya
The semiconductor industry is facing a crucial problem in the interconnect section when IC is scaled down below 32 nm technology. Scaling increases the number of devices per unit area, which in turn increases the performance of the transistor resulting in the overall increase of performance per unit area. But there is a decrease in the performance of interconnect especially in that of global interconnect. The reduction in the cross section of copper interconnects in accordance with technology scaling, increases the resistivity due to size effects. This increase in resistivity affects performance, namely delay and current carrying capability of copper interconnect. Carbon nanotube is proposed as the replacement for copper to alleviate the bottleneck in all levels of interconnects because it has high mean free path and ballistic transport. The performance evaluation of both single-walled carbon nanotube and multi-walled carbon nanotube interconnect delay is carried out and the results are compared with that of the copper interconnects. Both the CNTs and copper interconnects are examined thoroughly with the help of HSPICE simulation using its transmission line model. Comparison shows that MWCNT is the most promising candidate for local, intermediate and global levels of interconnects.
{"title":"Performance analysis of single-walled carbon nanotube and multi-walled carbon nanotube in 32nm technology for on-chip interconnect applications","authors":"P. Murugeswari, A. P. Kabilan, M. Vaishnavi, C. Divya","doi":"10.1109/ICCCNT.2014.6963141","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963141","url":null,"abstract":"The semiconductor industry is facing a crucial problem in the interconnect section when IC is scaled down below 32 nm technology. Scaling increases the number of devices per unit area, which in turn increases the performance of the transistor resulting in the overall increase of performance per unit area. But there is a decrease in the performance of interconnect especially in that of global interconnect. The reduction in the cross section of copper interconnects in accordance with technology scaling, increases the resistivity due to size effects. This increase in resistivity affects performance, namely delay and current carrying capability of copper interconnect. Carbon nanotube is proposed as the replacement for copper to alleviate the bottleneck in all levels of interconnects because it has high mean free path and ballistic transport. The performance evaluation of both single-walled carbon nanotube and multi-walled carbon nanotube interconnect delay is carried out and the results are compared with that of the copper interconnects. Both the CNTs and copper interconnects are examined thoroughly with the help of HSPICE simulation using its transmission line model. Comparison shows that MWCNT is the most promising candidate for local, intermediate and global levels of interconnects.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124256700","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}
Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963143
G. Garg, S. Kaushal, Akashdeep Sharma
Ad-hoc Networks are constantly prone to variety of attacks at different layers because of its features. Wormhole attack is one of the severe attacks which can be implemented in five different modes. This attack acts as a curse as well as boon for the network users. This paper presents the analysis of reactive protocols (AODV, DSR, DYMO, ANODR) with wormhole attack in both mobile and non-mobile ad-hoc networks. Simulations are carried out under Qualnet 4.5.
{"title":"Reactive protocols analysis with wormhole attack in ad-hoc networks","authors":"G. Garg, S. Kaushal, Akashdeep Sharma","doi":"10.1109/ICCCNT.2014.6963143","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963143","url":null,"abstract":"Ad-hoc Networks are constantly prone to variety of attacks at different layers because of its features. Wormhole attack is one of the severe attacks which can be implemented in five different modes. This attack acts as a curse as well as boon for the network users. This paper presents the analysis of reactive protocols (AODV, DSR, DYMO, ANODR) with wormhole attack in both mobile and non-mobile ad-hoc networks. Simulations are carried out under Qualnet 4.5.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"102 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120877101","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}
Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963067
Wang Hong, Su Yanshen, Yu Xiaomei
Personalized recommendation is one of the most effective methods to solve the problem of information overloading. As many real existing systems in nature, a recommendation system can also be considered as a complex network system, so we can do personalized recommendation by using the link prediction method which is a new one in complex networks research area. In this paper, we present personalized recommendation method based on the link prediction in Super-networks. Firstly, we give several definitions such as a Super-network, a dynamic Super-network and a utility matrix etc. Secondly, we construct a personalized recommendation model based on these definitions. Thirdly, we define a similarity metric for users and some similarity criteria, put forward five link prediction related algorithms in dynamic Supernetworks and present our recommendation algorithms based on these link prediction algorithms. Finally, we apply our methods to classic datasets in order to evaluate the performance of our algorithms.
{"title":"Personalized recommendation based on link prediction in dynamic super-networks","authors":"Wang Hong, Su Yanshen, Yu Xiaomei","doi":"10.1109/ICCCNT.2014.6963067","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963067","url":null,"abstract":"Personalized recommendation is one of the most effective methods to solve the problem of information overloading. As many real existing systems in nature, a recommendation system can also be considered as a complex network system, so we can do personalized recommendation by using the link prediction method which is a new one in complex networks research area. In this paper, we present personalized recommendation method based on the link prediction in Super-networks. Firstly, we give several definitions such as a Super-network, a dynamic Super-network and a utility matrix etc. Secondly, we construct a personalized recommendation model based on these definitions. Thirdly, we define a similarity metric for users and some similarity criteria, put forward five link prediction related algorithms in dynamic Supernetworks and present our recommendation algorithms based on these link prediction algorithms. Finally, we apply our methods to classic datasets in order to evaluate the performance of our algorithms.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121405227","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}
Pub Date : 2014-07-11DOI: 10.1109/ICCCNT.2014.6963078
S. Shinde, U. Kulkarni
The fuzzy hyperline segment neural network (FHLSNN) utilizes fuzzy sets as pattern classes in which each fuzzy set is an union of fuzzy set hyperline segments. The fuzzy set hyperline segment is a n-dimensional hyperline segment defined by two end points with a corresponding membership function. In FHLSNN, membership function calculates membership value of the input pattern based on its distance from both the end points of the hyperline segment. But sometimes input pattern is nearer to the hyperline segment but far from its endpoints. To solve this problem, this paper proposes modified fuzzy hyperline segment neural network (MFHLSNN). In MHLSNN membership function is based on minimum of the distance of the input pattern from the midpoint of the hyperline segment and its distance from both the end points. The proposed model is applied to eight different benchmark datasets taken from the UCI machine learning repository. The experimental results of the MFHLSNN are compared with earlier methods like fuzzy min-max neural network, generalized fuzzy min-max neural network and fuzzy hyperline segment neural network. These results show that the MFHLSNN gives improved performance as compared to its earlier methods.
{"title":"Modified fuzzy hyperline-segment neural network for classification with mixed attribues","authors":"S. Shinde, U. Kulkarni","doi":"10.1109/ICCCNT.2014.6963078","DOIUrl":"https://doi.org/10.1109/ICCCNT.2014.6963078","url":null,"abstract":"The fuzzy hyperline segment neural network (FHLSNN) utilizes fuzzy sets as pattern classes in which each fuzzy set is an union of fuzzy set hyperline segments. The fuzzy set hyperline segment is a n-dimensional hyperline segment defined by two end points with a corresponding membership function. In FHLSNN, membership function calculates membership value of the input pattern based on its distance from both the end points of the hyperline segment. But sometimes input pattern is nearer to the hyperline segment but far from its endpoints. To solve this problem, this paper proposes modified fuzzy hyperline segment neural network (MFHLSNN). In MHLSNN membership function is based on minimum of the distance of the input pattern from the midpoint of the hyperline segment and its distance from both the end points. The proposed model is applied to eight different benchmark datasets taken from the UCI machine learning repository. The experimental results of the MFHLSNN are compared with earlier methods like fuzzy min-max neural network, generalized fuzzy min-max neural network and fuzzy hyperline segment neural network. These results show that the MFHLSNN gives improved performance as compared to its earlier methods.","PeriodicalId":140744,"journal":{"name":"Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"257 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122466374","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：