Recently, cyber security to protect information systems or personal information against threats of the internet is big issue. We are studying a distributed autonomous cooperative system about exclusive Web crawling for cyber security. The system is divided into three subsystems, that is, Web space projection system, autonomous cooperative Web crawler, and the crawler runtime environment. The Web crawlers to collect Web sites effectively and exclusively. In addition, by introduction of virtualization technology to crawler runtime environment, dynamic reconstruction for effective detection of malicious Web sites is realized. This paper only discusses about design of the Web crawler and its runtime environment. Future works are development of the crawler and the runtime environment, and evaluation.
{"title":"A Proposal of Distributed Autonomous Cooperative System about Exclusive Web Crawling for Cyber Security","authors":"Yoshihiro Kawano, Eiji Nunohiro","doi":"10.1109/NBiS.2016.34","DOIUrl":"https://doi.org/10.1109/NBiS.2016.34","url":null,"abstract":"Recently, cyber security to protect information systems or personal information against threats of the internet is big issue. We are studying a distributed autonomous cooperative system about exclusive Web crawling for cyber security. The system is divided into three subsystems, that is, Web space projection system, autonomous cooperative Web crawler, and the crawler runtime environment. The Web crawlers to collect Web sites effectively and exclusively. In addition, by introduction of virtualization technology to crawler runtime environment, dynamic reconstruction for effective detection of malicious Web sites is realized. This paper only discusses about design of the Web crawler and its runtime environment. Future works are development of the crawler and the runtime environment, and evaluation.","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121376985","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}
Today, many people are constantly using user-generated recipe sites when they prepare their meals. Users search for recipes for their meals from the recipe sites. However, when they search for a recipe using an ingredient name, numerous similar pages which are coincidentally similar or which have been plagiarized are found for them. Moreover, a user who searches for a recipe usually does not select a high-ranking recipe from the search results, reacting better than one might with usual web searches. Given many similar recipes included in the search results, it appears to be difficult for them to compare multiple recipes. Actually, when users compare similar recipes, they must better understand the different points of similar recipes. That need for comparison imposes a great burden on users. Therefore, a system classifying the results of user searches according to similar pages in real time would be beneficial for users. In this paper, we propose a clustering method for user-generated recipe sites based on page structure and main ingredient and main seasoning of the food. It provides a means of classifying the user search results according to similar pages. We conducted an experiment to measure the benefits of our proposed method. The experiment results presents the benefits of our proposed method, which classifies similar recipes based on the main ingredients and main seasonings.
{"title":"Clustering for Similar Recipes in User-Generated Recipe Sites Based on Main Ingredients and Main Seasoning","authors":"Akiyo Nadamoto, Shunsuke Hanai, Hidetsugu Nanba","doi":"10.1109/NBiS.2016.49","DOIUrl":"https://doi.org/10.1109/NBiS.2016.49","url":null,"abstract":"Today, many people are constantly using user-generated recipe sites when they prepare their meals. Users search for recipes for their meals from the recipe sites. However, when they search for a recipe using an ingredient name, numerous similar pages which are coincidentally similar or which have been plagiarized are found for them. Moreover, a user who searches for a recipe usually does not select a high-ranking recipe from the search results, reacting better than one might with usual web searches. Given many similar recipes included in the search results, it appears to be difficult for them to compare multiple recipes. Actually, when users compare similar recipes, they must better understand the different points of similar recipes. That need for comparison imposes a great burden on users. Therefore, a system classifying the results of user searches according to similar pages in real time would be beneficial for users. In this paper, we propose a clustering method for user-generated recipe sites based on page structure and main ingredient and main seasoning of the food. It provides a means of classifying the user search results according to similar pages. We conducted an experiment to measure the benefits of our proposed method. The experiment results presents the benefits of our proposed method, which classifies similar recipes based on the main ingredients and main seasonings.","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127395410","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}
S. Tanimoto, Shunsuke Shiraki, M. Iwashita, Tohru Kobayashi, Hiroyuki Sato, Atsushi Kanai
Temporary communications networks need to established during a disaster, such as an earthquake. Thus, ad hoc networks have been attracting attention, particularly use of a mobile or smart phone for a mobile ad hoc network. However, a mobile or smart phone contains much personal information, a list of telephone numbers, etc. Therefore, security of a mobile ad hoc network must be investigated. This paper describes the risk assessment supposing the case where a mobile or smart phone is used for an ad hoc network. Thus, the risk factor of the mobile ad hoc network on the mobile or smart phone is extracted and analyzed, and future proposed measures are clarified. This contributes to achieving a mobile ad hoc network that is safe and secure from a user's viewpoint.
{"title":"Risk Assessment Based on User's Viewpoint for Mobile Ad Hoc Network","authors":"S. Tanimoto, Shunsuke Shiraki, M. Iwashita, Tohru Kobayashi, Hiroyuki Sato, Atsushi Kanai","doi":"10.1109/NBiS.2016.30","DOIUrl":"https://doi.org/10.1109/NBiS.2016.30","url":null,"abstract":"Temporary communications networks need to established during a disaster, such as an earthquake. Thus, ad hoc networks have been attracting attention, particularly use of a mobile or smart phone for a mobile ad hoc network. However, a mobile or smart phone contains much personal information, a list of telephone numbers, etc. Therefore, security of a mobile ad hoc network must be investigated. This paper describes the risk assessment supposing the case where a mobile or smart phone is used for an ad hoc network. Thus, the risk factor of the mobile ad hoc network on the mobile or smart phone is extracted and analyzed, and future proposed measures are clarified. This contributes to achieving a mobile ad hoc network that is safe and secure from a user's viewpoint.","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126920576","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}
A. Khan, Mudassir Ejaz, N. Javaid, Muhammad Qaisar Azeemi, U. Qasim, Z. Khan
In this paper, an energy efficient optimal relay selection protocol is proposed for underwater wireless sensor networks (UWSNs). Sensor nodes are randomly deployed in a three dimensional underwater network and is partitioned into three zones based on depth. The mid zone contains the relay nodes. Nodes in the relay zone are assigned values on the bases of location and depth. Nodes residing in the center of the relay zone are assigned highest location values. These values decrease as the nodes become farther from the center. Values are also assigned to the relay nodes based on depth. The optimal relay is the one having the highest (maximum) location and depth values. If the optimal relay is within the transmission range of the source nodes in the bottom zone, they send the data packets to the optimal relay that further forwards them to the sink. Direct transmission from source to sink at the expense of more energy is accomplished when the optimal relay lies outside the transmission range of the source nodes. Nodes in the top zone send data directly to sink. Relay nodes in the mid zone send the data to sink either directly or through the optimal relay node. When the most optimal relay node dies, the second optimal node becomes the most optimal relay node. Simulation results show that the proposed scheme outperforms the counterpart scheme in terms of energy efficiency due to the selection of the optimal relay.
{"title":"EEORS: Energy Efficient Optimal Relay Selection Protocol for Underwater WSNs","authors":"A. Khan, Mudassir Ejaz, N. Javaid, Muhammad Qaisar Azeemi, U. Qasim, Z. Khan","doi":"10.1109/NBiS.2016.74","DOIUrl":"https://doi.org/10.1109/NBiS.2016.74","url":null,"abstract":"In this paper, an energy efficient optimal relay selection protocol is proposed for underwater wireless sensor networks (UWSNs). Sensor nodes are randomly deployed in a three dimensional underwater network and is partitioned into three zones based on depth. The mid zone contains the relay nodes. Nodes in the relay zone are assigned values on the bases of location and depth. Nodes residing in the center of the relay zone are assigned highest location values. These values decrease as the nodes become farther from the center. Values are also assigned to the relay nodes based on depth. The optimal relay is the one having the highest (maximum) location and depth values. If the optimal relay is within the transmission range of the source nodes in the bottom zone, they send the data packets to the optimal relay that further forwards them to the sink. Direct transmission from source to sink at the expense of more energy is accomplished when the optimal relay lies outside the transmission range of the source nodes. Nodes in the top zone send data directly to sink. Relay nodes in the mid zone send the data to sink either directly or through the optimal relay node. When the most optimal relay node dies, the second optimal node becomes the most optimal relay node. Simulation results show that the proposed scheme outperforms the counterpart scheme in terms of energy efficiency due to the selection of the optimal relay.","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131161592","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}
Optical pulse wave propagation in nonlinear and dispersive medium is simulated by constrained interpolated profile (CIP) method. In one dimensional space with dispersion and nonlinearity, Gaussian envelope pulse modulated by optical carrier wave propagates successfully with physically reliable behavior for variety of electric field amplitudes, showing the spreading and the concentrating envelope wave form. The spreading and compressing effect for small and large input amplitudes are considered to be caused by trade-off between linear dispersion and nonlinear refractive index modulation of the medium.
{"title":"Control of Envelope Pulse through Nonlinear and Dispersive Medium","authors":"H. Maeda, Jianming Jin, Kazuya Tomiura","doi":"10.1109/NBiS.2016.65","DOIUrl":"https://doi.org/10.1109/NBiS.2016.65","url":null,"abstract":"Optical pulse wave propagation in nonlinear and dispersive medium is simulated by constrained interpolated profile (CIP) method. In one dimensional space with dispersion and nonlinearity, Gaussian envelope pulse modulated by optical carrier wave propagates successfully with physically reliable behavior for variety of electric field amplitudes, showing the spreading and the concentrating envelope wave form. The spreading and compressing effect for small and large input amplitudes are considered to be caused by trade-off between linear dispersion and nonlinear refractive index modulation of the medium.","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114630676","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}
Dilawaer Duolikun, Ryoma Watanabe, T. Enokido, M. Takizawa
In order to realize eco-society, we have to reduce the electric energy consumed by servers in a cluster in addition to satisfying performance requirements. Virtual machines are now widely used to support applications with virtual computation service in clusters like cloud computing systems. Here, a virtual machine on a host server can migrate to a guest server while processes are being performed on the virtual machine. For example, if the host server of a virtual machine is heavily loaded and a guest server is less loaded, the virtual machine migrates to the guest server. In our previous studies, the EAMV (Energy-Aware Migration of Virtual machines) algorithm is proposed where a virtual machine migrates to a guest server which is expected to consume smaller electric energy to perform processes on the virtual machines. Here, the termination time of each process on each virtual machine is estimated. It is not easy to obtain the state of each process and take time to calculate the expected termination time. In this paper, a virtual machine is considered to be a unit of computation. Termination time of a virtual machine, i.e. time when every process is to terminate on the virtual machine'C is estimated by considering the virtual machines.
为了实现生态社会，除了满足性能要求外，我们还必须减少集群中服务器消耗的电能。虚拟机现在被广泛用于支持云计算系统等集群中具有虚拟计算服务的应用程序。在这里，主机服务器上的虚拟机可以在虚拟机上执行进程时迁移到客户服务器。例如，如果虚拟机的主机服务器负载过重，而客户机服务器负载较轻，则虚拟机将迁移到客户机服务器。在我们之前的研究中，我们提出了EAMV (energy - aware Migration of Virtual machines)算法，其中虚拟机迁移到客户服务器上，预计会消耗更少的电能来执行虚拟机上的进程。这里，估计每个虚拟机上每个进程的终止时间。获取每个进程的状态并不容易，并且需要花费一定的时间来计算预期的终止时间。在本文中，虚拟机被认为是一个计算单元。虚拟机的终止时间，即每个进程在虚拟机上终止的时间，通过考虑虚拟机来估计。
{"title":"A Model for Energy-Aware Migration of Virtual Machines","authors":"Dilawaer Duolikun, Ryoma Watanabe, T. Enokido, M. Takizawa","doi":"10.1109/NBiS.2016.86","DOIUrl":"https://doi.org/10.1109/NBiS.2016.86","url":null,"abstract":"In order to realize eco-society, we have to reduce the electric energy consumed by servers in a cluster in addition to satisfying performance requirements. Virtual machines are now widely used to support applications with virtual computation service in clusters like cloud computing systems. Here, a virtual machine on a host server can migrate to a guest server while processes are being performed on the virtual machine. For example, if the host server of a virtual machine is heavily loaded and a guest server is less loaded, the virtual machine migrates to the guest server. In our previous studies, the EAMV (Energy-Aware Migration of Virtual machines) algorithm is proposed where a virtual machine migrates to a guest server which is expected to consume smaller electric energy to perform processes on the virtual machines. Here, the termination time of each process on each virtual machine is estimated. It is not easy to obtain the state of each process and take time to calculate the expected termination time. In this paper, a virtual machine is considered to be a unit of computation. Termination time of a virtual machine, i.e. time when every process is to terminate on the virtual machine'C is estimated by considering the virtual machines.","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117224572","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}
M. B. Rasheed, M. Awais, N. Javaid, Waseem Nazar, U. Qasim, Z. Khan
In this paper, we investigate some aspects related to microgrid (MG) stability. Due to different applications of MG, its structure and deployment topology vary depending upon the nature of application and operating modes (islanded or grid connected). So, the stability of MGs varies accordingly. This paper precisely explains the stability aspects (e.g., phase angle and power losses) of remotely located islanded MG having the capability to integrate distributed energy sources. Initially, the stability of three bus system is assessed under variable load and find some gaps related to stability as MG involves a high penetration of distributed energy sources. These gaps indicate that stability of a MG is not only in the control of generation/load but also in its coordination with other loads. After that, we implement the load coordination technique and analyze the stability against fixed and dynamic loads. For comprehensive analysis, four different cases are considered in which we vary load at different bus bars and check the performance. Lastly, we integrate the distributed energy source to islanded MG and perform the stability analysis. For validation purpose, extensive simulations of the proposed cases are conducted using Matlab. Simulation results depict that load coordination technique is more efficient regarding MG stability.
{"title":"Transient Stability Analysis of an Islanded Microgrid under Variable Load","authors":"M. B. Rasheed, M. Awais, N. Javaid, Waseem Nazar, U. Qasim, Z. Khan","doi":"10.1109/NBiS.2016.79","DOIUrl":"https://doi.org/10.1109/NBiS.2016.79","url":null,"abstract":"In this paper, we investigate some aspects related to microgrid (MG) stability. Due to different applications of MG, its structure and deployment topology vary depending upon the nature of application and operating modes (islanded or grid connected). So, the stability of MGs varies accordingly. This paper precisely explains the stability aspects (e.g., phase angle and power losses) of remotely located islanded MG having the capability to integrate distributed energy sources. Initially, the stability of three bus system is assessed under variable load and find some gaps related to stability as MG involves a high penetration of distributed energy sources. These gaps indicate that stability of a MG is not only in the control of generation/load but also in its coordination with other loads. After that, we implement the load coordination technique and analyze the stability against fixed and dynamic loads. For comprehensive analysis, four different cases are considered in which we vary load at different bus bars and check the performance. Lastly, we integrate the distributed energy source to islanded MG and perform the stability analysis. For validation purpose, extensive simulations of the proposed cases are conducted using Matlab. Simulation results depict that load coordination technique is more efficient regarding MG stability.","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117287093","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}
With the recent rapid growth of V2X (Vehicle-to-X) developments, there are many expectations for the purpose of safety driving, road guidance, and the road surveillance system during the winter. However, in case of the road surveillance system during the winter, there are some difficulties for the recognition of the frozen road conditions by the current sensor system such as the locations or elapsed time of the observed data. Therefore, this paper proposes Wireless V2X Communication Systems of for Winter Road Surveillance Systems by the Delay Tolerant Networks (DTN). In the proposed systems, the vehicles equip the wireless V2X networks, and the observed data by the sensor of Quasi Electrostatic Field (QEF) are transferred to the target node with the DTN routing. Then, this papers are evaluated the various wireless networks such as IEEE802.11a/b/g/p, Wi-SUN, and the radio directional controls, and the results are discussed for the effectiveness of the proposed systems and the future studies.
{"title":"Evaluations of Wireless V2X Communication Systems of for Winter Road Surveillance Systems","authors":"Noriki Uchida, Kenta Ito, Go Hirakawa, Y. Shibata","doi":"10.1109/NBiS.2016.83","DOIUrl":"https://doi.org/10.1109/NBiS.2016.83","url":null,"abstract":"With the recent rapid growth of V2X (Vehicle-to-X) developments, there are many expectations for the purpose of safety driving, road guidance, and the road surveillance system during the winter. However, in case of the road surveillance system during the winter, there are some difficulties for the recognition of the frozen road conditions by the current sensor system such as the locations or elapsed time of the observed data. Therefore, this paper proposes Wireless V2X Communication Systems of for Winter Road Surveillance Systems by the Delay Tolerant Networks (DTN). In the proposed systems, the vehicles equip the wireless V2X networks, and the observed data by the sensor of Quasi Electrostatic Field (QEF) are transferred to the target node with the DTN routing. Then, this papers are evaluated the various wireless networks such as IEEE802.11a/b/g/p, Wi-SUN, and the radio directional controls, and the results are discussed for the effectiveness of the proposed systems and the future studies.","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126855380","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}
Secure group key management is an important task to realize reliable machine-to-machine (M2M) systems. Although many group key management schemes have been proposed, most of them do not consider the communication cost and the number of keys held by each node. In this paper, we address these challenges by proposing a novel subgroup key management scheme, which we called SGM. SGM is a key tree hierarchy scheme which uses an alternative node to the key management server. Since the SGM node encrypts and distributes the group key during a rekeying process, the communication cost and the number of keys can be decreased. We also present a cost-efficient deployment method for the SGM node using a k-means clustering algorithm. Simulation results show that our proposed scheme can improve the energy efficiency of M2M networks, compared with the conventional scheme, logical key hierarchy (LKH).
{"title":"SGM: A Subgroup Management Scheme Using K-Means Clustering in M2M Systems","authors":"Jihoon Hong, Mirang Park, N. Okazaki","doi":"10.1109/NBiS.2016.14","DOIUrl":"https://doi.org/10.1109/NBiS.2016.14","url":null,"abstract":"Secure group key management is an important task to realize reliable machine-to-machine (M2M) systems. Although many group key management schemes have been proposed, most of them do not consider the communication cost and the number of keys held by each node. In this paper, we address these challenges by proposing a novel subgroup key management scheme, which we called SGM. SGM is a key tree hierarchy scheme which uses an alternative node to the key management server. Since the SGM node encrypts and distributes the group key during a rekeying process, the communication cost and the number of keys can be decreased. We also present a cost-efficient deployment method for the SGM node using a k-means clustering algorithm. Simulation results show that our proposed scheme can improve the energy efficiency of M2M networks, compared with the conventional scheme, logical key hierarchy (LKH).","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116875413","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}
Deep Learning also called Deep Neural Network (DNN) has a deep hierarchy that connect multiple internal layers for feature detection and recognition learning. DNNs are emerging fast and will continue to grow together with feature detection methods. In previous work, we applied deep learning for vegetable object recognition and explored the Convolutional Neural Network (CNN). In this paper, we propose an enhanced accessory category recognition system which is based on CNN. From the evaluation results, we found that for recognition learning process by CNN, seventy thousand iterations were suitable. The results of learning rate was 99.77% and recognition rate was 99.75%, respectively. We observed that our system can be applied also for accessory category recognition.
{"title":"Performance Evaluation of an Accessory Category Recognition System Using Deep Neural Network","authors":"Yuki Sakai, Tetsuya Oda, Makoto Ikeda, L. Barolli","doi":"10.1109/NBiS.2016.51","DOIUrl":"https://doi.org/10.1109/NBiS.2016.51","url":null,"abstract":"Deep Learning also called Deep Neural Network (DNN) has a deep hierarchy that connect multiple internal layers for feature detection and recognition learning. DNNs are emerging fast and will continue to grow together with feature detection methods. In previous work, we applied deep learning for vegetable object recognition and explored the Convolutional Neural Network (CNN). In this paper, we propose an enhanced accessory category recognition system which is based on CNN. From the evaluation results, we found that for recognition learning process by CNN, seventy thousand iterations were suitable. The results of learning rate was 99.77% and recognition rate was 99.75%, respectively. We observed that our system can be applied also for accessory category recognition.","PeriodicalId":390397,"journal":{"name":"2016 19th International Conference on Network-Based Information Systems (NBiS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130694686","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：