Pub Date : 2016-12-01DOI: 10.1109/IC3I.2016.7918791
Mamata Rath, M. R. Panda
To furnish protected and efficient routine activities in cluster based Mobile Adhoc Networks (MANETs), a Mobile Agent based QoS (MAQ) scheme using clustering algorithm for real time data communication has been designed in this paper. A Mobile agent architecture is projected in a way that it remains associated with the cluster head of every cluster and when real time application gets notified in these clusters then the proposed system gets activated to hold up prioritized service to these applications including checking and monitoring the flow qualities for real time applications. JADE (Java Agent Development Environment) based prioritized proposal at the mobile agent has been implemented in the proposed system. As this is an application oriented approach, so the overall network performance significantly improves resulting better throughput and packet delivery ratio. Prioritized functionalities relating to end-to-end delay, jitter in video streaming and power saving policies during real-time data transmission are controlled by operational modules defined in the mobile agent.
为了在基于集群的移动自组网(manet)中提供受保护的、高效的日常活动，本文设计了一种基于移动代理的、采用聚类算法的实时数据通信QoS (MAQ)方案。移动代理架构以一种与每个集群的集群头保持关联的方式进行规划，当实时应用程序在这些集群中得到通知时，提议的系统被激活，以保持对这些应用程序的优先级服务，包括检查和监控实时应用程序的流质量。在被提议的系统中实现了基于JADE (Java Agent Development Environment)的移动代理优先提议。由于这是一种面向应用程序的方法，因此整体网络性能显著提高，从而获得更好的吞吐量和数据包传递率。与端到端延迟、视频流中的抖动和实时数据传输中的节能策略相关的优先功能由移动代理中定义的操作模块控制。
{"title":"MAQ system development in mobile ad-hoc networks using mobile agents","authors":"Mamata Rath, M. R. Panda","doi":"10.1109/IC3I.2016.7918791","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7918791","url":null,"abstract":"To furnish protected and efficient routine activities in cluster based Mobile Adhoc Networks (MANETs), a Mobile Agent based QoS (MAQ) scheme using clustering algorithm for real time data communication has been designed in this paper. A Mobile agent architecture is projected in a way that it remains associated with the cluster head of every cluster and when real time application gets notified in these clusters then the proposed system gets activated to hold up prioritized service to these applications including checking and monitoring the flow qualities for real time applications. JADE (Java Agent Development Environment) based prioritized proposal at the mobile agent has been implemented in the proposed system. As this is an application oriented approach, so the overall network performance significantly improves resulting better throughput and packet delivery ratio. Prioritized functionalities relating to end-to-end delay, jitter in video streaming and power saving policies during real-time data transmission are controlled by operational modules defined in the mobile agent.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130218817","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}
Wireless sensor network will become isolated in various associated segments because of the disappointment of some of its hubs, which is known as a “cut”. In this paper, authors acknowledge the issue of distinguishing cuts by the remaining hubs of a wireless sensor network. System proposes an estimation which grants every hub to identify at the time of accessibility to an extremely assigned hub has been lost, and one or more hubs (that are connected with the unique hub after the cut) to recognize the cut's event. The calculation is passed on and strange: every hub needs to relate with simply those hubs that are within its correspondence range. The estimation relies on upon the iterative calculation of an invented “electrical potential” of the hubs. The combining rate of the concealed iterative arrangement is self-governing of the size as well as network structure. Also this system implements a lightweight encryption algorithm to rout data securely in the network and enhance the system performance.
{"title":"Cut detection and secure routing in wireless sensor networks","authors":"Pradnya Wagh, Pratik Mahamuni, Kaustubh Rajeshirke","doi":"10.1109/IC3I.2016.7917949","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7917949","url":null,"abstract":"Wireless sensor network will become isolated in various associated segments because of the disappointment of some of its hubs, which is known as a “cut”. In this paper, authors acknowledge the issue of distinguishing cuts by the remaining hubs of a wireless sensor network. System proposes an estimation which grants every hub to identify at the time of accessibility to an extremely assigned hub has been lost, and one or more hubs (that are connected with the unique hub after the cut) to recognize the cut's event. The calculation is passed on and strange: every hub needs to relate with simply those hubs that are within its correspondence range. The estimation relies on upon the iterative calculation of an invented “electrical potential” of the hubs. The combining rate of the concealed iterative arrangement is self-governing of the size as well as network structure. Also this system implements a lightweight encryption algorithm to rout data securely in the network and enhance the system performance.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134541355","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 : 2016-12-01DOI: 10.1109/IC3I.2016.7919047
Pawandeep Kaur, Amandeep Kaur
Information extraction is the sub topic of Artificial Intelligence method. Recognition of named entity tags for computer using NLP (Natural language processing) is very important. It is very first step in recognition of unstructured content. For classification and identification of given number of tasks for any data, named entity recognition can be used as a subtask for extraction of information. There are numerous methods that help in applying NE process. In this paper various methods of NER have been presented and various issues related to Punjabi language has been discussed.
{"title":"Named entity recognition model for Punjabi language: A survey","authors":"Pawandeep Kaur, Amandeep Kaur","doi":"10.1109/IC3I.2016.7919047","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7919047","url":null,"abstract":"Information extraction is the sub topic of Artificial Intelligence method. Recognition of named entity tags for computer using NLP (Natural language processing) is very important. It is very first step in recognition of unstructured content. For classification and identification of given number of tasks for any data, named entity recognition can be used as a subtask for extraction of information. There are numerous methods that help in applying NE process. In this paper various methods of NER have been presented and various issues related to Punjabi language has been discussed.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131618334","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 : 2016-12-01DOI: 10.1109/IC3I.2016.7917931
D. Vasundhara, M. Seetha
Spatial image classification meant to the mechanism of extracting meaningful knowledge information classes from spatial images dataset. Many traditional pixel based image classification techniques such as Support Vector Machines (SVM), ANN, Fuzzy methods, Decision Trees (DT) etc. exist. The performance and accuracy of these image classification methods depends upon the network structure and number of inputs. Here, in this paper, we have proposed an step-wise mechanism to significantly improve the classification performance of neural network, that uses rough sets approach for purpose of features/attributes selection of image pixels. The complexity analysis of the proposed algorithm and the comparison of mechanism, presented here, with existing classification techniques based on features over the interest area is carried out.
{"title":"Rough-set and artificial neural networks based image classification","authors":"D. Vasundhara, M. Seetha","doi":"10.1109/IC3I.2016.7917931","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7917931","url":null,"abstract":"Spatial image classification meant to the mechanism of extracting meaningful knowledge information classes from spatial images dataset. Many traditional pixel based image classification techniques such as Support Vector Machines (SVM), ANN, Fuzzy methods, Decision Trees (DT) etc. exist. The performance and accuracy of these image classification methods depends upon the network structure and number of inputs. Here, in this paper, we have proposed an step-wise mechanism to significantly improve the classification performance of neural network, that uses rough sets approach for purpose of features/attributes selection of image pixels. The complexity analysis of the proposed algorithm and the comparison of mechanism, presented here, with existing classification techniques based on features over the interest area is carried out.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131742057","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 : 2016-12-01DOI: 10.1109/IC3I.2016.7918027
R. Joshi, H. M. Jadav, A. Mali, S. Kulkarni
Ion Cyclotron Resonance Heating (ICRH) system has two different impedance matching systems for RF transmission. One is offline matching which has been used before applying the experimental shots. Another is online impedance matching which has been used during experimental shot. Offline matching network consists of two coarse tuner, static stubs and coarse phase shifter which are identical in both the transmission lines. There are motorized arrangement installed in each stubs and phase shifters. Both static and coarse stubs are used to vary length in order to match the source impedance with load impedance. Phase shifter is used for matching impedance via varying the phase of the power. Programmable Logic Controller (PLC) based instrumentation has been implemented for the system. Offline matching should be operated below 1 kHz frequency in order to move stepper motors using square pulses employed to motor controller. In existing system this operation has been carried out by VME instrumentation and control. In order to reduce load on VME, PLC based system has been designed and integrated with VME based DAC. SIMATIC Windows Control Center (WinCC) software has been used as SCADA i.e. front end user interface. WinCC SCADA can communicate with OPC (Open Process Control) server using different PLC signals. This paper describes technical details, design and development of PLC based offline impedance matching system using WinCC as SCADA. The developed system has proved accurate and reliable in use of application as per system requirement. The SCADA system also shows motor frequency and motor speed profile with upper and lower limits. It logs data at the end of operation by which it retrieve the last run status of each motor when it starts again.
离子回旋共振加热(ICRH)系统具有两种不同的射频传输阻抗匹配系统。一种是在应用实验镜头之前使用的离线匹配。另一种方法是在线阻抗匹配，该方法已在实验射击中得到应用。离线匹配网络由两个粗调谐器、静态存根和粗移相器组成，它们在两根传输线上相同。在每个存根和移相器上安装有电动装置。为了使源阻抗与负载阻抗相匹配，静态桩和粗桩都用来改变长度。移相器通过改变电源的相位来匹配阻抗。系统实现了基于可编程逻辑控制器(PLC)的仪器仪表。离线匹配应低于1khz频率操作，以便使用电机控制器使用的方波脉冲移动步进电机。在现有的系统中，该操作是由VME仪表和控制来完成的。为了减少VME的负载，设计了基于PLC的系统，并将其与基于VME的DAC集成在一起。SIMATIC Windows控制中心(WinCC)软件被用作SCADA，即前端用户界面。WinCC SCADA可以使用不同的PLC信号与OPC (Open Process Control)服务器通信。本文介绍了以WinCC作为SCADA的基于PLC的离线阻抗匹配系统的技术细节、设计与开发。经实际应用证明，所开发的系统准确可靠，符合系统要求。SCADA系统还显示了电机频率和电机速度的上下限。它在操作结束时记录数据，通过它检索每个电机再次启动时的最后运行状态。
{"title":"Integration of PLC based offline impedance matching system for ICRH experiments","authors":"R. Joshi, H. M. Jadav, A. Mali, S. Kulkarni","doi":"10.1109/IC3I.2016.7918027","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7918027","url":null,"abstract":"Ion Cyclotron Resonance Heating (ICRH) system has two different impedance matching systems for RF transmission. One is offline matching which has been used before applying the experimental shots. Another is online impedance matching which has been used during experimental shot. Offline matching network consists of two coarse tuner, static stubs and coarse phase shifter which are identical in both the transmission lines. There are motorized arrangement installed in each stubs and phase shifters. Both static and coarse stubs are used to vary length in order to match the source impedance with load impedance. Phase shifter is used for matching impedance via varying the phase of the power. Programmable Logic Controller (PLC) based instrumentation has been implemented for the system. Offline matching should be operated below 1 kHz frequency in order to move stepper motors using square pulses employed to motor controller. In existing system this operation has been carried out by VME instrumentation and control. In order to reduce load on VME, PLC based system has been designed and integrated with VME based DAC. SIMATIC Windows Control Center (WinCC) software has been used as SCADA i.e. front end user interface. WinCC SCADA can communicate with OPC (Open Process Control) server using different PLC signals. This paper describes technical details, design and development of PLC based offline impedance matching system using WinCC as SCADA. The developed system has proved accurate and reliable in use of application as per system requirement. The SCADA system also shows motor frequency and motor speed profile with upper and lower limits. It logs data at the end of operation by which it retrieve the last run status of each motor when it starts again.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132635343","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 : 2016-12-01DOI: 10.1109/IC3I.2016.7917952
Manpreet Kaur, Anjana Sharma
Routing stands for the sending the required data to the destination in such a manner that it reaches efficiently with high throughput and accuracy. The data is transferring over the network each sensor use some energy in receiving data, sending data. The life of the network depend how much energy used up in each transmission. The problem occurs when the transmission path meets with some sort of failure like path failure or node goes to sleep mode. The focus, however, has been given to the routing protocols which might differ depending on the application and network architecture. In this paper, we have proposed the state-of-the-art routing technique using SPEED protocol and NN technique to choose an alternative path in WSNs.
{"title":"Routing in WSN network using neural Network (NN) and SPEED protocol","authors":"Manpreet Kaur, Anjana Sharma","doi":"10.1109/IC3I.2016.7917952","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7917952","url":null,"abstract":"Routing stands for the sending the required data to the destination in such a manner that it reaches efficiently with high throughput and accuracy. The data is transferring over the network each sensor use some energy in receiving data, sending data. The life of the network depend how much energy used up in each transmission. The problem occurs when the transmission path meets with some sort of failure like path failure or node goes to sleep mode. The focus, however, has been given to the routing protocols which might differ depending on the application and network architecture. In this paper, we have proposed the state-of-the-art routing technique using SPEED protocol and NN technique to choose an alternative path in WSNs.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130869370","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 : 2016-12-01DOI: 10.1109/IC3I.2016.7917994
Shikha Sharma, Shivani Sharma
Sybil attack is an encounter in which the personality of a assaulter is contaminated into huge number of incognito personality which is produced to build up the route of the network. In this paper, we deliberate the timestamp approach for Sybil attack in associated system, self correlate network, and cordial network system. Also assorted mechanisms to extenuate the Sybil attack are evaluated, we have proposed timestamp approach for prevention and detection of Sybil attack. We have compared our result with EBRS Approach our approach shows better results as compared to previous approach.
{"title":"A defensive timestamp approach to detect and mitigate the Sybil attack in vanet","authors":"Shikha Sharma, Shivani Sharma","doi":"10.1109/IC3I.2016.7917994","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7917994","url":null,"abstract":"Sybil attack is an encounter in which the personality of a assaulter is contaminated into huge number of incognito personality which is produced to build up the route of the network. In this paper, we deliberate the timestamp approach for Sybil attack in associated system, self correlate network, and cordial network system. Also assorted mechanisms to extenuate the Sybil attack are evaluated, we have proposed timestamp approach for prevention and detection of Sybil attack. We have compared our result with EBRS Approach our approach shows better results as compared to previous approach.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115410705","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 : 2016-12-01DOI: 10.1109/IC3I.2016.7917995
Anita Chaudhari, Brinzel Rodrigues, Shraddha S. More
Energy crisis is one of the prime challenges being faced by many of the countries in the world today. Industrial development and population growth has tremendously increased the demand for energy to a huge extent. Many researchers and developers have come up with effective systems so as deal with this problem. A lot of techniques have been suggested such as an Energy monitoring system which is an efficient technique to monitor the devices present inside a house or industries and provide notification about their abnormal behavior. Main aim of this project is to design a SmartPlug: energy monitoring and control system which can control the devices, show power consumed by the devices and calculate electricity bills based on the total energy usage depending upon different vendors available. Our system includes a Raspberry pi, Arduino board and sensors which will be connected to each and every device. We have developed a website so that the user can just login and have information about the energy consumption by all the devices. A graphical representation of the power consumed by the devices will make the user aware if power consumed by any device exceeds a certain level. This system can reduce the electricity bills to a large extent and will prove beneficial for the users as well. It is not restricted to limited devices and thus can also be used in industries by using more Raspberry pi micro-controllers.
{"title":"Automated IOT based system for home automation and prediction of electricity usage and comparative analysis of various electricity providers: SmartPlug","authors":"Anita Chaudhari, Brinzel Rodrigues, Shraddha S. More","doi":"10.1109/IC3I.2016.7917995","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7917995","url":null,"abstract":"Energy crisis is one of the prime challenges being faced by many of the countries in the world today. Industrial development and population growth has tremendously increased the demand for energy to a huge extent. Many researchers and developers have come up with effective systems so as deal with this problem. A lot of techniques have been suggested such as an Energy monitoring system which is an efficient technique to monitor the devices present inside a house or industries and provide notification about their abnormal behavior. Main aim of this project is to design a SmartPlug: energy monitoring and control system which can control the devices, show power consumed by the devices and calculate electricity bills based on the total energy usage depending upon different vendors available. Our system includes a Raspberry pi, Arduino board and sensors which will be connected to each and every device. We have developed a website so that the user can just login and have information about the energy consumption by all the devices. A graphical representation of the power consumed by the devices will make the user aware if power consumed by any device exceeds a certain level. This system can reduce the electricity bills to a large extent and will prove beneficial for the users as well. It is not restricted to limited devices and thus can also be used in industries by using more Raspberry pi micro-controllers.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115578177","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 : 2016-12-01DOI: 10.1109/IC3I.2016.7918002
M. Sajjan, Lingangouda Kulkarni, B. Anami, N. G. Gaddagimath
The Paper work presents an approaches to classify chilli class from their bulk sample chilli images using RGB and HSI and L∗a∗b Model colour features. A rule based algorithm is implemented taking into account, best RGB, HSI and L∗a∗b colour features, 9 colour features were computed for R-(red), G-(green), B-(Blue), H-(hue), S-(saturation), I-(intensity), L-(brightness), a-(chromaticity layer red&green), b-(chromaticity layer blue&yellow) images from each image samples. Best features were used as an input to classifier and tests were performed to identify best classification model. R-Average, Hue-Average, a-average Hue-mean, L∗_mean, a∗_mean and standard deviation values are considered for Rule Based Classification, We have considered four different varieties of Chilli, with stalk and without stalk. The recognition rate for RGB colour features chilli with stalk is 70.% and for chilli without stalk is 85% is obtained. The recognition rate for HSI colour features, chilli with stalk is 80% and for chilli without stalk is 90% is obtained. The recognition rate for L∗a∗b colour features chilli with stalk is 85% and for chilli without stalk is 95% is obtained.
论文工作提出了一种方法来分类辣椒类从他们的散装样本辣椒图像使用RGB和HSI和L * a * b模型颜色特征。考虑到最佳的RGB、HSI和L * A * b颜色特征，实现了一种基于规则的算法，对每个图像样本中的R-(红色)、G-(绿色)、b-(蓝色)、H-(色调)、S-(饱和度)、I-(强度)、L-(亮度)、A -(色度层红与绿)、b-(色度层蓝与黄)图像计算了9个颜色特征。使用最佳特征作为分类器的输入，并进行测试以确定最佳分类模型。基于规则的分类考虑了R-Average, Hue-Average, a-average Hue-mean, L∗_mean, a∗_mean和标准差值。我们考虑了四种不同的辣椒品种，有茎和没有茎。带柄辣椒RGB颜色特征的识别率为70。%，而无茎辣椒则为85%。该方法对HSI颜色特征的识别率为80%，对无柄辣椒的识别率为90%。对L * a * b颜色特征有柄辣椒的识别率为85%，对无柄辣椒的识别率为95%。
{"title":"A comparative analysis of color features for classification of bulk chilli","authors":"M. Sajjan, Lingangouda Kulkarni, B. Anami, N. G. Gaddagimath","doi":"10.1109/IC3I.2016.7918002","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7918002","url":null,"abstract":"The Paper work presents an approaches to classify chilli class from their bulk sample chilli images using RGB and HSI and L∗a∗b Model colour features. A rule based algorithm is implemented taking into account, best RGB, HSI and L∗a∗b colour features, 9 colour features were computed for R-(red), G-(green), B-(Blue), H-(hue), S-(saturation), I-(intensity), L-(brightness), a-(chromaticity layer red&green), b-(chromaticity layer blue&yellow) images from each image samples. Best features were used as an input to classifier and tests were performed to identify best classification model. R-Average, Hue-Average, a-average Hue-mean, L∗_mean, a∗_mean and standard deviation values are considered for Rule Based Classification, We have considered four different varieties of Chilli, with stalk and without stalk. The recognition rate for RGB colour features chilli with stalk is 70.% and for chilli without stalk is 85% is obtained. The recognition rate for HSI colour features, chilli with stalk is 80% and for chilli without stalk is 90% is obtained. The recognition rate for L∗a∗b colour features chilli with stalk is 85% and for chilli without stalk is 95% is obtained.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115795191","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 : 2016-12-01DOI: 10.1109/IC3I.2016.7918000
M. J. Yashaswini, V. S. Vishnu, B N Annapuma, Tanik R Prasad
Biometrics and Pattern Recognition have various applications that are found and brought into real-time application use. Face recognition consist mainly of three stages namely: Pre-processing, Feature Extraction and Classification. Neural Networks basically deals with adaptation, classification and rendering noisy values to optimal solution. In this work we illustrate performance and accuracy of the above approaches. Subspace is a plane embedded in a higher dimensional vector space, PCA is a standout amongst the best systems that have been utilized in image recognition and compression while KPCA is utilized in ascertaining PCA conversion in a mapping space by a nonlinear mapping function. FFNN is used for pattern recognition, FNN frequently have at least one hidden layers of sigmoid neurons followed by a yield layer of linear neurons. Multiple layers of neurons with nonlinear transfer function permits the system to learn connections amongst information and yield vectors. LVQ learn to characterize input vectors into target classes picked by the user.
{"title":"The performance of multi-layer neural network on face recognition system","authors":"M. J. Yashaswini, V. S. Vishnu, B N Annapuma, Tanik R Prasad","doi":"10.1109/IC3I.2016.7918000","DOIUrl":"https://doi.org/10.1109/IC3I.2016.7918000","url":null,"abstract":"Biometrics and Pattern Recognition have various applications that are found and brought into real-time application use. Face recognition consist mainly of three stages namely: Pre-processing, Feature Extraction and Classification. Neural Networks basically deals with adaptation, classification and rendering noisy values to optimal solution. In this work we illustrate performance and accuracy of the above approaches. Subspace is a plane embedded in a higher dimensional vector space, PCA is a standout amongst the best systems that have been utilized in image recognition and compression while KPCA is utilized in ascertaining PCA conversion in a mapping space by a nonlinear mapping function. FFNN is used for pattern recognition, FNN frequently have at least one hidden layers of sigmoid neurons followed by a yield layer of linear neurons. Multiple layers of neurons with nonlinear transfer function permits the system to learn connections amongst information and yield vectors. LVQ learn to characterize input vectors into target classes picked by the user.","PeriodicalId":305971,"journal":{"name":"2016 2nd International Conference on Contemporary Computing and Informatics (IC3I)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124581214","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：