2014 International Conference on Parallel, Distributed and Grid Computing最新文献

{"title":"Area and power efficient 4-bit comparator design by using 1-bit full adder module","authors":"Anjali Sharma, Pranshu Sharma","doi":"10.1109/PDGC.2014.7030705","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030705","url":null,"abstract":"In this paper an area and power efficient 56T 4-bit comparator design has been presented by using GDI technique. The proposed 4-bit comparator design consist of 28 NMOS and 28 PMOS. A GDI full adder module has been used to design this comparator which consumes less area and power at 120 nm as compared to previous full adder designs. The proposed 4-bit comparator design is based on this area and power efficient 10T full adder module. To get area and power efficiency a centralized full adder module has been used which avoid cascade implementation of XOR module to get sum and carry output. Full adder modules outputs have been used for the generation of output of 4-bit comparator designs. The proposed 4-bit GDI comparator has been designed and simulated using DSCH 3.1 and Microwind 3.1 on 120nm. For proposed design Power and current variation with respect to the supply voltage has been performed on BSIM-4 using 120nm technology. Results show that Area of proposed 4-bit comparator design is 1320.3μm2 on 120nm technology. At 1.2V input supply voltage the proposed 4-bit GDI comparator consumes 13.739μW power at BSIM-4. At 1.2V proposed GDI 4-bit comparator has shown improvement of 6.3% in terms of area and 69.42% in power as compared to the PTL 4- bit comparator.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"352 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114615319","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}

{"title":"A credit based routing mechanism to contrast selfish nodes in Delay tolerant networks","authors":"Atul Sharma","doi":"10.1109/PDGC.2014.7030759","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030759","url":null,"abstract":"Delay Tolerance Networks (DTNs) are the networks in which no end to end path is present between nodes or may partially present with limited period of time. To forward a packet, DTN uses store, carry and forward mechanism. Security is one of the key issues in DTN. There are various security threats such as message modification, packet dropped, and selfish node etc. Nodes which are the part of a DTN, can behave selfishly due to the network reservation policy, especially for node energy or storage space. This paper proposes a secure credit based incentive scheme to contrast selfish behavior and stimulate bundle forwarding cooperation among DTN nodes. The contact graphs are created to distribute credits to the participating nodes. The proposed scheme can be implemented in a fully distributed manner to thwart various attacks without relying on any tamperproof hardware. The vulnerability of the above mentioned protocols is simulated using ONE simulator.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129941169","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}

{"title":"Simulation and analysis of authentication protocols for mobile Internet of Things (MIoT)","authors":"Adarsh Kumar, K. Gopal, A. Aggarwal","doi":"10.1109/PDGC.2014.7030783","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030783","url":null,"abstract":"Things are integrated for increasing the availability of information. MIoT is the connectivity of mobile devices to extend the information. Connectivity of mobile devices helps in managing the various social activities. Security is a major concern while integrating the heterogeneous devices in these social networks. Things embedded with radio frequency based identifications are having scarcity of resources thus require lightweight cryptography aspects. This work proposes a single bar circular topology based authentication protocol for MIoT. This protocol helps in authenticating the mobile devices for constructing secure network. The proposed protocol is modeled using Alloy model. Delay analysis shows that construction of secure network is possible with maximum delay of 0.91 msec. Node can enter or leave the network with minimum of 0.13 and maximum of 0.20 msec. Further, Zone Routing Protocol (ZRP) is considered to be the best protocol for constructing a secure network.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133198720","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}

{"title":"An efficient energy saving task consolidation algorithm for cloud computing systems","authors":"S. K. Panda, P. K. Jana","doi":"10.1109/PDGC.2014.7030753","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030753","url":null,"abstract":"Task consolidation is a process of maximizing resource utilization in a cloud system. However, maximum usage of resources does not necessarily imply that there will be proper use of energy as some resources which are sitting idle, also consume considerable amount of energy. Recent studies show that energy consumption due to idle resources is approximately 1 to 20%. So, the idle resources are assigned with some tasks to utilize the idle period, which in turn reduces the overall energy consumption of the resources. Note that higher resource utilization merely leads to high energy consumption. So, the tasks are likely to be assigned to all the resources for the proper use of energy. In this paper, we propose an energy saving task consolidation (ESTC) which minimizes the energy consumption by utilizing the idle period of the resources in a cloud environment. ESTC achieves it by assigning few tasks to all available resources to overcome the idleness of the resources. In addition to this, it calculates the energy consumption on arrival of a task to make the scheduling assessment. We perform extensive experiments to measure the performance of ESTC and we compare it with the recent energy-aware task consolidation (ETC) algorithm. The results show that the proposed algorithm outperforms ETC in terms of energy consumption and the total number of task completion.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130057351","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}

{"title":"Influence of link sensing mechanism of IMEP on the performance of TORA under different mobility models","authors":"A. Kaur, Meenakshi Mittal","doi":"10.1109/PDGC.2014.7030708","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030708","url":null,"abstract":"The performance evaluation of Mobile Ad Hoc Network (MANET) routing protocols is an important as well as open area of research worldwide. Temporally Ordered Routing Algorithm (TORA) is an adaptable and distributed MANET routing protocol which is dependent on the services of Internet MANET Encapsulation Protocol (IMEP) for its various necessary functions like link status detection. The incorrect link failure detection by IMEP leads to creation of congested network and initiation of avoidable route maintenance in TORA. Thus changes need to be introduced in the link sensing mechanism provided by IMEP to improve the detection of links in TORA. According to previously available research, if the maximum number of OBM retransmissions is increased, significant improvement in the performance of TORA is noticed. This modification has been implemented in this paper and performance of Enhanced TORA is evaluated under Random-Waypoint model, Manhattan-Grid mobility model and Random-Direction model using FTP traffic with 10 connections. The results are then compared with those of original TORA using various performance metrics like Packet Delivery Ratio, Average End to End Delay and Routing Overhead.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"735 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114066061","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}

{"title":"Super-fast parallel eigenface implementation on GPU for face recognition","authors":"Urvesh Devani, V. Nikam, B. Meshram","doi":"10.1109/PDGC.2014.7030729","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030729","url":null,"abstract":"Eigenface is one of the most common appearance based approaches for face recognition. Eigenfaces are the principal components which represent the training faces. Using Principal Component Analysis, each face is represented by very few parameters called weight vectors or feature vectors. While this makes testing process easy, it also includes cumbersome process of generating eigenspace and projecting every training image onto it to extract weight vectors. This approach works well with small set of images. As number of images to train increases, time taken for generating eigenspace and weight vectors also increases rapidly and it will not be feasible to recognize face in big data or perform real time video analysis. In this paper, we propose a super-fast parallel solution which harnesses the power of GPU and utilizes benefits of the thousands of cores to compute accurate match in fraction of second. We have implemented Parallel Eigenface, the first complete super-fast Parallel Eigenface implementation for face recognition, using CUDA on NVIDIA K20 GPU. Focus of the research has been to gain maximum performance by implementing highly optimized kernels for complete approach and utilizing available fastest library functions. We have used dataset of different size for training and noted very high increase in speedup. We are able to achieve highest 460X speed up for weight vectors generation of 1000 training images. We also get 73X speedup for overall training process on the same dataset. Speedup tends to increase with respect to training data, proving the scalability of solution. Results prove that our parallel implementation is best fit for various video analytics applications and real time face recognition. It also shows strong promise for excessive use of GPUs in face recognition systems.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116694899","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}

{"title":"Effective asthma disease prediction using naive Bayes — Neural network fusion technique","authors":"Saloni Aneja, Sangeeta Lal","doi":"10.1109/PDGC.2014.7030730","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030730","url":null,"abstract":"Asthma is a lung disease caused by the inflammation and narrowing of the airways that causes recurrent attacks of breathlessness and wheezing, and often can be life-threatening. Around 15-20 million people are suffering from asthma in India[1]. This paper aims at analyzing various data mining techniques for the prediction of asthma. The observations show that the fusion approach of naive bayes and neural network proved to be the best among classification algorithms in the diagnosis of asthma. This methodology is evaluated using 1024 raw data obtained from a city hospital. The proposed approach helps patients in their diagnosis of asthma.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132829569","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}

{"title":"Modeling and analysis of RFID authentication protocols for supply chain management","authors":"Adarsh Kumar, K. Gopal, A. Aggarwal","doi":"10.1109/PDGC.2014.7030752","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030752","url":null,"abstract":"A secure interconnection of objects through RFID technology extends the range of information availability. Security in this integration is achievable through proper identification, authentication, grouping / yoking, distance bounding, and tag and ownership transfer protocols. This work analyzes the computational and communicational cost of group and authentication protocols. Further, these protocols are modeled and analyzed using alloy model. Results show that a network of 255 nodes can be constructed with delays of 9.6 msec and 7.6 msec using peer to peer and centralized connectivity respectively.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122036563","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}

{"title":"Data agglomeration in wireless sensor networks","authors":"Jasminder Kaur Sandhu, S. Saxena","doi":"10.1109/PDGC.2014.7030757","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030757","url":null,"abstract":"The nodes which can conjointly send anticipated data to base terminal is called sensor networks. The critical coercion is consumption of power for sensors. The sensors can transmit inapplicable power origins which are confined. When the sensors are dispersed in any circumstances it is quite possible that these are placed farther from the terminal and in actual the sensors are in actual are at some distant from each other. The sensors are operable through battery therefore it can utilize power systematically for tapering data traffic and thus boosting the life span of the network. The wireless sensor networks have these sensors which are used for gathering and agglomerating data competently. We have discussed few aspects of wireless sensors associated with data agglomeration. As the wireless sensors have networks which are used for various applications like observing habitation, administering calamity, military and security, etc, its limited operational functionality and limited battery made a bigger issue in today's scenario. Thus data agglomeration techniques are being used for discarding similar data in order for saving energy and battery. In this paper, we focused on various approaches which are useful in data agglomeration efficiently in WSN.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122123937","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}

{"title":"Performance analysis of middleware distributed and clustered systems (PAMS) concept in mobile communication devices using Android operating system","authors":"V. Singh, A. Aggarwal","doi":"10.1109/PDGC.2014.7030768","DOIUrl":"https://doi.org/10.1109/PDGC.2014.7030768","url":null,"abstract":"Recent advances in computational power, memory, display etc. have propelled mobile and hand held devices as a platform to display and execute a variety of applications. Popular platform vendors like Nokia S60, iPhone, Samsung and Android offer extensive middleware support which helps in developers' port and in packaging of different application modules in a suitable format. These devices have several features like processing power, memory, energy, which exhibit the ability of these devices for performing complex tasks. Nowadays multi core processor architecture like Quad-Core Processor up to 3.0 GHz and Java enabled Android operating systems mobile devices are coming into the market which have potential for support and enhancements for an enterprise. In a complex and critical real time production support enterprise environment, a middleware production support analyst is primarily responsible to access, analyze the performance and control the middleware production application servers in a faster and precise manner. Production support analyst may or may not be available to Unix Production servers at all times due to many reasons. In this work a novel approach, Performance Analysis of Middleware distributed and clustered Systems (PAMS), is proposed using Android application by which a production support analyst can still support all critical real time web based application servers while he is away from the Unix based Middleware application server and can ensure that the same is available and accessible to their customers. An Android based application is proposed which will communicate to higher production layers installed in secure network of an organization and gather the data for performance monitoring and analysis. With the proposed concept production support analyst can easily login and open the console of middleware application servers using VPN (Virtual Private Network) and take immediate necessary actions so that business flow should not be impacted and enterprise web applications are available to end users all the time.","PeriodicalId":311953,"journal":{"name":"2014 International Conference on Parallel, Distributed and Grid Computing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125036550","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}