Pub Date : 2017-10-01DOI: 10.1109/UEMCON.2017.8249102
R. Rai, Huiling Zhu, Jiangzhou Wang
Cloud radio access network (C-RAN) is enabling innovation which can address a number of challenges that cellular network operators (CNOs) face while trying to support ever growing end users' needs towards 5th generation (5G) of mobile networks. This paper investigates a scheduling problem to enhance the performance of non-orthogonal multiple access (NOMA) based cloud radio access networks (C-RAN). We consider the downlink of a C-RAN where cloud is responsible for the scheduling policy and formulate the scheduling problem. In this paper non-orthogonal multiple access (NOMA) is adopted and resource scheduling techniques in an unconstrained C-RAN networks are proposed. We design an efficient resource scheduling algorithm to assist the resource scheduling process in NOMA based C-RAN systems. We formulate the problem as binary integer programming (BIP) optimization problem and propose a suboptimal BIP algorithm and a greedy heuristic allocation algorithm which leads to the maximization of throughput in terms of sum rate when compared with the standard techniques. Simulation results shows significant performance improvement with the proposed algorithms.
{"title":"Resource scheduling in non-orthogonal multiple access (NOMA) based cloud-RAN systems","authors":"R. Rai, Huiling Zhu, Jiangzhou Wang","doi":"10.1109/UEMCON.2017.8249102","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249102","url":null,"abstract":"Cloud radio access network (C-RAN) is enabling innovation which can address a number of challenges that cellular network operators (CNOs) face while trying to support ever growing end users' needs towards 5th generation (5G) of mobile networks. This paper investigates a scheduling problem to enhance the performance of non-orthogonal multiple access (NOMA) based cloud radio access networks (C-RAN). We consider the downlink of a C-RAN where cloud is responsible for the scheduling policy and formulate the scheduling problem. In this paper non-orthogonal multiple access (NOMA) is adopted and resource scheduling techniques in an unconstrained C-RAN networks are proposed. We design an efficient resource scheduling algorithm to assist the resource scheduling process in NOMA based C-RAN systems. We formulate the problem as binary integer programming (BIP) optimization problem and propose a suboptimal BIP algorithm and a greedy heuristic allocation algorithm which leads to the maximization of throughput in terms of sum rate when compared with the standard techniques. Simulation results shows significant performance improvement with the proposed algorithms.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129894685","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249113
P. Sharma, P. Kaushik, Prerna Agarwal, P. Jain, Shivangi Agarwal, Kamlesh Dixit
Now customers can opt for software and information technology services according to his requirements and can get these services on a leased basis from the network service provider and this has the facility to scale its requirements to up or down. This service is known as cloud computing, provided by the infrastructure provider which is a third party provider. Cloud computing provides many advantages to the customer like scalability, better economics of scaling, its ability to recover from problems, its ability to outsource non-core activities and flexibility. Cloud computing is a better option for the organizations to take as their best option without any initial investment and day by day frequent and heavy use of cloud computing is increasing but despite all the benefits a cloud offers to an organization there are certain doubts and threats regarding the security issues associated with a cloud computing platform. The security issues primarily involve the external control over organizational structure and management and personal and private data of the organization can be compromised. Personal and private data in this computing environment has a very high risk of breach of confidentiality, integrity and availability. Growth of cloud computing is mainly hampered due to these security concerns and challenges. Proper security arrangements are need to be placed before selecting the service provider for any cloud computing service and customers need to be very careful about understanding the risks of security breaches and challenges of using this new computing environment. This detailed study discusses about some of the challenges associated with cloud computing services and security issues related to this platform.
{"title":"Issues and challenges of data security in a cloud computing environment","authors":"P. Sharma, P. Kaushik, Prerna Agarwal, P. Jain, Shivangi Agarwal, Kamlesh Dixit","doi":"10.1109/UEMCON.2017.8249113","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249113","url":null,"abstract":"Now customers can opt for software and information technology services according to his requirements and can get these services on a leased basis from the network service provider and this has the facility to scale its requirements to up or down. This service is known as cloud computing, provided by the infrastructure provider which is a third party provider. Cloud computing provides many advantages to the customer like scalability, better economics of scaling, its ability to recover from problems, its ability to outsource non-core activities and flexibility. Cloud computing is a better option for the organizations to take as their best option without any initial investment and day by day frequent and heavy use of cloud computing is increasing but despite all the benefits a cloud offers to an organization there are certain doubts and threats regarding the security issues associated with a cloud computing platform. The security issues primarily involve the external control over organizational structure and management and personal and private data of the organization can be compromised. Personal and private data in this computing environment has a very high risk of breach of confidentiality, integrity and availability. Growth of cloud computing is mainly hampered due to these security concerns and challenges. Proper security arrangements are need to be placed before selecting the service provider for any cloud computing service and customers need to be very careful about understanding the risks of security breaches and challenges of using this new computing environment. This detailed study discusses about some of the challenges associated with cloud computing services and security issues related to this platform.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129947024","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249089
Preethi Josephina Mudialba, Siddharth Nair, Jun Ma
Nowadays, companies such as Google [1] and Facebook [2] are present on most websites either through advertising services or through social plugins. They follow users around the web collecting information to create unique user profiles. This serious threat to privacy is a major cause for concern, as this reveals that there are no restrictions on the type of information that can be collected, the duration it can be stored, the people who can access it and the purpose of use or misuse. In order to determine if there indeed is any statistically significant evidence that fingerprinting occurs on certain web services, we integrated 2 software namely, FPBlock [6], a prototype browser extension that blocks web-based device fingerprinting, and AdFisher [10], an automated tool that sending out thousands of automated Web browser instances, in such a manner so that the data collected by FP-Block could be fed to AdFisher for analysis.
{"title":"Finger printing on the web","authors":"Preethi Josephina Mudialba, Siddharth Nair, Jun Ma","doi":"10.1109/UEMCON.2017.8249089","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249089","url":null,"abstract":"Nowadays, companies such as Google [1] and Facebook [2] are present on most websites either through advertising services or through social plugins. They follow users around the web collecting information to create unique user profiles. This serious threat to privacy is a major cause for concern, as this reveals that there are no restrictions on the type of information that can be collected, the duration it can be stored, the people who can access it and the purpose of use or misuse. In order to determine if there indeed is any statistically significant evidence that fingerprinting occurs on certain web services, we integrated 2 software namely, FPBlock [6], a prototype browser extension that blocks web-based device fingerprinting, and AdFisher [10], an automated tool that sending out thousands of automated Web browser instances, in such a manner so that the data collected by FP-Block could be fed to AdFisher for analysis.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131230279","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249017
I. Jouny
Directions of Arrival (DOA) estimation of coherent or incoherent signals impinging on uniformly or non-uniformly spaced linear or uniformly spaced circular antenna arrays are investigated in this paper. DOA is accomplished by using Bayesian compressive sensing reconstruction method. This approach eliminates the need for spatial smoothing and/or array interpolation that are often used when dealing with correlated arrivals and when using non-uniformly spaced antenna arrays or circular arrays. Simulations show that reliable DOA estimates are attainable at signal-to-noise ratios above 5 dB.
{"title":"DOA using uniform/nonuniform linear and uniform circular antenna arrays with Bayesian compressive sensing","authors":"I. Jouny","doi":"10.1109/UEMCON.2017.8249017","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249017","url":null,"abstract":"Directions of Arrival (DOA) estimation of coherent or incoherent signals impinging on uniformly or non-uniformly spaced linear or uniformly spaced circular antenna arrays are investigated in this paper. DOA is accomplished by using Bayesian compressive sensing reconstruction method. This approach eliminates the need for spatial smoothing and/or array interpolation that are often used when dealing with correlated arrivals and when using non-uniformly spaced antenna arrays or circular arrays. Simulations show that reliable DOA estimates are attainable at signal-to-noise ratios above 5 dB.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133211491","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249024
D. Nguyen, C. Kwan, B. Ayhan
Target detection using hyperspectral images has gained popularity in recent years. In this paper, we present a preliminary comparative study of several simple, easy to use, and supervised target detection algorithms, including constrained signal detector (CSD), adaptive CSD, matched subspace detector (MSD), and adaptive subspace detector (ASD). Actual hyperspectral data have been used in our studies. Receiver operating characteristics (ROC) curves were used to compare the various algorithms. It was found that ASD yielded the best performance under the same set of conditions.
{"title":"A comparative study of several supervised target detection algorithms for hyperspectral images","authors":"D. Nguyen, C. Kwan, B. Ayhan","doi":"10.1109/UEMCON.2017.8249024","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249024","url":null,"abstract":"Target detection using hyperspectral images has gained popularity in recent years. In this paper, we present a preliminary comparative study of several simple, easy to use, and supervised target detection algorithms, including constrained signal detector (CSD), adaptive CSD, matched subspace detector (MSD), and adaptive subspace detector (ASD). Actual hyperspectral data have been used in our studies. Receiver operating characteristics (ROC) curves were used to compare the various algorithms. It was found that ASD yielded the best performance under the same set of conditions.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132290926","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}
Electronic mail (Email) is being used for communication in all over the world as a basic communicational media. Few decades ago English was the only language of email but now almost facility of each language for email is present. Now people can use Urdu language as medium of Emails, social media and blog discussions. This Paper finds approaches of Spam/Ham categorization of English Emails are not able to categorize the Urdu emails because Urdu and English script are totally different in many aspects, so these are not directly applicable to Urdu. To categorization of emails into spam and ham is called Emails Spam filtering. Moreover, we need to develop tool by using machine learning technique that is appropriate in Urdu Language. In our work we have performed spam classification for Emails in Urdu language. We have collected different Spam and Ham Urdu Emails from different users. Most of the algorithms and techniques that are used for Spam classification in English and others languages are discussed and evaluated from different countries in this paper.
{"title":"A mechanism to detect urdu Spam emails","authors":"Ayesha Akhtar, Ghulam Rasool Tahir, Khadija Shakeel","doi":"10.1109/UEMCON.2017.8249019","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249019","url":null,"abstract":"Electronic mail (Email) is being used for communication in all over the world as a basic communicational media. Few decades ago English was the only language of email but now almost facility of each language for email is present. Now people can use Urdu language as medium of Emails, social media and blog discussions. This Paper finds approaches of Spam/Ham categorization of English Emails are not able to categorize the Urdu emails because Urdu and English script are totally different in many aspects, so these are not directly applicable to Urdu. To categorization of emails into spam and ham is called Emails Spam filtering. Moreover, we need to develop tool by using machine learning technique that is appropriate in Urdu Language. In our work we have performed spam classification for Emails in Urdu language. We have collected different Spam and Ham Urdu Emails from different users. Most of the algorithms and techniques that are used for Spam classification in English and others languages are discussed and evaluated from different countries in this paper.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132196293","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249104
Muhammad Ajmal Khan, R. Rao, Xianbin Wang
The conventional dual-hop relaying system, without a direct link between the source and the destination, transmits one symbol in two time slots. However, if signal space diversity (SSD) is integrated into the conventional dual-hop relaying system, it transmits two symbols in three time slots to enhance the spectral efficiency of the conventional dual-hop relaying system. In this paper, the outage performance of an SSD-based dual-hop relaying system with multiple decode-and-forward (DF) relays over Rayleigh fading channel is analyzed, and its closed-form expression is derived. Moreover, an asymptotic approximation of the outage probability is obtained and it is used to investigate the impact of different system parameters. Furthermore, system optimization for power is investigated to enhance the outage performance by allocating optimal powers to transmitting nodes. In the end, extensive computer simulations are performed to validate the analytical results.
{"title":"Outage probability and system optimization of SSD-based dual-hop relaying system with multiple relays","authors":"Muhammad Ajmal Khan, R. Rao, Xianbin Wang","doi":"10.1109/UEMCON.2017.8249104","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249104","url":null,"abstract":"The conventional dual-hop relaying system, without a direct link between the source and the destination, transmits one symbol in two time slots. However, if signal space diversity (SSD) is integrated into the conventional dual-hop relaying system, it transmits two symbols in three time slots to enhance the spectral efficiency of the conventional dual-hop relaying system. In this paper, the outage performance of an SSD-based dual-hop relaying system with multiple decode-and-forward (DF) relays over Rayleigh fading channel is analyzed, and its closed-form expression is derived. Moreover, an asymptotic approximation of the outage probability is obtained and it is used to investigate the impact of different system parameters. Furthermore, system optimization for power is investigated to enhance the outage performance by allocating optimal powers to transmitting nodes. In the end, extensive computer simulations are performed to validate the analytical results.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114381848","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8248989
Wenshi Wang, Zhangqin Huang, Shuo Zhang
With the rapid increase of data, stream computation contributes to the improvement of data real time processing. One of characters of stream computing is in the pipeline to exploit parallelism in the MIMD way. Moreover, pipelined parallel implementation is a common problem and often yields much better parallel efficiency with respect to other commonly used methods. Plentiful physical modeling in the field of image processing and machine vision deals with the solution of partial differential equations, typical representative by Poisson's equation. The finite difference schemes as the main method for the solution of partial difference equation for physical modeling can be time-consuming and computationally expensive. Constructing highly parallel computation models can greatly solve the problem and it is important that quickly and efficiently carry out it. The paper mainly studies the parallel implementation of the mix of Jacobi iterative and Gauss-Seidel method for the finite difference schemes to solve Poisson equations in a pipelined fashion on FPGA.
{"title":"Study of a parallel algorithm on pipelined computation of the finite difference schemes on FPGA","authors":"Wenshi Wang, Zhangqin Huang, Shuo Zhang","doi":"10.1109/UEMCON.2017.8248989","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8248989","url":null,"abstract":"With the rapid increase of data, stream computation contributes to the improvement of data real time processing. One of characters of stream computing is in the pipeline to exploit parallelism in the MIMD way. Moreover, pipelined parallel implementation is a common problem and often yields much better parallel efficiency with respect to other commonly used methods. Plentiful physical modeling in the field of image processing and machine vision deals with the solution of partial differential equations, typical representative by Poisson's equation. The finite difference schemes as the main method for the solution of partial difference equation for physical modeling can be time-consuming and computationally expensive. Constructing highly parallel computation models can greatly solve the problem and it is important that quickly and efficiently carry out it. The paper mainly studies the parallel implementation of the mix of Jacobi iterative and Gauss-Seidel method for the finite difference schemes to solve Poisson equations in a pipelined fashion on FPGA.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114896402","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249075
Wyatt Yost, Chetan Jaiswal
The online portion of modern life is growing at an astonishing rate, with the consequence that more of the user's critical information is stored online. This poses an immediate threat to privacy and security of the user's data. This work will cover the increasing dangers and security risks of adware, adware injection, and malware injection. These programs increase in direct proportion to the number of users on the Internet. Each of these programs presents an imminent threat to a user's privacy and sensitive information, anytime they utilize the Internet. We will discuss how current ad blockers are not the actual solution to these threats, but rather a premise to our work. Current ad blocking tools can be discovered by the web servers which often requires suppression of the ad blocking tool. Suppressing the tool creates vulnerabilities in a user's system, but even when the tool is active their system is still susceptible to peril. It is possible, even when an ad blocking tool is functioning, for it to allow adware content through. Our solution to the contemporary threats is our tool, MalFire.
{"title":"MalFire: Malware firewall for malicious content detection and protection","authors":"Wyatt Yost, Chetan Jaiswal","doi":"10.1109/UEMCON.2017.8249075","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249075","url":null,"abstract":"The online portion of modern life is growing at an astonishing rate, with the consequence that more of the user's critical information is stored online. This poses an immediate threat to privacy and security of the user's data. This work will cover the increasing dangers and security risks of adware, adware injection, and malware injection. These programs increase in direct proportion to the number of users on the Internet. Each of these programs presents an imminent threat to a user's privacy and sensitive information, anytime they utilize the Internet. We will discuss how current ad blockers are not the actual solution to these threats, but rather a premise to our work. Current ad blocking tools can be discovered by the web servers which often requires suppression of the ad blocking tool. Suppressing the tool creates vulnerabilities in a user's system, but even when the tool is active their system is still susceptible to peril. It is possible, even when an ad blocking tool is functioning, for it to allow adware content through. Our solution to the contemporary threats is our tool, MalFire.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125792733","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8248969
Zhenwen Gui
In the context of mapping and mobile navigation services, the recognition of the urban infrastructure plays an important role. However, majority of the existing recognition methods cannot be effectively run on the smartphones due to their large computational costs and high storages. In this paper, a fast scene recognition approach is introduced by fusing the outputs of inertial sensors and cameras of smartphones for real-time applications in large scenes. The proposed algorithm possesses the virtues of implementation easiness, storage efficiency and computation significance. Experimental results on the datasets of outdoor scenes and UKBench datasets demonstrate the effectiveness and robustness of the proposed algorithm.
{"title":"A portable real-time scene recognition system on smartphone","authors":"Zhenwen Gui","doi":"10.1109/UEMCON.2017.8248969","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8248969","url":null,"abstract":"In the context of mapping and mobile navigation services, the recognition of the urban infrastructure plays an important role. However, majority of the existing recognition methods cannot be effectively run on the smartphones due to their large computational costs and high storages. In this paper, a fast scene recognition approach is introduced by fusing the outputs of inertial sensors and cameras of smartphones for real-time applications in large scenes. The proposed algorithm possesses the virtues of implementation easiness, storage efficiency and computation significance. Experimental results on the datasets of outdoor scenes and UKBench datasets demonstrate the effectiveness and robustness of the proposed algorithm.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123448160","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：