Pub Date : 2018-11-01DOI: 10.1109/CSPIS.2018.8642721
N. Aburaed, A. Panthakkan, Husameldin Mukhtar, W. Mansoor, S. Almansoori, Hussain Al-Ahmad
This paper proposes an algorithm for autonomous building detection in remote sensing images. The basis of the algorithm relies on the fact that each channel in RGB color space conveys different information. Furthermore, region properties and Principal Component Analysis (PCA) are used to distinguish between buildings and other regions in order to reduce false positive cases. The images used to test the proposed algorithm were obtained from DubaiSat-2, which offers multispectral images with 1-m accuracy.
{"title":"Autonomous Building Detection Using Region Properties and PCA","authors":"N. Aburaed, A. Panthakkan, Husameldin Mukhtar, W. Mansoor, S. Almansoori, Hussain Al-Ahmad","doi":"10.1109/CSPIS.2018.8642721","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642721","url":null,"abstract":"This paper proposes an algorithm for autonomous building detection in remote sensing images. The basis of the algorithm relies on the fact that each channel in RGB color space conveys different information. Furthermore, region properties and Principal Component Analysis (PCA) are used to distinguish between buildings and other regions in order to reduce false positive cases. The images used to test the proposed algorithm were obtained from DubaiSat-2, which offers multispectral images with 1-m accuracy.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116681392","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 : 2018-11-01DOI: 10.1109/CSPIS.2018.8642715
Khawla A. Alnajjar, S. Abdallah, M. Saad, Ali El-Moursy
In this work, we consider uplink receiver design for cloud radio access networks (C-RANs) employing massive multi-input multi-ouput (MIMO). Considering joint detection at the base band unit pool for user ends from multiple remote radio heads, we propose a low complexity C-RAN version of the Vertical Bell Laboratories Layered Space-Time (C-RAN-BLAST). The C-RAN versions of the zero-forcing (ZF) and minimum mean-squared error (MMSE) receivers are employed for comparison. The C-RAN-BLAST offers similar performance to the ZF receiver, at much lower complexity. The MMSE receiver performs somewhat better, at the cost of higher complexity, and requiring more detailed channel state information.
{"title":"Low Complexity Receivers for Massive MIMO Cloud Radio Access Systems","authors":"Khawla A. Alnajjar, S. Abdallah, M. Saad, Ali El-Moursy","doi":"10.1109/CSPIS.2018.8642715","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642715","url":null,"abstract":"In this work, we consider uplink receiver design for cloud radio access networks (C-RANs) employing massive multi-input multi-ouput (MIMO). Considering joint detection at the base band unit pool for user ends from multiple remote radio heads, we propose a low complexity C-RAN version of the Vertical Bell Laboratories Layered Space-Time (C-RAN-BLAST). The C-RAN versions of the zero-forcing (ZF) and minimum mean-squared error (MMSE) receivers are employed for comparison. The C-RAN-BLAST offers similar performance to the ZF receiver, at much lower complexity. The MMSE receiver performs somewhat better, at the cost of higher complexity, and requiring more detailed channel state information.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115175676","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 : 2018-11-01DOI: 10.1109/CSPIS.2018.8642723
Q. Chaudhari, Wayne S. T. Rowe
The infrastructure available to the mobile phones is too costly to deploy for localizing small wireless devices in an Internet of Things (IoT) framework. Among available RF solutions, those based on the time of arrival measurements at a network of unsynchronized anchors suit quite well to this application. In this paper, we consider a wireless device moving at a pedestrian speed within such a network of unsynchronized anchors and track its position using time of flight measurements that are processed through an Extended Kaiman Filter (EKF). The system dynamics here come from the uniform speed of the device as well as the skew of the clocks involved. The purpose is to compare the results with Time Difference of Arrival (TDoA) and Differential Time Difference of Arrival (DTDoA) measurements that act as a lower and upper bound for this system, respectively.
{"title":"Robust Localization of a Wireless Device by a Network of Unsynchronized Anchors","authors":"Q. Chaudhari, Wayne S. T. Rowe","doi":"10.1109/CSPIS.2018.8642723","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642723","url":null,"abstract":"The infrastructure available to the mobile phones is too costly to deploy for localizing small wireless devices in an Internet of Things (IoT) framework. Among available RF solutions, those based on the time of arrival measurements at a network of unsynchronized anchors suit quite well to this application. In this paper, we consider a wireless device moving at a pedestrian speed within such a network of unsynchronized anchors and track its position using time of flight measurements that are processed through an Extended Kaiman Filter (EKF). The system dynamics here come from the uniform speed of the device as well as the skew of the clocks involved. The purpose is to compare the results with Time Difference of Arrival (TDoA) and Differential Time Difference of Arrival (DTDoA) measurements that act as a lower and upper bound for this system, respectively.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132500723","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 : 2018-11-01DOI: 10.1109/CSPIS.2018.8642717
Nadiya Dilshad, Kamarul Faizal Bin Hashim, Sami Miniaoui, Shadi Atalla
The main objective of this paper is to discuss the implementation of a Smart Happiness Meter (SHM) prototype that adopts a face detection and recognition approach to provide a real-time statistic on customer satisfaction. This prototype does not only detect and recognize images but also determine customer emotion using sentiment analysis technique. The development of this prototype provides an alternative methodology to existing approach of measuring customer’s happiness which rely heavily on manual surveys using mobile applications. This paper discusses about the design and development methodology, its use-case diagrams and demonstrates the deliverables of the prototype in general.
{"title":"Smart Happiness Meter","authors":"Nadiya Dilshad, Kamarul Faizal Bin Hashim, Sami Miniaoui, Shadi Atalla","doi":"10.1109/CSPIS.2018.8642717","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642717","url":null,"abstract":"The main objective of this paper is to discuss the implementation of a Smart Happiness Meter (SHM) prototype that adopts a face detection and recognition approach to provide a real-time statistic on customer satisfaction. This prototype does not only detect and recognize images but also determine customer emotion using sentiment analysis technique. The development of this prototype provides an alternative methodology to existing approach of measuring customer’s happiness which rely heavily on manual surveys using mobile applications. This paper discusses about the design and development methodology, its use-case diagrams and demonstrates the deliverables of the prototype in general.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121658870","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 : 2018-11-01DOI: 10.1109/CSPIS.2018.8642724
S. Miniaoui, Suadad Muammar, Shadi Atalla, K. F. Hashim
This paper is proposing an innovative application (e-Pot) which uses QR Code technology along with a Web application for helping plant-fans manage, maintain and share practices using their mobile phones. Sharing experiences of growing a specific plant or identifying its requirements in terms of sunlight, temperature, recommended soil with other members can help in answering the crucial question which is: Why would you want to own this plant? The application is providing Facebook users with commenting option and notify them about any updates. Additionally, by leveraging mobile phones capabilities, this application provides users with a search by image feature by just picturing any plant on the go then searching among the recorded plants (Plantopedia) as well as Google image database. The e-Pot system is also allowing its members to maintain an account whereby they can register their own plants so the system can remind them through e-mail about convenient irrigation times according to the best practices.
{"title":"Innovating Plant-Care applications by combining QR-Technology & Image Search","authors":"S. Miniaoui, Suadad Muammar, Shadi Atalla, K. F. Hashim","doi":"10.1109/CSPIS.2018.8642724","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642724","url":null,"abstract":"This paper is proposing an innovative application (e-Pot) which uses QR Code technology along with a Web application for helping plant-fans manage, maintain and share practices using their mobile phones. Sharing experiences of growing a specific plant or identifying its requirements in terms of sunlight, temperature, recommended soil with other members can help in answering the crucial question which is: Why would you want to own this plant? The application is providing Facebook users with commenting option and notify them about any updates. Additionally, by leveraging mobile phones capabilities, this application provides users with a search by image feature by just picturing any plant on the go then searching among the recorded plants (Plantopedia) as well as Google image database. The e-Pot system is also allowing its members to maintain an account whereby they can register their own plants so the system can remind them through e-mail about convenient irrigation times according to the best practices.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121431339","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 : 2018-11-01DOI: 10.1109/CSPIS.2018.8642727
Bello Ahmed Dangiwa, Smitha S Kumar
As the accessibility of high-resolution smartphone camera has increased and an improved computational speed, it is now convenient to build Business Card Readers on mobile phones. The project aims to design and develop a Business Card Reader (BCR) Application for iOS devices, using an open-source OCR Engine – Tesseract. The system accuracy was tested and evaluated using a dataset of 55 digital business cards obtained from an online repository. The accuracy result of the system was up to 74% in terms of both text recognition and data detection. A comparative analysis was carried out against a commercial business card reader application and our application performed vastly reasonable.
{"title":"A Business Card Reader Application for iOS devices based on Tesseract","authors":"Bello Ahmed Dangiwa, Smitha S Kumar","doi":"10.1109/CSPIS.2018.8642727","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642727","url":null,"abstract":"As the accessibility of high-resolution smartphone camera has increased and an improved computational speed, it is now convenient to build Business Card Readers on mobile phones. The project aims to design and develop a Business Card Reader (BCR) Application for iOS devices, using an open-source OCR Engine – Tesseract. The system accuracy was tested and evaluated using a dataset of 55 digital business cards obtained from an online repository. The accuracy result of the system was up to 74% in terms of both text recognition and data detection. A comparative analysis was carried out against a commercial business card reader application and our application performed vastly reasonable.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123939149","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 : 2018-11-01DOI: 10.1109/cspis.2018.8642731
{"title":"ICSPIS 2018 List Reviewer","authors":"","doi":"10.1109/cspis.2018.8642731","DOIUrl":"https://doi.org/10.1109/cspis.2018.8642731","url":null,"abstract":"","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124653356","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 : 2018-11-01DOI: 10.1109/CSPIS.2018.8642713
Iman I. M. Abu Sulayman, Abdelkader H. Ouda
Big Data-based applications have been increased especially those which utilize anomaly detection techniques. This paper puts a new insight into the anomaly detection techniques, suitable for Big Data applications. This study is supported by novel classifications and practical based implementation. Three classifications are proposed for anomaly detection techniques that are aligned with Big Data characteristics and powered by several applications of the machine learning techniques, such as Support Vector Machine and neural network. This has helped to evaluate and recommend for the best practices in anomaly detection and hence a new implementation has been provided.
{"title":"Data Analytics Methods for Anomaly Detection: Evolution and Recommendations","authors":"Iman I. M. Abu Sulayman, Abdelkader H. Ouda","doi":"10.1109/CSPIS.2018.8642713","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642713","url":null,"abstract":"Big Data-based applications have been increased especially those which utilize anomaly detection techniques. This paper puts a new insight into the anomaly detection techniques, suitable for Big Data applications. This study is supported by novel classifications and practical based implementation. Three classifications are proposed for anomaly detection techniques that are aligned with Big Data characteristics and powered by several applications of the machine learning techniques, such as Support Vector Machine and neural network. This has helped to evaluate and recommend for the best practices in anomaly detection and hence a new implementation has been provided.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128832051","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 : 2018-11-01DOI: 10.1109/CSPIS.2018.8642726
A. Darya, I. Fernini
As a result of the ever-increasing number of space debris, space agencies all over the world are developing their own space debris monitoring and tracking systems. Due to the lack of any formal study of this nature in the Arabian Peninsula, this paper aims to remedy this by performing a study into space debris re-entry over the Arabian Peninsula for the last 15 years (2004-2018) using data provided by the Joint Space Operations Center (JSpOC). JSpOC provides information produced using radar measurements and various computational techniques that establish it as the leading provider of space debris data. The rate of space debris re-entry has been found to be accelerating during the study period, with growth rate increasing every 5 years. This study serves as a precursor to a more comprehensive analysis of debris re-entry over the Arabian Peninsula and the creation of a system to fulfill the regional need for space debris tracking.
{"title":"Analysis of Space Debris Re-Entry over the Arabian Peninsula (2004 to 2018)","authors":"A. Darya, I. Fernini","doi":"10.1109/CSPIS.2018.8642726","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642726","url":null,"abstract":"As a result of the ever-increasing number of space debris, space agencies all over the world are developing their own space debris monitoring and tracking systems. Due to the lack of any formal study of this nature in the Arabian Peninsula, this paper aims to remedy this by performing a study into space debris re-entry over the Arabian Peninsula for the last 15 years (2004-2018) using data provided by the Joint Space Operations Center (JSpOC). JSpOC provides information produced using radar measurements and various computational techniques that establish it as the leading provider of space debris data. The rate of space debris re-entry has been found to be accelerating during the study period, with growth rate increasing every 5 years. This study serves as a precursor to a more comprehensive analysis of debris re-entry over the Arabian Peninsula and the creation of a system to fulfill the regional need for space debris tracking.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126768089","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 : 2018-11-01DOI: 10.1109/CSPIS.2018.8642714
Wael A. Deabes, Alaa E. Abdel-Hakim
With the rapid growth of big data applications, the training process of deep neural networks is getting more expensive in terms of the computational cost. In this paper, we propose an algorithm to exploit the reliability of existing convolutional neural networks that has been gained during earlier training processes. We use fuzzy integrals to perform late fusion on the classification decisions taken by pre-trained classifiers. The proposed method was evaluated using the ImageNet benchmark with ten different pre-trained state-of-the-arts Convolutional Neural Networks (CNN) models. The evaluation results show that the proposed fuzzy-based fusion method could achieve better performance than the best of the contributing models, in terms of recognition accuracy. The accuracy improvement ranges from 8% to 30% better than the used pre-trained classifiers.
{"title":"Teaming Up Pre-Trained Deep Neural Networks","authors":"Wael A. Deabes, Alaa E. Abdel-Hakim","doi":"10.1109/CSPIS.2018.8642714","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642714","url":null,"abstract":"With the rapid growth of big data applications, the training process of deep neural networks is getting more expensive in terms of the computational cost. In this paper, we propose an algorithm to exploit the reliability of existing convolutional neural networks that has been gained during earlier training processes. We use fuzzy integrals to perform late fusion on the classification decisions taken by pre-trained classifiers. The proposed method was evaluated using the ImageNet benchmark with ten different pre-trained state-of-the-arts Convolutional Neural Networks (CNN) models. The evaluation results show that the proposed fuzzy-based fusion method could achieve better performance than the best of the contributing models, in terms of recognition accuracy. The accuracy improvement ranges from 8% to 30% better than the used pre-trained classifiers.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133069354","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：