Pub Date : 2018-11-01DOI: 10.1109/CSPIS.2018.8642751
G. Akkad, R. Ayoubi, A. Abche
In this paper a new and highly efficient hardware architecture for a bit-serial implementation of a 3*3 filter on FPGA is developed and presented. The concept is implemented on a Gaussian blur spatial filter and it can be extended to other filters with similar characteristics. The proposed Single Instruction Multiple Data (SIMD) architecture provides a constant operating time independent of the size of the given image while the arithmetic operations are limited to the operations of addition. The Multiple Instruction Multiple Data (MIMD) performance is achieved in a near fraction of the cost. Thus, the hardware’s utilization is optimized. The total time needed to perform the filter of interest on the given image is solely dependent on the working clock frequency. The proposed design is evaluated using a small image and is implemented on two FPGA families with various sizes of an image. Also, it is compared with other architectures.
{"title":"Constant Time Hardware Architecture for a Gaussian Smoothing Filter","authors":"G. Akkad, R. Ayoubi, A. Abche","doi":"10.1109/CSPIS.2018.8642751","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642751","url":null,"abstract":"In this paper a new and highly efficient hardware architecture for a bit-serial implementation of a 3*3 filter on FPGA is developed and presented. The concept is implemented on a Gaussian blur spatial filter and it can be extended to other filters with similar characteristics. The proposed Single Instruction Multiple Data (SIMD) architecture provides a constant operating time independent of the size of the given image while the arithmetic operations are limited to the operations of addition. The Multiple Instruction Multiple Data (MIMD) performance is achieved in a near fraction of the cost. Thus, the hardware’s utilization is optimized. The total time needed to perform the filter of interest on the given image is solely dependent on the working clock frequency. The proposed design is evaluated using a small image and is implemented on two FPGA families with various sizes of an image. Also, it is compared with other architectures.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"33 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":"122041748","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.2018.8642722
Prajowal Manandhar, P. Marpu, Z. Aung
The Environment Agency- Abu Dhabi developed extensive habitat, land cover, land use maps in 2015 using a very high resolution satellite imagery acquired between 2011 and 2013. This map can be used as a baseline map to allow efficient monitoring. In this work, we aim to establish a framework for short term updates to the maps to quickly enable efficient planning. With the availability of multi-spectral images, various spectral bands apart from visible (Red, Green and Blue) bands can be used in habitat mapping. This paper presents the work of land cover classification in the region of Abu Dhabi, UAE using a Worldview-2 satellite image. The proposed approach makes use of Random Forest algorithm, applied on the Fully-Connected features obtained from AlexNet framework using a 20% training samples on a 3-band input. Then, ensemble of outputs of Random Forest over different 3-bands combination is used to make the final prediction. The results are validated against the ground truth obtained from Environment Agency, Abu Dhabi. Eventually, our aim is to develop a robust classification approach and then adapt automatic change detection approaches to temporally update the baseline maps.
{"title":"An Ensemble Approach to Transfer Learning for Classification of Habitat Mapping","authors":"Prajowal Manandhar, P. Marpu, Z. Aung","doi":"10.1109/CSPIS.2018.8642722","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642722","url":null,"abstract":"The Environment Agency- Abu Dhabi developed extensive habitat, land cover, land use maps in 2015 using a very high resolution satellite imagery acquired between 2011 and 2013. This map can be used as a baseline map to allow efficient monitoring. In this work, we aim to establish a framework for short term updates to the maps to quickly enable efficient planning. With the availability of multi-spectral images, various spectral bands apart from visible (Red, Green and Blue) bands can be used in habitat mapping. This paper presents the work of land cover classification in the region of Abu Dhabi, UAE using a Worldview-2 satellite image. The proposed approach makes use of Random Forest algorithm, applied on the Fully-Connected features obtained from AlexNet framework using a 20% training samples on a 3-band input. Then, ensemble of outputs of Random Forest over different 3-bands combination is used to make the final prediction. The results are validated against the ground truth obtained from Environment Agency, Abu Dhabi. Eventually, our aim is to develop a robust classification approach and then adapt automatic change detection approaches to temporally update the baseline maps.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"115 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":"123979234","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.2018.8642716
Shibani Hamsa, A. Panthakkan, S. Al-Mansoori, Husain Alahamed
This paper proposes a novel approach for automatic vehicle detection from aerial images using cascaded Gaussian Mixture Model (GMM) and Support Vector Machine (SVM) algorithm. The GMM based background removal technique eliminates the image background to achieve efficient color classification using SVM classifier. The GMM classifier followed by SVM classification to ensure better results. In the proposed algorithm, the color and local features are the main cues for vehicle detection. To evaluate the performance of the proposed vehicle detection system, the metrics such as hit rate, accuracy and precision valued are used. This paper analyses the system performance and compared it with other background removal methods and classifiers.
{"title":"Automatic Vehicle Detection from Aerial Images using Cascaded Support Vector Machine and Gaussian Mixture Model","authors":"Shibani Hamsa, A. Panthakkan, S. Al-Mansoori, Husain Alahamed","doi":"10.1109/CSPIS.2018.8642716","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642716","url":null,"abstract":"This paper proposes a novel approach for automatic vehicle detection from aerial images using cascaded Gaussian Mixture Model (GMM) and Support Vector Machine (SVM) algorithm. The GMM based background removal technique eliminates the image background to achieve efficient color classification using SVM classifier. The GMM classifier followed by SVM classification to ensure better results. In the proposed algorithm, the color and local features are the main cues for vehicle detection. To evaluate the performance of the proposed vehicle detection system, the metrics such as hit rate, accuracy and precision valued are used. This paper analyses the system performance and compared it with other background removal methods and classifiers.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"15 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":"117007734","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.2018.8642718
Rabia Afzal Minhas, A. Javed
This paper presents an effective method of providing day-to-day mobility aid to visually impaired people. An android application named X-EYE using LOOXCIE wearable camera is designed for blind people to navigate safely. Existing navigation aid systems use various hardware components such as sensors that are expensive and cause health hazards. The proposed system presents an economical solution using a wearable camera and a smart phone to provide safe navigation facility to the visually impaired user. X-EYE provides the features of obstacle detection, person recognition, location tracking and sharing, SMS reader, and language translation. Audio messages are specifically generated to provide better usability to the blind/visually impaired user. The proposed system is robust to egocentric video limitations i.e. partial appearance of objects, sudden background change, jitter effects, and illumination conditions. Performance of the proposed method is evaluated on ten real-time egocentric videos. Experimental results indicate the effectiveness of our method in terms of providing safe mobility service to the visually impaired people.
{"title":"X-EYE: A Bio-smart Secure Navigation Framework for Visually Impaired People","authors":"Rabia Afzal Minhas, A. Javed","doi":"10.1109/CSPIS.2018.8642718","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642718","url":null,"abstract":"This paper presents an effective method of providing day-to-day mobility aid to visually impaired people. An android application named X-EYE using LOOXCIE wearable camera is designed for blind people to navigate safely. Existing navigation aid systems use various hardware components such as sensors that are expensive and cause health hazards. The proposed system presents an economical solution using a wearable camera and a smart phone to provide safe navigation facility to the visually impaired user. X-EYE provides the features of obstacle detection, person recognition, location tracking and sharing, SMS reader, and language translation. Audio messages are specifically generated to provide better usability to the blind/visually impaired user. The proposed system is robust to egocentric video limitations i.e. partial appearance of objects, sudden background change, jitter effects, and illumination conditions. Performance of the proposed method is evaluated on ten real-time egocentric videos. Experimental results indicate the effectiveness of our method in terms of providing safe mobility service to the visually impaired people.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"32 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":"132372673","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.2018.8642758
Alexander Giehl, S. Plaga
Security is an increased concern in smart manufacturing, however, is often met with concerns from operational technology (OT) operators. Performance is paramount in OT communication and, thus, a higher risk is currently deemed acceptable. However, the probability for cyber attacks is rising as recent, successful attacks on factory communication demonstrate. In this work, we present a performant security protocol extension for usage in OT networks. It enables message authentication and data integrity while keeping the protocol overhead within real-time constraints. The protocol extension protects against attacks targeting communication of cyber-physical systems in a smart manufacturing environment. The availability of OT operations facing these attack vectors is, thus, guaranteed.
{"title":"Implementing a performant security control for Industrial Ethernet","authors":"Alexander Giehl, S. Plaga","doi":"10.1109/CSPIS.2018.8642758","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642758","url":null,"abstract":"Security is an increased concern in smart manufacturing, however, is often met with concerns from operational technology (OT) operators. Performance is paramount in OT communication and, thus, a higher risk is currently deemed acceptable. However, the probability for cyber attacks is rising as recent, successful attacks on factory communication demonstrate. In this work, we present a performant security protocol extension for usage in OT networks. It enables message authentication and data integrity while keeping the protocol overhead within real-time constraints. The protocol extension protects against attacks targeting communication of cyber-physical systems in a smart manufacturing environment. The availability of OT operations facing these attack vectors is, thus, guaranteed.","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":"114154358","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.2018.8642729
Ahmed I. Salameh, S. Abdallah, M. Saad
In this paper, we present a novel pilot-based Maximum Likelihood (ML) estimation scheme for the channel and carrier frequency offset (CFO) in amplify-and-forward (AF) two-way relay networks (TWRNs). We develop an estimator for two separate channel scenarios, reciprocal and non-reciprocal. We use simulations to plot the mean-squared error (MSE) performance of the proposed scheme and show that it converges to the corresponding Cramer-Rao bound (CRB) in both cases.
{"title":"On the Performance of Two-way Relays in the Presence of Frequency Offsets","authors":"Ahmed I. Salameh, S. Abdallah, M. Saad","doi":"10.1109/CSPIS.2018.8642729","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642729","url":null,"abstract":"In this paper, we present a novel pilot-based Maximum Likelihood (ML) estimation scheme for the channel and carrier frequency offset (CFO) in amplify-and-forward (AF) two-way relay networks (TWRNs). We develop an estimator for two separate channel scenarios, reciprocal and non-reciprocal. We use simulations to plot the mean-squared error (MSE) performance of the proposed scheme and show that it converges to the corresponding Cramer-Rao bound (CRB) in both cases.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"41 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":"123341643","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.2018.8642734
Khaled Almejalli
Past several decades have witnessed a rapid increase in the nature-inspired computational techniques. Evolutionary Computation is one such group of algorithms inspired by the theory of natural selection and survival of the fittest. This paper presents some for the key problems in the fitness landscape of such algorithms that make it difficult to converge to an optimum solution. These problems not only yield poor convergence but makes the use of Evolutionary Computation techniques less effective. This work then suggests some of the remedies to overcome these hindrances while designing the problem and the objective function. If properly incorporated, the suggested countermeasures enhance the ability of these methods in reaching an optimum solution faster and without entrapment in the local optima.
{"title":"Hindrances in the Fitness Landscape and Remedies to Achieve Optimization","authors":"Khaled Almejalli","doi":"10.1109/CSPIS.2018.8642734","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642734","url":null,"abstract":"Past several decades have witnessed a rapid increase in the nature-inspired computational techniques. Evolutionary Computation is one such group of algorithms inspired by the theory of natural selection and survival of the fittest. This paper presents some for the key problems in the fitness landscape of such algorithms that make it difficult to converge to an optimum solution. These problems not only yield poor convergence but makes the use of Evolutionary Computation techniques less effective. This work then suggests some of the remedies to overcome these hindrances while designing the problem and the objective function. If properly incorporated, the suggested countermeasures enhance the ability of these methods in reaching an optimum solution faster and without entrapment in the local optima.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"87 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":"114898699","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 : 2018-10-09DOI: 10.1109/CSPIS.2018.8642750
Waled Gheth, Khaled Maaiuf Rabie, B. Adebisi, M. Ijaz, Georgina Harris
This paper presents a comprehensive performance analysis of an integrated indoor power line communication (PLC)/visible light communication (VLC) system with the presence of a decode-and-forward (DF) relay. The existing indoor power line networks are used as the backbone for VLCs. The performance of the proposed system is evaluated in terms of the average capacity and the outage probability. A new unified mathematical method is developed for the PLC/VLC system and analytical expressions for the aforementioned performance metrics are derived. Monte Carlo simulations are provided throughout the paper to verify the correctness of the analysis. The results reveal that the performance of the proposed system deteriorates with increasing the end-to-end distance and improves with increasing the relay transmit power. It is also shown that the outage probability of the system under consideration is negatively affected by the vertical distance to user plane.
{"title":"On the Performance of DF-based Power-Line/Visible-Light Communication Systems","authors":"Waled Gheth, Khaled Maaiuf Rabie, B. Adebisi, M. Ijaz, Georgina Harris","doi":"10.1109/CSPIS.2018.8642750","DOIUrl":"https://doi.org/10.1109/CSPIS.2018.8642750","url":null,"abstract":"This paper presents a comprehensive performance analysis of an integrated indoor power line communication (PLC)/visible light communication (VLC) system with the presence of a decode-and-forward (DF) relay. The existing indoor power line networks are used as the backbone for VLCs. The performance of the proposed system is evaluated in terms of the average capacity and the outage probability. A new unified mathematical method is developed for the PLC/VLC system and analytical expressions for the aforementioned performance metrics are derived. Monte Carlo simulations are provided throughout the paper to verify the correctness of the analysis. The results reveal that the performance of the proposed system deteriorates with increasing the end-to-end distance and improves with increasing the relay transmit power. It is also shown that the outage probability of the system under consideration is negatively affected by the vertical distance to user plane.","PeriodicalId":251356,"journal":{"name":"2018 International Conference on Signal Processing and Information Security (ICSPIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128353736","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：