Pub Date : 2015-12-01DOI: 10.1109/SPIS.2015.7422319
E. S. Abdolkarimi, M. Mosavi, A. Abedi, S. Mirzakuchaki
Both Global Positioning System (GPS) and Inertial Navigation System (INS) have complementary characteristics and their integration provides continuous and accurate navigation solution, compared to standalone INS or GPS. Extended Kalman filtering (EKF) is the most common INS/GPS integration technique used for this purpose. Kalman filter methods require prior knowledge of the error model of INS, which increases the complexity of the system. These methods have some disadvantages in terms of stability, robustness, immunity to noise effect, and observability, especially when used with low-cost MEMS-based inertial sensors. Therefore, in this paper, low-cost INS/GPS integration is enhanced based on artificial intelligence (AI) techniques that are aimed at providing high-accuracy vehicle state estimates. First, the INS and GPS measurements are fused via an EKF method. Second, an artificial intelligence-based approach for the integration of INS/GPS measurements is improved based upon an Adaptive Neuro-Fuzzy Inference System (ANFIS). The performance of the two sensor fusion approaches are evaluated using a real field test data. The experiments have been conducted using a high speed vehicle. The results show great improvements in positioning for low-cost MEMS-based inertial sensors in terms of GPS blockage compared to the EKF-based approach.
{"title":"Optimization of the low-cost INS/GPS navigation system using ANFIS for high speed vehicle application","authors":"E. S. Abdolkarimi, M. Mosavi, A. Abedi, S. Mirzakuchaki","doi":"10.1109/SPIS.2015.7422319","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422319","url":null,"abstract":"Both Global Positioning System (GPS) and Inertial Navigation System (INS) have complementary characteristics and their integration provides continuous and accurate navigation solution, compared to standalone INS or GPS. Extended Kalman filtering (EKF) is the most common INS/GPS integration technique used for this purpose. Kalman filter methods require prior knowledge of the error model of INS, which increases the complexity of the system. These methods have some disadvantages in terms of stability, robustness, immunity to noise effect, and observability, especially when used with low-cost MEMS-based inertial sensors. Therefore, in this paper, low-cost INS/GPS integration is enhanced based on artificial intelligence (AI) techniques that are aimed at providing high-accuracy vehicle state estimates. First, the INS and GPS measurements are fused via an EKF method. Second, an artificial intelligence-based approach for the integration of INS/GPS measurements is improved based upon an Adaptive Neuro-Fuzzy Inference System (ANFIS). The performance of the two sensor fusion approaches are evaluated using a real field test data. The experiments have been conducted using a high speed vehicle. The results show great improvements in positioning for low-cost MEMS-based inertial sensors in terms of GPS blockage compared to the EKF-based approach.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115689388","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422309
Mahdi Gholipour Aghchehkohal, W. Kumara
In this paper we propose a novel method to improve seam carving based on the method meta-heuristic algorithms combining simulated annealing (SA) and genetic algorithm (GA). SA is a single solution method which searches locally while GA belongs to population based algorithms that globally search to find the best answer. By this strategy, both speed and quality of the seam carving method can be increased simultaneously. First, SA is performed to find near optimum seams, which form initial population of GA. Then genetic algorithm develops this initial population to find optimum seam. Experimental results show that search for optimum seams by our proposed method successfully improves the retargeting results of seam carving.
{"title":"Improved seam carving using meta-heuristics algorithms combination","authors":"Mahdi Gholipour Aghchehkohal, W. Kumara","doi":"10.1109/SPIS.2015.7422309","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422309","url":null,"abstract":"In this paper we propose a novel method to improve seam carving based on the method meta-heuristic algorithms combining simulated annealing (SA) and genetic algorithm (GA). SA is a single solution method which searches locally while GA belongs to population based algorithms that globally search to find the best answer. By this strategy, both speed and quality of the seam carving method can be increased simultaneously. First, SA is performed to find near optimum seams, which form initial population of GA. Then genetic algorithm develops this initial population to find optimum seam. Experimental results show that search for optimum seams by our proposed method successfully improves the retargeting results of seam carving.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130272353","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422322
Ghazal Zand, M. Taherkhani, R. Safabakhsh
The six Degrees of freedom (6-Dof) Simultaneous Localization and Mapping (SLAM) aims to build a map of an unknown environment and simultaneously use this map to compute the location with 6-Dof poses. To solve this problem, probabilistic approaches such as Particle Filters (PF) have become dominant methods. PF suffers from certain problems (e.g. the need for large number of particles and so on) which induce high computational complexity. In this paper, an efficient SLAM framework is proposed and new ideas for each module are presented. By combining machine vision and a PF algorithm called the Exponential Natural Particle Filter (xNPF), the predicted results converge close to the true target states. Experimental results validate the potential of the proposed approach.
六自由度(6-Dof) Simultaneous Localization and Mapping (SLAM)旨在构建未知环境的地图，并同时使用该地图计算具有6-Dof姿态的位置。为了解决这一问题，概率方法如粒子滤波(PF)已成为主流方法。PF存在某些问题(例如需要大量粒子等)，这些问题会导致高计算复杂性。本文提出了一个高效的SLAM框架，并对各个模块提出了新的思路。通过将机器视觉和称为指数自然粒子滤波(xNPF)的PF算法相结合，预测结果收敛于接近真实目标状态。实验结果验证了该方法的可行性。
{"title":"A novel framework for simultaneous localization and mapping","authors":"Ghazal Zand, M. Taherkhani, R. Safabakhsh","doi":"10.1109/SPIS.2015.7422322","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422322","url":null,"abstract":"The six Degrees of freedom (6-Dof) Simultaneous Localization and Mapping (SLAM) aims to build a map of an unknown environment and simultaneously use this map to compute the location with 6-Dof poses. To solve this problem, probabilistic approaches such as Particle Filters (PF) have become dominant methods. PF suffers from certain problems (e.g. the need for large number of particles and so on) which induce high computational complexity. In this paper, an efficient SLAM framework is proposed and new ideas for each module are presented. By combining machine vision and a PF algorithm called the Exponential Natural Particle Filter (xNPF), the predicted results converge close to the true target states. Experimental results validate the potential of the proposed approach.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125412350","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422301
M. A. Golroudbari, B. M. Tazehkand
The performance of Beamforming has been significantly improved in antenna array signal processing during recent years. To suppress high sidelobe levels of output beampattern and signal direction mismatches, some notable optimization techniques have been developed. In this paper, an improved convex optimization problem is introduced, which minimizes beamformer output power via using a modified objective function. In addition, to increase the convexity of the proposed approach, an ℓ1-norm constraint is applied to the main problem in order to considerably nullify the interference signals. Moreover, the proposed method effectively deals with steering vector mismatch errors. Simulation results demonstrate the efficiency of the proposed method over the other robust beamforming methods.
{"title":"Robust beamforming based on convex programming with sidelobe and signal direction mismatch control","authors":"M. A. Golroudbari, B. M. Tazehkand","doi":"10.1109/SPIS.2015.7422301","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422301","url":null,"abstract":"The performance of Beamforming has been significantly improved in antenna array signal processing during recent years. To suppress high sidelobe levels of output beampattern and signal direction mismatches, some notable optimization techniques have been developed. In this paper, an improved convex optimization problem is introduced, which minimizes beamformer output power via using a modified objective function. In addition, to increase the convexity of the proposed approach, an ℓ1-norm constraint is applied to the main problem in order to considerably nullify the interference signals. Moreover, the proposed method effectively deals with steering vector mismatch errors. Simulation results demonstrate the efficiency of the proposed method over the other robust beamforming methods.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121909068","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422327
R. Moradi, Rahman Yousefzadeh
In recent years different methods for detecting objectionable images have proposed. All of the previous systems are based on extracting pre-defined and certain features from the images. In this paper a method is proposed in order to detect objectionable images using convolutional neural networks. In this method first features are learned through a sparse auto-encoder and then training is done by a convolutional neural network. The architecture of the network consists of convolution and sub-sampling layers followed by a fully connected output layer which feeds a softmax classifier with cross entropy cost function. The proposed method is able to effectively detect 90.5% of images correctly employing a rather small training dataset.
{"title":"Recognizing objectionable images using convolutional neural nets","authors":"R. Moradi, Rahman Yousefzadeh","doi":"10.1109/SPIS.2015.7422327","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422327","url":null,"abstract":"In recent years different methods for detecting objectionable images have proposed. All of the previous systems are based on extracting pre-defined and certain features from the images. In this paper a method is proposed in order to detect objectionable images using convolutional neural networks. In this method first features are learned through a sparse auto-encoder and then training is done by a convolutional neural network. The architecture of the network consists of convolution and sub-sampling layers followed by a fully connected output layer which feeds a softmax classifier with cross entropy cost function. The proposed method is able to effectively detect 90.5% of images correctly employing a rather small training dataset.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124364135","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422306
Behrouz Bokharaeian, Alberto Díaz
Extracting biomedical relations such as drug-drug interaction (DDI) from text is an important task in biomedical NLP. Due to the large number of complex sentences in biomedical literature, researchers have employed some sentence simplification techniques to improve the performance of the relation extraction methods. However, due to difficulty of the task, there is no noteworthy improvement in the research literature. This paper aims to explore clause dependency related features alongside to linguistic-based negation scope and cues to overcome complexity of the sentences. The experiments indicate the ratio of negation cues which is another source of inaccuracy is higher in complex sentences in comparison with simple ones. Additionally, the results show by employing the proposed features combined with a bag of words kernel, the performance of the used kernel methods improves. Moreover, experiments show the enhanced local context kernel outperforms other methods. The proposed method can be used as an alternative approach for sentence simplification techniques in biomedical area which is an error-prone task.
{"title":"Automatic extraction of drug-drug interaction from literature through detecting clause dependency and linguistic-based negation","authors":"Behrouz Bokharaeian, Alberto Díaz","doi":"10.1109/SPIS.2015.7422306","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422306","url":null,"abstract":"Extracting biomedical relations such as drug-drug interaction (DDI) from text is an important task in biomedical NLP. Due to the large number of complex sentences in biomedical literature, researchers have employed some sentence simplification techniques to improve the performance of the relation extraction methods. However, due to difficulty of the task, there is no noteworthy improvement in the research literature. This paper aims to explore clause dependency related features alongside to linguistic-based negation scope and cues to overcome complexity of the sentences. The experiments indicate the ratio of negation cues which is another source of inaccuracy is higher in complex sentences in comparison with simple ones. Additionally, the results show by employing the proposed features combined with a bag of words kernel, the performance of the used kernel methods improves. Moreover, experiments show the enhanced local context kernel outperforms other methods. The proposed method can be used as an alternative approach for sentence simplification techniques in biomedical area which is an error-prone task.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133656984","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422335
A. Mokari, Alireza Ahmadifard
In this paper we propose a fast method for single image super resolution using self-example learning method. We first divide input image into a number of blocks. For each block a dictionary, is learnt using image patches in the block and its eight neighborhood block around it. In this learning we only use the image patches with considerable details. Each low resolution patch in image is presented as a linear combination of associated local dictionary atoms using Tikhonov regularization. In contrast to existing methods since we only use patches with high details for learning, the complexity of the proposed method is relatively low. The experimental result show the proposed method is significantly faster than existing methods whereas the performance in terms of PSNR criterions is comparable with the existing methods.
{"title":"A fast method for single image super resolution using dictionary learning","authors":"A. Mokari, Alireza Ahmadifard","doi":"10.1109/SPIS.2015.7422335","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422335","url":null,"abstract":"In this paper we propose a fast method for single image super resolution using self-example learning method. We first divide input image into a number of blocks. For each block a dictionary, is learnt using image patches in the block and its eight neighborhood block around it. In this learning we only use the image patches with considerable details. Each low resolution patch in image is presented as a linear combination of associated local dictionary atoms using Tikhonov regularization. In contrast to existing methods since we only use patches with high details for learning, the complexity of the proposed method is relatively low. The experimental result show the proposed method is significantly faster than existing methods whereas the performance in terms of PSNR criterions is comparable with the existing methods.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"626 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131270315","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}
Mohammad Jafar Rezaei, M. Sabahi, K. Shahtalebi, Reza Mahin Zaeem, Rasool Sadeghi
In this paper, a new fairness index to measure resource allocation performance for real-time/delay-tolerant applications is introduced. This index can suggest a new approach for resource allocation. There are several methods have been previously introduced in the literature for resource allocation in cellular networks. Fairness index have an important role to evaluate the performance of these methods. Here, we focus on utility function based resources allocation and related algorithms. According to the introduced method, the base station (BS) allocates resources based on different services requirements. Because of using the appropriate utility function for each application, the requested quality-of-services (QoS) are satisfied. The new well-defined fairness index shows that the proposed method has a good performance for different real-time/delay-tolerant applications. Additionally, numerical results show that this approach is able to improve other important indicators such as throughput and mean opinion score (MOS) as well.
{"title":"A new fairness index and novel approach for QoS-aware resource allocation in LTE networks based on utility functions","authors":"Mohammad Jafar Rezaei, M. Sabahi, K. Shahtalebi, Reza Mahin Zaeem, Rasool Sadeghi","doi":"10.22060/EEJ.2015.579","DOIUrl":"https://doi.org/10.22060/EEJ.2015.579","url":null,"abstract":"In this paper, a new fairness index to measure resource allocation performance for real-time/delay-tolerant applications is introduced. This index can suggest a new approach for resource allocation. There are several methods have been previously introduced in the literature for resource allocation in cellular networks. Fairness index have an important role to evaluate the performance of these methods. Here, we focus on utility function based resources allocation and related algorithms. According to the introduced method, the base station (BS) allocates resources based on different services requirements. Because of using the appropriate utility function for each application, the requested quality-of-services (QoS) are satisfied. The new well-defined fairness index shows that the proposed method has a good performance for different real-time/delay-tolerant applications. Additionally, numerical results show that this approach is able to improve other important indicators such as throughput and mean opinion score (MOS) as well.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115341696","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：