2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)最新文献_第4页

Random noise attenuation in 3D seismic data by iterative block tensor singular value thresholding 基于迭代块张量奇异值阈值法的三维地震数据随机噪声抑制

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311609

R. Anvari, A. R. Kahoo, M. Mohammadi, A. Pouyan

{"title":"Random noise attenuation in 3D seismic data by iterative block tensor singular value thresholding","authors":"R. Anvari, A. R. Kahoo, M. Mohammadi, A. Pouyan","doi":"10.1109/ICSPIS.2017.8311609","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311609","url":null,"abstract":"The principal component analysis (PCA) is one of the most widely used technique in two-dimensional data analysis which uses singular value decomposition of matrix data and extracts its low-rank components. Using the PCA, seismic signals are represented in a sparse way which is a useful and popular methodology in signal-processing applications. Tensor principal component analysis (TPCA) as a multi-linear extension of principal component analysis, converts a set of correlated measurements into several principal components. In this paper, based on the singular value decomposition and extracting low-rank component as the denoised data, we used a new version of TPCA for denoising 3D seismic data in which, tensor data split into a number of blocks of the same size. The low-rank component of each block tensor is extracted using iterative tensor singular value thresholding method. The principal components of the multi-way data are the concatenation of all the low-rank components of all the block tensors. To demonstrate the performance of the proposed method for denoising 3D seismic data, we apply it to a 3D synthetic seismic data and a 3D real seismic data.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130388007","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}

引用次数: 4

Scalable image tamper detection and recovery based on dual-rate source-channel coding 基于双速率源信道编码的可扩展图像篡改检测与恢复

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311600

N. Daneshmandpour, H. Danyali, M. Helfroush

{"title":"Scalable image tamper detection and recovery based on dual-rate source-channel coding","authors":"N. Daneshmandpour, H. Danyali, M. Helfroush","doi":"10.1109/ICSPIS.2017.8311600","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311600","url":null,"abstract":"In image tamper detection and recovery methods prevalently two sets of data need to be embedded into the main image, one known as authentication data for tamper detection and the other known as reference data for tamper recovery. In this paper, a scalable method for image tamper detection and recovery based on a dual-rate source-channel coding is proposed. In the proposed method the original image is first compressed by a scalable source coding algorithm. The compressed bitstream is then partitioned into two parts. Both parts are protected with a channel coding algorithm but with two different rates according to their importance for tamper recovery process. The proposed method takes advantage of two state-of-the-art algorithms, SPIHT for source coding and LDPC for channel coding. Simulation results show a noticeable improvement compared with related tamper detection and recovery schemes in the literature. Besides the reconstruction quality of the recovered image is scalable. This means that in low tampering rates, high-quality images are recovered and in high tampering rates, the image is still recoverable but with less reconstruction quality. Therefore the proposed method succeeded to both recover higher tampering rates and preserve the image quality.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"2003 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128700963","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}

引用次数: 1

Interference modeling for energy aware geographical routing in cognitive radio ad hoc networks 认知无线电自组网中能量感知地理路由的干扰建模

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311597

Soodeh Amiri Doomari, Ghasem Miijalily

{"title":"Interference modeling for energy aware geographical routing in cognitive radio ad hoc networks","authors":"Soodeh Amiri Doomari, Ghasem Miijalily","doi":"10.1109/ICSPIS.2017.8311597","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311597","url":null,"abstract":"In an energy constrained cognitive radio ad-hoc network, protecting primary users from interferences caused by secondary users and saving more energy are crucial aims. In designing interference aware routing protocols, correct modeling of the interference is an important factor that affects the network performance considerably. In this paper, we propose an interference and energy aware geographical routing algorithm for cognitive radio ad-hoc networks by considering two different interference models. The novelty of the proposed algorithm lies in the new modeling of the interference and proposing a normalized linear utility function to have more control over design metrics such as end-to-end delay, aggregate interference energy and goodput. In proposed algorithm, we estimate the total interference power caused by secondary users in two ways: i) By using the path loss model, and ii) By considering the overlap areas between the secondary and primary users. The performance of the proposed algorithm is evaluated for both interference models from different perspectives such as end-to-end delay, average aggregate interference energy and goodput. The simulation results clarify the efficiency of the proposed scheme compared to the Spectrum and Energy aware Routing algorithm suggested in [1].","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129629851","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}

引用次数: 0

Using artificial neural networks and system identification methods for electricity price modeling 采用人工神经网络和系统辨识方法对电价进行建模

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/icspis.2017.8311587

MohammadHossein Jamshidi, H. Siahkamari, M. Jamshidi

引用次数: 10

NPC: Neighbors' progressive competition algorithm for classification of imbalanced data sets 邻域渐进竞争算法用于不平衡数据集的分类

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-11-29 DOI: 10.1109/ICSPIS.2017.8311584

Soroush Saryazdi, Bahareh Nikpour, H. Nezamabadi-pour

{"title":"NPC: Neighbors' progressive competition algorithm for classification of imbalanced data sets","authors":"Soroush Saryazdi, Bahareh Nikpour, H. Nezamabadi-pour","doi":"10.1109/ICSPIS.2017.8311584","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311584","url":null,"abstract":"Learning from many real-world datasets is limited by a problem called the class imbalance problem. A dataset is imbalanced when one class (the majority class) has significantly more samples than the other class (the minority class). Such datasets cause typical machine learning algorithms to perform poorly on the classification task. To overcome this issue, this paper proposes a new approach Neighbors' Progressive Competition (NPC) for classification of imbalanced datasets. Whilst the proposed algorithm is inspired by weighted k-Nearest Neighbor (k-NN) algorithms, it has major differences from them. Unlike k-NN, NPC does not limit its decision criteria to a preset number of nearest neighbors. In contrast, NPC considers progressively more neighbors of the query sample in its decision making until the sum of grades for one class is much higher than the other classes. Furthermore, NPC uses a novel method for grading the training samples to compensate for the imbalance issue. The grades are calculated using both local and global information. In brief, the contribution of this paper is an entirely new classifier for handling the imbalance issue effectively without any manually-set parameters or any need for expert knowledge. Experimental results compare the proposed approach with five representative algorithms applied to fifteen imbalanced datasets and illustrate this algorithm's effectiveness.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115717980","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}

引用次数: 15

Semi-supervised hierarchical semantic object parsing 半监督分层语义对象解析

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-09-23 DOI: 10.1109/ICSPIS.2017.8311588

Jalal Mirakhorli, H. Amindavar

{"title":"Semi-supervised hierarchical semantic object parsing","authors":"Jalal Mirakhorli, H. Amindavar","doi":"10.1109/ICSPIS.2017.8311588","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311588","url":null,"abstract":"Models based on Convolutional Neural Networks (CNNs) have been proven very successful for semantic segmentation and object parsing that yield hierarchies of features. Our key insight is to build convolutional networks that take input of arbitrary size and produce object parsing output with efficient inference and learning. In this work, we focus on the task of instance segmentation and parsing which recognizes and localizes objects down to a pixel level base on deep CNN. Therefore, unlike some related work, a pixel cannot belong to multiple instances and parsing. Our model is based on a deep neural network trained for object masking that supervised with input image and follow incorporates a Conditional Random Field (CRF) with end-to-end trainable piecewise order potentials based on object parsing outputs. In each CRF unit we designed terms to capture the short range and long range dependencies from various neighbors. The accurate instance-level segmentation that our network produce is reflected by the considerable improvements obtained over previous work at high APr thresholds. We demonstrate the effectiveness of our model with extensive experiments on challenging dataset subset of PASCAL VOC 2012.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133658915","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}

引用次数: 6

Grid impedance estimation using low power signal injection in noisy measurement condition based on wavelet denoising 基于小波去噪的低功率信号注入网格阻抗估计

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 1900-01-01 DOI: 10.1109/ICSPIS.2017.8311594

Mohammad. M. Alyan Nezhadi, H. Hassanpour, Firuz Zare

{"title":"Grid impedance estimation using low power signal injection in noisy measurement condition based on wavelet denoising","authors":"Mohammad. M. Alyan Nezhadi, H. Hassanpour, Firuz Zare","doi":"10.1109/ICSPIS.2017.8311594","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311594","url":null,"abstract":"Grid impedance estimation is used in many power system applications such as power quality analysis of smart grids and grid connected renewable energy systems. In this paper a low power and high frequency range signal injected to grid, and the ratio of voltage to current signal is calculated as impedance. Accuracy of impedance estimation in noiseless systems is independent to energy of injected signal. However, in noisy system, energy of injected signal must be sufficient for an accurate approximation. In this paper, two groups of noise (source harmonic voltage noise and measurement noise) are considered. The additive white Gaussian noise is assumed as the measurement noise. In this paper, we proposed to denoising the current and voltage signals using stationary wavelet denoising without increasing the energy of the injected signal. The injection signal is a short duration rectangular pulse. Accurate impedance estimation using signal injection can be done in frequencies that the energy of signal is bigger enough than the energy of noise. The simulation results show that the proposed method can properly estimate grid impedance in a wide frequency range 2 kHz to 150 kHz.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132588160","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}

引用次数: 6