发布求助
文献互助 智能选刊 最新文献

2017 Artificial Intelligence and Signal Processing Conference (AISP)最新文献

筛选
英文 中文
An improved cartoon+texture decomposition based pansharpening method 改进的基于卡通+纹理分解的泛锐化方法
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8324121
M. Lotfi, H. Ghassemian
{"title":"An improved cartoon+texture decomposition based pansharpening method","authors":"M. Lotfi, H. Ghassemian","doi":"10.1109/AISP.2017.8324121","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324121","url":null,"abstract":"Pansharpening is the most widely used fusion method, in the field of remote sensing, to increase spatial information of the multispectral image while preserving spectral signatures. Based on the nature of spatial and spectral information, there is a lack of correlation between them. Therefore, separation of them can be considered as an image decomposition to uncorrelated components. Recently, the cartoon+texture decomposition was used in the pansharpening and decrease spectral distortion. However, details have not been strengthened enough. Therefore, in this paper we aim to use a filter based detail extraction to improve spatial information while mitigate spectral distortion.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130358864","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: 2
Proposing an efficient approach for malware clustering 提出了一种有效的恶意软件聚类方法
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8324094
Maryam Mohammadi, A. Hamzeh
{"title":"Proposing an efficient approach for malware clustering","authors":"Maryam Mohammadi, A. Hamzeh","doi":"10.1109/AISP.2017.8324094","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324094","url":null,"abstract":"Recently, malwares in security threats have a top rank which can damage computing systems and networks seriously. Over time malwares become more complicated and detection of them gets harder. Because traditional techniques such as signature based were not successful to detect metamorphic malwares, machine learning algorithms have been used to detect them. The Hidden Markov Model (HMM) has been successfully used in speech recognition, pattern recognition, part-of-speech tagging and biological sequence analysis. Previous work has shown that HMM is a convincing method for malware detection. However, some advanced metamorphic malwares have demonstrated to be more challenging to detect with these techniques. In this paper, we use clustering techniques with the probabilities as features based on HMM to the malware detection problem. In fact, we use clustering as classifier to detect malware. We compute clusters with K-means and Expectation Maximization algorithms. Results revealed that using clustering instead of HMM based approach, can have reasonable accuracy for metamorphic malware detection.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132943970","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: 2
Fuzzy transfer learning approach for analysing imagery BCI tasks 图像BCI任务分析的模糊迁移学习方法
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8324101
Abbas Salami, M. Khodabakhshi, M. Moradi
{"title":"Fuzzy transfer learning approach for analysing imagery BCI tasks","authors":"Abbas Salami, M. Khodabakhshi, M. Moradi","doi":"10.1109/AISP.2017.8324101","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324101","url":null,"abstract":"In brain-computer interfaces (BCI), the statistical distribution of the data could differ across subjects as well as across sessions for an individual subject. Moreover, the lack of data due to the difficulties in collecting data in BCI is a common challenge in training the systems. Since most of machine learning tools are based on the assumption that the distribution of training and testing data are the same and they need adequate training data, they would fail in such situations. To overcome this problem and because of the vague and uncertain essence of EEG data, in this paper, we used a fuzzy transfer learning (FTL) method based on Generalized Hidden-Mapping Ridge Regression (GHRR) to improve the classification task in BCI. Takagi-Sugeno-Kang fuzzy logical system (TSK) with proposed modified Wang-Mendel fuzzy rule generation were employed for classification. Then the session-to-session transfer of knowledge is adopted. The results demonstrate the effectiveness of our proposed method in classification and outperform the well-known SVM classifier.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"18 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132146480","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: 5
RDPSO diversity enhancement based on repulsion between similar ions for robotic target searching 基于相似离子间斥力的RDPSO多样性增强机器人目标搜索
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8324096
Masoud Dadgar, M. Couceiro, A. Hamzeh
{"title":"RDPSO diversity enhancement based on repulsion between similar ions for robotic target searching","authors":"Masoud Dadgar, M. Couceiro, A. Hamzeh","doi":"10.1109/AISP.2017.8324096","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324096","url":null,"abstract":"In this paper, we studied the problem of multi-robot target searching. We contributed to the current state-of-the-art by proposing a novel mechanism to increase the convergence speed based on a repulsion mechanism between similar ions. In this article, we perceive robots as ions, wherein the main purpose of the adopted approach is to keep the level of diversity among the robots stable. This mechanism will be applied to a particle swarm optimization (PSO) approach, denoted as Robotic Darwinian PSO (RDPSO). This improvement was done to speed up the previously proposed approaches and to provide accurate search results. The results depict the superiority of the proposed approach both in terms of speed and search result. Also, the proposed approach shows a superior performance when it is compared with other approaches as the number of robots decreases.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133023435","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: 9
A reversible data hiding scheme based on prediction-error expansion using pixel-based pixel value ordering predictor 一种基于基于像素的像素值排序预测器的预测误差扩展的可逆数据隐藏方案
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8324085
Peyman Rahmani, G. Dastghaibyfard
{"title":"A reversible data hiding scheme based on prediction-error expansion using pixel-based pixel value ordering predictor","authors":"Peyman Rahmani, G. Dastghaibyfard","doi":"10.1109/AISP.2017.8324085","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324085","url":null,"abstract":"In this paper, a reversible data hiding (RDH) scheme based on prediction-error expansion (PEE) technique is proposed. PEE-based RDH methods exploit the correlations between neighboring pixels of the cover image to predict the pixel values and then embed data into the expanded prediction-errors. Traditional predictors exploit only the neighboring pixels and do not utilize the value of to be predicted pixel. Recently, Qu and Kim developed a pixel-based pixel value ordering (PPVO) predictor, which exploit the neighboring pixels as well as the pixel value itself, then the histogram shifting technique is applied to embed data. In the scheme proposed in this paper, the PPVO predictor is modified and a PEE-based RDH scheme is developed for data embedding. The experimental results show that the proposed scheme significantly outperforms some existing schemes in terms of the embedding capacity and visual quality.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"64 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114120837","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
A new approach on multi-agent Multi-Objective Reinforcement Learning based on agents' preferences 基于智能体偏好的多智能体多目标强化学习新方法
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8324111
Zeinab Daavarani Asl, V. Derhami, Mehdi Yazdian-Dehkordi
{"title":"A new approach on multi-agent Multi-Objective Reinforcement Learning based on agents' preferences","authors":"Zeinab Daavarani Asl, V. Derhami, Mehdi Yazdian-Dehkordi","doi":"10.1109/AISP.2017.8324111","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324111","url":null,"abstract":"Reinforcement Learning (RL) is a powerful machine learning paradigm for solving Markov Decision Process (MDP). Traditional RL algorithms aim to solve one-objective problems, but many real-world problems have more than one objective which conflict each other. In recent years, Multi-Objective Reinforcement Learning (MORL) algorithms, which employ a reward vector instead of a scalar reward signal, have been proposed to solve multi-objective problems. In MORL, because of conflicting objectives, there is no one optimal solution and a set of solutions named Pareto Front will be learned. In this paper, we proposed a new multi-agent method, which uses a shared Q-table for all agents to solve bi-objective problems. However, each agent selects actions based on its preference. These preferences are different with each other and the agents reach to Pareto Front solutions based on this preferences. The proposed method is simple in understanding and its computational cost is very low. Moreover, after finding the Pareto Front set, we can easily track the policy. Simulation results show that our proposed method outperforms the available methods in the term of learning speed.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114390858","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: 3
Automatic query-based keyword and keyphrase extraction 自动基于查询的关键字和关键短语提取
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8515121
Farnoush Bayatmakou, Abbas Ahmadi, Azadeh Mohebi
{"title":"Automatic query-based keyword and keyphrase extraction","authors":"Farnoush Bayatmakou, Abbas Ahmadi, Azadeh Mohebi","doi":"10.1109/AISP.2017.8515121","DOIUrl":"https://doi.org/10.1109/AISP.2017.8515121","url":null,"abstract":"Extracting keywords and keyphrases mainly for identifying content of a document, has an importance role in text processing tasks such as text summarization, information retrieval, and query expansion. In this research, we introduce a new keyword/keyphrase extraction approach in which both single and multi-document keyword/keyphrase extraction techniques are considered. The proposed approach is specifically practical when a user is interested in additional data such as keywords/keyphrases related to a topic or query. In the proposed approach, first a set of documents are retrieved based on user's query, then a single document keyword extraction method is applied to extract candidate keyword/keyphrases from each retrieved document. Finally, a new re-scoring scheme is introduced to extract final keywords/keyphrases. We have evaluated the proposed method based on the relationship between the final keyword/keyphrases with the initial user query, and based user's satisfaction. Our experimental results show how much the extracted keywords/keyphrases are relevant and wellmatched with user's need.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114602321","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
Multi-label classification systems by the use of supervised clustering 使用监督聚类的多标签分类系统
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8324090
Niloofar Rastin, M. Z. Jahromi, M. Taheri
{"title":"Multi-label classification systems by the use of supervised clustering","authors":"Niloofar Rastin, M. Z. Jahromi, M. Taheri","doi":"10.1109/AISP.2017.8324090","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324090","url":null,"abstract":"Multi-label classification problem involves finding a model that maps a set of input features to more than one output labels. It is well known that, exploiting label correlations is important for multi-label learning. In this paper, a supervised clustering-based multi-label classification method is proposed that uses supervised clustering for considering label correlations. The proposed approach enhanced the performance of multi-label classification systems in comparison with the state of the art. Experimental results on a number of image, music and text datasets validate the effectiveness of the proposed approach.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133520317","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
Developing a fast supervised optimum-path forest based on coreset 基于核心集的快速监督最优路径森林
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8324076
Hamid Bostani, M. Sheikhan, B. Mahboobi
{"title":"Developing a fast supervised optimum-path forest based on coreset","authors":"Hamid Bostani, M. Sheikhan, B. Mahboobi","doi":"10.1109/AISP.2017.8324076","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324076","url":null,"abstract":"Optimum-path forest (OPF) is an effective graph-based machine learning that simplifies the pattern recognition problems into the partitioning the corresponding derived graphs of the input datasets. The amounts of the samples in the input datasets and, consequently the size of the node set of their corresponding derived graphs has a major effect on the speed of OPF. In this study a novel version of OPF is introduced which utilizes coreset approach for reducing the scale of the input dataset. From the aspect of the computational geometry, coreset is a small set of points that includes the best representative points of the original point set with regard to a geometric objective function. Our method finds the most informative vertices (samples) by proposing a novel incremental coreset construction algorithm. The experimental results of the proposed method reduces the input data samples, and the execution times of the construction and the classification phases of OPF by 80%, 60%, and 12%, respectively, in contrast to the traditional OPF.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133557184","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: 3
High performance implementation of 2D convolution using Intel's advanced vector extensions 使用英特尔先进的矢量扩展的二维卷积的高性能实现
2017 Artificial Intelligence and Signal Processing Conference (AISP) Pub Date : 2017-10-01 DOI: 10.1109/AISP.2017.8324097
Hossein Amiri, A. Shahbahrami
{"title":"High performance implementation of 2D convolution using Intel's advanced vector extensions","authors":"Hossein Amiri, A. Shahbahrami","doi":"10.1109/AISP.2017.8324097","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324097","url":null,"abstract":"Convolution is the most important and fundamental concept in multimedia processing. For example, for digital image processing 2D convolution is used for different filtering operations. It has many mathematical operations and is performed on all image pixels. Therefore, it is almost a compute-intensive kernel. In order to improve its performance in this paper, we apply two approaches to vectorize it, broadcasting of coefficients and repetition of coefficients using Intrinsic Programming Model (IPM) and AVX technology. Our experimental results on an Intel Skylake microarchitecture show that the performance of broadcasting of coefficients is much higher than repetition of coefficients for different filter sizes and different image sizes. In addition, in order to evaluate the performance of Compiler Automatic Vectorization (CAV), and OpenCV library for this kernel, we use GCC and LLVM compilers. Our experimental results show that the performance of both IPM implementations are faster than GCC's and LLVM auto-vectorizations.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123824270","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: 7
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信