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

Keystroke recognition using chaotic neural network 基于混沌神经网络的击键识别

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311590

Purvashi Baynath, K. Soyjaudah, Maleika Heenaye-Mamode Khan

引用次数: 4

Frame-based face emotion recognition using linear discriminant analysis 基于帧的线性判别分析人脸情感识别

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311605

Hatef Otroshi-Shahreza

引用次数: 4

Classification of EEG-based attention for brain computer interface 基于脑电图的脑机接口注意分类

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311585

Mostafa Mohammadpour, S. Mozaffari

{"title":"Classification of EEG-based attention for brain computer interface","authors":"Mostafa Mohammadpour, S. Mozaffari","doi":"10.1109/ICSPIS.2017.8311585","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311585","url":null,"abstract":"This paper reports on an EEG-based brain computer interface (BCI) development, which recognizes four levels of attention. In order to measure the levels of subject's attention, many types of biological signals can be recorded such as electroencephalogram (EEG), electrocardiogram(ECG), electrooculo-gram(EOG), and electromyogram (EMG). Among these methods EEG generally is used as the most effective one for assessing subject's cognitive functions. Recognizing attention levels can be used in a wide variety of applications such as students' attention level, clinical application in detecting Attention Deficit Hyperactivity Disorder (ADHD), and driver fatigue detecting system. Highlighting the four levels of attention is proposed here, in which the acquired signals from subjects are modeled in a designed task so that attention levels vary from non-attention conditions (closed eyes and reading task) to full attention conditions (mathematics task and vigilance). While the previous studies only worked on two levels of attention (low and high levels), the novelty of proposed method is in using four levels of attention. After proving the effectiveness of proposed system, the results reveal appropriate signal processing and classification methods for discriminating the levels of attention which can be used for boosting the BCI performance.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"8 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":"134198359","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: 21

Text coherence new method using word2vec sentence vectors and most likely n-grams 使用word2vec句子向量和最有可能n-grams的文本连贯新方法

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311598

Mohamad Abdolahi Kharazmi, M. Kharazmi

{"title":"Text coherence new method using word2vec sentence vectors and most likely n-grams","authors":"Mohamad Abdolahi Kharazmi, M. Kharazmi","doi":"10.1109/ICSPIS.2017.8311598","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311598","url":null,"abstract":"Discourse coherence modeling evaluation remains a challenge task in all Natural Language Processing subfields. Most proposed approaches focus on feature engineering, which accepts the sophisticated features to capture the logic, syntactic or semantic relationships between all sentences within a text. This paper investigates the automatic evaluation of text coherence. We introduce a fully-automatic rich statistical model of local and global coherence that uses word2vec approach to assess the coherence a document. Our modeling approach relies on numerical vectors derived from word2vec algorithm applied on a very large collection of texts. We successfully combined the word2vec vectors and most likely n-grams with cohesive LD-n-grams perplexity to assess the coherence and topic integrity of document. We present experimental results that assess the predictive power that it does not depend on the language and its semantic concepts. So it has the ability to apply on any language. Our model achieves state-of-the-art performance in coherence evaluation and order discrimination task on two datasets widely used in the previous methods.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"1 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":"131297451","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

Optimal MFCC features extraction by differential evolution algorithm for speaker recognition 基于差分进化算法的最优MFCC特征提取用于说话人识别

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311610

Mohsen Sadeghi, H. Marvi

引用次数: 15

RLOSD: Representation learning based opinion spam detection RLOSD:基于表示学习的意见垃圾检测

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311593

Z. Sedighi, H. Ebrahimpour-Komleh, A. Bagheri

引用次数: 9

Feature reduction in spectral unmixing using neural networks 基于神经网络的光谱分解特征缩减

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311612

Farshid Khajeh Rayeni, H. Ghassemian

{"title":"Feature reduction in spectral unmixing using neural networks","authors":"Farshid Khajeh Rayeni, H. Ghassemian","doi":"10.1109/ICSPIS.2017.8311612","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311612","url":null,"abstract":"Spectral unmixing (SU) is a standard approach to solve the mixed pixel problem in hyperspectral (HS) images. In this study, the application of feature reduction in SU using multi-layer perceptron (MLP) with some data-independent approaches is investigated. MLP is a popular artificial neural network that can learn complex nonlinear relationships between the endmembers and the abundance fractions in HS images if it is properly trained. So far, various approaches have been introduced to extract training samples from the data itself. Since it is not possible to access the actual abundance fractions of materials in real HS images, MLP training becomes complicated. Due to a large number of bands in HS images, complexity and large training time are some of the remaining problems that would be investigated in this study. In order to overcome the problem of unavailability of the actual abundance fractions, a synthetic library is generated based on scene mixture models. And some data-independent approaches, such as discrete cosine transform and discrete wavelet transform are utilized to reduce the complexity and the training time of the MLP. The experimental results are provided using both synthetic and real datasets with different mixture models. The results show the acceptable estimated abundance fractions with root mean square error, up to 0.0008 in the linear dataset and 0.0062 in the nonlinear dataset.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"45 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":"127267643","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

Dependency evaluation of financial market returns for classifying and grouping stocks 股票分类与分组的金融市场收益相关性评价

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311615

Sasan Barak

引用次数: 3

A short-term learning framework based on relevance feedback for content-based image retrieval 基于相关性反馈的基于内容的图像检索短期学习框架

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311604

Hamed Qazanfari, H. Hassanpour, Kazem Qazanfari

{"title":"A short-term learning framework based on relevance feedback for content-based image retrieval","authors":"Hamed Qazanfari, H. Hassanpour, Kazem Qazanfari","doi":"10.1109/ICSPIS.2017.8311604","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311604","url":null,"abstract":"In this paper a short-term learning method based on relevance feedback for content-based image retrieval is proposed. In content based image retrieval systems, a set of low level features is used to find similar images to the query image. However, the extracted features are not able to represent the content of the images precisely. To resolve this issue, a learning method based on relevance feedback is proposed. The proposed method is built on a short-term learning method which is based on near strangers or distant relatives model. Based on this model, if two individuals are relatives, it is more likely that they have the same characteristics. In our proposed method, after the first iteration of retrieval, in each step of the proposed relevance feedback method, some retrieved images are labeled manually to be related to the query image. Then, new similar images are retrieved based on the labeled images. In the next step, based on the distance of these similar images from the query image, the more similar images to the query image are considered to be the retrieved images for the next iteration. Finally, over iterations, the more similar images to the query are retrieved. The proposed method has been evaluated on Corel-10k dataset which has 10,000 images in 100 different classes. Experimental results show that the precision of the proposed method is significantly higher than the precision of some recently developed methods.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"1 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":"131209053","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

Singer's voice elimination from stereophonic pop music using ICA 用ICA消除立体声流行音乐歌手的声音

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311611

Danial Katoozian, F. Faradji

引用次数: 2