2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)最新文献_第2页

Text language identification using signal processing techniques 使用信号处理技术的文本语言识别

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311606

Mohammad. M. Alyan Nezhadi, M. Forghani, H. Hassanpour

{"title":"Text language identification using signal processing techniques","authors":"Mohammad. M. Alyan Nezhadi, M. Forghani, H. Hassanpour","doi":"10.1109/ICSPIS.2017.8311606","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311606","url":null,"abstract":"Human is often able to recognize spoken languages even if the meaning could not be understood. Text language determination is an important requirement in any text processing system. In this paper, a novel text language identification based on signal processing techniques is presented. In each language, there is a dependency between components of a sentence as well as components those construct the words. Considering the text as a time series, this dependency can be observed using signal processing techniques. The proposed method recognizes the language of a text, in a three-stage manner, using Wavelet packet and neural networks. First the preprocessing section that prepares the text for signal processing via adding some additional spaces between consecutive words, then represents the text using UTF8 coding system. In the second stage, the Wavelet packet is applied on the coded text, i.e. time-series, and a feature vector is extracted from wavelet packet coefficients of sub-bands. Finally the classification section applies a neural network classifier on extracted feature vector. The proposed method has been tested on the database gathered from Wikipedia with seven different languages (Arabic, English, French, Germany, Italian, Persian and Russian). The proposed method earned the accuracy above 97%. The proposed method is enough fast that makes it suitable to use in real-time applications.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"40 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":"132692588","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

Automated breast cancer diagnosis using artificial neural network (ANN) 基于人工神经网络(ANN)的乳腺癌自动诊断

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311589

Maleika Heenaye-Mamode Khan

引用次数: 20

Sine Optimization Algorithm (SOA): A novel optimization algorithm by change update position strategy of search agent in Sine Cosine Algorithm 正弦优化算法(SOA):一种利用正弦余弦算法中搜索主体改变更新位置策略的优化算法

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311581

Mostafa Meshkat, Mohsen Parhizgar

引用次数: 7

3Ds MAX to FEM for building thermal distribution: A case study 3Ds MAX到FEM的建筑热分布:一个案例研究

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311599

Zahra Pezeshki, A. Soleimani, A. Darabi

{"title":"3Ds MAX to FEM for building thermal distribution: A case study","authors":"Zahra Pezeshki, A. Soleimani, A. Darabi","doi":"10.1109/ICSPIS.2017.8311599","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311599","url":null,"abstract":"The complication of building constructions, with irregular geometry, different building materials, variable morphology, alterations and damages, poses numerous challenges in the digital modeling and simulation of structural performances under different types of actions. Most of the research is focused on importing Three Dimension (3D) geometry data in a Finite Element Method (FEM) applications. This paper presents an innovative two-step methodology (3ds MAX-to-FEM) able to convert a Three Dimension Studio Modeling, Animation & Rendering Software/Autodesk (3ds MAX) file into a FEM for structural simulation. In this study, the 3ds MAX file is a large building, has been carried out with an accurate survey that integrates geometrical aspects, element interconnections, and architectural considerations. Then it is turned into COMSOL Multiphysics environment and tested thermal simulation with a geometric rationalization which preserves irregularities and anomalies, such as verticality deviation and variable thickness. After setting material properties, loads, and boundary conditions, the structural simulation is run with a detailed model that respects the uniqueness and authenticity of the building. A real case study is illustrated and discussed to prove that a rigorous 3ds MAX to FEM workflow allows the generation of an accurate practical methodology for 3D visualization and simulation for thermal distribution operation in COMSOL. Structural simulation was carried out with a 3D mesh derived from the 3ds MAX file in order to take into consideration the geometrical irregularity of a building. COMSOL Multiphysics is a software tool uses artificial intelligent and soft computing for doing computations with high speed and accuracy, and computes and shows different types of phenomenon together. In this study simulation results compare with the reality results. Here, the advantages and disadvantages of the proposed approach are illustrated.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"74 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":"134180103","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

Radon transform for adaptive directional time-frequency distributions: Application to seizure detection in EEG signals 自适应定向时频分布的Radon变换:在脑电图信号中癫痫检测中的应用

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311580

M. Mohammadi, A. Pouyan, V. Abolghasemi, Nabeel Ali Khan

引用次数: 1

A multivariate clustering of AAindex database for protein numerical representation 蛋白质数值表示的aindex数据库多变量聚类

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311579

M. Forghani, Rouhollah Khani

{"title":"A multivariate clustering of AAindex database for protein numerical representation","authors":"M. Forghani, Rouhollah Khani","doi":"10.1109/ICSPIS.2017.8311579","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311579","url":null,"abstract":"As a first step of genomics signal processing, alphabetical sequence is mapped to numerical. The choice of mapping techniques depends on the application and affects the result of the study. Since biological function is the result of amino acids interactions, a significant method for alphabetical to numerical conversion of sequence is to use the physico-chemical and biochemical properties of amino acids. AAindex database is a rich collection of such properties that can be used for numerical representation of protein. Each of these properties gives a viewpoint in the study of biological functions. Taking into account all AAindex indices leads to a multi-viewpoint representation and provides more options to observe and study the target biological phenomena. But this advantage increases variables number, space dimension and computation time. Since there is correlation between AAindex databases, to handle the issue of space dimension increasement, compact versions of correlated indices are extracted. This paper aims at the construction of new indices through clustering of AAindex database with correlation distance. The results suggest that due to the correlation of these new maps with groups of AAindex indices (in clusters); they have the potential to be used for numerical representation of protein sequence in different studies.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"22 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":"114508935","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

Accurate prediction of differential GPS corrections using fuzzy cognitive map 模糊认知地图对差分GPS改正量的准确预测

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311591

Zahra Eshagh Nimvari, M. Mosavi

引用次数: 2

Vehicle tracking at intersection in image sequences with multilayer concept 基于多层概念的图像序列交叉口车辆跟踪

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/icspis.2017.8311603

M. Delavarian, Omidreza Maarouzi

引用次数: 2

Dynamic clustering with a mobile sink in wireless sensor networks 无线传感器网络中带有移动sink的动态聚类

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311596

G. Ekbatanifard, Kianoush Mada

引用次数: 0

Regularized sparse feature selection with constraints embedded in graph Laplacian matrix 约束嵌入图拉普拉斯矩阵的正则化稀疏特征选择

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311602

Zahir Noorie, F. Afsari

引用次数: 1