2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)最新文献_第3页

Automated Sleep Stage Scoring Using Brain Effective Connectivity and EEG Signals 使用大脑有效连接和脑电图信号的自动睡眠阶段评分

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/ICSPIS54653.2021.9729377

Masood Hamed Saghayan, Saman Seifpour, Ali Khadem

{"title":"Automated Sleep Stage Scoring Using Brain Effective Connectivity and EEG Signals","authors":"Masood Hamed Saghayan, Saman Seifpour, Ali Khadem","doi":"10.1109/ICSPIS54653.2021.9729377","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729377","url":null,"abstract":"Sleep staging is necessary for the diagnosis of sleep disorders and evaluating the quality of sleep. Scoring of sleep stages is mainly done manually by a specialist based on Polysomnography data and mainly EEG, which is very time consuming and costly. Hence, it is essential to provide an automated method. This paper proposes an automatic sleep staging method based on brain effective connectivity. In this study, using the Granger causality criterion, causality matrices for each epoch of EEG data sampled from 10 healthy individuals were extracted as features. Then, the Gaussian SVM classifier has been employed to classify sleep stages using extracted features. For feature reduction, two algorithms, PCA and RSFS, were assessed, but we did not apply feature reduction in the final method due to the insignificant effect on classification accuracy. Finally, we were able to classify sleep stages with 72.7% accuracy and Cohen's Kappa Coefficient of 0.65. The experimental results demonstrate that the combination of Granger causality features and SVM can be used as an efficient framework for automated sleep stage scoring with regard to promising classification performance in terms of accuracy and Cohen's Kappa coefficient.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127784717","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

Speech Emotion Recognition Using a New Hybrid Quaternion-Based Echo State Network-Bilinear Filter 基于混合四元数的回声状态网络双线性滤波器的语音情感识别

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/ICSPIS54653.2021.9729337

Fatemeh Daneshfar, S. J. Kabudian

{"title":"Speech Emotion Recognition Using a New Hybrid Quaternion-Based Echo State Network-Bilinear Filter","authors":"Fatemeh Daneshfar, S. J. Kabudian","doi":"10.1109/ICSPIS54653.2021.9729337","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729337","url":null,"abstract":"Echo state network (ESN) is one of the efficient tools for displaying dynamic data. However, there are limitations to model high-dimensional data by ESNs. The most important limitation is the high amount of memory consumed due to their echo state and the linear output of the ESN network, which prevents the increase of reservoir units and the effective use of higher-order statistics of the features provided by its reservoir units. In this research, a new structure based on ESN is presented, in which quaternion algebra is used to compress the network data with the simple split function, and the output linear combiner is replaced by a multidimensional bilinear filter. This filter will be used for nonlinear calculations of the output layer of the ESN. In addition, the two-dimensional principal component analysis (2dPCA) technique is used to reduce the number of data transferred to the bilinear filter. In this study, the coefficients and the weights of the quaternion nonlinear ESN (QNESN) are optimized using genetic algorithm (GA). In order to prove the effectiveness of the proposed model compared to the previous methods, experiments for speech emotion recognition (SER) have been performed on EMODB dataset. Comparisons show that the proposed QNESN network performs better than the simple ESN and most currently SER systems.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116863621","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

Intelligent Fault Diagnosis of Rolling BearingBased on Deep Transfer Learning Using Time-Frequency Representation 基于时频表示深度迁移学习的滚动轴承智能故障诊断

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/ICSPIS54653.2021.9729385

M. Kavianpour, Mohammadreza Ghorvei, A. Ramezani, Mohammad T. H. Beheshti

{"title":"Intelligent Fault Diagnosis of Rolling BearingBased on Deep Transfer Learning Using Time-Frequency Representation","authors":"M. Kavianpour, Mohammadreza Ghorvei, A. Ramezani, Mohammad T. H. Beheshti","doi":"10.1109/ICSPIS54653.2021.9729385","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729385","url":null,"abstract":"With the expansion of deep learning (DL) and machine learning (ML) methods, fault diagnosis based on data-driven models has recently become controversial. However, due to the lack of sufficient labeled data in fault diagnosis, the depth of proposed DL models is less than other models in computer vision areas, which decreases the generalization and accuracy of models. Deep transfer convolutional neural network (DTCNN) with powerful feature extracting is used to tackle this dilemma. In this study, DenseNet201, ResNet152V2 and, MobileNetV2 are chosen as DTCNN models for feature extraction. Firstly, vibration signals are converted into time-frequency RGB images by continuous wavelet transform (CWT). Then, the high-level features of images are extracted by the DTCNN models. Finally, different types of bearing faults are classified by DL and ML classifiers. The experiment is validated on the famous Case Western Reserve University (CWRU) bearing data set. The result demonstrates that the proposed DTCNN models achieve the best accuracy rate in the classification task and are faster to learn than many other existing DL and ML models.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"28 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113970998","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

A novel local approach for identifying bridging edges in complex networks 复杂网络中桥接边识别的一种新的局部方法

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/ICSPIS54653.2021.9729373

Negin Samadi, J. Tanha, Nazila Razzaghi-Asl, Mehdi Nabatian

引用次数: 0

CA-Market: A Partially Categorical AnnotatingApproach Based on Market1501 Dataset for Attribute Detection CA-Market:一种基于Market1501数据集的部分分类标注方法

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/ICSPIS54653.2021.9729331

Hossein Bodaghi, Shayan Samiee, Mehdi Tale Masoulehe, A. Kalhor

{"title":"CA-Market: A Partially Categorical AnnotatingApproach Based on Market1501 Dataset for Attribute Detection","authors":"Hossein Bodaghi, Shayan Samiee, Mehdi Tale Masoulehe, A. Kalhor","doi":"10.1109/ICSPIS54653.2021.9729331","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729331","url":null,"abstract":"In this paper, a new partial categorical attributes dataset (CA-Market) based on images of the Market1501 dataset has been introduced, for the sake of improving the attribute detection task. Most attributes detection datasets (human appearance features detection) are not partially categorical and do not properly take into account the inner classes diversity. Increasing the diversity of inner parts (gender, head, upper-body clothes, lower-body clothes, bags, shoes, and colors) before annotating can ease the decision-making process by dividing labels into individual categories. CA-Market contains 46 binary attributes in 10 parts from head to foot and their colors which are annotated in image-level. For example, the attributes of the leg part are skirts, shorts, and pants which are carefully chosen to be categorized for a classification task. In this research, the effect of the labeling approach is studied. Hence, a common classification method is used and only datasets or baselines are changed for comparisons. Baselines are based on Omni-Scale, Resnet50, and Hydra-Plus architectures to compare the CA-Market1501 dataset with the Market1501 attribute dataset in the same setting. CA-Market demonstrates a new representation of data as a part-based format which can gain better results. This approach, without adding any extra modules, achieved a significant enhancement. For instance, accuracy in the vectorized format is over 92%, in the categorized is over 90% which shows the effectiveness of part-based attribute annotating. Also, hair, backpack, upper color, and lower color as the common attributes between Market1501-attribute and CA-Market datasets are achieved 90.26, 88.04, 94.55, and 94.18 classification accuracy which can outperform existing state-of- the-art approaches.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123419901","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

Multivariate Mutual Information Measures Functional Connectivity Accurately 多元互信息准确地衡量功能连通性

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/ICSPIS54653.2021.9729361

Mahnaz Ashrafi, Hamid Soltanian-Zadeh

引用次数: 0

Genre Classification of Movies from a Single Poster Image Using Feature Fusion 利用特征融合从单个海报图像中进行电影类型分类

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/ICSPIS54653.2021.9729380

Farzaneh Nadem, Rahil Mahdian, Hassan Zareian

{"title":"Genre Classification of Movies from a Single Poster Image Using Feature Fusion","authors":"Farzaneh Nadem, Rahil Mahdian, Hassan Zareian","doi":"10.1109/ICSPIS54653.2021.9729380","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729380","url":null,"abstract":"The movie industry is one of the largest and most influential sectors of any community. Each movie in the industry consists of different elements such as actors, directors, preparation elements, posters, etc. One of the most important elements in any movie is its poster, that plays an important role in attracting the audience. Various information can be obtained from the movie poster, including the movie genre. Today, the movie genre is recognized manually. In this paper, we aim to consider the automatic detection of movie genres based on its poster. Automatic detection of movie genres can have various applications in movie archive systems, search engines, recommender systems, and more. In the proposed method of this paper, four categories of embedding features including the objects in the poster, identifying the actors, age, and gender of the actors in the poster, and their facial expressions are used. Our proposed method is compared with some outstanding previous works over the IMDB dataset poster. By incorporating an ensemble classification approach in our work, the results of our proposed method could achieve the average predicting accuracy of 92% which could outperform the previous works.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130735683","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

Article Titles Index 文章标题索引

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/icspis54653.2021.9729344

引用次数: 0

An improvement on quantum clustering 量子聚类的改进

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/ICSPIS54653.2021.9729349

Mehdi Nabatian, J. Tanha, A. R. Ebrahimzadeh, Negin Samadi, Nazila Razzaghi-Asl

{"title":"An improvement on quantum clustering","authors":"Mehdi Nabatian, J. Tanha, A. R. Ebrahimzadeh, Negin Samadi, Nazila Razzaghi-Asl","doi":"10.1109/ICSPIS54653.2021.9729349","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729349","url":null,"abstract":"Data and patterns are the most important indicators in the world of information. Clustering is one of the best ways to enter the big data world. The main ability of the clustering is to enter the data space and recognize the data structure. Quantum Clustering (QC) is a innovative clustering method that aims to detect the potential components of a data set, based on physical concepts. QC is a new heuristic formulating procedure based on the Schrödinger equation. The main assumption in QC is that the number and location of minimums Schrödinger potential(V) will assign the number and centers of the clusters. In standard QC, first step is to construct the wave function using the Parzen window symmetric estimator, and the next step is to solve the Schrödinger equation for this wave function. These hypotheses lead the clustering problem to solve the Schrödinger equation for an asymmetric harmonic oscillator. In this paper, we improve the results of QC clustering by considering the asymmetric Parzen estimator and solving the Schrödinger equation for the asymmetric harmonic oscillator.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130428136","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

Combination of ConvLSTM and Attention mechanism to diagnose ADHD based on EEG signals 结合ConvLSTM和注意机制诊断ADHD的脑电图信号

2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) Pub Date : 2021-12-29 DOI: 10.1109/ICSPIS54653.2021.9729359

M. Bakhtyari, S. Mirzaei, H. Amiri

{"title":"Combination of ConvLSTM and Attention mechanism to diagnose ADHD based on EEG signals","authors":"M. Bakhtyari, S. Mirzaei, H. Amiri","doi":"10.1109/ICSPIS54653.2021.9729359","DOIUrl":"https://doi.org/10.1109/ICSPIS54653.2021.9729359","url":null,"abstract":"Among neurodevelopmental disorders, attention deficit hyperactivity disorder (ADHD) is the most prevalent disorder in childhood. Early diagnosis and treatment of this disorder can reduce negative impacts, such as learning difficulty, antisocial behaviours, financial problems and divorce in adulthood. Although clinical diagnoses are currently available, they are based on patient behaviours and are not reliable. Researchers developed different methods to discover a biomarker that can help accurate diagnosis. Biological signals such as electroencephalography (EEG) draw the most interest because of their ability to record neurons electrical activity. We propose a deep learning framework that combines the ConvLSTM and attention mechanism. To provide the input for this framework, we first calculate a dynamic connectivity tensor. This technique is more effective than feature extraction methods such as Fourier transform-based approaches and nonlinear analyses. Due to the structure of ConvLSTM, the model can extract temporal and spatial features simultaneously, and the attention mechanism provides insights for the model to score different time instants in EEG data. These two steps lead to effectively encoding a compact representation of EEG signals. It is the first time to apply ConvLSTM and the attention mechanism combination on time series data. To examine the proposed framework, we run our experiments on 400 data instances. We trained our model using 5-fold cross-validation. After ten different executions, the best model has an accuracy of 99.75%, which is the superior performance among the studies on this data.","PeriodicalId":286966,"journal":{"name":"2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125675972","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