Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147171
M. Zarei, A. Nickfarjam
In this paper, we propose a combination of K-means algorithm and Particle Swarm Optimization (PSO) method. The K-means algorithm is utilized for data clustering. On one hand, the number of clusters (K) should be determined by expert or found by try-and-error procedure in the K-means algorithm. On the other hand, initial centroids and number of clusters (K) are influenced on the quality of resulted grouping. Therefore, the aim of the proposed procedure is using PSO and the Structural Similarity Index (SSIM) criterion as a fitness function in order to find the best value for K parameter and better initial clusters' center. Due to different value of K parameter, the number of initial centroids which should be produced is variant. Thus, length of particles in PSO method may be different in each iteration. Experimental results show the superiority of this approach in comparison with standard K-means algorithm and both of them are evaluated on image segmentation problem.
{"title":"PSO-based procedure to find number of clusters and better initial centroids for K-means algorithm: Image segmentation as case study","authors":"M. Zarei, A. Nickfarjam","doi":"10.1109/IPRIA59240.2023.10147171","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147171","url":null,"abstract":"In this paper, we propose a combination of K-means algorithm and Particle Swarm Optimization (PSO) method. The K-means algorithm is utilized for data clustering. On one hand, the number of clusters (K) should be determined by expert or found by try-and-error procedure in the K-means algorithm. On the other hand, initial centroids and number of clusters (K) are influenced on the quality of resulted grouping. Therefore, the aim of the proposed procedure is using PSO and the Structural Similarity Index (SSIM) criterion as a fitness function in order to find the best value for K parameter and better initial clusters' center. Due to different value of K parameter, the number of initial centroids which should be produced is variant. Thus, length of particles in PSO method may be different in each iteration. Experimental results show the superiority of this approach in comparison with standard K-means algorithm and both of them are evaluated on image segmentation problem.","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124457034","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}
Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147186
Zainab Tabanmehr, Ehsan Akhtarkavan
The increasing spread of data and text documents such as articles, web pages, books, posts on social networks, etc. on the Internet, creates a fundamental challenge in various fields of text processing under the title of “automatic text summarization”. Manual processing and summarization of large volumes of textual data is a very difficult, expensive, time-consuming, and impossible process for human users. Text summarization systems are divided into extractive and abstract categories. In the extractive summarization method, the final summary of a text document is extracted from the important sentences of the same document without any kind of change. In this method, it is possible to repeat a series of sentences repeatedly and interfere with pronouns. But in the abstract summarization method, the final summary of a textual document is extracted from the meaning of the sentences and words of the same document or other documents. Many of the performed works have used extraction methods or abstracts to summarize the collection of web documents, each of which has advantages and disadvantages in the results obtained in terms of similarity or size. In this research, by developing a crawler, extracting the popular text posts from the Instagram social network, suitable pre-processing, and combining the set of extractive and abstract algorithms, the researcher showed how to use each of the abstract algorithms. and used extraction as a supplement to increase the accuracy and accuracy of another algorithm. Observations made on 820 popular text posts on the Instagram social network show the accuracy (80%) of the proposed system.
{"title":"Automatic summarization of Instagram social network posts by combining semantic and statistical approaches","authors":"Zainab Tabanmehr, Ehsan Akhtarkavan","doi":"10.1109/IPRIA59240.2023.10147186","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147186","url":null,"abstract":"The increasing spread of data and text documents such as articles, web pages, books, posts on social networks, etc. on the Internet, creates a fundamental challenge in various fields of text processing under the title of “automatic text summarization”. Manual processing and summarization of large volumes of textual data is a very difficult, expensive, time-consuming, and impossible process for human users. Text summarization systems are divided into extractive and abstract categories. In the extractive summarization method, the final summary of a text document is extracted from the important sentences of the same document without any kind of change. In this method, it is possible to repeat a series of sentences repeatedly and interfere with pronouns. But in the abstract summarization method, the final summary of a textual document is extracted from the meaning of the sentences and words of the same document or other documents. Many of the performed works have used extraction methods or abstracts to summarize the collection of web documents, each of which has advantages and disadvantages in the results obtained in terms of similarity or size. In this research, by developing a crawler, extracting the popular text posts from the Instagram social network, suitable pre-processing, and combining the set of extractive and abstract algorithms, the researcher showed how to use each of the abstract algorithms. and used extraction as a supplement to increase the accuracy and accuracy of another algorithm. Observations made on 820 popular text posts on the Instagram social network show the accuracy (80%) of the proposed system.","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125002503","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}
Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147195
S. F. Hosseini-Benvidi, Azadeh Mansouri
The objective of the No-Reference Image Quality Assessment (NR-IQA) is to evaluate the perceived image quality subjectively. Since there is no reference image, this is a challenging and unresolved issue. Convolutional neural networks (CNNs) have gained popularity in recent years and have outperformed many traditional techniques in the field of image processing. In order to overcome overfitting, a large percentage of deep learning based IQA methods work with tiny image patches and assess the quality of the entire image based on the average scores of patches. Patch extraction is one of the most crucial elements of CNN-based methods in quality assessment problems. Assuming that visual perception in humans is well suited to extract structural details from a scene, we analyzed the effect of feeding informative and structural patches to the quality framework. In this paper, a method for structural patch extraction is presented, which is based on the variance values of each patch. The obtained results show that the presented method has an acceptable improvement compared to the random patch selection. The proposed model has also performed well in cross-dataset experiments on common distortions, indicating the model's high generalizability. Additionally, the test was run on the flipped images, and the outcomes are satisfactory.
{"title":"The Effect of Variance-Based Patch Selection on No-Reference Image Quality Assessment","authors":"S. F. Hosseini-Benvidi, Azadeh Mansouri","doi":"10.1109/IPRIA59240.2023.10147195","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147195","url":null,"abstract":"The objective of the No-Reference Image Quality Assessment (NR-IQA) is to evaluate the perceived image quality subjectively. Since there is no reference image, this is a challenging and unresolved issue. Convolutional neural networks (CNNs) have gained popularity in recent years and have outperformed many traditional techniques in the field of image processing. In order to overcome overfitting, a large percentage of deep learning based IQA methods work with tiny image patches and assess the quality of the entire image based on the average scores of patches. Patch extraction is one of the most crucial elements of CNN-based methods in quality assessment problems. Assuming that visual perception in humans is well suited to extract structural details from a scene, we analyzed the effect of feeding informative and structural patches to the quality framework. In this paper, a method for structural patch extraction is presented, which is based on the variance values of each patch. The obtained results show that the presented method has an acceptable improvement compared to the random patch selection. The proposed model has also performed well in cross-dataset experiments on common distortions, indicating the model's high generalizability. Additionally, the test was run on the flipped images, and the outcomes are satisfactory.","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132382640","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}
Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147194
Laleh Armi, Hossein Ebrahimpour-komleh
Skin cancer is one of the most common forms of cancer in the world that has grown dramatically over the past decades. Malignant melanoma is the deadliest type of skin cancer. Melanocytic nevi are benign whereas melanoma is malignant. Most skin cancers are treatable in the early stages. So, rapid diagnosis and the importance of early stage can be very important to cure it and increasing day by day. Today, artificial intelligence can represent an important role in medical image diagnosis. The aim of this paper is to an auto-diagnosis system can be deployed to help dermatologists in identifying melanoma that may facilitate early detection of melanoma, and hence substantially reduce the mortality chance of this dangerous malignancy. We used image processing tools to diagnose melanoma skin cancer. In this paper, the advantage of improved local quinary pattern (ILQP) is used as texture feature extraction method and used mixture of ELM-based experts with a trainable gating network (MEETG) for skin cancer classification. Our proposed method achieved the classification accuracy on f and d datasets, 97.05% and 86.61% respectively.
{"title":"Classification of Skin Cancer With Using Color-ILQP and MEETG","authors":"Laleh Armi, Hossein Ebrahimpour-komleh","doi":"10.1109/IPRIA59240.2023.10147194","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147194","url":null,"abstract":"Skin cancer is one of the most common forms of cancer in the world that has grown dramatically over the past decades. Malignant melanoma is the deadliest type of skin cancer. Melanocytic nevi are benign whereas melanoma is malignant. Most skin cancers are treatable in the early stages. So, rapid diagnosis and the importance of early stage can be very important to cure it and increasing day by day. Today, artificial intelligence can represent an important role in medical image diagnosis. The aim of this paper is to an auto-diagnosis system can be deployed to help dermatologists in identifying melanoma that may facilitate early detection of melanoma, and hence substantially reduce the mortality chance of this dangerous malignancy. We used image processing tools to diagnose melanoma skin cancer. In this paper, the advantage of improved local quinary pattern (ILQP) is used as texture feature extraction method and used mixture of ELM-based experts with a trainable gating network (MEETG) for skin cancer classification. Our proposed method achieved the classification accuracy on f and d datasets, 97.05% and 86.61% respectively.","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124507768","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}
Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147175
Meysam Alavi, Arefeh Valiollahi, M. Kargari
The Coronavirus pandemic (COVID-19) has encouraged researchers to produce significant scientific research in this field in reputable international citation databases. It is important to constantly identify and assess scientific outputs in order to learn more about the situation. One of the methods used for evaluating scientific research activities is scientometrics, which has many applications in describing, explaining and predicting the scientific status of researchers and research centers in various national and international fields. It also provides efficient methods for monitoring and ranking organizations, researchers, journals and countries. On the other hand, in recent years, the use of various scientometric techniques, including co-word analysis, co-authorship network and scientific network, has been of great help in discovering the direction of researchers' production in scientific domain and its hidden and overt dimensions. One of the most popular areas since the COVID-19 epidemic started, has been research the use of artificial intelligence and especially machine learning techniques in the prediction, diagnosis and treatment of this disease. In this regard, 2659 documents from the PubMed citation database since the start of the COVID-19 epidemic have been reviewed. The findings of this research show that America, China, India and England are the countries that have cooperated the most with other countries. In addition, the results of this research showed that deep learning and CNN had been significantly used in the researchers' studies.
{"title":"Machine Learning Techniques During the COVID-19 Pandemic: A Bibliometric Analysis","authors":"Meysam Alavi, Arefeh Valiollahi, M. Kargari","doi":"10.1109/IPRIA59240.2023.10147175","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147175","url":null,"abstract":"The Coronavirus pandemic (COVID-19) has encouraged researchers to produce significant scientific research in this field in reputable international citation databases. It is important to constantly identify and assess scientific outputs in order to learn more about the situation. One of the methods used for evaluating scientific research activities is scientometrics, which has many applications in describing, explaining and predicting the scientific status of researchers and research centers in various national and international fields. It also provides efficient methods for monitoring and ranking organizations, researchers, journals and countries. On the other hand, in recent years, the use of various scientometric techniques, including co-word analysis, co-authorship network and scientific network, has been of great help in discovering the direction of researchers' production in scientific domain and its hidden and overt dimensions. One of the most popular areas since the COVID-19 epidemic started, has been research the use of artificial intelligence and especially machine learning techniques in the prediction, diagnosis and treatment of this disease. In this regard, 2659 documents from the PubMed citation database since the start of the COVID-19 epidemic have been reviewed. The findings of this research show that America, China, India and England are the countries that have cooperated the most with other countries. In addition, the results of this research showed that deep learning and CNN had been significantly used in the researchers' studies.","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115198276","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}
Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147185
Pouya Ardehkhani, Amir Vahedi, Hossein Aghababa
As deep learning became more sophisticated, it significantly increased the use of AI in industry, academia, and other sectors. NLP is a part of the deep learning paradigm that offers different types of systems mainly related to human language understanding, meaning, and interpretations. Nowadays, NLP is used in several applications, including sentiment analysis, categorization of texts, translation, etc. Due to this new usage, new challenges occurred. This paper discusses the challenges of developing or creating an NLP model and the problems that will be occurred in NLU. Moreover, the paper illustrates issues in both technical and natural domains that should be considered upon deployment or creation of NLP models or NLU systems.
{"title":"Challenges in natural language processing and natural language understanding by considering both technical and natural domains","authors":"Pouya Ardehkhani, Amir Vahedi, Hossein Aghababa","doi":"10.1109/IPRIA59240.2023.10147185","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147185","url":null,"abstract":"As deep learning became more sophisticated, it significantly increased the use of AI in industry, academia, and other sectors. NLP is a part of the deep learning paradigm that offers different types of systems mainly related to human language understanding, meaning, and interpretations. Nowadays, NLP is used in several applications, including sentiment analysis, categorization of texts, translation, etc. Due to this new usage, new challenges occurred. This paper discusses the challenges of developing or creating an NLP model and the problems that will be occurred in NLU. Moreover, the paper illustrates issues in both technical and natural domains that should be considered upon deployment or creation of NLP models or NLU systems.","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125090324","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}
Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147170
Alireza Khatami, Ahmad Mahmoudi-Aznaveh
Measuring the perceptual similarity between two images is a long-standing problem. This assessment should mimic human judgments. Considering the complexity of the human visual system, it is challenging to model human perception. On the other hand, the recent low-level vision task approaches, mostly based on supervised deep learning, require an appropriate loss for the backward pass. The per-pixel loss, such as MSE and MAE, between the output of the network and the ground-truth images were among the first choices. More complicated and common similarity measures in which the error is computed in a hand-designed feature space are also employed. Furthermore, Deep Perceptual Similarity (DPS) metrics, where the similarity is measured in the deep feature space, also have promising results. This feature can be selected from a pre-trained or optimized model for the task at hand. Recently many studies have been conducted to thoroughly investigate DPS. In this research, we provide an in-depth analysis of the pros and cons of DPS in assessing the full reference quality assessment. In addition, to compare different similarity measures, we propose a metric which aggregates various desired factors. Based on our experiment, it can be concluded that perceptual similarity is not directly related to classification accuracy. It is discovered that the outliers mostly contain high-frequency elements. The code and complete outcomes described in results, can be found on: https://github.com/Alireza-Khatami/PerceptualQuality
{"title":"Deep perceptual similarity and Quality Assessment","authors":"Alireza Khatami, Ahmad Mahmoudi-Aznaveh","doi":"10.1109/IPRIA59240.2023.10147170","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147170","url":null,"abstract":"Measuring the perceptual similarity between two images is a long-standing problem. This assessment should mimic human judgments. Considering the complexity of the human visual system, it is challenging to model human perception. On the other hand, the recent low-level vision task approaches, mostly based on supervised deep learning, require an appropriate loss for the backward pass. The per-pixel loss, such as MSE and MAE, between the output of the network and the ground-truth images were among the first choices. More complicated and common similarity measures in which the error is computed in a hand-designed feature space are also employed. Furthermore, Deep Perceptual Similarity (DPS) metrics, where the similarity is measured in the deep feature space, also have promising results. This feature can be selected from a pre-trained or optimized model for the task at hand. Recently many studies have been conducted to thoroughly investigate DPS. In this research, we provide an in-depth analysis of the pros and cons of DPS in assessing the full reference quality assessment. In addition, to compare different similarity measures, we propose a metric which aggregates various desired factors. Based on our experiment, it can be concluded that perceptual similarity is not directly related to classification accuracy. It is discovered that the outliers mostly contain high-frequency elements. The code and complete outcomes described in results, can be found on: https://github.com/Alireza-Khatami/PerceptualQuality","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126049493","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}
Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147192
Masoumeh Sharafi, M. Yazdchi, J. Rasti
Emotion recognition is a challenging task due to the emotional gap between subjective feeling and low-level audio-visual characteristics. Thus, the development of a feasible approach for high-performance emotion recognition might enhance human-computer interaction. Deep learning methods have enhanced the performance of emotion recognition systems in comparison to other current methods. In this paper, a multimodal deep convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) network are proposed, which fuses the audio and visual cues in a deep model. The spatial and temporal features extracted from video frames are fused with short-term Fourier transform (STFT) extracted from audio signals. Finally, a Softmax classifier is used to classify inputs into seven groups: anger, disgust, fear, happiness, sadness, surprise, and neutral mode. The proposed model is evaluated on Surrey Audio-Visual Expressed Emotion (SAVEE) database with an accuracy of 95.48%. Our experimental study reveals that the suggested method is more effective than existing algorithms in adapting to emotion recognition in this dataset.
{"title":"Audio-Visual Emotion Recognition Using K-Means Clustering and Spatio-Temporal CNN","authors":"Masoumeh Sharafi, M. Yazdchi, J. Rasti","doi":"10.1109/IPRIA59240.2023.10147192","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147192","url":null,"abstract":"Emotion recognition is a challenging task due to the emotional gap between subjective feeling and low-level audio-visual characteristics. Thus, the development of a feasible approach for high-performance emotion recognition might enhance human-computer interaction. Deep learning methods have enhanced the performance of emotion recognition systems in comparison to other current methods. In this paper, a multimodal deep convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) network are proposed, which fuses the audio and visual cues in a deep model. The spatial and temporal features extracted from video frames are fused with short-term Fourier transform (STFT) extracted from audio signals. Finally, a Softmax classifier is used to classify inputs into seven groups: anger, disgust, fear, happiness, sadness, surprise, and neutral mode. The proposed model is evaluated on Surrey Audio-Visual Expressed Emotion (SAVEE) database with an accuracy of 95.48%. Our experimental study reveals that the suggested method is more effective than existing algorithms in adapting to emotion recognition in this dataset.","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116618260","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}
Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147191
Seyed Amir Latifi, H. Ghassemian, M. Imani
Bacteria, viruses, and fungi can cause respiratory infections. It is usually possible to detect respiratory diseases early by listening to the lung sounds with a stethoscope. In reality, lung sound analysis is a time-consuming and difficult task that depends on medical skills and recognition experience. Recent advances in automatic respiratory sound recognition and classification have attracted more attention. The outbreak of COVID-19 throughout the world and the high patient numbers have placed a great deal of pressure on medical professionals. A smart algorithm is therefore a necessity to provide a faster and more accurate detection of lung infections by automatically processing the sounds of the lungs. This paper proposes two new lung sound feature extraction, maximum entropy Gabor filter bank (MAGFB), and maximum entropy Mel filter bank (MAMFB). The classification is performed by a deep neural convolution network (DCNN) by using 50% of data for training the classifier. The filter banks have been substituted, instead of the convolutional layers. Experiments were conducted on the ICBHI 2017 Challenge dataset (with eight classes). The proposed method has a better performance compared to famous methods such as MFCC and Wavelet transform. Particularly, the performance of the second method is significant. For ICBHI 2017 challenge dataset, the overall accuracy of MFCC, Wavelet, MAGFB and MAMFB were 87%, 86%,90% and 93%, respectively.
{"title":"Feature Extraction and Classification of Respiratory Sound and Lung Diseases","authors":"Seyed Amir Latifi, H. Ghassemian, M. Imani","doi":"10.1109/IPRIA59240.2023.10147191","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147191","url":null,"abstract":"Bacteria, viruses, and fungi can cause respiratory infections. It is usually possible to detect respiratory diseases early by listening to the lung sounds with a stethoscope. In reality, lung sound analysis is a time-consuming and difficult task that depends on medical skills and recognition experience. Recent advances in automatic respiratory sound recognition and classification have attracted more attention. The outbreak of COVID-19 throughout the world and the high patient numbers have placed a great deal of pressure on medical professionals. A smart algorithm is therefore a necessity to provide a faster and more accurate detection of lung infections by automatically processing the sounds of the lungs. This paper proposes two new lung sound feature extraction, maximum entropy Gabor filter bank (MAGFB), and maximum entropy Mel filter bank (MAMFB). The classification is performed by a deep neural convolution network (DCNN) by using 50% of data for training the classifier. The filter banks have been substituted, instead of the convolutional layers. Experiments were conducted on the ICBHI 2017 Challenge dataset (with eight classes). The proposed method has a better performance compared to famous methods such as MFCC and Wavelet transform. Particularly, the performance of the second method is significant. For ICBHI 2017 challenge dataset, the overall accuracy of MFCC, Wavelet, MAGFB and MAMFB were 87%, 86%,90% and 93%, respectively.","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117321147","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}
Pub Date : 2023-02-14DOI: 10.1109/IPRIA59240.2023.10147188
Alireza Sadeghi, Hassan Khutanlou
The hippocampus is an important part of the human brain that is damaged in some diseases such as Alzheimer's, schizophrenia, and epilepsy. This paper presents a new method in hippocampus segmentation which is applicable in the early diagnosis of mentioned diseases. This method has introduced a two-section model to detect the hippocampus region in brain MR images. In the first section, the location of the hippocampus is roughly detected using a U-Net neural network model, and then a fuzzy mask is created around the detected area using a fuzzy function. In the second section, this mask is applied to the brain images and a U-Net neural network is used to segment these masked images, which finally predicts the location of the hippocampus. The main advantage and idea of this method is the use of a pre-trained fuzzy mask, which increases the quality of segmentation. The proposed method in this research was trained and tested using the HARP dataset, which contains 135 T1-weighted MRI volumes and the proposed model reached 0.95 dice in the best case.
{"title":"Hippocampus segmentation in MR brain images using learned fuzzy mask and U-Net","authors":"Alireza Sadeghi, Hassan Khutanlou","doi":"10.1109/IPRIA59240.2023.10147188","DOIUrl":"https://doi.org/10.1109/IPRIA59240.2023.10147188","url":null,"abstract":"The hippocampus is an important part of the human brain that is damaged in some diseases such as Alzheimer's, schizophrenia, and epilepsy. This paper presents a new method in hippocampus segmentation which is applicable in the early diagnosis of mentioned diseases. This method has introduced a two-section model to detect the hippocampus region in brain MR images. In the first section, the location of the hippocampus is roughly detected using a U-Net neural network model, and then a fuzzy mask is created around the detected area using a fuzzy function. In the second section, this mask is applied to the brain images and a U-Net neural network is used to segment these masked images, which finally predicts the location of the hippocampus. The main advantage and idea of this method is the use of a pre-trained fuzzy mask, which increases the quality of segmentation. The proposed method in this research was trained and tested using the HARP dataset, which contains 135 T1-weighted MRI volumes and the proposed model reached 0.95 dice in the best case.","PeriodicalId":109390,"journal":{"name":"2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA)","volume":"29 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134035191","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：