Pub Date : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263498
Yan Wang, Xiangrong Tong
Trust evaluation is one of the most important issues in trust related research. How to evaluate the trust between two users is the main problem faced by many current recommendation systems and trust research. Currently in many applications, such as movie recommendation, spam detection, and online borrowing, evaluating trust among users in a trust social network (TSN) is a key issue. Therefore, this paper introduces the development process of trust evaluation in two aspects. The first is trust evaluation under different factors, such as user information and evidence. The second is trust evaluation based on different methods, such as neural networks and collaborative filtering methods. In the future, more factors can be combined with neural networks and reinforcement learning for trust assessment. For user privacy protection, blockchain technology can be combined to better encrypt user information, making the results more accurate and close to reality, and apply to more recommendation systems.
{"title":"Research Progress of Trust Evaluation","authors":"Yan Wang, Xiangrong Tong","doi":"10.1109/CISP-BMEI51763.2020.9263498","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263498","url":null,"abstract":"Trust evaluation is one of the most important issues in trust related research. How to evaluate the trust between two users is the main problem faced by many current recommendation systems and trust research. Currently in many applications, such as movie recommendation, spam detection, and online borrowing, evaluating trust among users in a trust social network (TSN) is a key issue. Therefore, this paper introduces the development process of trust evaluation in two aspects. The first is trust evaluation under different factors, such as user information and evidence. The second is trust evaluation based on different methods, such as neural networks and collaborative filtering methods. In the future, more factors can be combined with neural networks and reinforcement learning for trust assessment. For user privacy protection, blockchain technology can be combined to better encrypt user information, making the results more accurate and close to reality, and apply to more recommendation systems.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124822552","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}
This study aimed to develop an experimental method for minimizing masking in signal detection using a data removal strategy. Reports in the Chinese Spontaneous Reporting Database (CSRD) between 2010 and 2011 were selected as the initial database. A reference database including known signals was used for performance evaluation. The data removal strategy was as follows: 1) the data were sorted according to the frequency of drug–event combinations (DECs), and the top n% of DECs was removed from the initial database; 2) signals of disproportionate reporting were detected using the MHRA for each new database; and 3) the performance was evaluated based on the reference database before and after data removal. The five adverse events (AEs) of interest: renal failure acute, skin exfoliation, syncope, leucopenia, and tetany were selected to test the result. Our experimental results showed that the value of F index increased first and then decreased with data removal, and the value of benefit rate (BR) rose in the new database constantly. In the sixth experiment, the F index reached a peak value (50.63%), and the performance of unmasking achieved the best, where the value of BR was changed from 10.72% to 52.12% and the number of known signals exposed was changed from 6314 to 6787. The performance of unmasking achieved the best when the top 6% of DECs were removed from the CSRD.
{"title":"Minimization of masking in signal detection from Chinese spontaneous reporting databases based on data removal strategy","authors":"Jianxiang Wei, Mei-Han Liu, Zhi-Qiang Lu, Junchang Wang, Shuai Chen, Yue Lan, Guangjun Feng","doi":"10.1109/CISP-BMEI51763.2020.9263656","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263656","url":null,"abstract":"This study aimed to develop an experimental method for minimizing masking in signal detection using a data removal strategy. Reports in the Chinese Spontaneous Reporting Database (CSRD) between 2010 and 2011 were selected as the initial database. A reference database including known signals was used for performance evaluation. The data removal strategy was as follows: 1) the data were sorted according to the frequency of drug–event combinations (DECs), and the top n% of DECs was removed from the initial database; 2) signals of disproportionate reporting were detected using the MHRA for each new database; and 3) the performance was evaluated based on the reference database before and after data removal. The five adverse events (AEs) of interest: renal failure acute, skin exfoliation, syncope, leucopenia, and tetany were selected to test the result. Our experimental results showed that the value of F index increased first and then decreased with data removal, and the value of benefit rate (BR) rose in the new database constantly. In the sixth experiment, the F index reached a peak value (50.63%), and the performance of unmasking achieved the best, where the value of BR was changed from 10.72% to 52.12% and the number of known signals exposed was changed from 6314 to 6787. The performance of unmasking achieved the best when the top 6% of DECs were removed from the CSRD.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127248240","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 : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263574
Senlin Chen, Shihan Shan, W. Zhang, Xiaoping Wang, Mengmeng Tong
Red tide occurs frequently these years and have become a great threat to marine ecology and human health. Monitoring the abundance of red tide algae is very crucial for forecasting and responding potential red tide outbreak. Now there are lots of imaging techniques can rapidly collect algae images which can be used to estimate the algae concentration by classification and counting, but few technologies are specific to red tide algae. In this study, we construct a high-solution color microscopic image dataset contain nine common species of red tide algae. Based on the dataset, we develop a computer vision- based automated red tide recognition and classification system involving image segmentation, artificial feature extraction and classification based on machine learning algorithm. Image segmentation detect the single algae’s boundaries and acquire its bounding rectangular areas as the subimage from the original images, even where several objects stick together. Feature extraction process is applied to extract specific feature vectors in terms of own artificial features including shape, color and texture features. Considering the uncertainty of the rotation of the red tide algae and the possible influence of environmental light, the features both have rotation and brightness invariance. we use three different algorithms including Logistic Regression (LR), Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) to construct classifiers to classify algae images based on extracted features. We also adopt the idea of ensemble learning to achieve better performance than a single algorithm.¬ The system achieves over 95% segmentation efficiency in the and 96% classification accuracy in about 200 test images, making it comparable with a trained biologist can achieve by manual method. The study proves the potential of identifying and classifying red tide algae by color microscopic images, which may provide new ideas for monitoring red tide by imaging techniques.
{"title":"Automated red tide algae recognition by the color microscopic image","authors":"Senlin Chen, Shihan Shan, W. Zhang, Xiaoping Wang, Mengmeng Tong","doi":"10.1109/CISP-BMEI51763.2020.9263574","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263574","url":null,"abstract":"Red tide occurs frequently these years and have become a great threat to marine ecology and human health. Monitoring the abundance of red tide algae is very crucial for forecasting and responding potential red tide outbreak. Now there are lots of imaging techniques can rapidly collect algae images which can be used to estimate the algae concentration by classification and counting, but few technologies are specific to red tide algae. In this study, we construct a high-solution color microscopic image dataset contain nine common species of red tide algae. Based on the dataset, we develop a computer vision- based automated red tide recognition and classification system involving image segmentation, artificial feature extraction and classification based on machine learning algorithm. Image segmentation detect the single algae’s boundaries and acquire its bounding rectangular areas as the subimage from the original images, even where several objects stick together. Feature extraction process is applied to extract specific feature vectors in terms of own artificial features including shape, color and texture features. Considering the uncertainty of the rotation of the red tide algae and the possible influence of environmental light, the features both have rotation and brightness invariance. we use three different algorithms including Logistic Regression (LR), Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) to construct classifiers to classify algae images based on extracted features. We also adopt the idea of ensemble learning to achieve better performance than a single algorithm.¬ The system achieves over 95% segmentation efficiency in the and 96% classification accuracy in about 200 test images, making it comparable with a trained biologist can achieve by manual method. The study proves the potential of identifying and classifying red tide algae by color microscopic images, which may provide new ideas for monitoring red tide by imaging techniques.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125338862","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 : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263535
Zhan Sun, Wei Han, Yuxiao Yang
The battery size is measured by the proposed machine vision method. The morphological method is used to locate the edge at the pixel level quickly, and then the Zernike moment method is used to extract the sub-pixel edge. An in-situ comparison method is proposed to calculate the size deviation between the battery and the standard board, by which the measurement error caused by the distortion when the image has residual distortion can be effectively reduce.(Abstract)
{"title":"High precision machine vision measurement based on the in situ comparison","authors":"Zhan Sun, Wei Han, Yuxiao Yang","doi":"10.1109/CISP-BMEI51763.2020.9263535","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263535","url":null,"abstract":"The battery size is measured by the proposed machine vision method. The morphological method is used to locate the edge at the pixel level quickly, and then the Zernike moment method is used to extract the sub-pixel edge. An in-situ comparison method is proposed to calculate the size deviation between the battery and the standard board, by which the measurement error caused by the distortion when the image has residual distortion can be effectively reduce.(Abstract)","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121506824","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 : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263644
Romesh Laishram, Rinku Rabidas
Since early detection of breast cancer can effectively reduce the mortality rate, hence, in an attempt, mass, a symptom of breast cancer which is difficult to identify due to its subtle nature, is targeted to locate it efficiently with the proposed detection scheme. This paper introduces FRFCM-PSO, a hybrid model of fast and robust fuzzy c-means clustering (FRFCM) and particle swarm optimization (PSO), for the localization of mammographic masses. FRFCM is an improvised version of FCM by employing morphological reconstruction and member-ship filters which alleviates the necessity of additional local spatial information which burdens the method with computational complexity. Moreover, the general limitation of clustering technique of initializing the center point has been mitigated by incorporating optimization method– PSO. Hence, the combinational approach yields a sensitivity of 96.6 % with 2.29 as false positives per image (FPs/I) when evaluated on the mini-MIAS dataset. Further, the FPs are reduced using feature extraction (LBP) and classification (Ensemble classifier) technique where an Az value of 0.846 is observed with an improvement of 74 % in FPs/I which is further compared with the similar competing scheme.
{"title":"Detection of Mammographic Masses using FRFCM Optimized by PSO","authors":"Romesh Laishram, Rinku Rabidas","doi":"10.1109/CISP-BMEI51763.2020.9263644","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263644","url":null,"abstract":"Since early detection of breast cancer can effectively reduce the mortality rate, hence, in an attempt, mass, a symptom of breast cancer which is difficult to identify due to its subtle nature, is targeted to locate it efficiently with the proposed detection scheme. This paper introduces FRFCM-PSO, a hybrid model of fast and robust fuzzy c-means clustering (FRFCM) and particle swarm optimization (PSO), for the localization of mammographic masses. FRFCM is an improvised version of FCM by employing morphological reconstruction and member-ship filters which alleviates the necessity of additional local spatial information which burdens the method with computational complexity. Moreover, the general limitation of clustering technique of initializing the center point has been mitigated by incorporating optimization method– PSO. Hence, the combinational approach yields a sensitivity of 96.6 % with 2.29 as false positives per image (FPs/I) when evaluated on the mini-MIAS dataset. Further, the FPs are reduced using feature extraction (LBP) and classification (Ensemble classifier) technique where an Az value of 0.846 is observed with an improvement of 74 % in FPs/I which is further compared with the similar competing scheme.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124914270","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 : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263639
Li Yu, Dequan Zhu, Jian He
As a specific application of image inpainting, face inpainting based on generative adversarial network (GAN) has made great process in recent years. However, there are still many problems in the current face inpainting methods, such as asymmetric eyes, unsuitable size of nose and artificial expression. Considering the obvious structural feature of human face, this paper proposes a face image restoration method based on semantic segmentation guidance. In the base of the repair network Spectral-Normalized PatchGAN (SN-PatchGAN), the semantic segmentation network is used to guide the repair process, which can make the inpainting face image to be more realistic. Moreover, an asymmetry loss is designed to reduce the eye asymmetry. Experiments on public dataset show that our approach outperform existing methods quantitatively and qualitatively.
{"title":"Semantic segmentation guided face inpainting based on SN-PatchGAN","authors":"Li Yu, Dequan Zhu, Jian He","doi":"10.1109/CISP-BMEI51763.2020.9263639","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263639","url":null,"abstract":"As a specific application of image inpainting, face inpainting based on generative adversarial network (GAN) has made great process in recent years. However, there are still many problems in the current face inpainting methods, such as asymmetric eyes, unsuitable size of nose and artificial expression. Considering the obvious structural feature of human face, this paper proposes a face image restoration method based on semantic segmentation guidance. In the base of the repair network Spectral-Normalized PatchGAN (SN-PatchGAN), the semantic segmentation network is used to guide the repair process, which can make the inpainting face image to be more realistic. Moreover, an asymmetry loss is designed to reduce the eye asymmetry. Experiments on public dataset show that our approach outperform existing methods quantitatively and qualitatively.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121472014","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}
Network security has become an important issue in our work and life. Hackers' attack mode has been upgraded from normal attack to APT( ( Advanced Persistent Threat, APT) attack. The key of APT attack chain is the penetration and intrusion of active directory, which can not be completely detected via the traditional IDS and antivirus software. Further more, lack of security protection of existing solutions for domain control aggravates this problem. Although researchers have proposed methods for domain attack detection, many of them have not yet been converted into effective market-oriented products. In this paper, we analyzes the common domain intrusion methods, various domain related attack behavior characteristics were extracted from ATT&CK matrix (Advanced tactics, techniques, and common knowledge) for analysis and simulation test. Based on analyzing the log file generated by the attack, the domain attack detection rules are established and input into the analysis engine. Finally, the available domain intrusion detection system is designed and implemented. Experimental results show that the network attack detection method based on the analysis of domain attack behavior can analyze the log file in real time and effectively detect the malicious intrusion behavior of hackers , which could facilitate managers find and eliminate network security threats immediately.
网络安全已经成为我们工作和生活中的一个重要问题。黑客攻击模式由普通攻击升级为APT(Advanced Persistent Threat, APT)攻击。APT攻击链的关键是活动目录的渗透和入侵，传统的IDS和杀毒软件无法完全检测到。此外，现有的域控制解决方案缺乏安全保护，加剧了这一问题。虽然研究人员提出了一些领域攻击检测的方法，但许多方法尚未转化为有效的市场产品。本文分析了常用的领域入侵方法，从ATT&CK矩阵(Advanced tactics, techniques, and common knowledge)中提取了各种领域相关的攻击行为特征，用于分析和仿真测试。通过对攻击产生的日志文件进行分析，建立域攻击检测规则，并输入到分析引擎中。最后，设计并实现了可用的域入侵检测系统。实验结果表明，基于域攻击行为分析的网络攻击检测方法能够实时分析日志文件，有效检测黑客的恶意入侵行为，便于管理者及时发现并消除网络安全威胁。
{"title":"Network Attack Detection based on Domain Attack Behavior Analysis","authors":"Weifeng Wang, Xinyu Zhang, Likai Dong, Yuling Fan, Xinyi Diao, Tao Xu","doi":"10.1109/CISP-BMEI51763.2020.9263663","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263663","url":null,"abstract":"Network security has become an important issue in our work and life. Hackers' attack mode has been upgraded from normal attack to APT( ( Advanced Persistent Threat, APT) attack. The key of APT attack chain is the penetration and intrusion of active directory, which can not be completely detected via the traditional IDS and antivirus software. Further more, lack of security protection of existing solutions for domain control aggravates this problem. Although researchers have proposed methods for domain attack detection, many of them have not yet been converted into effective market-oriented products. In this paper, we analyzes the common domain intrusion methods, various domain related attack behavior characteristics were extracted from ATT&CK matrix (Advanced tactics, techniques, and common knowledge) for analysis and simulation test. Based on analyzing the log file generated by the attack, the domain attack detection rules are established and input into the analysis engine. Finally, the available domain intrusion detection system is designed and implemented. Experimental results show that the network attack detection method based on the analysis of domain attack behavior can analyze the log file in real time and effectively detect the malicious intrusion behavior of hackers , which could facilitate managers find and eliminate network security threats immediately.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"10 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114052151","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 : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263563
Tianyu Zhao, Jindong Xu
The "synonyms spectrum" and "foreign body with the spectrum" of remote sensing images have caused the traditional segmentation methods to be greatly limited. Existing segmentation methods represented by deep convolution neural network have made breakthrough progress. However, traditional deep learning is a completely deterministic model, which can not describe the data uncertainty well. To solve this problem, a new fuzzy deep neural network is proposed in this paper, called RSFCNN (Remote Sensing image segmentation with Fuzzy Convolutional Neural Network). The network integrates fuzzy unit and traditional convolution unit. Convolution unit is used to extract discriminant features with different proportions, thus providing comprehensive information for pixel-level remote sensing image segmentation. Fuzzy logic unit is used to deal with various uncertainties and provide more reliable segmentation results. In this paper, end-to-end training scheme is used to learn the parameters of fuzzy and convolution units. Experiments were carried out on the data set of ISPRS Vaihingen. According to the experimental results, the proposed method has higher segmentation accuracy and better performance than other algorithms.
{"title":"Hyperspectral Remote Sensing Image Segmentation Based on the Fuzzy Deep Convolutional Neural Network","authors":"Tianyu Zhao, Jindong Xu","doi":"10.1109/CISP-BMEI51763.2020.9263563","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263563","url":null,"abstract":"The \"synonyms spectrum\" and \"foreign body with the spectrum\" of remote sensing images have caused the traditional segmentation methods to be greatly limited. Existing segmentation methods represented by deep convolution neural network have made breakthrough progress. However, traditional deep learning is a completely deterministic model, which can not describe the data uncertainty well. To solve this problem, a new fuzzy deep neural network is proposed in this paper, called RSFCNN (Remote Sensing image segmentation with Fuzzy Convolutional Neural Network). The network integrates fuzzy unit and traditional convolution unit. Convolution unit is used to extract discriminant features with different proportions, thus providing comprehensive information for pixel-level remote sensing image segmentation. Fuzzy logic unit is used to deal with various uncertainties and provide more reliable segmentation results. In this paper, end-to-end training scheme is used to learn the parameters of fuzzy and convolution units. Experiments were carried out on the data set of ISPRS Vaihingen. According to the experimental results, the proposed method has higher segmentation accuracy and better performance than other algorithms.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122618262","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 : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263516
Xuebao Wang, Tao Ying, Wei Tian
A new spectrum representation method based on short time Fourier transform (STFT) is proposed. The formula of new spectrum representation is derived base on energy cumulant of short time Fourier transform (EC-STFT), which indicates that EC-STFT has the spectrum characteristics. Simulations on the linear frequency modulation (LFM) signal show that the EC-STFT spectrum is closer to the ideal spectrum curve than FT spectrum. During calculating EC-STFT, a time frequency domain iterative mean threshold (TFD-IMT) denoising method is presented to remove the addictive white Gaussian noise (AWGN), by which the EC-STFT spectrum has better anti-noise capacity than FT spectrum. Theoretical analyses and simulations verify the advantages of the EC-STFT over FT in conditions of low SNR.
{"title":"Spectrum Representation Based on STFT","authors":"Xuebao Wang, Tao Ying, Wei Tian","doi":"10.1109/CISP-BMEI51763.2020.9263516","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263516","url":null,"abstract":"A new spectrum representation method based on short time Fourier transform (STFT) is proposed. The formula of new spectrum representation is derived base on energy cumulant of short time Fourier transform (EC-STFT), which indicates that EC-STFT has the spectrum characteristics. Simulations on the linear frequency modulation (LFM) signal show that the EC-STFT spectrum is closer to the ideal spectrum curve than FT spectrum. During calculating EC-STFT, a time frequency domain iterative mean threshold (TFD-IMT) denoising method is presented to remove the addictive white Gaussian noise (AWGN), by which the EC-STFT spectrum has better anti-noise capacity than FT spectrum. Theoretical analyses and simulations verify the advantages of the EC-STFT over FT in conditions of low SNR.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132909851","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 : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263589
Ru Kong, Xiangrong Tong
Path search is designed to find a path by traversing the state spaces from the initial state to the target state. Given enough memory and run time, the A* algorithm can find an optimal solution, but it expends much time to distinguish similar paths. Therefore, many scholars have proposed variants of the A* algorithm that find a suboptimal solution to speed up the searching efficiency. In this paper, the A* algorithm is improved and a new anytime dynamic heuristic search algorithm (ADHS) is proposed. It can find a solution quickly and then continuously optimize the quality of the solution to find the suboptimal solution until the end of time. The ADHS includes two stages, in the exploration stage, given an arbitrary cost bound, the solution is quickly obtained; in the update stage, where no setting parameters are required, reuses the previous search results. According to the cost of the latest solution, the dynamic weight factor w is introduced, which is half of the error between the current cost bound and the current solution. The next cost bound is dynamically adjusted, and the suboptimal solution is output. We tested the performance of the ADHS on the grid maps, and the experiments demonstrated that the performance of the ADHS was better than other algorithms.
{"title":"Anytime Dynamic Heuristic Search for Suboptimal Solution on Path Search","authors":"Ru Kong, Xiangrong Tong","doi":"10.1109/CISP-BMEI51763.2020.9263589","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263589","url":null,"abstract":"Path search is designed to find a path by traversing the state spaces from the initial state to the target state. Given enough memory and run time, the A* algorithm can find an optimal solution, but it expends much time to distinguish similar paths. Therefore, many scholars have proposed variants of the A* algorithm that find a suboptimal solution to speed up the searching efficiency. In this paper, the A* algorithm is improved and a new anytime dynamic heuristic search algorithm (ADHS) is proposed. It can find a solution quickly and then continuously optimize the quality of the solution to find the suboptimal solution until the end of time. The ADHS includes two stages, in the exploration stage, given an arbitrary cost bound, the solution is quickly obtained; in the update stage, where no setting parameters are required, reuses the previous search results. According to the cost of the latest solution, the dynamic weight factor w is introduced, which is half of the error between the current cost bound and the current solution. The next cost bound is dynamically adjusted, and the suboptimal solution is output. We tested the performance of the ADHS on the grid maps, and the experiments demonstrated that the performance of the ADHS was better than other algorithms.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134162461","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：