Pub Date : 2024-10-11DOI: 10.1109/MSP.2024.3448099
{"title":"Special Issue on Accelerating Brain Discovery Through Data Science and Neurotechnology","authors":"","doi":"10.1109/MSP.2024.3448099","DOIUrl":"https://doi.org/10.1109/MSP.2024.3448099","url":null,"abstract":"","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 4","pages":"7-7"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714508","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142409052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-11DOI: 10.1109/MSP.2024.3440568
Alan V. Oppenheim;Ronald W. Schafer;James Ward
{"title":"Efficient Deconvolution With the Discrete Fourier Transform","authors":"Alan V. Oppenheim;Ronald W. Schafer;James Ward","doi":"10.1109/MSP.2024.3440568","DOIUrl":"https://doi.org/10.1109/MSP.2024.3440568","url":null,"abstract":"","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 4","pages":"76-83"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714910","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-11DOI: 10.1109/MSP.2024.3424578
Zafar Rafii;Erling Wold;Richard Boulderstone
We show how to design a cheap system for detecting when music is present in audio recordings. We make use of a small neural network consisting of a simple multilayer perceptron (MLP) along with compact features derived from the mel spectrogram by means of temporal integration.
{"title":"How to Design a Cheap Music Detection System Using a Simple Multilayer Perceptron With Temporal Integration","authors":"Zafar Rafii;Erling Wold;Richard Boulderstone","doi":"10.1109/MSP.2024.3424578","DOIUrl":"https://doi.org/10.1109/MSP.2024.3424578","url":null,"abstract":"We show how to design a cheap system for detecting when music is present in audio recordings. We make use of a small neural network consisting of a simple multilayer perceptron (MLP) along with compact features derived from the mel spectrogram by means of temporal integration.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 4","pages":"83-88"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3394153
Roman Jacome;Kumar Vijay Mishra;Brian M. Sadler;Henry Arguello
Hypercomplex signal processing (HSP) provides state-of-the-art tools to handle multidimensional signals by harnessing the intrinsic correlation of the signal dimensions through Clifford algebra. Recently, the hypercomplex representation of the phase retrieval (PR) problem, wherein a complex-valued signal is estimated through its intensity-only projections, has attracted significant interest. The hypercomplex PR (HPR) arises in many optical imaging and computational sensing applications that usually comprise quaternion- and octonion-valued signals. Analogous to the traditional PR, measurements in HPR may involve complex, hypercomplex, Fourier, and other sensing matrices. This set of problems opens opportunities for developing novel HSP tools and algorithms. This article provides a synopsis of the emerging areas and applications of HPR with a focus on optical imaging.
{"title":"An Invitation to Hypercomplex Phase Retrieval: Theory and applications [Hypercomplex Signal and Image Processing]","authors":"Roman Jacome;Kumar Vijay Mishra;Brian M. Sadler;Henry Arguello","doi":"10.1109/MSP.2024.3394153","DOIUrl":"https://doi.org/10.1109/MSP.2024.3394153","url":null,"abstract":"Hypercomplex signal processing (HSP) provides state-of-the-art tools to handle multidimensional signals by harnessing the intrinsic correlation of the signal dimensions through Clifford algebra. Recently, the hypercomplex representation of the phase retrieval (PR) problem, wherein a complex-valued signal is estimated through its intensity-only projections, has attracted significant interest. The hypercomplex PR (HPR) arises in many optical imaging and computational sensing applications that usually comprise quaternion- and octonion-valued signals. Analogous to the traditional PR, measurements in HPR may involve complex, hypercomplex, Fourier, and other sensing matrices. This set of problems opens opportunities for developing novel HSP tools and algorithms. This article provides a synopsis of the emerging areas and applications of HPR with a focus on optical imaging.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"22-32"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3384178
Clive Cheong Took;Sayed Pouria Talebi;Rosa Maria Fernandez Alcala;Danilo P. Mandic
Learning machines for vector sensor data are naturally developed in the quaternion domain and are underpinned by quaternion statistics. To this end, we revisit the “augmented” representation basis for discrete quaternion random variables (RVs) ${bf{q}}^{a}[n]$ , i.e., ${[}{bf{q}}{[}{n}{]};{bf{q}}^{imath}{[}{n}{]};{bf{q}}^{jmath}{[}{n}{]}{bf{q}}^{kappa}{[}{n}{]]}$ , and demonstrate its pivotal role in the treatment of the generality of quaternion RVs. This is achieved by a rigorous consideration of the augmented quaternion RV and by involving the additional second-order statistics, besides the traditional covariance $E{{bf{q}}mathbf{[}{n}mathbf{]}{bf{q}}^{{*}}mathbf{[}{n}mathbf{]}}$[1] . To illuminate the usefulness of quaternions, we consider their most well-known application—3D orientation—and offer an account of augmented statistics for purely imaginary (pure) quaternions. The quaternion statistics presented here can be exploited in the analysis of existing and the development of novel statistical machine learning methods, hence acting as a lynchpin for quaternion learning machines.
{"title":"Augmented Statistics of Quaternion Random Variables: A lynchpin of quaternion learning machines [Hypercomplex Signal and Image Processing]","authors":"Clive Cheong Took;Sayed Pouria Talebi;Rosa Maria Fernandez Alcala;Danilo P. Mandic","doi":"10.1109/MSP.2024.3384178","DOIUrl":"https://doi.org/10.1109/MSP.2024.3384178","url":null,"abstract":"Learning machines for vector sensor data are naturally developed in the quaternion domain and are underpinned by quaternion statistics. To this end, we revisit the “augmented” representation basis for discrete quaternion random variables (RVs) \u0000<inline-formula><tex-math>${bf{q}}^{a}[n]$</tex-math></inline-formula>\u0000, i.e., \u0000<inline-formula><tex-math>${[}{bf{q}}{[}{n}{]};{bf{q}}^{imath}{[}{n}{]};{bf{q}}^{jmath}{[}{n}{]}{bf{q}}^{kappa}{[}{n}{]]}$</tex-math></inline-formula>\u0000, and demonstrate its pivotal role in the treatment of the generality of quaternion RVs. This is achieved by a rigorous consideration of the augmented quaternion RV and by involving the additional second-order statistics, besides the traditional covariance \u0000<inline-formula><tex-math>$E{{bf{q}}mathbf{[}{n}mathbf{]}{bf{q}}^{{*}}mathbf{[}{n}mathbf{]}}$</tex-math></inline-formula>\u0000 \u0000<xref>[1]</xref>\u0000. To illuminate the usefulness of quaternions, we consider their most well-known application—3D orientation—and offer an account of augmented statistics for purely imaginary (pure) quaternions. The quaternion statistics presented here can be exploited in the analysis of existing and the development of novel statistical machine learning methods, hence acting as a lynchpin for quaternion learning machines.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"72-87"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3429689
Tülay Adali
In the first issue of 2024, we introduced the new lead editorial team of IEEE Signal Processing Magazine ( SPM ), composed of our four area editors. Their terms started with mine this January, and they oversee the Society e-newsletter and the three main components of our magazine: feature articles, special issues, and columns and forum articles. As a team, we have undertaken a complete revision of the specifications for all article types and the information we provide our authors. We also revised the templates for all article types along with proposals and white papers, and all are included within the IEEE Author Center’s template selector [1] .
{"title":"Volunteer Power Through Noisy Gradients and Self-Organization: What About Pruning? [From the Editor]","authors":"Tülay Adali","doi":"10.1109/MSP.2024.3429689","DOIUrl":"https://doi.org/10.1109/MSP.2024.3429689","url":null,"abstract":"In the first issue of 2024, we introduced the new lead editorial team of \u0000<italic>IEEE Signal Processing Magazine</i>\u0000 (\u0000<italic>SPM</i>\u0000), composed of our four area editors. Their terms started with mine this January, and they oversee the Society e-newsletter and the three main components of our magazine: feature articles, special issues, and columns and forum articles. As a team, we have undertaken a complete revision of the specifications for all article types and the information we provide our authors. We also revised the templates for all article types along with proposals and white papers, and all are included within the IEEE Author Center’s template selector \u0000<xref>[1]</xref>\u0000.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"3-5"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10640316","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The digital twin of the ocean (DTO) is a groundbreaking concept that uses interactive simulations to improve decision-making and promote sustainability in earth science. The DTO effectively combines ocean observations, artificial intelligence (AI), advanced modeling, and high-performance computing to unite digital replicas, forecasting, and what-if scenario simulations of the ocean systems. However, there are several challenges to overcome in achieving the DTO’s objectives, including the integration of heterogeneous data with multiple coordinate systems, multidimensional data analysis, feature extraction, high-fidelity scene modeling, and interactive virtual–real feedback. Hypercomplex signal processing offers a promising solution to these challenges, and this study provides a comprehensive overview of its application in DTO development. We investigate a range of techniques, including geometric algebra, quaternion signal processing, Clifford signal processing, and hypercomplex machine learning, as the theoretical foundation for hypercomplex signal processing in the DTO. We also review the various application aspects of the DTO that can benefit from hypercomplex signal processing, such as data representation and information fusion, feature extraction and pattern recognition, and intelligent process simulation and forecasting, as well as visualization and interactive virtual–real feedback. Our research demonstrates that hypercomplex signal processing provides innovative solutions for DTO advancement and resolving scientific challenges in oceanography and broader earth science.
{"title":"Hypercomplex Signal Processing in Digital Twin of the Ocean: Theory and application [Hypercomplex Signal and Image Processing]","authors":"Zhaoyuan Yu;Dongshuang Li;Pei Du;Wen Luo;Kit Ian Kou;Uzair Aslam Bhatti;Werner Benger;Guonian Lv;Linwang Yuan","doi":"10.1109/MSP.2024.3389496","DOIUrl":"https://doi.org/10.1109/MSP.2024.3389496","url":null,"abstract":"The digital twin of the ocean (DTO) is a groundbreaking concept that uses interactive simulations to improve decision-making and promote sustainability in earth science. The DTO effectively combines ocean observations, artificial intelligence (AI), advanced modeling, and high-performance computing to unite digital replicas, forecasting, and what-if scenario simulations of the ocean systems. However, there are several challenges to overcome in achieving the DTO’s objectives, including the integration of heterogeneous data with multiple coordinate systems, multidimensional data analysis, feature extraction, high-fidelity scene modeling, and interactive virtual–real feedback. Hypercomplex signal processing offers a promising solution to these challenges, and this study provides a comprehensive overview of its application in DTO development. We investigate a range of techniques, including geometric algebra, quaternion signal processing, Clifford signal processing, and hypercomplex machine learning, as the theoretical foundation for hypercomplex signal processing in the DTO. We also review the various application aspects of the DTO that can benefit from hypercomplex signal processing, such as data representation and information fusion, feature extraction and pattern recognition, and intelligent process simulation and forecasting, as well as visualization and interactive virtual–real feedback. Our research demonstrates that hypercomplex signal processing provides innovative solutions for DTO advancement and resolving scientific challenges in oceanography and broader earth science.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"33-48"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3401621
Marcos Eduardo Valle
Despite the many successful applications of deep learning models for multidimensional signal and image processing, most traditional neural networks process data represented by (multidimensional) arrays of real numbers. The intercorrelation between feature channels is usually expected to be learned from the training data, requiring numerous parameters and careful training. In contrast, vector-valued neural networks (referred to as V-nets ) are conceived to process arrays of vectors and naturally consider the intercorrelation between feature channels. Consequently, they usually have fewer parameters and often undergo more robust training than traditional neural networks. This article aims to present a broad framework for V-nets. In this context, hypercomplex-valued neural networks are regarded as vector-valued models with additional algebraic properties. Furthermore, this article explains the relationship between vector-valued and traditional neural networks. To be precise, a V-net can be obtained by placing restrictions on a real-valued model to consider the intercorrelation between feature channels. Finally, I show how V-nets, including hypercomplex-valued neural networks, can be implemented in current deep learning libraries as real-valued networks.
尽管深度学习模型在多维信号和图像处理方面有许多成功应用，但大多数传统神经网络处理的数据都是由实数（多维）阵列表示的。特征通道之间的相互关系通常需要从训练数据中学习，因此需要大量参数和仔细的训练。与此相反，向量值神经网络（简称 V-网络）的设计理念是处理向量数组，并自然地考虑特征通道之间的相互关系。因此，与传统的神经网络相比，它们的参数通常较少，而且往往需要经过更稳健的训练。本文旨在为 V 型网络提供一个广泛的框架。在此背景下，超复值神经网络被视为具有额外代数特性的向量值模型。此外，本文还解释了向量值神经网络与传统神经网络之间的关系。准确地说，V-网络可以通过对实值模型施加限制来获得，以考虑特征通道之间的相互关系。最后，我展示了 V 型网络（包括超复值神经网络）如何在当前的深度学习库中作为实值网络来实现。
{"title":"Understanding Vector-Valued Neural Networks and Their Relationship With Real and Hypercomplex-Valued Neural Networks: Incorporating intercorrelation between features into neural networks [Hypercomplex Signal and Image Processing]","authors":"Marcos Eduardo Valle","doi":"10.1109/MSP.2024.3401621","DOIUrl":"https://doi.org/10.1109/MSP.2024.3401621","url":null,"abstract":"Despite the many successful applications of deep learning models for multidimensional signal and image processing, most traditional neural networks process data represented by (multidimensional) arrays of real numbers. The intercorrelation between feature channels is usually expected to be learned from the training data, requiring numerous parameters and careful training. In contrast, vector-valued neural networks (referred to as \u0000<italic>V-nets</i>\u0000) are conceived to process arrays of vectors and naturally consider the intercorrelation between feature channels. Consequently, they usually have fewer parameters and often undergo more robust training than traditional neural networks. This article aims to present a broad framework for V-nets. In this context, hypercomplex-valued neural networks are regarded as vector-valued models with additional algebraic properties. Furthermore, this article explains the relationship between vector-valued and traditional neural networks. To be precise, a V-net can be obtained by placing restrictions on a real-valued model to consider the intercorrelation between feature channels. Finally, I show how V-nets, including hypercomplex-valued neural networks, can be implemented in current deep learning libraries as real-valued networks.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"49-58"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","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：