Pub Date : 2024-08-19DOI: 10.1109/JPROC.2024.3440211
Nathan J. Kong;J. Joe Payne;James Zhu;Aaron M. Johnson
Hybrid dynamical systems, i.e., systems that have both continuous and discrete states, are ubiquitous in engineering but are difficult to work with due to their discontinuous transitions. For example, a robot leg is able to exert very little control effort, while it is in the air compared to when it is on the ground. When the leg hits the ground, the penetrating velocity instantaneously collapses to zero. These instantaneous changes in dynamics and discontinuities (or jumps) in state make standard smooth tools for planning, estimation, control, and learning difficult for hybrid systems. One of the key tools for accounting for these jumps is called the saltation matrix. The saltation matrix is the sensitivity update when a hybrid jump occurs and has been used in a variety of fields, including robotics, power circuits, and computational neuroscience. This article presents an intuitive derivation of the saltation matrix and discusses what it captures, where it has been used in the past, how it is used for linear and quadratic forms, how it is computed for rigid body systems with unilateral constraints, and some of the structural properties of the saltation matrix in these cases.
{"title":"Saltation Matrices: The Essential Tool for Linearizing Hybrid Dynamical Systems","authors":"Nathan J. Kong;J. Joe Payne;James Zhu;Aaron M. Johnson","doi":"10.1109/JPROC.2024.3440211","DOIUrl":"10.1109/JPROC.2024.3440211","url":null,"abstract":"Hybrid dynamical systems, i.e., systems that have both continuous and discrete states, are ubiquitous in engineering but are difficult to work with due to their discontinuous transitions. For example, a robot leg is able to exert very little control effort, while it is in the air compared to when it is on the ground. When the leg hits the ground, the penetrating velocity instantaneously collapses to zero. These instantaneous changes in dynamics and discontinuities (or jumps) in state make standard smooth tools for planning, estimation, control, and learning difficult for hybrid systems. One of the key tools for accounting for these jumps is called the saltation matrix. The saltation matrix is the sensitivity update when a hybrid jump occurs and has been used in a variety of fields, including robotics, power circuits, and computational neuroscience. This article presents an intuitive derivation of the saltation matrix and discusses what it captures, where it has been used in the past, how it is used for linear and quadratic forms, how it is computed for rigid body systems with unilateral constraints, and some of the structural properties of the saltation matrix in these cases.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"112 6","pages":"585-608"},"PeriodicalIF":23.2,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142007272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artificial intelligence (AI) technologies have emerged as pivotal enablers across a multitude of industries, including consumer electronics, healthcare, and manufacturing, largely due to their significant resurgence over the past decade. The transformative power of AI is primarily derived from the utilization of deep neural networks (DNNs), which require extensive data for training and substantial computational resources for processing. Consequently, DNN models are typically trained and deployed on resource-rich cloud servers. However, due to potential latency issues associated with cloud communications, deep learning (DL) workflows (e.g., DNN training and inference) are increasingly being transitioned to wireless edge networks in proximity to end-user devices (EUDs). This shift is designed to support latency-sensitive applications and has given rise to a new paradigm of edge AI, which will play a critical role in upcoming sixth-generation (6G) networks to support ubiquitous AI applications. Despite its considerable potential, edge AI faces substantial challenges, mostly due to the dichotomy between the resource limitations of wireless edge networks and the resource-intensive nature of DL. Specifically, the acquisition of large-scale data, as well as the training and inference processes of DNNs, can rapidly deplete the battery energy of EUDs. This necessitates an energy-conscious approach to edge AI to ensure both optimal and sustainable performance. In this article, we present a contemporary survey on green edge AI. We commence by analyzing the principal energy consumption components of edge AI systems to identify the fundamental design principles of green edge AI. Guided by these principles, we then explore energy-efficient design methodologies for the three critical tasks in edge AI systems, including training data acquisition, edge training, and edge inference. Finally, we underscore potential future research directions to further enhance the energy efficiency (EE) of edge AI.
{"title":"Green Edge AI: A Contemporary Survey","authors":"Yuyi Mao;Xianghao Yu;Kaibin Huang;Ying-Jun Angela Zhang;Jun Zhang","doi":"10.1109/JPROC.2024.3437365","DOIUrl":"10.1109/JPROC.2024.3437365","url":null,"abstract":"Artificial intelligence (AI) technologies have emerged as pivotal enablers across a multitude of industries, including consumer electronics, healthcare, and manufacturing, largely due to their significant resurgence over the past decade. The transformative power of AI is primarily derived from the utilization of deep neural networks (DNNs), which require extensive data for training and substantial computational resources for processing. Consequently, DNN models are typically trained and deployed on resource-rich cloud servers. However, due to potential latency issues associated with cloud communications, deep learning (DL) workflows (e.g., DNN training and inference) are increasingly being transitioned to wireless edge networks in proximity to end-user devices (EUDs). This shift is designed to support latency-sensitive applications and has given rise to a new paradigm of edge AI, which will play a critical role in upcoming sixth-generation (6G) networks to support ubiquitous AI applications. Despite its considerable potential, edge AI faces substantial challenges, mostly due to the dichotomy between the resource limitations of wireless edge networks and the resource-intensive nature of DL. Specifically, the acquisition of large-scale data, as well as the training and inference processes of DNNs, can rapidly deplete the battery energy of EUDs. This necessitates an energy-conscious approach to edge AI to ensure both optimal and sustainable performance. In this article, we present a contemporary survey on green edge AI. We commence by analyzing the principal energy consumption components of edge AI systems to identify the fundamental design principles of green edge AI. Guided by these principles, we then explore energy-efficient design methodologies for the three critical tasks in edge AI systems, including training data acquisition, edge training, and edge inference. Finally, we underscore potential future research directions to further enhance the energy efficiency (EE) of edge AI.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"112 7","pages":"880-911"},"PeriodicalIF":23.2,"publicationDate":"2024-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141991776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brain-inspired computing (BIC) is an emerging research field that aims to build fundamental theories, models, hardware architectures, and application systems toward more general artificial intelligence (AI) by learning from the information processing mechanisms or structures/functions of biological nervous systems. It is regarded as one of the most promising research directions for future intelligent computing in the post-Moore era. In the past few years, various new schemes in this field have sprung up to explore more general AI. These works are quite divergent in the aspects of modeling/algorithm, software tool, hardware platform, and benchmark data since BIC is an interdisciplinary field that consists of many different domains, including computational neuroscience, AI, computer science, statistical physics, material science, and microelectronics. This situation greatly impedes researchers from obtaining a clear picture and getting started in the right way. Hence, there is an urgent requirement to do a comprehensive survey in this field to help correctly recognize and analyze such bewildering methodologies. What are the key issues to enhance the development of BIC? What roles do the current mainstream technologies play in the general framework of BIC? Which techniques are truly useful in real-world applications? These questions largely remain open. To address the above issues, in this survey, we first clarify the biggest challenge of BIC: how can AI models benefit from the recent advancements in computational neuroscience? With this challenge in mind, we will focus on discussing the concept of BIC and summarize four components of BIC infrastructure development: 1) modeling/algorithm; 2) hardware platform; 3) software tool; and 4) benchmark data. For each component, we will summarize its recent progress, main challenges to resolve, and future trends. Based on these studies, we present a general framework for the real-world applications of BIC systems, which is promising to benefit both AI and brain science. Finally, we claim that it is extremely important to build a research ecology to promote prosperity continuously in this field.
{"title":"Brain-Inspired Computing: A Systematic Survey and Future Trends","authors":"Guoqi Li;Lei Deng;Huajin Tang;Gang Pan;Yonghong Tian;Kaushik Roy;Wolfgang Maass","doi":"10.1109/JPROC.2024.3429360","DOIUrl":"10.1109/JPROC.2024.3429360","url":null,"abstract":"Brain-inspired computing (BIC) is an emerging research field that aims to build fundamental theories, models, hardware architectures, and application systems toward more general artificial intelligence (AI) by learning from the information processing mechanisms or structures/functions of biological nervous systems. It is regarded as one of the most promising research directions for future intelligent computing in the post-Moore era. In the past few years, various new schemes in this field have sprung up to explore more general AI. These works are quite divergent in the aspects of modeling/algorithm, software tool, hardware platform, and benchmark data since BIC is an interdisciplinary field that consists of many different domains, including computational neuroscience, AI, computer science, statistical physics, material science, and microelectronics. This situation greatly impedes researchers from obtaining a clear picture and getting started in the right way. Hence, there is an urgent requirement to do a comprehensive survey in this field to help correctly recognize and analyze such bewildering methodologies. What are the key issues to enhance the development of BIC? What roles do the current mainstream technologies play in the general framework of BIC? Which techniques are truly useful in real-world applications? These questions largely remain open. To address the above issues, in this survey, we first clarify the biggest challenge of BIC: how can AI models benefit from the recent advancements in computational neuroscience? With this challenge in mind, we will focus on discussing the concept of BIC and summarize four components of BIC infrastructure development: 1) modeling/algorithm; 2) hardware platform; 3) software tool; and 4) benchmark data. For each component, we will summarize its recent progress, main challenges to resolve, and future trends. Based on these studies, we present a general framework for the real-world applications of BIC systems, which is promising to benefit both AI and brain science. Finally, we claim that it is extremely important to build a research ecology to promote prosperity continuously in this field.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"112 6","pages":"544-584"},"PeriodicalIF":23.2,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141986412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The relentless demand for data in our society has driven the continuous evolution of wireless technologies to enhance network capacity. While current deployments of 5G have made strides in this direction using massive multiple-input-multiple-output (MIMO) and millimeter-wave (mmWave) bands, all existing wireless systems operate in a half-duplex (HD) mode. Full-duplex (FD) wireless communication, on the other hand, enables simultaneous transmission and reception (STAR) of signals at the same frequency, offering advantages such as enhanced spectrum efficiency, improved data rates, and reduced latency. This article presents a comprehensive review of FD wireless systems, with a focus on hardware design, implementation, cross-layered considerations, and applications. The major bottleneck in achieving FD communication is the presence of self-interference (SI) signals from the transmitter (TX) to the receiver, and achieving SI cancellation (SIC) with real-time adaption is critical for FD deployment. The review starts by establishing a system-level understanding of FD wireless systems, followed by a review of the architectures of antenna interfaces and integrated RF and baseband (BB) SI cancellers, which show promise in enabling low-cost, small-form-factor, portable FD systems. We then discuss digital cancellation techniques, including digital signal processing (DSP)- and learning-based algorithms. The challenges presented by FD phased-array and MIMO systems are discussed, followed by system-level aspects, including optimization algorithms, opportunities in the higher layers of the networking protocol stack, and testbed integration. Finally, the relevance of FD systems in applications such as next-generation (xG) wireless, mmWave repeaters, radars, and noncommunication domains is highlighted. Overall, this comprehensive review provides valuable insights into the design, implementation, and applications of FD wireless systems while opening up new directions for future research.
{"title":"Doubling Down on Wireless Capacity: A Review of Integrated Circuits, Systems, and Networks for Full Duplex","authors":"Aravind Nagulu;Negar Reiskarimian;Tingjun Chen;Sasank Garikapati;Igor Kadota;Tolga Dinc;Sastry Lakshmi Garimella;Manav Kohli;Alon Simon Levin;Gil Zussman;Harish Krishnaswamy","doi":"10.1109/JPROC.2024.3438755","DOIUrl":"10.1109/JPROC.2024.3438755","url":null,"abstract":"The relentless demand for data in our society has driven the continuous evolution of wireless technologies to enhance network capacity. While current deployments of 5G have made strides in this direction using massive multiple-input-multiple-output (MIMO) and millimeter-wave (mmWave) bands, all existing wireless systems operate in a half-duplex (HD) mode. Full-duplex (FD) wireless communication, on the other hand, enables simultaneous transmission and reception (STAR) of signals at the same frequency, offering advantages such as enhanced spectrum efficiency, improved data rates, and reduced latency. This article presents a comprehensive review of FD wireless systems, with a focus on hardware design, implementation, cross-layered considerations, and applications. The major bottleneck in achieving FD communication is the presence of self-interference (SI) signals from the transmitter (TX) to the receiver, and achieving SI cancellation (SIC) with real-time adaption is critical for FD deployment. The review starts by establishing a system-level understanding of FD wireless systems, followed by a review of the architectures of antenna interfaces and integrated RF and baseband (BB) SI cancellers, which show promise in enabling low-cost, small-form-factor, portable FD systems. We then discuss digital cancellation techniques, including digital signal processing (DSP)- and learning-based algorithms. The challenges presented by FD phased-array and MIMO systems are discussed, followed by system-level aspects, including optimization algorithms, opportunities in the higher layers of the networking protocol stack, and testbed integration. Finally, the relevance of FD systems in applications such as next-generation (xG) wireless, mmWave repeaters, radars, and noncommunication domains is highlighted. Overall, this comprehensive review provides valuable insights into the design, implementation, and applications of FD wireless systems while opening up new directions for future research.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"112 5","pages":"405-432"},"PeriodicalIF":23.2,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141986411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-12DOI: 10.1109/JPROC.2024.3437208
Gianluigi Liva;Yury Polyanskiy
This article is a tutorial introduction to the field of unsourced multiple access (UMAC) protocols. We first provide a historical survey of the evolution of random access protocols, focusing specifically on the case in which uncoordinated users share a wireless broadcasting medium. Next, we highlight the change of perspective originated by the UMAC model, in which the physical and medium access layer’s protocols cooperate, thus reframing random access as a novel coding-theoretic problem. By now, a large variety of UMAC protocols (codes) emerged, necessitating a certain classification that we indeed propose here. Although some random access schemes require a radical change of the physical layer, others can be implemented with minimal changes to existing industry standards. As an example, we discuss a simple modification to the 5G New Radio (5GNR) Release 16 random access channel that builds on the UMAC theory and that dramatically improves energy efficiency for systems with even moderate number of simultaneous users (e.g., 5–10-dB gain for 10–50 users) and also enables handling of high number of users, something completely out of reach of the state of the art.
{"title":"Unsourced Multiple Access: A Coding Paradigm for Massive Random Access","authors":"Gianluigi Liva;Yury Polyanskiy","doi":"10.1109/JPROC.2024.3437208","DOIUrl":"10.1109/JPROC.2024.3437208","url":null,"abstract":"This article is a tutorial introduction to the field of unsourced multiple access (UMAC) protocols. We first provide a historical survey of the evolution of random access protocols, focusing specifically on the case in which uncoordinated users share a wireless broadcasting medium. Next, we highlight the change of perspective originated by the UMAC model, in which the physical and medium access layer’s protocols cooperate, thus reframing random access as a novel coding-theoretic problem. By now, a large variety of UMAC protocols (codes) emerged, necessitating a certain classification that we indeed propose here. Although some random access schemes require a radical change of the physical layer, others can be implemented with minimal changes to existing industry standards. As an example, we discuss a simple modification to the 5G New Radio (5GNR) Release 16 random access channel that builds on the UMAC theory and that dramatically improves energy efficiency for systems with even moderate number of simultaneous users (e.g., 5–10-dB gain for 10–50 users) and also enables handling of high number of users, something completely out of reach of the state of the art.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"112 9","pages":"1214-1229"},"PeriodicalIF":23.2,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141973871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multiple access is the cornerstone technology for each generation of wireless cellular networks, which fundamentally determines the method of radio resource sharing and significantly influences both the system performance and transceiver complexity. Meanwhile, resource allocation (RA) design plays a crucial role in multiple access, as it can manage both encompassing radio resources and interference, and it is critical for providing high-speed and reliable communication services to multiple users. Given that the RA design is intrinsically scenario-specific and the optimization tools for RA design are typically varied, in this article, we present a comprehensive tutorial overview for junior researchers in this field, aiming to offer a foundational guide for RA design in the context of next-generation multiple access (NGMA). Our discussion spans a broad range of fundamental topics: from typical system models, through intriguing problem formulation in RA design, to the exploration of various potential optimization solution methodologies. Initially, we identify three types of channels in future wireless cellular networks over which NGMA will be implemented, namely, natural channels, reconfigurable channels, and functional channels. Natural channels are traditional uplink and downlink communication channels; reconfigurable channels are defined as channels that can be proactively reshaped via emerging platforms or techniques, such as intelligent reflecting surface (IRS), unmanned aerial vehicle (UAV), and movable/fluid antenna (M/FA); and functional channels support not only communication but also other functionalities simultaneously, with typical examples, including integrated sensing and communication (ISAC) and joint computing and communication (JCAC) channels. Then, we introduce NGMA models applicable to these three types of channels that cover most of the practical communication scenarios of future wireless communications. Subsequently, we articulate the key optimization technical challenges inherent in the RA design for NGMA, categorizing them into rate-, power-, and reliability-oriented RA designs. The corresponding optimization approaches for solving the formulated RA design problems are then presented. Finally, the simulation results are presented and discussed to elucidate the practical implications and insights derived from RA designs in NGMA.
{"title":"Resource Allocation Design for Next-Generation Multiple Access: A Tutorial Overview","authors":"Zhiqiang Wei;Dongfang Xu;Shuangyang Li;Shenghui Song;Derrick Wing Kwan Ng;Giuseppe Caire","doi":"10.1109/JPROC.2024.3434700","DOIUrl":"10.1109/JPROC.2024.3434700","url":null,"abstract":"Multiple access is the cornerstone technology for each generation of wireless cellular networks, which fundamentally determines the method of radio resource sharing and significantly influences both the system performance and transceiver complexity. Meanwhile, resource allocation (RA) design plays a crucial role in multiple access, as it can manage both encompassing radio resources and interference, and it is critical for providing high-speed and reliable communication services to multiple users. Given that the RA design is intrinsically scenario-specific and the optimization tools for RA design are typically varied, in this article, we present a comprehensive tutorial overview for junior researchers in this field, aiming to offer a foundational guide for RA design in the context of next-generation multiple access (NGMA). Our discussion spans a broad range of fundamental topics: from typical system models, through intriguing problem formulation in RA design, to the exploration of various potential optimization solution methodologies. Initially, we identify three types of channels in future wireless cellular networks over which NGMA will be implemented, namely, natural channels, reconfigurable channels, and functional channels. Natural channels are traditional uplink and downlink communication channels; reconfigurable channels are defined as channels that can be proactively reshaped via emerging platforms or techniques, such as intelligent reflecting surface (IRS), unmanned aerial vehicle (UAV), and movable/fluid antenna (M/FA); and functional channels support not only communication but also other functionalities simultaneously, with typical examples, including integrated sensing and communication (ISAC) and joint computing and communication (JCAC) channels. Then, we introduce NGMA models applicable to these three types of channels that cover most of the practical communication scenarios of future wireless communications. Subsequently, we articulate the key optimization technical challenges inherent in the RA design for NGMA, categorizing them into rate-, power-, and reliability-oriented RA designs. The corresponding optimization approaches for solving the formulated RA design problems are then presented. Finally, the simulation results are presented and discussed to elucidate the practical implications and insights derived from RA designs in NGMA.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"112 9","pages":"1230-1263"},"PeriodicalIF":23.2,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141910427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-07DOI: 10.1109/JPROC.2024.3435012
Maxime Fontana;Michael Spratling;Miaojing Shi
Multitask learning (MTL) aims to learn multiple tasks simultaneously while exploiting their mutual relationships. By using shared resources to simultaneously calculate multiple outputs, this learning paradigm has the potential to have lower memory requirements and inference times compared to the traditional approach of using separate methods for each task. Previous work in MTL has mainly focused on fully supervised methods, as task relationships (TRs) can not only be leveraged to lower the level of data dependency of those methods but also improve the performance. However, MTL introduces a set of challenges due to a complex optimization scheme and a higher labeling requirement. This article focuses on how MTL could be utilized under different partial supervision settings to address these challenges. First, this article analyses how MTL traditionally uses different parameter sharing techniques to transfer knowledge in between tasks. Second, it presents different challenges arising from such a multiobjective optimization (MOO) scheme. Third, it introduces how task groupings (TGs) can be achieved by analyzing TRs. Fourth, it focuses on how partially supervised methods applied to MTL can tackle the aforementioned challenges. Lastly, this article presents the available datasets, tools, and benchmarking results of such methods. The reviewed articles, categorized following this work, are available at https://github.com/Klodivio355/MTL-CV-Review .
{"title":"When Multitask Learning Meets Partial Supervision: A Computer Vision Review","authors":"Maxime Fontana;Michael Spratling;Miaojing Shi","doi":"10.1109/JPROC.2024.3435012","DOIUrl":"10.1109/JPROC.2024.3435012","url":null,"abstract":"Multitask learning (MTL) aims to learn multiple tasks simultaneously while exploiting their mutual relationships. By using shared resources to simultaneously calculate multiple outputs, this learning paradigm has the potential to have lower memory requirements and inference times compared to the traditional approach of using separate methods for each task. Previous work in MTL has mainly focused on fully supervised methods, as task relationships (TRs) can not only be leveraged to lower the level of data dependency of those methods but also improve the performance. However, MTL introduces a set of challenges due to a complex optimization scheme and a higher labeling requirement. This article focuses on how MTL could be utilized under different partial supervision settings to address these challenges. First, this article analyses how MTL traditionally uses different parameter sharing techniques to transfer knowledge in between tasks. Second, it presents different challenges arising from such a multiobjective optimization (MOO) scheme. Third, it introduces how task groupings (TGs) can be achieved by analyzing TRs. Fourth, it focuses on how partially supervised methods applied to MTL can tackle the aforementioned challenges. Lastly, this article presents the available datasets, tools, and benchmarking results of such methods. The reviewed articles, categorized following this work, are available at \u0000<uri>https://github.com/Klodivio355/MTL-CV-Review</uri>\u0000.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"112 6","pages":"516-543"},"PeriodicalIF":23.2,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141904438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-05DOI: 10.1109/JPROC.2024.3419158
Muhammad Abdelghaffar;Thomas Valerrian Pasca Santhappan;Yeliz Tokgoz;Kiran Mukkavilli;and Tingfang Ji
Time-division duplex (TDD) and frequency-division duplex (FDD) are mainly used in commercial new radio (NR) deployments, where the time- or frequency-domain resources are split between downlink (DL) and uplink (UL). Full duplex (FD) will enable 5G-advanced and 6G systems to go beyond TDD and FDD operation into a new duplexing mode that leverages the benefits of both TDD/FDD deployments. It achieves higher throughput and lower latency while enabling flexible UL/DL scheduling. However, there are several challenges that need to be overcome to enable FD operation in large-scale system deployment, including intranode and internode [user equipment (UE) and next-generation node B (5G base station)] interference along with intercarrier interference. In this article, we present solutions to mitigate self-interference (SI) and cross-link interference (CLI) in 5G-advanced/6G systems, provide system-level evaluations, and discuss the outcome of Third Generation Partnership Project (3GPP) study item on duplexing evolution. We introduce the concept of subband FD (SBFD) as an effective solution for a macro network to achieve the key features of FD, such as latency reduction and UL link budget improvement. Finally, we present the field test results for the performance of world-first SBFD prototype of high transmit power massive-multi-input-multioutput (MIMO) macro network.
{"title":"Subband Full-Duplex Large-Scale Deployed Network Designs and Tradeoffs","authors":"Muhammad Abdelghaffar;Thomas Valerrian Pasca Santhappan;Yeliz Tokgoz;Kiran Mukkavilli;and Tingfang Ji","doi":"10.1109/JPROC.2024.3419158","DOIUrl":"10.1109/JPROC.2024.3419158","url":null,"abstract":"Time-division duplex (TDD) and frequency-division duplex (FDD) are mainly used in commercial new radio (NR) deployments, where the time- or frequency-domain resources are split between downlink (DL) and uplink (UL). Full duplex (FD) will enable 5G-advanced and 6G systems to go beyond TDD and FDD operation into a new duplexing mode that leverages the benefits of both TDD/FDD deployments. It achieves higher throughput and lower latency while enabling flexible UL/DL scheduling. However, there are several challenges that need to be overcome to enable FD operation in large-scale system deployment, including intranode and internode [user equipment (UE) and next-generation node B (5G base station)] interference along with intercarrier interference. In this article, we present solutions to mitigate self-interference (SI) and cross-link interference (CLI) in 5G-advanced/6G systems, provide system-level evaluations, and discuss the outcome of Third Generation Partnership Project (3GPP) study item on duplexing evolution. We introduce the concept of subband FD (SBFD) as an effective solution for a macro network to achieve the key features of FD, such as latency reduction and UL link budget improvement. Finally, we present the field test results for the performance of world-first SBFD prototype of high transmit power massive-multi-input-multioutput (MIMO) macro network.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"112 5","pages":"487-510"},"PeriodicalIF":23.2,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141895552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-22DOI: 10.1109/JPROC.2024.3420127
Lu Lv;Dongyang Xu;Rose Qingyang Hu;Yinghui Ye;Long Yang;Xianfu Lei;Xianbin Wang;Dong In Kim;Arumugam Nallanathan
Driven by the ever-increasing requirements of ultrahigh spectral efficiency, ultralow latency, and massive connectivity, the forefront of wireless research calls for the design of advanced next-generation multiple access schemes to facilitate the provisioning of these stringent demands. This inspires the embrace of nonorthogonal multiple access (NOMA) in future wireless communication networks. Nevertheless, the support of massive access via NOMA leads to additional security threats due to the open nature of the air interface, the broadcast characteristic of radio propagation, and the intertwined relationship among paired NOMA users. To address this specific challenge, the superimposed transmission of NOMA can be explored as new opportunities for security-aware design; for example, multiuser interference inherent in NOMA can be constructively engineered to benefit communication secrecy and privacy. The purpose of this tutorial is to provide a comprehensive overview of the state-of-the-art physical layer security techniques that guarantee wireless security and privacy for NOMA networks, along with the opportunities, technical challenges, and future research trends.
{"title":"Safeguarding Next-Generation Multiple Access Using Physical Layer Security Techniques: A Tutorial","authors":"Lu Lv;Dongyang Xu;Rose Qingyang Hu;Yinghui Ye;Long Yang;Xianfu Lei;Xianbin Wang;Dong In Kim;Arumugam Nallanathan","doi":"10.1109/JPROC.2024.3420127","DOIUrl":"10.1109/JPROC.2024.3420127","url":null,"abstract":"Driven by the ever-increasing requirements of ultrahigh spectral efficiency, ultralow latency, and massive connectivity, the forefront of wireless research calls for the design of advanced next-generation multiple access schemes to facilitate the provisioning of these stringent demands. This inspires the embrace of nonorthogonal multiple access (NOMA) in future wireless communication networks. Nevertheless, the support of massive access via NOMA leads to additional security threats due to the open nature of the air interface, the broadcast characteristic of radio propagation, and the intertwined relationship among paired NOMA users. To address this specific challenge, the superimposed transmission of NOMA can be explored as new opportunities for security-aware design; for example, multiuser interference inherent in NOMA can be constructively engineered to benefit communication secrecy and privacy. The purpose of this tutorial is to provide a comprehensive overview of the state-of-the-art physical layer security techniques that guarantee wireless security and privacy for NOMA networks, along with the opportunities, technical challenges, and future research trends.","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"112 9","pages":"1421-1466"},"PeriodicalIF":23.2,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10605790","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141754996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-01DOI: 10.1109/jproc.2024.3412828
Josep M. Jornet, Vitaly Petrov, Hua Wang, Zoya Popović, Dipankar Shakya, Jose V. Siles, Theodore S. Rappaport
{"title":"The Evolution of Applications, Hardware Design, and Channel Modeling for Terahertz (THz) Band Communications and Sensing: Ready for 6G?","authors":"Josep M. Jornet, Vitaly Petrov, Hua Wang, Zoya Popović, Dipankar Shakya, Jose V. Siles, Theodore S. Rappaport","doi":"10.1109/jproc.2024.3412828","DOIUrl":"https://doi.org/10.1109/jproc.2024.3412828","url":null,"abstract":"","PeriodicalId":20556,"journal":{"name":"Proceedings of the IEEE","volume":"14 1","pages":""},"PeriodicalIF":20.6,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141489333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","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：