Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.
提供社会信息，可能包括新闻，评论或技术笔记，从业者和研究人员应该感兴趣。
{"title":"Efficient Approximation of the Arctangent Function for Computing Platforms With Limited Hardware Resources [Tips & Tricks]","authors":"Ewa Deelman;Pawel Gepner;Leonid Moroz;Pawel Poczekajło;Jerzy Krawiec;Martyna Wybraniak-Kujawa","doi":"10.1109/MSP.2025.3636383","DOIUrl":"https://doi.org/10.1109/MSP.2025.3636383","url":null,"abstract":"Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"42 6","pages":"110-120"},"PeriodicalIF":9.6,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11364199","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146045301","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 : 2026-01-26DOI: 10.1109/MSP.2025.3590807
Tosin Adewumi;Foteini Simistira Liwicki;Marcus Liwicki;Viktor Gardelli;Lama Alkhaled;Hamam Mokayed
This article presents an intervention study on the effects of the combined methods of 1) the Socratic method, 2) chain-of-thought (CoT) reasoning, 3) simplified gamification, and 4) formative feedback on university students’ math learning driven by large language models (LLMs). We call our approach Mathematics Explanations through Games by AI LLMs (MEGA). Some students struggle with math, and as a result, avoid math-related disciplines or subjects despite the importance of math across many fields, including signal processing. Oftentimes, students’ math difficulties stem from suboptimal pedagogy. We compared the MEGA method to the traditional step-by-step (CoT) method to ascertain which is better by using a within-group design after randomly assigning questions for the participants, who are university students. Samples ${(}{n}{=}{60}{)}$ were randomly drawn from each of the two test sets of the Grade School Math 8 K (GSM8K) and Mathematics Aptitude Test of Heuristics (MATH) datasets, based on an error margin of 11%, a confidence level of 90%, and a manageable number of samples for the student evaluators. These samples were used to evaluate two capable LLMs at length [Generative Pretrained Transformer 4o (GPT4o) and Claude 3.5 Sonnet] out of the initial six that were tested for capability. The results showed that students agree in more instances that the MEGA method is experienced as better for learning for both datasets. It is even much better than the CoT (47.5% compared to 26.67%) in the more difficult MATH dataset, indicating that MEGA is better at explaining difficult math problems. We also calculated the accuracies of the two LLMs and showed that model accuracies differ for the methods. MEGA appears to expose the hallucination challenge that still exists with these LLMs better than CoT. We provide public access to the MEGA app, the preset instructions that we created, and the annotations by the students for transparency.
{"title":"Findings of Mega: Math explanation with LLMs using the socratic method for active learning","authors":"Tosin Adewumi;Foteini Simistira Liwicki;Marcus Liwicki;Viktor Gardelli;Lama Alkhaled;Hamam Mokayed","doi":"10.1109/MSP.2025.3590807","DOIUrl":"https://doi.org/10.1109/MSP.2025.3590807","url":null,"abstract":"This article presents an intervention study on the effects of the combined methods of 1) the Socratic method, 2) chain-of-thought (CoT) reasoning, 3) simplified gamification, and 4) formative feedback on university students’ math learning driven by large language models (LLMs). We call our approach Mathematics Explanations through Games by AI LLMs (MEGA). Some students struggle with math, and as a result, avoid math-related disciplines or subjects despite the importance of math across many fields, including signal processing. Oftentimes, students’ math difficulties stem from suboptimal pedagogy. We compared the MEGA method to the traditional step-by-step (CoT) method to ascertain which is better by using a within-group design after randomly assigning questions for the participants, who are university students. Samples <inline-formula><tex-math>${(}{n}{=}{60}{)}$</tex-math></inline-formula> were randomly drawn from each of the two test sets of the Grade School Math 8 K (GSM8K) and Mathematics Aptitude Test of Heuristics (MATH) datasets, based on an error margin of 11%, a confidence level of 90%, and a manageable number of samples for the student evaluators. These samples were used to evaluate two capable LLMs at length [Generative Pretrained Transformer 4o (GPT4o) and Claude 3.5 Sonnet] out of the initial six that were tested for capability. The results showed that students agree in more instances that the MEGA method is experienced as better for learning for both datasets. It is even much better than the CoT (47.5% compared to 26.67%) in the more difficult MATH dataset, indicating that MEGA is better at explaining difficult math problems. We also calculated the accuracies of the two LLMs and showed that model accuracies differ for the methods. MEGA appears to expose the hallucination challenge that still exists with these LLMs better than CoT. We provide public access to the MEGA app, the preset instructions that we created, and the annotations by the students for transparency.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"42 6","pages":"77-94"},"PeriodicalIF":9.6,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146045331","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 : 2026-01-26DOI: 10.1109/MSP.2025.3633004
Danilo Mandic;Mónica Bugallo;Christina Jayne;Irwin King
{"title":"Artificial Intelligience for Education: A Signal Processing Perspective: Part I: From Active Learning to Mitigating Gender Bias [From The Guest Editors]","authors":"Danilo Mandic;Mónica Bugallo;Christina Jayne;Irwin King","doi":"10.1109/MSP.2025.3633004","DOIUrl":"https://doi.org/10.1109/MSP.2025.3633004","url":null,"abstract":"","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"42 6","pages":"35-38"},"PeriodicalIF":9.6,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11364181","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146045312","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}
Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.
提供社会信息，可能包括新闻，评论或技术笔记，从业者和研究人员应该感兴趣。
{"title":"The IEEE Signal Processing Society (SPS) Announces the 2026 Class of Distinguished Lecturers and Distinguished Industry Speakers [Contributors]","authors":"Ghassan AlRegib;Jingdong Chen;Pin-Yu Chen;Alessandro Foi;Jianquan Liu;Scott McCloskey;Anderson Rocha;Beibei Wang;Dong Yu;Junsong Yuan","doi":"10.1109/MSP.2025.3650064","DOIUrl":"https://doi.org/10.1109/MSP.2025.3650064","url":null,"abstract":"Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"42 6","pages":"8-12"},"PeriodicalIF":9.6,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11364187","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146045297","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}
Artificial intelligence (AI) holds transformative potential in education, enabling personalized learning, enhancing inclusivity, and encouraging creativity and curiosity. In this article, we explore how large language models (LLMs) can act as both patient tutors and collaborative partners to enhance education delivery. As tutors, LLMs personalize learning by offering step-by-step explanations and addressing individual needs, making education more inclusive for students with diverse backgrounds or abilities. As collaborators, they expand students’ horizons, supporting them in tackling complex, real-world problems and cocreating innovative projects. However, to fully realize these benefits, LLMs must be leveraged not as tools for providing direct solutions but rather to guide students in developing resolving strategies and finding learning paths together. Therefore, a strong emphasis should be placed on educating students and teachers on the successful use of LLMs to ensure their effective integration into classrooms. Through practical examples and real-world case studies, this article illustrates how LLMs can make education more inclusive and engaging while empowering students to reach their full potential.
{"title":"Beyond Answers: How large language models can pursue strategic thinking in education","authors":"Eleonora Grassucci;Gualtiero Grassucci;Aurelio Uncini;Danilo Comminiello","doi":"10.1109/MSP.2025.3589180","DOIUrl":"https://doi.org/10.1109/MSP.2025.3589180","url":null,"abstract":"Artificial intelligence (AI) holds transformative potential in education, enabling personalized learning, enhancing inclusivity, and encouraging creativity and curiosity. In this article, we explore how large language models (LLMs) can act as both <italic>patient tutors</i> and <italic>collaborative partners</i> to enhance education delivery. As tutors, LLMs personalize learning by offering step-by-step explanations and addressing individual needs, making education more inclusive for students with diverse backgrounds or abilities. As collaborators, they expand students’ horizons, supporting them in tackling complex, real-world problems and cocreating innovative projects. However, to fully realize these benefits, LLMs must be leveraged not as tools for providing direct solutions but rather to guide students in developing resolving strategies and finding learning paths together. Therefore, a strong emphasis should be placed on educating students and teachers on the successful use of LLMs to ensure their effective integration into classrooms. Through practical examples and real-world case studies, this article illustrates how LLMs can make education more inclusive and engaging while empowering students to reach their full potential.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"42 6","pages":"64-76"},"PeriodicalIF":9.6,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146045336","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 : 2026-01-26DOI: 10.1109/MSP.2026.3652655
Tülay Adali
{"title":"Embracing Challenges: Teaching in the Age of AI [From The Editor]","authors":"Tülay Adali","doi":"10.1109/MSP.2026.3652655","DOIUrl":"https://doi.org/10.1109/MSP.2026.3652655","url":null,"abstract":"","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"42 6","pages":"3-3"},"PeriodicalIF":9.6,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11364196","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146045328","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 : 2025-12-22DOI: 10.1109/MSP.2025.3611565
Carlo Chiurco;Andrea Favaro;Silvia Francesca Storti;Lorenza Brusini;Ahmed M. Salih;Ilaria Boscolo Galazzo;Sergey Plis;Gloria Menegaz
The dual concepts of neurotechnology and artificial intelligence (AI) form an intriguing but also potentially explosive mixture because of its many ethical and legal implications. The advent of AI and the progress in neurotechnologies are reshaping the landscape not only in all scientific fields but also in everyday life both individually and collectively, ushering in a new era where the centrality, integrity and identity of humans is no longer a fact. Such tumultuous progress has implications at all levels, individual, societal, economical and political. Without the pretension of exploring the whole set of relevant aspects, we aim at providing a multi-disciplinary view on the main ethical, legal and societal issues stemming from neurotechnology and AI, by assessing them using keywords like trustworthiness, fairness, awareness, security, and privacy. In this paper, we propose an overview on the current scenario, taking a philosophical perspective in the light of ethics, and boiling it down to aspects closely related to the technological developments and the regulatory measures that are currently in-place and called for.
{"title":"The Marriage of Neurotechnologies and Artificial Intelligence: Ethical, regulatory, and technological aspects","authors":"Carlo Chiurco;Andrea Favaro;Silvia Francesca Storti;Lorenza Brusini;Ahmed M. Salih;Ilaria Boscolo Galazzo;Sergey Plis;Gloria Menegaz","doi":"10.1109/MSP.2025.3611565","DOIUrl":"10.1109/MSP.2025.3611565","url":null,"abstract":"The dual concepts of neurotechnology and artificial intelligence (AI) form an intriguing but also potentially explosive mixture because of its many ethical and legal implications. The advent of AI and the progress in neurotechnologies are reshaping the landscape not only in all scientific fields but also in everyday life both individually and collectively, ushering in a new era where the centrality, integrity and identity of humans is no longer a fact. Such tumultuous progress has implications at all levels, individual, societal, economical and political. Without the pretension of exploring the whole set of relevant aspects, we aim at providing a multi-disciplinary view on the main ethical, legal and societal issues stemming from neurotechnology and AI, by assessing them using keywords like trustworthiness, fairness, awareness, security, and privacy. In this paper, we propose an overview on the current scenario, taking a philosophical perspective in the light of ethics, and boiling it down to aspects closely related to the technological developments and the regulatory measures that are currently in-place and called for.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"42 5","pages":"80-97"},"PeriodicalIF":9.6,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145807460","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 : 2025-12-22DOI: 10.1109/MSP.2025.3595320
Zhe Sage Chen;Bao-Liang Lu;Wei Wu
Since the first groundbreaking human electroencephalography (EEG) recordings in 1924 [1], the past century has witnessed a tremendous growth of EEG applications in cognitive neuroscience, clinical, and engineering applications due to EEG’s low operational cost and mobility [2]. On the one hand, advances in high-density noninvasive scalp EEG or invasive intracranial EEG (iEEG) have offered both excellent temporal resolution and increasingly improved spatial resolution to study brain functions and their link to emotions, memory, learning, and diseases. EEG-based brain–computer interfaces (BCIs) can offer new dimensions for entertainment, virtual reality, neurofeedback, and closed-loop therapy. On the other hand, recent advances in artificial intelligence (AI) and machine learning have opened new opportunities for analyses of EEG and other neural data [3]. This article aims at presenting an overview of the cutting-edge machine learning techniques for EEG analyses. By leveraging large-scale EEG data with state-of-the-art representation learning and transfer learning (TL) paradigms, we are empowered to discover latent EEG features that are proved useful for clinical care and BCIs. We discuss some general principles of representation learning and show walk-through practical examples of EEG analysis. The article also aims at highlighting the effort of applying AI models to discover neuroscience insights and linking them to the fundamentals of EEG signal analyses from a signal processing perspective. While our focus is on EEG and iEEG signals, most of the approaches discussed here are generally applicable to other brain signal modalities.
{"title":"Representation Learning and Foundation Models for Electroencephalography Analyses: Current trends, fundamental insights, and future directions","authors":"Zhe Sage Chen;Bao-Liang Lu;Wei Wu","doi":"10.1109/MSP.2025.3595320","DOIUrl":"10.1109/MSP.2025.3595320","url":null,"abstract":"Since the first groundbreaking human electroencephalography (EEG) recordings in 1924 <xref>[1]</xref>, the past century has witnessed a tremendous growth of EEG applications in cognitive neuroscience, clinical, and engineering applications due to EEG’s low operational cost and mobility <xref>[2]</xref>. On the one hand, advances in high-density noninvasive scalp EEG or invasive intracranial EEG (iEEG) have offered both excellent temporal resolution and increasingly improved spatial resolution to study brain functions and their link to emotions, memory, learning, and diseases. EEG-based brain–computer interfaces (BCIs) can offer new dimensions for entertainment, virtual reality, neurofeedback, and closed-loop therapy. On the other hand, recent advances in artificial intelligence (AI) and machine learning have opened new opportunities for analyses of EEG and other neural data <xref>[3]</xref>. This article aims at presenting an overview of the cutting-edge machine learning techniques for EEG analyses. By leveraging large-scale EEG data with state-of-the-art representation learning and transfer learning (TL) paradigms, we are empowered to discover latent EEG features that are proved useful for clinical care and BCIs. We discuss some general principles of representation learning and show walk-through practical examples of EEG analysis. The article also aims at highlighting the effort of applying AI models to discover neuroscience insights and linking them to the fundamentals of EEG signal analyses from a signal processing perspective. While our focus is on EEG and iEEG signals, most of the approaches discussed here are generally applicable to other brain signal modalities.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"42 5","pages":"36-57"},"PeriodicalIF":9.6,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145807461","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 : 2025-12-22DOI: 10.1109/MSP.2025.3632789
Xiaoya Liu;Shuang Liu;Dong Ming
Affective brain–computer interfaces (aBCIs) are an emerging technology that decodes brain signals—primarily electroencephalography (EEG)—to monitor and regulate emotional states in real time. By detecting and responding to users’ emotional processes, aBCIs hold significant promise for transformative applications in health care, adaptive education, and immersive entertainment. This tutorial introduces the foundational concepts of aBCIs, outlines their key methodologies, and highlights recent advances, as well as ongoing challenges. Our objective is to provide researchers, engineers, and practitioners with a structured roadmap for developing robust, generalizable, and user-adaptive aBCI systems.
{"title":"Affective Brain–Computer Interfaces: A Tutorial","authors":"Xiaoya Liu;Shuang Liu;Dong Ming","doi":"10.1109/MSP.2025.3632789","DOIUrl":"10.1109/MSP.2025.3632789","url":null,"abstract":"Affective brain–computer interfaces (aBCIs) are an emerging technology that decodes brain signals—primarily electroencephalography (EEG)—to monitor and regulate emotional states in real time. By detecting and responding to users’ emotional processes, aBCIs hold significant promise for transformative applications in health care, adaptive education, and immersive entertainment. This tutorial introduces the foundational concepts of aBCIs, outlines their key methodologies, and highlights recent advances, as well as ongoing challenges. Our objective is to provide researchers, engineers, and practitioners with a structured roadmap for developing robust, generalizable, and user-adaptive aBCI systems.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"42 5","pages":"58-70"},"PeriodicalIF":9.6,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145807459","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：