IEEE Signal Processing Magazine

The Markov random field (MRF) is one of the most widely used models in image processing, constituting a prior model for addressing problems such as image segmentation, object detection, and reconstruction. What is not often appreciated is that the MRF owes its origin to the physics of solids, making it an ideal prior model for processing microscopic observations of materials. While both fields know of their respective interpretations of the MRF, each knows very little about the other’s version of it. Hence, both fields have “blind spots,” where some concepts readily appreciated by one field are completely obscured from the other. 

In an age when signal processing lies at the core of so many different technologies, nothing is more important than its contribution to health care. From improved cardiac patient support to enhanced magnetic resonance imaging (MRI) and advanced diagnostics, signal processing is helping physicians work more safely, efficiently, and accurately. Here is a look at three important research projects that are using signal processing to assist both patients and health-care providers.

With the year coming to a close, I couldn’t help but reflect on our experiences in 2020 and 2021. I began my term as president of the IEEE Signal Processing Society (SPS) roughly 65 days before we were told to work from home due to the COVID-19 pandemic. As I write this column 18 months later, I find myself, like many of you, still largely working remotely.

Given the increasing prevalence of facial analysis technology, the problem of bias in the tools is now becoming an even greater source of concern. Several studies have highlighted the pervasiveness of such discrimination, and many have sought to address the problem by proposing solutions to mitigate it. Despite this effort, to date, understanding, investigating, and mitigating bias for facial affect analysis remain an understudied problem.

Researchers in an almost endless number of fields are embracing artificial intelligence (AI) and machine learning (ML) to develop tools and systems that can predict and adapt to a wide range of changing situations, optimize system performance, and intelligently filter signals. In areas as diverse as firefighter protection, solar power optimization, and exoplanet discovery, researchers are turning to AI, ML, and signal processing to help them achieve breakthroughs that were unimaginable only a few years ago.

Recent advances in the field of machine learning have shown great potential for the automatic recognition of apparent human emotions. In the era of Internet of Things and big-data processing, where voice-based systems are well established, opportunities to leverage cutting-edge technologies to develop personalized and human-centered services are genuinely real, with a growing demand in many areas such as education, health, well-being, and entertainment. 

Affective computing is computing that relates to, arises from, or deliberately influences emotion or other affective phenomena. Human emotion and affect in general are fundamental to human experience, influencing cognition, perception, and everyday tasks such as learning and communication, but are also fundamental to human health and well-being. 

Imagine standing on a street corner in the city. With your eyes closed you can hear and recognize a succession of sounds: cars passing by, people speaking, their footsteps when they walk by, and the continuous falling of rain. The recognition of all these sounds and interpretation of the perceived scene as a city street soundscape comes naturally to humans. It is, however, the result of years of "training": 

Formulas for estimating and tracking the (time-dependent) frequency, form factor, and amplitude of harmonic time series are presented in this lecture note; in particular, sine-dominant signals, where the harmonics follow roughly the dominant first harmonic, such as photoplethysmography (PPG) and breathing signals. Special attention is paid to the convergence behavior of the algorithm for stationary signals and the dynamic behavior in case of a transition to another stationary state. The latter issue is considered to be important for assessing the tracking abilities for nonstationary signals.

Big data can be a blessing: with very large training data sets it becomes possible to perform complex learning tasks with unprecedented accuracy. Yet, this improved performance comes at the price of enormous computational challenges. Thus, one may wonder: Is it possible to leverage the information content of huge data sets while keeping computational resources under control?