SPM Article

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? 

Smart home technologies, designed to make users happier, healthier, and wealthier, are rapidly becoming a mainstay of everyday life. In most cases, signal processing is essential to the devices' operation and performance. These days, a variety of intelligent automated devices can be found in nearly every home. The trend is accelerating so rapidly that it now appears inevitable that smart technology will soon be integrated into virtually every facet of daily life.

It’s been a while since I last wrote a column for IEEE Signal Processing Magazine. I will try to address here some of the many questions and changes that arose since the beginning of the year. But before I do so, I would like to invite you to watch a short documentary by Ben Proudfoot with the exact title of this column: “She Changed Astronomy Forever. He Won the Nobel Prize for It.”

This issue of IEEE Signal Processing Magazine is mainly focused on neurorehabilitation and assistive technologies. For a few decades, microelectronics, signal processing, robotics, and computer science have been the driver of many scientific and technological advances, with applications in many domains, including health.