SPM Article

Many problems in signal processing [e.g., filter bank design, independent component analysis (ICA), beamforming design, and neural network training] can be formulated as optimization over groups of transformations that depend continuously on real parameters (Lie groups). Such problems are usually tackled in two ways: using a constrained optimization procedure or using some parameterization to transform them into unconstrained problems.

The old adage "you are what you wear" is taking on an entirely new meaning as smart watches, fitness trackers, and a rapidly expanding array of other wearable devices flood onto the market, enabling users to monitor their exercise progress, retrieve critical health data, and accomplish a wide range of other useful and informative tasks.

Deep neural networks provide unprecedented performance gains in many real-world problems in signal and image processing. Despite these gains, the future development and practical deployment of deep networks are hindered by their black-box nature, i.e., a lack of interpretability and the need for very large training sets. 

A little over a century and a half ago, Victor Hugo wrote “Il n’y a ni mauvaises herbes ni mauvais hommes. Il n’y a que de mauvais cultivateurs,” which translates to “there are no weeds and no bad men. There are only bad cultivators.” These two sentences provide a stark reminder of the heavy responsibility we all bear, as parents, educators, mentors, members of professional societies, and citizens of states, nations, and earth. Indeed, arguably our main goal as a professional society is to help develop our human capital. Everything else flows from there.

Enabling autonomous driving (AD) can be considered one of the biggest challenges in today?s technology. AD is a complex task accomplished by several functionalities, with environment perception being one of its core functions. Environment perception is usually performed by combining the semantic information captured by several sensors, i.e., lidar or camera. The semantic information from the respective sensor can be extracted by using convolutional neural networks (CNNs) for dense prediction. In the past, CNNs constantly showed stateof-the-art performance on several vision-related tasks, such as semantic segmentation of traffic scenes using nothing but the red-green-blue (RGB) images provided by a camera. 

First, I would like to wish you a happy New Year and, especially, health for you and your families. I am very honored to be the new editor-in-chief (EIC) of IEEE Signal Processing Magazine (SPM) for the next three years. It is a great challenge for me, as it was probably for its previous EICs since SPM is not an ordinary magazine.

Three years have gone by quickly. I started as the editor-in-chief (EIC) of IEEE Signal Processing Magazine (SPM) in January 2018. It coincided with other changes in my personal life that made the transition steeper than I had expected. Looking back, it is how I imagine the New Year’s polar bear plunge might be. Of course, three years of service is a tad bit longer than a few minutes of swimming in ridiculously cold water. 

The study of sampling signals on graphs, with the goal of building an analog of sampling for standard signals in the time and spatial domains, has attracted considerable attention recently. Beyond adding to the growing theory on graph signal processing (GSP), sampling on graphs has various promising applications. In this article, we review the current progress on sampling over graphs, focusing on theory and potential applications.

A major line of work in graph signal processing [2] during the past 10 years has been to design new transform methods that account for the underlying graph structure to identify and exploit structure in data residing on a connected, weighted, undirected graph. The most common approach is to construct a dictionary of atoms (building block signals) and represent the graph signal of interest as a linear combination of these atoms. Such representations enable visual analysis of data, statistical analysis of data, and data compression, and they can also be leveraged as regularizers in machine learning and ill-posed inverse problems, such as inpainting, denoising, and classification.

The notion of graph filters can be used to define generative models for graph data. In fact, the data obtained from many examples of network dynamics may be viewed as the output of a graph filter. With this interpretation, classical signal processing tools, such as frequency analysis, have been successfully applied with analogous interpretation to graph data, generating new insights for data science. What follows is a user guide on a specific class of graph data, where the generating graph filters are low pass; i.e., the filter attenuates contents in the higher graph frequencies while retaining contents in the lower frequencies. Our choice is motivated by the prevalence of low-pass models in application domains such as social networks, financial markets, and power systems.