Edge signal processing facilitates distributed learning and inference in the client-server model proposed in federated learning. In traditional machine learning, clients (IoT devices) that acquire raw signal samples can aid a data center (server) learn a global signal model by pooling these distributed samples at a third-party location. Despite the promising capabilities of IoTs, these distributed deployments often face the challenge of sensitive private data and communication rate constraints. This necessitates a learning approach that communicates a processed approximation of the distributed samples instead of the raw signals. Such a decentralized learning approach using signal approximations will be termed distributed signal analytics in this work. Overpredictive signal approximations may be desired for distributed signal analytics, especially in network demand (capacity) planning applications motivated by federated learning. In this work, we propose algorithms that compute an overpredictive signal approximation at the client devices using an efficient convex optimization framework. Tradeoffs between communication cost, sampling rate, and the signal approximation error are quantified using mathematical analysis. We also show the performance of the proposed distributed algorithms on a publicly available residential energy consumption dataset.

Without the right tools or materials, a builder can't properly construct a house, and without the right data and market insights, a company cannot make the best decisions. Consumers' rapidly shifting needs are pushing companies across all sectors to need to pivot their strategies constantly in order to stay relevant and drive revenues - and the best way to do this is through data and analytics. Businesses now know that they must expect and be prepared to navigate the unexpected. With this in mind, there are 10 major trends that will flourish in the advanced analytics market in 2021. It will not just be about collecting data, but rather about taking that data and putting it into action.

Trends change faster than ever and within minutes or hours, something can go viral. This is especially true for the food and consumer goods industries, where social media popularity can realistically translate into higher sales or controversy, as seen late last year with Popeyes Chicken Sandwich and a Peloton bike advertisement. Signals Analytics, an AI-powered platform, helps companies in the food and pharmaceutical industries identify trends and capitalize on troves of previously untapped data streams. Frances Zelazny, Signals Analytics chief marketing officer and head of strategy spoke to TechRepublic about the food trends in 2020 and what people may be eating in six months based on their research. "We are focused on external data, so you should think about social media posts, product reviews, commentary on news websites, patent filings, research papers, conference agendas and other data sources. Think about what it would be like if you could have access to all that data and could use that data in order to make decisions. Most companies use two or three external data sources," Zelazny said.