The large population of wireless users is a key driver of data-crowdsourced Machine Learning (ML). However, data privacy remains a significant concern. Federated Learning (FL) encourages data sharing in ML without requiring data to leave users' devices but imposes heavy computation and communications overheads on mobile devices. Hierarchical FL (HFL) alleviates this problem by performing partial model aggregation at edge servers. HFL can effectively reduce energy consumption and latency through effective resource allocation and appropriate user assignment. Nevertheless, resource allocation in HFL involves optimizing multiple variables, and the objective function should consider both energy consumption and latency, making the development of resource allocation algorithms very complicated. Moreover, it is challenging to perform user assignment, which is a combinatorial optimization problem in a large search space. This article proposes a spectrum resource optimization algorithm (SROA) and a two-stage iterative algorithm (TSIA) for HFL. Given an arbitrary user assignment pattern, SROA optimizes CPU frequency, transmit power, and bandwidth to minimize system cost. TSIA aims to find a user assignment pattern that considerably reduces the total system cost. Experimental results demonstrate the superiority of the proposed HFL framework over existing studies in energy and latency reduction.

"Improving Service Delivery Performance with Machine Learning and Artificial Intelligence," presented by TSIA. Learn how to enable smart, connected products, build the data model, and operationalize data analytics. Hear a panel of experienced service executives talk about how their companies leverage data collected from their install base to create business value for customers. "How Intelligent Algorithms and Spare Parts Combine to Deliver Outcome-Based Offers," co-presented by Becton Dickinson & Company and TSIA. With 60-70% of service incidents involving spare parts and the need for an on-site visit from an engineer/technician, the use of intelligent algorithms for install base demographics, failure rates, and stocking locations have enabled Becton Dickinson & Company to improve their operations.

Artificial intelligence (machines doing things instead of humans) and augmented intelligence (machines helping humans do what they need to do better) are vogue concepts but what's the relevance to professional services organizations? In this free webinar, we will discuss how machine intelligence can be applied to help drive performance in consulting. John Ragsdale, VP Research, Technology and Social for TSIA will explain where TSIA members see the most opportunity and Kimble will talk about how Kimble customers are using intelligence and gamification to drive behaviors that speed up and improve the impact of positive decision making in selling, resourcing, delivery and operational management.