Search for: All records

Quantum federated learning (QFL) can facilitate collaborative learning across multiple clients using quantum machine learning (QML) models, while preserving data privacy. Although recent advances in QFL span different tasks like classification while leveraging several data types, no prior work has focused on developing a QFL framework that utilizes temporal data to approximate functions useful to analyze the performance of distributed quantum sensing networks. In this paper, a novel QFL framework that is the first to integrate quantum long short-term memory (QLSTM) models with temporal data is proposed. The proposedfederated QLSTM (FedQLSTM)framework is exploited for performing the task of function approximation. In this regard, three key use cases are presented: Bessel function approximation, sinusoidal delayed quantum feedback control function approximation, and Struve function approximation. Simulation results confirm that, for all considered use cases, the proposed FedQLSTM framework achieves a faster convergence rate under one local training epoch, minimizing the overall computations, and saving 25–33% of the number of communication rounds needed until convergence compared to an FL framework with classical LSTM models.

 

Modern cellular networks are multi-cell and use universal frequency reuse to maximize spectral efficiency. This results in high inter-cell interference. This challenge is growing as cellular networks become three-dimensional with the adoption of unmanned aerial vehicles (UAVs). This is because the strength and number of interference links rapidly increase due to the line-of-sight channels in UAV communications. Existing interference management solutions require each transmitter to know the channel information of interfering signals, rendering them impractical due to excessive signaling overhead. In this article, we propose leveraging deep reinforcement learning for interference management to tackle this shortcoming. In particular, we show that interference can still be effectively mitigated even without knowing its channel information. We then discuss novel approaches to scale the algorithms with linear/sublinear complexity and decentralize them using multi-agent reinforcement learning. By harnessing interference, the proposed solutions enable the continued growth of civilian UAVs. 

The construction industry has been a predominantly White/Caucasian Men community with a very low representation of women and people from traditionally marginalized backgrounds. Even though companies have been implementing Diversity, Equity, and Inclusion (DEI) statements for many years, we still believe it is neither a diverse nor equitable field. To better understand how DEI statements declared by companies have been understood and recognized by employees, a survey was deployed nationwide to understand how professionals in the construction industry perceive their organization's DEI statements or policies. A complete data set was built from 249 participants. 75% identified themselves as men and 25% as women, and nobody identified with other gender identities. More than 80% of participants were White/Caucasian, 4% Black or African American, 4% Hispanic or Latinx, and 6% Asian. Participants are currently working in small (24%), medium (30%), and large (46%) construction and design companies located across The United States. Regarding the number of employees, companies are small, less than 99 employees; medium, between 100 and 499 employees; and large, more than 500 employees. Also, companies were grouped into four main types, building construction companies (67%), transportation construction companies (6%), special trade contractor companies (17%), and design companies (10%). For more than 65% of professionals in the construction industry who participated in this study, DEI was mainly related to proper representation of women and minoritized populations in the workforce; Merit-based transparent recruitment and promotion; equality, social justice, and nondiscrimination policy statement; and equitable payment and compensation. Other factors such as proper representation of women and minoritized populations at the top management level and payment structure transparency did not emerge from the results. We also found that 70% of professionals identified DEI statements in their companies and 30% of professionals did not identify or did not know about DEI statements. Looking at the company size, 85% of professionals in large companies identified DEI statements in their companies, but 71% and 42% of professionals in medium and small companies identified DEI statements in their companies, respectively. According to the company type, more than 80% of professionals working in design companies recognized DEI statements in their companies, but around 60% in construction and special trade companies. We can highlight that large companies have established policies and practices that result in better socialization and recognition of their DEI statements than medium and small companies. Also, construction and special trade companies need to strengthen their DEI statements and increase the representation of women and people from traditionally marginalized backgrounds. Results from this research give an idea about the current state of DEI in the construction industry and would contribute to the current effort to increase the diversity of the nation's construction workforce.