Integrated photonics arises as a fast and energy-efficient technology for the implementation of artificial neural networks (ANNs). Indeed, with the growing interest in ANNs, photonics shows great promise to overcome current limitations of electronic-based implementation. For example, it has been shown that neural networks integrating optical matrix multiplications can potentially run two orders of magnitude faster than their electronic counterparts. However, the transposition in the optical domain of the activation functions, which is a key feature of ANNs, remains a challenge. There is no direct optical implementation of state-of-the-art activation functions. Currently, most designs require time-consuming and power-hungry electro-optical conversions. In this survey, we review both all-optical and opto-electronic activation functions proposed in the state-of-the-art. We present activation functions with their key characteristics, and we summarize challenges for their use in the context of all-optical neural networks. We then highlight research directions for the implementation of fully optical neural networks.

The widespread use of sensor devices in IoT networks imposes a significant burden on energy consumption at the network’s edge. To address energy concerns, a prompt anomaly detection strategy is required on demand for troubleshooting resource-constrained IoT devices. It enables devices to adapt their configuration according to the dynamic signal quality and transmission settings. However, obtaining accurate energy data from IoT nodes without external devices is unfeasible. This paper proposes a framework for energy anomaly detection of IoT nodes using data transmission analysis. We use a public dataset that contains peer-to-peer IoT communication energy and link quality data. Our framework first utilizes linear regression to analyze and identify the dominant features of data communication for IoT transceivers. Later, a deep neural network modifies the gradient flow to focus on the dominant features. This modification improves the detection accuracy of anomalies by minimizing the associated reconstruction error. Finally, the energy stabilization feedback provides nodes with insight to change their transmission configuration for future communication. The experimental results show that the proposed approach outperforms other unsupervised models in anomalous energy detection. It also proves that redesigning the conventional loss function by enhancing the impact of our dominant features can dramatically improve the reliability of the anomaly detection method.

The use of unmanned aerial aircrafts (UAVs) is governed by strict regulatory frameworks that prioritize safety. To guarantee safety, it is necessary to acquire and maintain situational awareness (SA) throughout the operation. Existing Canadian regulations require pilots to operate their aircrafts in the visual line-of-sight. Therefore, the task of acquiring and maintaining SA primary falls to the pilots. However, the development of aerial transport is entering a new era with the adoption of a highly dynamic and complex system known as advanced air mobility (AAM), which involves UAVs operating autonomously beyond the visual line-of-sight. SA must therefore be acquired and maintained primarily by each UAV through specific technologies and procedures. In this paper, we review these technologies and procedures in order to decompose the SA of the UAV in the AAM. We then use the system modeling language to provide a high-level structural and behavioral representation of the AAM as a system having UAV as its main entity. In a case study, we analyze one of the flagship UAVs of our industrial partner. Results show that this UAV does not have all of the technologies and methodologies necessary to achieve all of the identified SA goals for the safety of the AAM. This work is a theoretical framework intended to contribute to the realization of the AAM, and we also expect to impact the future design and utilization of UAVs.