Our journal welcomes not only original high-quality papers covering the theoretical, experimental and operational aspects of electrical and electronics engineering in mobile radio, motor vehicles and land transportation, but also industry-focused publication focusing on research findings and suggesting ideas that may be useful to those conducting similar research.

Our first monthly feature paper, co-authored by researchers from The Ohio State University and University of Michigan, Ann Arbor, creatively leverages the wireless medium to enhance privacy by developing a decentralized dynamic power control strategy tailored for differentially private over-the-air federal learning.

The second feature article, coauthored by industry practitioners Valeo Vision Systems and researchers from University of Galway, presents the first comprehensive review of hyperspectral imaging (HSI) for automotive applications, examining the strengths, limitations, and suitability of current HSI technologies in the context of Advanced Driver Assistance Systems (ADAS) and autonomous driving (AD).

We’ve provided short summaries of these feature articles, written in accessible language that we hope will make your reading experience enjoyable.

Providing Differential Privacy for Federated Learning Over Wireless: A Cross-Layer Framework
Jiayu Mao, Tongxin Yin, Aylin Yener, and Mingyan Liu

Summary by Jiayu Mao: Federated learning allows devices such as smartphones and connected vehicles to train a shared machine learning model without sending their raw data to a central server. However, the model updates exchanged during training can still reveal sensitive information.

Our paper turns the wireless communication process itself into part of the privacy solution. We develop an adaptive power control method that uses the noise naturally present in wireless channels to protect each device’s data. When this natural noise is insufficient, a helper transmitter, called a cooperative jammer, provides only the additional noise needed to meet the desired privacy level. Unlike conventional approaches that require resource-constrained devices to generate privacy-preserving noise themselves, our design shifts this burden to the helper and activates it only when necessary. The method can be integrated with several widely used federated learning frameworks.

Experiments on a real-world dataset show that it achieves higher learning accuracy than existing approaches under the same privacy requirements, remains effective with imperfect channel information, and reveals the practical trade-off among privacy, accuracy, and energy consumption.

Hyperspectral Sensors and Autonomous Driving: Technologies, Limitations, and Opportunities
Imad Ali Shah, Jiarong Li, Roshan George, Tim Brophy, Enda Ward, Martin Glavin, Edward Jones, and Brian Deegan

Summary by Imad Ali Shah: While traditional RGB cameras often struggle to distinguish between visually similar objects and hazards such as black ice and wet asphalt, hyperspectral imaging (HSI) offers a solution to this perceptual bottleneck. By capturing tens to hundreds of light spectral bands, HSI can identify the exact material "fingerprint" of an object, which can enable vehicles to see critical scene details that typical RGB cameras miss in complex or adverse weather conditions.

This article presents the first feasibility study that consolidates the scope of HSI for autonomous driving, offering a comprehensive view of how this modality can support next-generation autonomous systems rather than treating individual sensors or use cases in isolation. Going beyond high-level theory, the study delivers a reality check for bringing HSI technology out of the lab and onto the road: the research systematically benchmarked 216 commercially available cameras against vehicular requirements, revealing a huge gap between theoretical research potential and commercial readiness. Most notably, not a single reviewed camera meets even the baseline AEC-Q100 automotive operating temperature qualification. This combination of domain and technology review makes the work a foundational guide for developing the next generation of safe, all-weather autonomous sensors.

IEEE VTS Website