By Andreas Pellkofer and Madhura Deyanda Poonacha, Analog Devices Automakers aim to provide vehicles with home-like comfort and entertainment, which raises demand for electronic control units (ECUs). Older bus technologies and electrical/electronic architectures struggle to keep up. 10Base-T1S Ethernet is transforming cars into fully connected experiences. Automotive electronic control units (ECUs), which control each component […]
FAQ
How software segregation minimizes the impact of AI/ML on safety-critical software
With the growing use of artificial intelligence and machine learning in safety-critical software, developers are considering software segregation and guardian applications to mitigate functional safety risks. By Mark Pitchford, LDRA The push toward artificial intelligence (AI) and machine learning (ML) in embedded systems raises questions about adapting functional safety processes and tools to achieve compliance. […]
What is the automotive SENT protocol?
Get the basics on the SENT bus, which transmits sensor data to ECUs and other vehicle processors, one nibble at a time. How do you test the automotive SENT protocol? Test & Measurement Tips describes how to test the data bus. The Single Edge Nibble Transmission (SENT) protocol defines an approach to data communications in […]
How is Zephyr used for edge AI and sensors?
Zephyr is a scalable open-source real-time operating system (RTOS) hosted by the Internet of Things (IoT) and embedded technology section of the Linux Foundation. Its modular architecture makes it highly flexible and suitable for use on resource-constrained edge devices and sensors. This article reviews Zephyr’s structure and features, examines how Zephyr supports neural networks and […]
How do AI and ML enhance SASE security?
Secure Access Service Edge (SASE) has emerged as a leading architecture for cloud deployments. Its primary function is to provide comprehensive cloud-based secure access while maintaining seamless access to data and applications for users of cloud computing services. This article compares SASE with a traditional network architecture and then looks at how artificial intelligence (AI) […]
How is HIL testing used for onboard EV chargers?
Hardware-in-the-loop (HIL) testing is a real-time simulation that enables designers to test embedded code for EV chargers without needing the actual system hardware. It speeds development efforts and reduces development costs. This article begins with an overview of HIL testing and onboard chargers (OBCs), looks at specific types of HIL testing applied to OBCs, and […]
How does a recurrent neural network (RNN) remember?
There are several types of neural networks (NNs). Recurrent NNs (RNNs) can “remember” data and use past information for inferences. This article compares recurrent NNs with feed-forward NNs (FFNNs) that can’t remember, then digs into the concept of backpropagation through time (BPTT) and closes by looking at long short-term memory (LSTM) RNNs. RNNs and FFNNs […]
What’s the difference between GPUs and TPUs for AI processing?
Graphic processing units (GPUs) and tensor processing units (TPUs) are specialized ICs that support different types of artificial intelligence (AI) and machine learning (ML) algorithms. This article begins with a brief overview of tensors and where they fit into the mathematics of AI and ML; it then looks at the different structures of GPUs and […]
What are the programming essentials for LoRa nodes?
LoRa (long-range) technology ensures reliable long-range communication between a node and gateway, making it well-suited for a range of Internet-of-Things (IoT) applications. The purpose of building a LoRa node is to reduce costs while ensuring long-term, low-power use for devices. LoRa’s low power is affected by several features, covered below. Features Smart programming. The written […]
Build a 5G Open RAN test lab with open-source software tools
Open-source software provides network components that you can use to simulate 5G network functions from the network core to the radio. Developing and deploying a laboratory infrastructure to support testing 5G and open radio-access network (Open RAN) systems can present a daunting and complex task. Prior to Open RAN, this task was only possible by…
