Technology and Applications

In the rapidly evolving landscape of edge computing and artificial intelligence (AI) development, complete developer toolchains have become vital resources for technical teams aiming to efficiently develop and deploy applications. These toolchains typically include debugging tools, application programming interfaces (APIs), and software development kits (SDKs). They not only help developers build and optimize applications more quickly but also address complex …

As edge computing becomes widely adopted in IoT, industrial automation, and AI deployment, the choice of operating systems (OS) for edge devices has become increasingly critical. Operating systems not only determine device performance and functionality but also impact developer workflows and application deployment efficiency. This article explores the common types of operating systems used in edge computing devices, including Linux …

With the rise of IoT, industrial automation, and edge computing, the AI tasks run on edge devices are becoming increasingly complex. In real-world scenarios such as video analytics in smart cities, vehicle perception in autonomous driving, or device monitoring in industrial IoT, a single device may need to run multiple AI models simultaneously. So, can edge devices run multiple models …

With the widespread adoption of edge computing across IoT, industrial AI, and autonomous driving, balancing inference performance (low latency) and model accuracy on edge devices has become a critical challenge for developers. Even in hardware-constrained environments, AI frameworks need to effectively support deep learning models to meet key business demands. Fortunately, several frameworks and tools have been designed to optimize …

With the widespread adoption of artificial intelligence (AI), the high computational cost due to model complexity has become a significant challenge. This is particularly critical when running AI models on resource-constrained devices such as edge computing hardware, where optimization is imperative for better performance and efficiency. Quantization, pruning, and distillation are three of the most prominent AI model optimization techniques …

With the increasing size of AI models, deploying large-scale AI models like GPT and Vision Transformer on the cloud has become a common practice. However, cloud-based operations can introduce challenges such as latency, significant data transmission, privacy concerns, and high costs. As a result, users are increasingly focused on whether these complex models can be deployed and run on edge …

In fields like smart manufacturing, IoT, and intelligent transportation, the demand for customized AI models has grown rapidly. While many edge computing devices come equipped with predefined AI frameworks such as TensorFlow Lite or PyTorch, some users may need to run custom AI models tailored to their unique business needs. This calls for edge devices to be highly flexible, enabling …

With the rapid evolution of artificial intelligence (AI) and edge computing technologies, deploying AI models on edge devices has become common practice across various industries. Whether in industrial automation, smart cities, or intelligent transportation, supporting AI frameworks is critical for edge computing devices to execute tasks efficiently. So, which popular AI frameworks are currently supported by edge computing devices? How …

In Industrial IoT (IIoT) and Vehicle-to-Everything (V2X) networks, low-latency communication is critical for the successful implementation of tasks. For example, industrial automation requires real-time control of production lines, while V2X technology demands millisecond-level responses to ensure driving safety. The key question is: Can edge devices deliver the required low-latency performance? The answer is yes. Edge computing demonstrates high adaptability and …