UAV usually combines the Global Navigation Satellite System (GNNS) and the Inertial Navigation System (INS) to realize real-time localization and navigation. However, UAVs may lose GNSS signals due to complex terrain environments and electronic ...

This paper presents a simple yet effective approach for compressing binary files by detecting and folding similar patterns. Until now, methods for compressing these files were mostly limited to compiler optimization and traditional compression tools. ...

Endowing artificial objects with intelligence is a longstanding computer science and engineering vision that recently converged under the umbrella of Artificial Intelligence of Things (AIoT). Nevertheless, AIoT's mission cannot be fulfilled if objects ...

While real-time face recognition has become increasingly popular, its use in decentralized systems and on embedded hardware presents numerous challenges. One challenge is the trade-off between accuracy and inference-time on constrained hardware ...

Computer-vision algorithms have been used to enhance hands-free user interactions with smart systems. Traditional approaches for object and gesture detection and recognition are through the processing of video frames by convolutional neural networks (...

As embedded devices are widely used in increasingly complex settings (e.g., smart homes and industrial control systems), one device is usually connected with multiple entities, such as mobile apps and the cloud. Recent research has shown that ...

Embedded systems have evolved tremendously in recent years. We perform a study on SQLite and find that the multiple layers of abstraction drastically reduce bandwidth utilization. To minimize the bandwidth loss in the I/O path, we propose Lunar, a ...

Denial constraints (DCs) are at the heart of maintaining data consistency. Formulating DCs by hand is difficult and susceptible to errors. Automatically discovering DCs from data is an alternative, but this is computationally expensive due to the large ...

The Internet of Things (IoT) is transforming the world. On the one hand, its rapid integration into many systems is making automation easier, but on the other hand dependence of many processes on IoT is also making the IoT an attractive target for ...

We observe significant interest in reinforcement learning methods for real-world sensing-control scenarios driven by the sensor data streams. However, the delay introduced to the data by the communication channels may degrade the system's performance. ...

The challenges in real-time cluster computing, particularly in computing efficiency and reliability, have evolved significantly due to the increase of Internet of Things (IoT), cloud and edge computing applications. Lately, a number of low-power and low-...

Deep learning-based object detection algorithms have some limitations, such as complex network structure and high computing power requirements, which makes it difficult to meet real-time detection in transmission line inspection robots. In response to ...

With Internet of things technologies, billions of embedded devices, including smart gateways, smart phones, and mobile robots, are connected and deeply integrated. Almost all these embedded devices are battery-constrained and energy-limited systems. In ...

cREAtIve targets the development of novel highly-adaptable embedded deep learning solutions for automotive and traffic monitoring applications, including position sensor processing, scene interpretation based on LiDAR, and object detection and ...

Measuring temperature of humans in light of the COVID-19 pandemic has become crucial in various places. Although there are already commercial systems to measure temperature contactless, we attempted to develop a deep learning based low-cost method ...

Information leakage through side-channels poses a serious threat to the security of distributed systems. Recent research on countermeasures against side-channel attacks show that, on embedded platforms with predictable execution times, certain classes ...

Logarithmic number systems (LNS) reduce hardware complexity for multiplication and division in embedded systems, at the cost of more complicated addition and subtraction. Existing LNS typically use base-2, meaning that representable numbers are some (...

The exploration of interconnected devices, embedded devices, sensors, and various network-connected devices helps to communicate each other and exchange communications. These devices overcome with security threats related to privacy and data exchange over ...

Pattern matching is an important building block for many security applications, including Network Intrusion Detection Systems (NIDS). As NIDS grow in functionality and complexity, the time overhead and energy consumption of pattern matching become a ...

In autonomous embedded systems, it is often vital to reduce the amount of actions taken in the real world and energy required to learn a policy. Training reinforcement learning agents from high dimensional image representations can be very expensive and ...