ESWEEK

Recent emerging technologies such as artificial intelligence and machine learning have been promising enormous economic and societal benefits. While it is desirable to deploy these technologies to Internet-of-Things (IoT) infrastructures in many ...

System-Performance Engineering (SysPE) encompasses modeling formalisms, methods, techniques, and industrial practices to design systems for performance, where performance is taken integrally into account during the whole system life cycle. Industrial ...

3D deep learning has been applied in safety-critical scenarios, e.g., autonomous driving. Several works have raised the security problems of 3D deep learnings mainly from the perspective of adversarial attacks. In this paper, we propose a novel backdoor ...

With the development of wireless network technology, the WiFi-based indoor localization methods incorporating machine learning have attracted wide attention due to its easy deployment and low cost characteristics. However, the existing learning methods ...

Previous online reachability algorithms for hybrid automata reduced conservatism in verified Simplex controller architectures, but were restricted to the imprecise real-time paradigm, i.e., their precision increases over time. Yet, many safety-critical ...

Dual modular redundancy (DMR) is not only an established solution for systems with high reliability demands, it is even required in aviation certification standards such as DO-254 [5, Clause 2.3.1]. A safety critical avionic application such as the ...

Different to traditional works on frame-level features and temporal characteristics, we propose a deepfake video detection method based on visual-audio synchronism, which compares the audio stream and the visual stream by an improved siamese neural ...

In this paper, we approach to improve the fault tolerance of Deep Neural Networks (DNNs) for safety-critical artificial intelligent applications. We propose to remap the range of 32-bit float to weights to reduce the influence of invalid weights caused ...

We report on our ongoing development of an optimized low-level timer-API for the RIOT operating system. Starting with a survey of hardware timer peripherals from 43 MCU-families and 8 manufacturers, we identify common properties and differences of all ...

Decision trees (DTs) offer a popular implementation choice for machine learning classifiers since they are highly interpretable and easy to use. Resource management decision overheads must be minimal in embedded systems to meet latency targets and ...

In many safety-critical applications, Multi-Processor Systems-on-Chip (MPSoC) must operate within a given thermal envelope under harsh environmental conditions. Meeting the thermal requirements often requires using advanced task allocation and ...

Requirements-driven search-based testing (SBT), also known as falsification, has proven to be a practical and effective method for discovering erroneous behaviors in Cyber-Physical Systems. However, SBT techniques do not provide guarantees on ...

Cyber-Physical Systems (CPS) are important components of critical infrastructure and must operate with high levels of reliability and security. We propose a conceptual approach to securing CPSs: the Cyber-Physical Immune System (CPIS), a collection of ...

Energy efficiency considerations are required for resource reservations in real-time systems. However, current systems lack considerations of energy efficiency when calculating the optimum processor speed to ensure that the supply of resources is no ...

Arbitrary processor affinities are used in multiprocessor systems to specify the processors on which a task can be scheduled. However, affinity constraints can prevent some high priority real-time tasks from being scheduled, while lower priority tasks ...