A Survey on Deep Learning for Ultra-Reliable and Low-Latency Communications Challenges on 6G Wireless Systems

As machine learning becomes ubiquitous, the need to deploy models on real-time, embedded systems will become increasingly critical. This is especially true for deep learning solutions, whose large models pose interesting challenges for target architectures at the “edge” that are resource-constrained. The realization of machine learning, and deep learning, is being driven by the availability of specialized hardware, such as system-on-chip solutions, which provide some alleviation of constraints. Equally important, however, are the operating systems that run on this hardware, and specifically the ability to leverage commercial real-time operating systems which, unlike general purpose operating systems such as Linux, can provide the low-latency, deterministic execution required for embedded, and potentially safety-critical, applications at the edge. Despite this, studies considering the integration of real-time operating systems, specialized hardware, and machine learning/deep learning algorithms remain limited. In particular, better mechanisms for real-time scheduling in the context of machine learning applications will prove to be critical as these technologies move to the edge. In order to address some of these challenges, we present a resource management framework designed to provide a dynamic on-device approach to the allocation and scheduling of limited resources in a real-time processing environment. These types of mechanisms are necessary to support the deterministic behavior required by the control components contained in the edge nodes. To validate the effectiveness of our approach, we applied rigorous schedulability analysis to a large set of randomly generated simulated task sets and then verified the most time critical applications, such as the control tasks which maintained low-latency deterministic behavior even during off-nominal conditions. The practicality of our scheduling framework was demonstrated by integrating it into a commercial real-time operating system (VxWorks) then running a typical deep learning image processing application to perform simple object detection. The results indicate that our proposed resource management framework can be leveraged to facilitate integration of machine learning algorithms with real-time operating systems and embedded platforms, including widely-used, industry-standard real-time operating systems.

Download Full-text

Toward Polymorphic Internet of Things Receivers Through Real-Time Waveform-Level Deep Learning

GetMobile Mobile Computing and Communications ◽

10.1145/3511285.3511294 ◽

2022 ◽

Vol 25 (3) ◽

pp. 28-33

Author(s):

Francesco Restuccia ◽

Tommaso Melodia

Keyword(s):

Deep Learning ◽

Internet Of Things ◽

Real Time ◽

Software Defined Radio ◽

Wireless Systems ◽

Physical World ◽

Wireless Protocols ◽

Key Innovation ◽

Custom Made ◽

Time Waveform

Wireless systems such as the Internet of Things (IoT) are changing the way we interact with the cyber and the physical world. As IoT systems become more and more pervasive, it is imperative to design wireless protocols that can effectively and efficiently support IoT devices and operations. On the other hand, today's IoT wireless systems are based on inflexible designs, which makes them inefficient and prone to a variety of wireless attacks. In this paper, we introduce the new notion of a deep learning-based polymorphic IoT receiver, able to reconfigure its waveform demodulation strategy itself in real time, based on the inferred waveform parameters. Our key innovation is the introduction of a novel embedded deep learning architecture that enables the solution of waveform inference problems, which is then integrated into a generalized hardware/software architecture with radio components and signal processing. Our polymorphic wireless receiver is prototyped on a custom-made software-defined radio platform. We show through extensive over-the-air experiments that the system achieves throughput within 87% of a perfect-knowledge Oracle system, thus demonstrating for the first time that polymorphic receivers are feasible.

Download Full-text

Deep Learning Model for Imbalanced Multi-label Surface Defect Classification

Measurement Science and Technology ◽

10.1088/1361-6501/ac41a6 ◽

2021 ◽

Author(s):

Yang Liu ◽

Yachao Yuan ◽

Jing Liu

Keyword(s):

Deep Learning ◽

Surface Defect ◽

State Of The Art ◽

Steel Production ◽

Learning Model ◽

The State ◽

Low Latency ◽

Defect Classification ◽

Key Techniques ◽

Deep Learning Model

Abstract Automatic defect classification is vital to ensure product quality, especially for steel production. In the real world, the amount of collected samples with labels is limited due to high labor costs, and the gathered dataset is usually imbalanced, making accurate steel defect classification very challenging. In this paper, a novel deep learning model for imbalanced multi-label surface defect classification, named ImDeep, is proposed. It can be deployed easily in steel production lines to identify different defect types on the steel's surface. ImDeep incorporates three key techniques, i.e., Imbalanced Sampler, Fussy-FusionNet, and Transfer Learning. It improves the model's classification performance with multi-label and reduces the model's complexity over small datasets with low latency. The performance of different fusion strategies and three key techniques of ImDeep is verified. Simulation results prove that ImDeep accomplishes better performance than the state-of-the-art over the public dataset with varied sizes. Specifically, ImDeep achieves about 97% accuracy of steel surface defect classification over a small imbalanced dataset with a low latency, which improves about 10% compared with that of the state-of-the-art.

Download Full-text