Explainable Neural Network-based Modulation Classification via Concept Bottleneck Models

Wong, Lauren J.; McPherson, Sean

doi:10.1109/ccwc51732.2021.9376108

Cited by 7 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This involves developing methodologies and tools to elucidate how the models arrive at their classifications, enabling users to understand and validate the reasoning behind the model's predictions. Potential frameworks for exploration could be based on those proposed for byte-based MTL TC [12] and AMC [59].…”

Section: Conclusion and Open Challengesmentioning

confidence: 99%

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

Góez,

Aycan Beyazit,

Fletscher

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Traffic Classification (TC) systems are designed to identify the applications generating network traffic. Recent advancements in TC leverage Deep Learning (DL) techniques, surpassing traditional methods in complex scenarios, including those with encrypted traffic. Notably, state-of-the-art DL-based TC systems have been developed for wireless networks using Physical Layer (L1) packets. This approach overcomes the common limitation in TC research that assumes traffic flows within a wired network under a single network management domain. Despite their benefits, DL-based TC systems often demand significant computational resources, typically available only in cloud environments. Consequently, deploying models at the edge is often infeasible due to their resource-intensive nature, given their original training and optimization for high-resource environments. The inherent challenge lies in adapting these systems for edge computing scenarios, including deployment at access points. In this paper, we propose a novel methodology that exploits expert knowledge in combination with recent advances in Multi-Task Learning (MTL) and Deep Neural Network (DNN) optimization to allow spectrum-based TC systems to run on constrained devices. Performance evaluations on an NVIDIA Jetson TX2 demonstrate that our most optimized MTL model, handling four TC tasks, can reduce memory requirements by a factor of 2.65x and improve execution time by 3.6x compared to sequential execution of four Single-Task Learning (STL) models in a servergrade configuration, with minimal accuracy impact (less than a 0.5% drop) and energy efficiency of 0.97 millijoules per sample at inference. Compared to other edge platforms such as the Raspberry Pi model 3B+ (RPI3B+) with a low-power Artificial Intelligence (AI)-accelerator such as the Coral Tensor Processing Unit (TPU), the NVIDIA Jetson achieves a 12-fold improvement in energy efficiency with no impact on accuracy. These are the first available results to provide a benchmark for different performance metrics (memory, computing, energy) over heterogeneous constrained devices for this type of TC system.

show abstract

Section: Conclusion and Open Challengesmentioning

confidence: 99%

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

Góez,

Aycan Beyazit,

Fletscher

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…More specifically, in both [34,35], modulation classes are broken into subgroups, either by modulation type (i.e., linear, frequency, etc.) or in order to separate the modulation schemes that cause the most confusion (i.e., 16QAM and 64QAM); moreover, in [36], concept bottleneck models were used to provide inherent decision explanations while performing AMC via the prediction of a set of intermediate concepts defined prior to training.…”

Section: Multitask Learningmentioning

confidence: 99%

Transfer Learning for Radio Frequency Machine Learning: A Taxonomy and Survey

Wong

Michaels

2022

Sensors

Self Cite

View full text Add to dashboard Cite

Transfer learning is a pervasive technology in computer vision and natural language processing fields, yielding exponential performance improvements by leveraging prior knowledge gained from data with different distributions. However, while recent works seek to mature machine learning and deep learning techniques in applications related to wireless communications, a field loosely termed radio frequency machine learning, few have demonstrated the use of transfer learning techniques for yielding performance gains, improved generalization, or to address concerns of training data costs. With modifications to existing transfer learning taxonomies constructed to support transfer learning in other modalities, this paper presents a tailored taxonomy for radio frequency applications, yielding a consistent framework that can be used to compare and contrast existing and future works. This work offers such a taxonomy, discusses the small body of existing works in transfer learning for radio frequency machine learning, and outlines directions where future research is needed to mature the field.

show abstract

“…For example, with the multi-class modulation classification using CNN in [77], many ambiguous points are explained thoroughly, such as which modules in the architecture can help to improve the accuracy and why some modulations show better performance than others with the same condition. In this context, XAI, which can provide explanations concerning automated decisions and predictions, is recommended because it offers profound insights [78]. Those insights can help the system operators and network designer to solve unexpected problems, which in turn guarantees the reliability of the network and enhances the overall performance of 6G services in communication systems [79].…”

Section: A Intelligent Radio 1) Introductionmentioning

confidence: 99%

Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges

Wang¹,

Qureshi²,

Miralles-Pechuaán³

et al. 2021

Preprint

View full text Add to dashboard Cite

When 5G began its commercialisation journey around 2020, the discussion on the vision of 6G also surfaced. Researchers expect 6G to have higher bandwidth, coverage, reliability, energy efficiency, lower latency, and, more importantly, an integrated "human-centric" network system powered by artificial intelligence (AI). Such a 6G network will lead to an excessive number of automated decisions made every second. These decisions can range widely, from network resource allocation to collision avoidance for self-driving cars. However, the risk of losing control over decision-making may increase due to high-speed data-intensive AI decision-making beyond designers and users' comprehension. The promising explainable AI (XAI) methods can mitigate such risks by enhancing the transparency of the black box AI decision-making process. This survey paper highlights the need for XAI towards the upcoming 6G age in every aspect, including 6G technologies (e.g., intelligent radio, zero-touch network management) and 6G use cases (e.g., industry 5.0). Moreover, we summarised the lessons learned from the recent attempts and outlined important research challenges in applying XAI for building 6G systems. This research aligns with goals 9, 11, 16, and 17 of the United Nations Sustainable Development Goals (UN-SDG) 1 , promoting innovation and building infrastructure, sustainable and inclusive human settlement, advancing justice and strong institutions, and fostering partnership at the global level.

show abstract

Explainable Neural Network-based Modulation Classification via Concept Bottleneck Models

Cited by 7 publications

References 11 publications

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

Transfer Learning for Radio Frequency Machine Learning: A Taxonomy and Survey

Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges

Contact Info

Product

Resources

About