The Internet of Things (IoT) is considered an evolving technology, consisting of different types of connected devices that have sensors, specialized hardware, and software. However, considerable challenges related to ...
详细信息
ISBN:
(数字)9798331506995
ISBN:
(纸本)9798331507008
The Internet of Things (IoT) is considered an evolving technology, consisting of different types of connected devices that have sensors, specialized hardware, and software. However, considerable challenges related to user data privacy, security, and device integrity are presented by this swift expansion, with digital identity being identified as a significant concern in the online landscape. Established by the World Wide Web Consortium (W3C) [2], Decentralized Identifiers (DIDs) represent a standardized format for defining identity. A peer-to-peer model for managing identity and credentials through self-sovereign identity is facilitated by DIDs, in conjunction with blockchain technology and public-key cryptography. The development of verifiable credentials is enabled by the combination of DIDs and blockchain technology, allowing for the verification of the identities of transacting parties through distributed identity registration and the identification of cryptographic keys necessary for validating electronic authentication during transactions. This integrated framework is regarded as both reliable and trusted. Device registration, verification, and credential revocation are enabled by it. In addition, security is ensured, the privacy of participating nodes is respected, and data integrity is upheld to address several existing challenges, such as data scalability and confidentiality. Trusted management and transaction of IoT data are ensured by the presented IoT data platform. Blockchain, decentralized identifiers, and public key cryptography are integrated by the authors to develop this platform. Self-sovereign identity is granted to each participating device, and dynamic changes in components like consensus algorithms and databases are supported by key features. Different IoT communication protocols are evaluated within a decentralized blockchain infrastructure for identity verification by the authors, focusing on interactions between IoT devices and networked se
B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue’s surface contour remains a significant challenge due to the ...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue’s surface contour remains a significant challenge due to the low signal-to-noise ratio (SNR) and prevalent speckle noise in ultrasound images. Traditional supervised learning models often require large labeled datasets, which are labor-intensive to produce and susceptible to noise interference. To address these limitations, we present a novel Counterfactual Ultrasound Anti-Interference Self-Supervised Network (CUAI-SSN), which integrates self-supervised learning (SSL) with counterfactual data augmentation, progressively disentangles confounding factors, ensuring that the model generalizes well across varied ultrasound conditions. Our approach leverages causal reasoning to decouple noise from relevant features, enabling the model to learn robust representations that focus on essential tongue structures. By generating counterfactual image-label pairs, our method introduces alternative, noise-independent scenarios that enhance model training. Furthermore, we introduce attention mechanisms to enhance the network’s ability to capture fine-grained details even in noisy conditions. Extensive experiments on real ultrasound tongue images demonstrate that CUAI-SSN outperforms existing methods, setting a new benchmark for automated contour extraction in ultrasound tongue imaging. Our code is publicly available at https://***/inexhaustible419/CounterfactualultrasoundAI.
暂无评论