Rollups have emerged as a promising approach to improving blockchains’ scalability by offloading transactions execution off-chain. Existing rollup solutions either leverage complex zero-knowledge proofs or optimistic...
详细信息
The recovery of shapes from a few numbers of their projections is very important in Computed tomography. In this paper, we propose a novel scheme based on a collocation set of Gaussian functions to represent any objec...
详细信息
ISBN:
(纸本)9781450386487
The recovery of shapes from a few numbers of their projections is very important in Computed tomography. In this paper, we propose a novel scheme based on a collocation set of Gaussian functions to represent any object by using a limited number of projections. This approach provides a continuous representation of both the implicit function and its zero level set. We show that the appropriate choice of a basis function to represent the parametric level-set leads to an optimization problem with a modest number of parameters, which exceeds many difficulties with traditional level set methods, such as regularization, re-initialization, and use of signed distance function. For the purposes of this paper, we used a dictionary of Gaussian function to provide flexibility in the representation of shapes with few terms as a basis function located at lattice points to parameterize the level set function. We propose a convex program to recover the dictionary coefficients successfully so it works stably with only four projections by overcoming the issue of local-minimum of the cost function. Finally, the performance of the proposed approach in three examples of inverse problems shows that our method compares favorably to Sparse Shape Composition (SSC), Total Variation, and Dual Problem.
Anterior segment optical coherence tomography (AS-OCT) is a non-invasive imaging technique that is highly valuable for ophthalmic diagnosis. However, speckles in AS-OCT images can often degrade the image quality and a...
详细信息
In this paper, we consider the analysis and control of continuous-time nonlinear systems to ensure universal shifted stability and performance, i.e., stability and performance w.r.t. each forced equilibrium point of t...
详细信息
Medical internet of things leads to revolutionary improvements in medical services, also known as smart healthcare. With the big healthcare data, data mining and machine learning can assist wellness management and int...
详细信息
Wheelchair and mobility aid users often face challenges in navigating the built environment due to uneven sidewalks, temporary barriers, steep inclines, and narrow lanes. To assist these users, accessible routing syst...
详细信息
ISBN:
(数字)9798350376968
ISBN:
(纸本)9798350376975
Wheelchair and mobility aid users often face challenges in navigating the built environment due to uneven sidewalks, temporary barriers, steep inclines, and narrow lanes. To assist these users, accessible routing systems have been introduced that generate wheelchair-accessible paths to facilitate navigation in unfamiliar environments. In general, accessible routing systems rely on surface and path characteristics like surface type, incline, width, etc., and crowd-sourced information about barriers to provide the optimal route. Emerging routing systems even provide personalized routing to users that are catered to the user's specific needs and requirements. However, these types of systems collect crowd-sourced personal/identifiable information which introduces privacy and data heterogeneity concerns that are not addressed by them or elsewhere in the concerned domain. To address these two issues specifically, we propose the novel FedAccess system for accessible routing that utilizes the federated learning paradigm for surface recognition using vibration data. The surface-induced vibrations are captured through smartphone-embedded motion sensors (accelerometers and gyroscopes) from 23 manual wheelchair users during their regular navigation. We have covered 10 distinct surfaces from the USA. As a result, the distribution of the data is naturally non-IID. Empirical evaluation shows that the FedAccess system can protect user data and identity while dealing with non-IID data and still recognize heterogeneous surfaces with higher accuracy than the state-of-the-art.
As cyber-physical systems, power networks exchange data to ensure smooth operation. Through communication networks, the exchanged data becomes vulnerable to cyberattacks where malicious entities establish malevolent c...
详细信息
ISBN:
(数字)9798350391183
ISBN:
(纸本)9798350391190
As cyber-physical systems, power networks exchange data to ensure smooth operation. Through communication networks, the exchanged data becomes vulnerable to cyberattacks where malicious entities establish malevolent connections to falsify the data, which exploit the data integrity, leading to network instability. Machine learning-based solutions have been proposed to identify such malevolent actions, including false data injection attacks. This paper aims to (a) enhance the attack detection performance and (b) quantify the performance of non-recurrent and recurrent machine learning-based attack detection systems against multiple replay attacks that involve falsifying data via presenting normal operation patterns from previous timestamps. It turns out that capturing temporal aspects from the data using recurrent models outperforms non-recurrent models by 5-32% in accuracy (ACC). Specifically, we propose a recurrent graph neural network (RGNN) model that captures the temporal and spatial aspects of the network data. The RGNN model outperforms non-recurrent models by 14 – 32% and other recurrent models by 6 – 13% in ACC. The experiments are conducted on IEEE 14, 39, and 118-bus power networks where the model performance is enhanced (by up to 8% in ACC) in larger systems due to capturing more spatial and temporal features.
Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comp...
Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence.
Vehicle-to-Everything (V2X) communications play a crucial role in ensuring safe and efficient modern transportation systems. However, challenges arise in scenarios with buildings, leading to signal obstruction and cov...
详细信息
Technology will continue to be an important thing in life, technological developments can be found in everyday life. In medical intelligence technology, to identify bio-Terrorism actions, and aspects that can threaten...
详细信息
暂无评论