Within the innovative landscape of Industry 4.0, the seamless melding of digital systems has amplified the manufacturing arena's capacities. Notwithstanding these advancements, the latent vulnerabilities intrinsic...
详细信息
Human-computer interactions require systems that work out of the box without requiring lots of data to adapt to a new task or user. In this research, we address low resource spoken language understanding tasks such as...
Human-computer interactions require systems that work out of the box without requiring lots of data to adapt to a new task or user. In this research, we address low resource spoken language understanding tasks such as named entity recognition (NER), intent recognition (IR), and slot filling (SF) to research how a pretrained model can be modified for a new task, then finetuned with few labelled data. We propose extending the Whisper model with task-specific modules for NER, SF, and IR, leveraging a Markov network as output structure. We develop a novel approach to finetuning by removing irrelevant weights and reorganizing the embeddings to drastically improve the performance in a low-resource setting. Our approach outperforms previous models without external language models and demonstrates effective transfer learning, even with very limited training data. The models exhibit a small footprint, making them suitable for applications requiring robustness, few-shot learning, and efficiency.
We consider the problem of classifying trajectories on a discrete or discretised 2-dimensional manifold modelled by a simplicial complex. Previous works have proposed to project the trajectories into the harmonic eige...
详细信息
ISBN:
(数字)9798350354058
ISBN:
(纸本)9798350354065
We consider the problem of classifying trajectories on a discrete or discretised 2-dimensional manifold modelled by a simplicial complex. Previous works have proposed to project the trajectories into the harmonic eigenspace of the Hodge Laplacian, and then cluster the resulting embeddings. However, if the considered space has vanishing homology (i.e., no “holes”), then the harmonic space of the 1-Hodge Laplacian is trivial and thus the approach fails. Here we propose to view this issue akin to a sensor placement problem and present an algorithm that aims to learn “optimal holes” to distinguish a set of given trajectory classes. Specifically, given a set of labelled trajectories, which we interpret as edge-flows on the underlying simplicial complex, we search for 2-simplicies whose deletion results in an optimal separation of the trajectory labels according to the corresponding spectral embedding of the trajectories into the harmonic space. Finally, we generalise this approach to the unsupervised setting.
The Internet of Things is revolutionizing how in-terconnected devices communicate and interact within several applications, ranging from health monitoring to smart city development. Yet, the data management in these s...
详细信息
ISBN:
(数字)9798350319545
ISBN:
(纸本)9798350319552
The Internet of Things is revolutionizing how in-terconnected devices communicate and interact within several applications, ranging from health monitoring to smart city development. Yet, the data management in these systems is challenged by imprecision and noise inherent in Internet of Things environments. Fuzzy Rule-Based Systems have emerged as a solution, aptly handling the uncertainty and complexity in decision-making processes these environments present. However, current Fuzzy Rule-Based Systems implementations in Internet of Things often face limitations due to their ad-hoc nature and heavy reliance on specific hardware, thereby restricting their application in diverse and evolving Internet of Things infrastructures. In response to these challenges, we present JFML-IoT, an innovative open-source library that bridges the gap between Fuzzy Rule-Based Systems and Internet of Things devices. JFML-IoT extends the JFML library, implementing the IEEE Std 1855-2016 for Fuzzy Markup Language and adapting its capabilities to the unique demands of the Internet of Things paradigm. This library not only facilitates remote Fuzzy Rule-Based Systems deployment but also excels in generating source code for Internet of Things microcontrollers, thus enabling a new level of hardware abstraction and versatility. Our approach significantly enhances the scalability, flexibility, and integration of Fuzzy Rule-Based Systems within varied Internet of Things systems. To demonstrate the practical application and effectiveness of JFML-IoT, we conducted a case study in a real-world environment. This case study showcases how JFML-IoT can improve data management in Internet of Things systems, offering scalable, efficient, and adaptable solutions that are critical in modern Internet of Things applications.
System for determining the position of the human body in the virtual world has been designed, implemented and researched. The system consists of two independent subsystems: subsystem for collecting, processing and tra...
详细信息
Homomorphic encryption is a groundbreaking cryptographic method that has made giant contributions to healthcare by addressing the urgent need for steady and privacy-keeping information analysis and sharing. This encry...
详细信息
ISBN:
(纸本)9798400716263
Homomorphic encryption is a groundbreaking cryptographic method that has made giant contributions to healthcare by addressing the urgent need for steady and privacy-keeping information analysis and sharing. This encryption approach permits information to be processed while nonetheless in its encrypted form, permitting healthcare businesses to perform complex computations on confidential patient information without compromising character privacy or data protection. It paved the way for secure cloud-based facts storage, sharing, and collaborative healthcare research, facilitating advancements in fact-driven selection-making, customized medicinal drugs, and remote affected person tracking. Homomorphic encryption has emerged as a vital enabler of innovation by maintaining the confidentiality of affected personal information while enabling meaningful analysis.
We consider the problem of classifying trajectories on a discrete or discretised 2-dimensional manifold modelled by a simplicial complex. Previous works have proposed to project the trajectories into the harmonic eige...
详细信息
Reducing electrophysiological (EP) signal noise is essential for diagnosis, mapping, and ablation, yet traditional approaches are suboptimal. This study tests the hypothesis that generative artificial intelligence (AI...
详细信息
ISBN:
(数字)9798350371499
ISBN:
(纸本)9798350371505
Reducing electrophysiological (EP) signal noise is essential for diagnosis, mapping, and ablation, yet traditional approaches are suboptimal. This study tests the hypothesis that generative artificial intelligence (AI), specifically Variational Autoencoders (VAEs), can effectively denoise these signals by forming robust internal representations of ‘clean' signals. Utilizing a dataset of 5706 time series from 42 patients with ischemic cardiomyopathy at risk of cardiac sudden death, we set out to apply a β-VAE model to denoise and reconstruct intra-ventricular monophasic action potential (MAP) signals, which have verifiable morphology. The β-VAE model is evaluated against various noise types, including EP noise, demonstrating superior denoising performance compared to traditional methods (Pearson’s Correlation of denoised vs original of 0.967 ± 0.009 for our proposed model vs 0.879 ± 0.022 for the best performing baseline). Results indicate that the model effectively reduces a wide array of noise types, particularly EP noise. We conclude that generative AI provides powerful tools that can eliminate diverse sources of noise in single beats by learning essential signal features without manual annotation, outperforming state-of-the-art denoising *** Relevance— The proposed β-VAE model’s ability to effectively denoise and reconstruct intracardiac signals, particularly in the challenging context of arrhythmias, can significantly enhance diagnostic accuracy across a variety of heart rhythm disorders and improve treatment efficacy.
The creation of a framework in which traditional Machine Learning and neuromorphic algorithms compete to solve a shared Reinforcement Learning environment is presented in this work. In addition, this configuration all...
详细信息
ISBN:
(纸本)9798400716263
The creation of a framework in which traditional Machine Learning and neuromorphic algorithms compete to solve a shared Reinforcement Learning environment is presented in this work. In addition, this configuration allows the exploitation of modern and widely-used Machine Learning libraries. The PyTorch framework is used to investigate the expanded capabilities and potential of training an action-critic network pair comprised of specialised units using a custom learning algorithm. The policy and value networks utilised in this context are fully interconnected MultiLayer Perceptrons. The training procedure employs two distinct algorithms: an algorithm inspired by Reward Modulated Spiked Timing Dependent Plasticity and the conventional Back Propagation technique. A comparative evaluation and analysis of the findings is performed.
In this paper, we present a human-based computation approach for the analysis of peripheral blood smear (PBS) images images in patients with Sickle Cell Disease (SCD). We used the Mechanical Turk microtask market to c...
详细信息
暂无评论