Search

Thematic Analysis (TA) is a fundamental method in healthcare research for analyzing transcript data, but it is resource-intensive and difficult to scale for large, complex datasets. This study investigates the potential of large language models (LLMs) to augment the inductive TA process in high-stakes healthcare settings. Focusing on interview transcripts from parents of children with Anomalous Aortic Origin of a Coronary Artery (AAOCA), a rare congenital heart disease, we propose an LLM-Enhanced Thematic Analysis (LLM-TA) pipeline. Our pipeline integrates an affordable state-of-the-art LLM (GPT-4o mini), LangChain, and prompt engineering with chunking techniques to analyze nine detailed transcripts following the inductive TA framework. We evaluate the LLM-generated themes against human-generated results using thematic similarity metrics, LLM-assisted assessments, and expert reviews. Results demonstrate that our pipeline outperforms existing LLM-assisted TA methods significantly. While the pipeline alone has not yet reached human-level quality in inductive TA, it shows great potential to improve scalability, efficiency, and accuracy while reducing analyst workload when working collaboratively with domain experts. We provide practical recommendations for incorporating LLMs into high-stakes TA workflows and emphasize the importance of close collaboration with domain experts to address challenges related to real-world applicability and dataset complexity. https://github.com/jiaweixu98/LLM-TA, Comment: Accepted by GenAI for Health Workshop @ AAAI 2025, Philadelphia

Low-energy light ion beams are an essential resource in lithography for nanopatterning magnetic materials and interfaces due to their ability to modify the structure and properties of metamaterials. Here we create ferromagnetic/non-ferromagnetic heterostructures with a controlled layer thickness and nanometer-scale precision. For this, hydrogen ion (H+) irradiation is used to reduce the antiferromagnetic nickel oxide (NiO) layer into ferromagnetic Ni with lower fluence than in the case of helium ion (He+) irradiation. Our results indicate that H+ chemical affinity with oxygen is the primary mechanism for efficient atom remotion, as opposed to He+ irradiation, where the chemical affinity for oxygen is negligible.

We investigated the effects of annealing temperatures (TA) on a Pd (5 nm)/CoFeB (10 nm)/Pd (3 nm)/Ta (10 nm) multilayer structure. The as-deposited sample showed an amorphous state with in-plane uniaxial magnetic anisotropy (UMA), resulting in low coercivity and moderate damping constant ({\alpha}) values. Increasing TA led to crystallization, forming bcc-CoFe (110) crystals, which increased in-plane coercivity and introduced isotropic magnetic anisotropy, slightly reducing the {\alpha}. The two-fold UMA persists up to 600 C, and the thermal stability of the in-plane magnetic anisotropy remains intact even TA = 700 C. The TA significantly influenced the magnetic properties such as in-plane saturation magnetization (Ms//), in-plane and out-of-plane coercivities, and in-plane effective magnetic anisotropy energy density (Keff). Above 600 C, Keff decreased, indicating a transition towards uniaxial perpendicular magnetic anisotropy. Interfacial oxidation and diffusion from the Ta capping layer to the Pd/CoFeB/Pd interfaces were observed, influencing chemical bonding states. Annealing at 700 C, reduced oxygen within TaOx through a redox reaction involving Ta crystallization, forming TaB, PdO, and BOx states. Ferromagnetic resonance spectra analysis indicated variations in resonance field (Hr) due to local chemical environments. The {\alpha} reduction, reaching a minimum at 300 C annealing, was attributed to reduced structural disorder from inhomogeneities. Tailoring magnetic anisotropy and spin dynamic properties in Pd/CoFeB/Pd/Ta structures through TA-controlled oxygen diffusion/oxidation highlights their potential for SOT, DMI, and magnetic skyrmion-based spintronic devices.

In recent years, facial recognition (FR) models have become the most widely used biometric tool, achieving impressive results on numerous datasets. However, inherent hardware challenges or shooting distances often result in low-resolution images, which significantly impact the performance of FR models. To address this issue, several solutions have been proposed, including super-resolution (SR) models that generate highly realistic faces. Despite these efforts, significant improvements in FR algorithms have not been achieved. We propose a novel SR model FTLGAN, which focuses on generating high-resolution images that preserve individual identities rather than merely improving image quality, thereby maximizing the performance of FR models. The results are compelling, demonstrating a mean value of d' 21% above the best current state-of-the-art models, specifically having a value of d' = 1.099 and AUC = 0.78 for 14x14 pixels, d' = 2.112 and AUC = 0.92 for 28x28 pixels, and d' = 3.049 and AUC = 0.98 for 56x56 pixels. The contributions of this study are significant in several key areas. Firstly, a notable improvement in facial recognition performance has been achieved in low-resolution images, specifically at resolutions of 14x14, 28x28, and 56x56 pixels. Secondly, the enhancements demonstrated by FTLGAN show a consistent response across all resolutions, delivering outstanding performance uniformly, unlike other comparative models. Thirdly, an innovative approach has been implemented using triplet loss logic, enabling the training of the super-resolution model solely with real images, contrasting with current models, and expanding potential real-world applications. Lastly, this study introduces a novel model that specifically addresses the challenge of improving classification performance in facial recognition systems by integrating facial recognition quality as a loss during model training., Comment: 10 pages, 8 figures

We present our results regarding the automatic construction of a knowledge graph from historical documents related to the Chilean dictatorship period (1973-1990). Our approach consists on using LLMs to automatically recognize entities and relations between these entities, and also to perform resolution between these sets of values. In order to prevent hallucination, the interaction with the LLM is grounded in a simple ontology with 4 types of entities and 7 types of relations. To evaluate our architecture, we use a gold standard graph constructed using a small subset of the documents, and compare this to the graph obtained from our approach when processing the same set of documents. Results show that the automatic construction manages to recognize a good portion of all the entities in the gold standard, and that those not recognized are mostly explained by the level of granularity in which the information is structured in the graph, and not because the automatic approach misses an important entity in the graph. Looking forward, we expect this report will encourage work on other similar projects focused on enhancing research in humanities and social science, but we remark that better evaluation metrics are needed in order to accurately fine-tune these types of architectures., Comment: 11 pages, 1 figure, 2 tables. Paper submitted to KBC-LM 2024

This paper gives a broad account of the various sequent-based proof formalisms in the proof-theoretic literature. We consider formalisms for various modal and tense logics, intuitionistic logic, conditional logics, and bunched logics. After providing an overview of the logics and proof formalisms under consideration, we show how these sequent-based formalisms can be placed in a hierarchy in terms of the underlying data structure of the sequents. We then discuss how this hierarchy can be traversed using translations. Translating proofs up this hierarchy is found to be relatively easy while translating proofs down the hierarchy is substantially more difficult. Finally, we inspect the prevalent distinction in structural proof theory between 'internal calculi' and 'external calculi'. It is observed that these classes resist a rigorous separation, and we critically assess the properties that (calculi from) these classes are purported to possess.

The first layer of a deep CNN backbone applies filters to an image to extract the basic features available to later layers. During training, some filters may go inactive, mean ing all weights in the filter approach zero. An inactive fil ter in the final model represents a missed opportunity to extract a useful feature. This phenomenon is especially prevalent in specialized CNNs such as for face recogni tion (as opposed to, e.g., ImageNet). For example, in one the most widely face recognition model (ArcFace), about half of the convolution filters in the first layer are inactive. We propose a novel approach designed and tested specif ically for face recognition networks, known as "CRAFT: Contextual Re-Activation of Filters for Face Recognition Training". CRAFT identifies inactive filters during training and reinitializes them based on the context of strong filters at that stage in training. We show that CRAFT reduces fraction of inactive filters from 44% to 32% on average and discovers filter patterns not found by standard training. Compared to standard training without reactivation, CRAFT demonstrates enhanced model accuracy on standard face-recognition benchmark datasets including AgeDB-30, CPLFW, LFW, CALFW, and CFP-FP, as well as on more challenging datasets like IJBB and IJBC.

State-of-the-art deep CNN face matchers are typically created using extensive training sets of color face images. Our study reveals that such matchers attain virtually identical accuracy when trained on either grayscale or color versions of the training set, even when the evaluation is done using color test images. Furthermore, we demonstrate that shallower models, lacking the capacity to model complex representations, rely more heavily on low-level features such as those associated with color. As a result, they display diminished accuracy when trained with grayscale images. We then consider possible causes for deeper CNN face matchers "not seeing color". Popular web-scraped face datasets actually have 30 to 60% of their identities with one or more grayscale images. We analyze whether this grayscale element in the training set impacts the accuracy achieved, and conclude that it does not. We demonstrate that using only grayscale images for both training and testing achieves accuracy comparable to that achieved using only color images for deeper models. This holds true for both real and synthetic training datasets. HSV color space, which separates chroma and luma information, does not improve the network's learning about color any more than in the RGB color space. We then show that the skin region of an individual's images in a web-scraped training set exhibits significant variation in their mapping to color space. This suggests that color carries limited identity-specific information. We also show that when the first convolution layer is restricted to a single filter, models learn a grayscale conversion filter and pass a grayscale version of the input color image to the next layer. Finally, we demonstrate that leveraging the lower per-image storage for grayscale to increase the number of images in the training set can improve accuracy of the face recognition model., Comment: This is replacement version of the previous arxiv submission: 2309.05180 (Our Deep CNN Face Matchers Have Developed Achromatopsia). The past version is published in CVPRW and available in IEEE proceedings. This submitted version is an extension of the conference paper

Current space-based missions, such as the Transiting Exoplanet Survey Satellite (TESS), provide a large database of light curves that must be analysed efficiently and systematically. In recent years, deep learning (DL) methods, particularly convolutional neural networks (CNN), have been used to classify transit signals of candidate exoplanets automatically. However, CNNs have some drawbacks; for example, they require many layers to capture dependencies on sequential data, such as light curves, making the network so large that it eventually becomes impractical. The self-attention mechanism is a DL technique that attempts to mimic the action of selectively focusing on some relevant things while ignoring others. Models, such as the Transformer architecture, were recently proposed for sequential data with successful results. Based on these successful models, we present a new architecture for the automatic classification of transit signals. Our proposed architecture is designed to capture the most significant features of a transit signal and stellar parameters through the self-attention mechanism. In addition to model prediction, we take advantage of attention map inspection, obtaining a more interpretable DL approach. Thus, we can identify the relevance of each element to differentiate a transit signal from false positives, simplifying the manual examination of candidates. We show that our architecture achieves competitive results concerning the CNNs applied for recognizing exoplanetary transit signals in data from the TESS telescope. Based on these results, we demonstrate that applying this state-of-the-art DL model to light curves can be a powerful technique for transit signal detection while offering a level of interpretability.

In recent decades, machine learning has provided valuable models and algorithms for processing and extracting knowledge from time-series surveys. Different classifiers have been proposed and performed to an excellent standard. Nevertheless, few papers have tackled the data shift problem in labeled training sets, which occurs when there is a mismatch between the data distribution in the training set and the testing set. This drawback can damage the prediction performance in unseen data. Consequently, we propose a scalable and easily adaptable approach based on an informative regularization and an ad-hoc training procedure to mitigate the shift problem during the training of a multi-layer perceptron for RR Lyrae classification. We collect ranges for characteristic features to construct a symbolic representation of prior knowledge, which was used to model the informative regularizer component. Simultaneously, we design a two-step back-propagation algorithm to integrate this knowledge into the neural network, whereby one step is applied in each epoch to minimize classification error, while another is applied to ensure regularization. Our algorithm defines a subset of parameters (a mask) for each loss function. This approach handles the forgetting effect, which stems from a trade-off between these loss functions (learning from data versus learning expert knowledge) during training. Experiments were conducted using recently proposed shifted benchmark sets for RR Lyrae stars, outperforming baseline models by up to 3\% through a more reliable classifier. Our method provides a new path to incorporate knowledge from characteristic features into artificial neural networks to manage the underlying data shift problem.