Search

While deep learning-based computer-aided diagnosis for skin lesion image analysis is approaching dermatologists' performance levels, there are several works showing that incorporating additional features such as shape priors, texture, color constancy, and illumination further improves the lesion diagnosis performance. In this work, we look at another clinically useful feature, skin lesion elevation, and investigate the feasibility of predicting and leveraging skin lesion elevation labels. Specifically, we use a deep learning model to predict image-level lesion elevation labels from 2D skin lesion images. We test the elevation prediction accuracy on the derm7pt dataset, and use the elevation prediction model to estimate elevation labels for images from five other datasets: ISIC 2016, 2017, and 2018 Challenge datasets, MSK, and DermoFit. We evaluate cross-domain generalization by using these estimated elevation labels as auxiliary inputs to diagnosis models, and show that these improve the classification performance, with AUROC improvements of up to 6.29% and 2.69% for dermoscopic and clinical images, respectively. The code is publicly available at https://github.com/sfu-mial/LesionElevation., Comment: Medical Image Computing and Computer-Assisted Intervention (MICCAI) ISIC Skin Image Analysis Workshop (MICCAI ISIC) 2024; 12 pages, 2 tables, 4 figures

Variability in medical image segmentation, arising from annotator preferences, expertise, and their choice of tools, has been well documented. While the majority of multi-annotator segmentation approaches focus on modeling annotator-specific preferences, they require annotator-segmentation correspondence. In this work, we introduce the problem of segmentation style discovery, and propose StyleSeg, a segmentation method that learns plausible, diverse, and semantically consistent segmentation styles from a corpus of image-mask pairs without any knowledge of annotator correspondence. StyleSeg consistently outperforms competing methods on four publicly available skin lesion segmentation (SLS) datasets. We also curate ISIC-MultiAnnot, the largest multi-annotator SLS dataset with annotator correspondence, and our results show a strong alignment, using our newly proposed measure AS2, between the predicted styles and annotator preferences. The code and the dataset are available at https://github.com/sfu-mial/StyleSeg., Comment: Medical Image Computing and Computer-Assisted Intervention (MICCAI) ISIC Skin Image Analysis Workshop (MICCAI ISIC) 2024; 13 pages, 2 tables, 3 figures

Large Language Models (LLMs) have demonstrated remarkable zero-shot and few-shot capabilities in unseen tasks, including context-grounded question answering (QA) in English. However, the evaluation of LLMs' capabilities in non-English languages for context-based QA is limited by the scarcity of benchmarks in non-English languages. To address this gap, we introduce Indic-QA, the largest publicly available context-grounded question-answering dataset for 11 major Indian languages from two language families. The dataset comprises both extractive and abstractive question-answering tasks and includes existing datasets as well as English QA datasets translated into Indian languages. Additionally, we generate a synthetic dataset using the Gemini model to create question-answer pairs given a passage, which is then manually verified for quality assurance. We evaluate various multilingual Large Language Models and their instruction-fine-tuned variants on the benchmark and observe that their performance is subpar, particularly for low-resource languages. We hope that the release of this dataset will stimulate further research on the question-answering abilities of LLMs for low-resource languages.

The electronic, structural, optical, and thermoelectric properties of the Cs2O cubic structure have been investigated using density functional theory (DFT). The calculations utilize a full relativistic version of the full-potential augmented plane-wave plus local orbitals method, which is based on density functional theory, employing both the GGA and LDA approximations. Additionally, we employed the GGA proposed by Trans-Blaha (GGA-mBJ) for band structure computations, revealing the indirect band gap nature of Cs2O. The optical properties are also addressed by computing the refractive index, extinction coefficient, and complex dielectric tensor. The electrical conductivity, Seebeck coefficient, and thermal conductivity exhibit temperature-dependent variations, indicating the formation of a thermoelectric material. Our findings indicate that the compound under investigation is categorized as a p-type semiconductor, with the majority of charge carriers responsible for conduction being holes rather than electrons., Comment: 21 pages

The structural, electronic, and dielectric (optical) properties of graphene-like 2D MgO monolayer have been explored through first-principles calculations under bi-axial tensile and compressive mechanical strain within a range of -10% to +10%. Our findings revealed that the pristine MgO monolayer is an indirect band gap semiconducting material and the semiconducting mature of MgO monolayer remains consistent under both compressive and tensile mechanical strain. This nature of MgO is confirmed through partial density of states (PDOS) as well as electronic band structure. PDOS exhibits the contribution of different atomic orbitals in bond formation and nature of bond, while band structure provides insight into electron transitions between energy levels of valance and conduction bands. All optical parameters (dielectric function, reflectivity, energy loss, refractive index, extinction coefficient and absorption) are plotted in an energy range 0-15 eV. Within this energy interval, MgO possesses the highest value of the refractive index (2.13) at 3.12 eV energy. Also, a detailed analysis of changes in the geometrical structure of MgO monolayer is provided., Comment: 6 figures

In this paper, Dirac Quantization of $3D$ gravity in the first-order formalism is attempted where instead of quantizing the connection and triad fields, the connection and the triad 1-forms themselves are quantized. The exterior derivative operator on the space of differential forms is treated as the `time' derivative to compute the momenta conjugate to these 1-forms. This manner of quantization allows one to compute the transition amplitude in $3D$ gravity which has a close, but not exact, match with the transition amplitude computed via LQG techniques. This inconsistency is interpreted as being due to the non-quantizable nature of differential geometry., Comment: 12 pages, 3 figures, Added my grant number in the acknowledgement

The quantum speed limits (QSLs) set fundamental lower bounds on the time required for a quantum system to evolve from a given initial state to a final state. In this work, we investigate CP violation and the mass hierarchy problem of neutrino oscillations in matter using the QSL time as a key analytical tool. We examine the QSL time for the unitary evolution of two- and three-flavor neutrino states, both in vacuum and in the presence of matter. Two-flavor neutrino oscillations are used as a precursor to their three-flavor counterparts. We further compute the QSL time for neutrino state evolution and entanglement in terms of neutrino survival and oscillation probabilities, which are experimentally measurable quantities in neutrino experiments. A difference in the QSL time between the normal and inverted mass hierarchy scenarios, for neutrino state evolution as well as for entanglement, under the effect of a CP violation phase is observed. Our results are illustrated using energy-varying sets of accelerator neutrino sources from experiments such as T2K, NOvA, and DUNE. Notably, three-flavor neutrino oscillations in constant matter density exhibit faster state evolution across all these neutrino experiments in the normal mass hierarchy scenario. Additionally, we observe fast entanglement growth in DUNE assuming a normal mass hierarchy., Comment: v1: 18 pages, 10 figures. Comments welcome

First-principles based calculations were executed to investigate the sensing properties of ammonia gas molecules on two-dimensional pristine black phosphorene towards its application as a gas sensor and related applications. We discuss in detail, the interaction of ammonia gas molecules on the phosphorene single sheet through the structural change analysis, electronic band gap, Bader charge transfer, and density-of-states calculations. Our calculations indicate that the phosphorene could be used as a detector of ammonia, where good sensitivity and very short recovery time at room temperature have confirmed the potential use of phosphorene in the detection of ammonia., Comment: 21 pages, Figures 8

The least squares method provides the best-fit curve by minimizing the total squares error. In this work, we provide the modified least squares method based on the fractional orthogonal polynomials that belong to the space $M_{n}^{\lambda} := \text{span}\{1,x^{\lambda},x^{2\lambda},\ldots,x^{n\lambda}\},~\lambda \in (0,2]$. Numerical experiments demonstrate how to solve different problems using the modified least squares method. Moreover, the results show the advantage of the modified least squares method compared to the classical least squares method. Furthermore, we discuss the various applications of the modified least squares method in the fields like fractional differential/integral equations and machine learning.

The rapid evolution of the fashion industry increasingly intersects with technological advancements, particularly through the integration of generative AI. This study introduces a novel generative pipeline designed to transform the fashion design process by employing latent diffusion models. Utilizing ControlNet and LoRA fine-tuning, our approach generates high-quality images from multimodal inputs such as text and sketches. We leverage and enhance state-of-the-art virtual try-on datasets, including Multimodal Dress Code and VITON-HD, by integrating sketch data. Our evaluation, utilizing metrics like FID, CLIP Score, and KID, demonstrates that our model significantly outperforms traditional stable diffusion models. The results not only highlight the effectiveness of our model in generating fashion-appropriate outputs but also underscore the potential of diffusion models in revolutionizing fashion design workflows. This research paves the way for more interactive, personalized, and technologically enriched methodologies in fashion design and representation, bridging the gap between creative vision and practical application., Comment: 9 pages, 8 figures

The last couple of years have seen an ever-increasing interest in using different Ising solvers, like Quantum annealers, Coherent Ising machines, and Oscillator-based Ising machines, for solving tough computational problems in various domains. Although the simulations predict massive performance improvements for several tough computational problems, the real implementations of the Ising solvers tend to have limited precision, which can cause significant performance deterioration. This paper presents a novel methodology for mapping the problem on the Ising solvers to artificially increase the effective precision. We further evaluate our method for the Multiple-Input-Multiple-Output signal detection problem., Comment: version 1.0

Reconfigurable antenna multiple-input multiple-output (MIMO) is a promising technology for upcoming 6G communication systems. In this paper, we deal with the problem of configuration selection for reconfigurable antenna MIMO by leveraging Coherent Ising Machines (CIMs). By adopting the CIM as a heuristic solver for the Ising problem, the optimal antenna configuration that maximizes the received signal-to-noise ratio is investigated. A mathematical framework that converts the selection problem into a CIM-compatible unconstrained quadratic formulation is presented. Numerical studies show that the proposed CIM-based design outperforms classical counterparts and achieves near-optimal performance (similar to exponentially complex exhaustive searching) while ensuring polynomial complexity.

Quantum Annealing (QA)-accelerated MIMO detection is an emerging research approach in the context of NextG wireless networks. The opportunity is to enable large MIMO systems and thus improve wireless performance. The approach aims to leverage QA to expedite the computation required for theoretically optimal but computationally-demanding Maximum Likelihood detection to overcome the limitations of the currently deployed linear detectors. This paper presents X-ResQ, a QA-based MIMO detector system featuring fine-grained quantum task parallelism that is uniquely enabled by the Reverse Annealing (RA) protocol. Unlike prior designs, X-ResQ has many desirable system properties for a parallel QA detector and has effectively improved detection performance as more qubits are assigned. In our evaluations on a state-of-the-art quantum annealer, fully parallel X-ResQ achieves near-optimal throughput (over 10 bits/s/Hz) for $4\times6$ MIMO with 16-QAM using six levels of parallelism with 240 qubits and $220~\mu$s QA compute time, achieving 2.5--5$\times$ gains compared against other tested detectors. For more comprehensive evaluations, we implement and evaluate X-ResQ in the non-quantum digital setting. This non-quantum X-ResQ demonstration showcases the potential to realize ultra-large $1024\times1024$ MIMO, significantly outperforming other MIMO detectors, including the state-of-the-art RA detector classically implemented in the same way., Comment: 22 pages

The remarkable progress of deep learning in dermatological tasks has brought us closer to achieving diagnostic accuracies comparable to those of human experts. However, while large datasets play a crucial role in the development of reliable deep neural network models, the quality of data therein and their correct usage are of paramount importance. Several factors can impact data quality, such as the presence of duplicates, data leakage across train-test partitions, mislabeled images, and the absence of a well-defined test partition. In this paper, we conduct meticulous analyses of two popular dermatological image datasets: DermaMNIST and Fitzpatrick17k, uncovering these data quality issues, measure the effects of these problems on the benchmark results, and propose corrections to the datasets. Besides ensuring the reproducibility of our analysis, by making our analysis pipeline and the accompanying code publicly available, we aim to encourage similar explorations and to facilitate the identification and addressing of potential data quality issues in other large datasets., Comment: 36 pages, 8 figures, 3 tables

Twisted 2D layered materials have garnered a lot of attention recently as a class of 2D materials whose interlayer interactions and electronic properties are dictated by the relative rotation / twist angle between the adjacent layers. In this work, we explore a prototype of such a twisted 2D system, artificially stacked twisted bilayer graphene (TBLG), where we probe the changes in the interlayer interactions and electron-phonon scattering pathways as the twist angle is varied from 0{\deg} to 30{\deg}, using Raman spectroscopy. The long range Moir\'e potential of the superlattice gives rise to additional intravalley and intervalley scattering of the electrons in TBLG which have been investigated through their Raman signatures. The density functional theory (DFT) calculations of the electronic band structure of the TBLG superlattices was found to be in agreement with the resonant Raman excitations across the van Hove singularities in the valence and conduction bands predicted for TBLG due to hybridization of bands from the two layers. We also observe that the relative rotation between the graphene layers has a marked influence on the second order overtone and combination Raman modes signalling a commensurate-incommensurate transition in TBLG as the twist angle increases. This serves as a convenient and rapid characterization tool to determine the degree of commensurability in TBLG systems.

Traditional methods of collecting user feedback through transit surveys are often time-consuming, resource intensive, and costly. In this paper, we propose a novel NLP-based framework that harnesses the vast, abundant, and inexpensive data available on social media platforms like Twitter to understand users' perceptions of various service issues. Twitter, being a microblogging platform, hosts a wealth of real-time user-generated content that often includes valuable feedback and opinions on various products, services, and experiences. The proposed framework streamlines the process of gathering and analyzing user feedback without the need for costly and time-consuming user feedback surveys using two techniques. First, it utilizes few-shot learning for tweet classification within predefined categories, allowing effective identification of the issues described in tweets. It then employs a lexicon-based sentiment analysis model to assess the intensity and polarity of the tweet sentiments, distinguishing between positive, negative, and neutral tweets. The effectiveness of the framework was validated on a subset of manually labeled Twitter data and was applied to the NYC subway system as a case study. The framework accurately classifies tweets into predefined categories related to safety, reliability, and maintenance of the subway system and effectively measured sentiment intensities within each category. The general findings were corroborated through a comparison with an agency-run customer survey conducted in the same year. The findings highlight the effectiveness of the proposed framework in gauging user feedback through inexpensive social media data to understand the pain points of the transit system and plan for targeted improvements., Comment: Word Count: 5515 words + 3 table (250 words per table) = 6265 words

In this paper, a high-order approximation to Caputo-type time-fractional diffusion equations involving an initial-time singularity of the solution is proposed. At first, we employ a numerical algorithm based on the Lagrange polynomial interpolation to approximate the Caputo derivative on the non-uniform mesh. Then truncation error rate and the optimal grading constant of the approximation on a graded mesh are obtained as $\min\{4-\alpha,r\alpha\}$ and $\frac{4-\alpha}{\alpha}$, respectively, where $\alpha\in(0,1)$ is the order of fractional derivative and $r\geq 1$ is the mesh grading parameter. Using this new approximation, a difference scheme for the Caputo-type time-fractional diffusion equation on graded temporal mesh is formulated. The scheme proves to be uniquely solvable for general $r$. Then we derive the unconditional stability of the scheme on uniform mesh. The convergence of the scheme, in particular for $r=1$, is analyzed for non-smooth solutions and concluded for smooth solutions. Finally, the accuracy of the scheme is verified by analyzing the error through a few numerical examples., Comment: 18 pages, 2 figures and 7 tables

This work aims to explore the community structure of Santiago de Chile by analyzing the movement patterns of its residents. We use a dataset containing the approximate locations of home and work places for a subset of anonymized residents to construct a network that represents the movement patterns within the city. Through the analysis of this network, we aim to identify the communities or sub-cities that exist within Santiago de Chile and gain insights into the factors that drive the spatial organization of the city. We employ modularity optimization algorithms and clustering techniques to identify the communities within the network. Our results present that the novelty of combining community detection algorithms with segregation tools provides new insights to further the understanding of the complex geography of segregation during working hours., Comment: 6 pages excluding References