Search

There is an increasing global emphasis on information accessibility, with numerous researchers actively developing automated tools to detect and repair accessibility issues, thereby ensuring that individuals with diverse abilities can independently access software products and services. However, current research still encounters significant challenges in two key areas: the absence of a comprehensive taxonomy of accessibility issue types, and the lack of comprehensive analysis of the capabilities of detection and repair tools, as well as the status of corresponding datasets. To address these challenges, this paper introduces the Accessibility Issue Analysis (AIA) framework. Utilizing this framework, we develop a comprehensive taxonomy that categorizes 55 types of accessibility issues across four pivotal dimensions: Perceivability, Operability, Understandability, and Robustness. This taxonomy has been rigorously recognized through a questionnaire survey (n=130). Building on this taxonomy, we conduct an in-depth analysis of existing detection and repair tools, as well as the status of corresponding datasets. In terms of tools, our findings indicate that 14 detection tools can identify 31 issue types, achieving a 56.3% rate (31/55). Meanwhile, 9 repair tools address just 13 issue types, with a 23.6% rate. In terms of datasets, those for detection tools cover 21 issue types, at a 38.1% coverage rate, whereas those for repair tools cover only 7 types, at a 12.7% coverage rate., Comment: 16 pages, 3 figures

DNA microarray gene-expression data has been widely used to identify cancerous gene signatures. Microarray can increase the accuracy of cancer diagnosis and prognosis. However, analyzing the large amount of gene expression data from microarray chips pose a challenge for current machine learning researches. One of the challenges lie within classification of healthy and cancerous tissues is high dimensionality of gene expressions. High dimensionality decreases the accuracy of the classification. This research aims to apply a hybrid model of Genetic Algorithm and Neural Network to overcome the problem during subset selection of informative genes. Whereby, a Genetic Algorithm (GA) reduced dimensionality during feature selection and then a Multi-Layer perceptron Neural Network (MLP) is applied to classify selected genes. The performance evaluated by considering to the accuracy and the number of selected genes. Experimental results show the proposed method suggested high accuracy and minimum number of selected genes in comparison with other machine learning algorithms.

This paper presents an approach to joint wireless and computing resource management in slice-enabled metaverse networks, addressing the challenges of inter-slice and intra-slice resource allocation in the presence of in-network computing. We formulate the problem as a mixed-integer nonlinear programming (MINLP) problem and derive an optimal solution using standard optimization techniques. Through extensive simulations, we demonstrate that our proposed method significantly improves system performance by effectively balancing the allocation of radio and computing resources across multiple slices. Our approach outperforms existing benchmarks, particularly in scenarios with high user demand and varying computational tasks.

Banded energy distributions of H$^{+}$, O$^{++}$, S$^{+++}$, and O$^+$ or S$^{++}$ ions between 100 eV to ~20 keV are consistently observed in Jupiter's magnetosphere mapping to M-shells between M=10-20. The bands correspond to flux enhancements at similar speeds for different ion species, providing the first evidence of simultaneous bounce-resonant acceleration of multiple ion species in Jupiter's magnetosphere. Ion enhancements occur for energies at which the bounce frequencies of the trapped ions matched integer harmonics of the System-III corotation frequency. The observations highlight a previously unknown interaction between corotation and bounce motion of <10 keV energy ions that is a fundamental and persistent process occurring in Jupiter's magnetosphere.

A pivotal attribute of 5G networks is their capability to cater to diverse application requirements. This is achieved by creating logically isolated virtual networks, or slices, with distinct service level agreements (SLAs) tailored to specific use cases. However, efficiently allocating resources to maintain slice SLA is challenging due to varying traffic and QoS requirements. Traditional peak traffic-based resource allocation leads to over-provisioning, as actual traffic rarely peaks. Additionally, the complex relationship between resource allocation and QoS in end-to-end slices spanning different network segments makes conventional optimization techniques impractical. Existing approaches in this domain use network models or simulations and various optimization methods but struggle with optimality, tractability, and generalizability across different slice types. In this paper, we propose MicroOpt, a novel framework that leverages a differentiable neural network-based slice model with gradient descent for resource optimization and Lagrangian decomposition for QoS constraint satisfaction. We evaluate MicroOpt against two state-of-the-art approaches using an open-source 5G testbed with real-world traffic traces. Our results demonstrate up to 21.9% improvement in resource allocation compared to these approaches across various scenarios, including different QoS thresholds and dynamic slice traffic., Comment: 12 pages, 10 figures

Motivated by the generation by optical pulses of non-thermal distributions of nuclear spins in quantum dots we investigate the effect of optical pulses applied to Bardeen-Cooper-Schrieffer (BCS) superconductors. Using time-dependent mean-field theory formulated with Anderson pseudospins, we study the electronic configurations and the energy deposited in the system by optical pulses. The pulses are included by Peierls substitution and we study short rectangular pulses as well as idealized $\delta$ pulses. Already a few and even a single pulse generates highly non-trivial distributions of electron expectation values which we simulate numerically and explain analytically based on the linearization of the equations of motion. These results suggest so far unexplored experimental possibilities for the optical control of superconducting states., Comment: 14 pages, 19 figures

The potential health risks of cement dust exposure are increasingly raising concern worldwide as the cement industry expands in response to rising cement demand. This necessitates the need to determine the nature of the risks in order to develop appropriate measures. This study determined the effects of cement dust exposure on the weight and blood glucose levels of people residing or working around a cement company in Sokoto, Nigeria. Demographic information was obtained using questionnaires from 72 participants, which included age, gender, educational level, exposure hours, occupation, and lifestyle. The blood glucose levels and body mass index (BMI) were measured using a Fine Test glucometer and a mechanical scale, respectively. The results showed that most of the people living or working around the cement company were middle-aged men (31-40; 42.06%) with a primary (33.33%) or secondary (45.83%) school education. It showed that 30 (41.69%) of the participants were overweight while 5 (6.94%) were obese. Additionally, 52.78% of the participants were diabetic while 31.94% were prediabetic. Participants that were exposed for long hours (> 15 hours per day) were the most diabetic (20% of the participants), followed by smokers (15%), and artisans (7%). It can be concluded that exposure to cement dust from the company increased the risk of overweight, obesity, and hyperglycemia among the participants. These health risks were worsened by daily long hours of exposure, smoking, and artisanal pollutant exposure. Human settlements and artisans should not be located near the cement company, and the company should minimize pollutant emissions., Comment: accept

Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ oracle complexity to find an $\varepsilon$-stationary point. Some works indicate that this complexity can be improved to $\mathcal{O}(\varepsilon^{-3})$ when the loss gradient is Lipschitz continuous. The question of achieving enhanced convergence rates under distinct conditions, remains unresolved. In this work, we address this question for optimization problems that are nonconvex in the minimization variable and strongly concave or Polyak-Lojasiewicz (PL) in the maximization variable. We introduce novel bias-corrected momentum algorithms utilizing efficient Hessian-vector products. We establish convergence conditions and demonstrate a lower iteration complexity of $\mathcal{O}(\varepsilon^{-3})$ for the proposed algorithms. The effectiveness of the method is validated through applications to robust logistic regression using real-world datasets.

In this report, we propose three novel methods for developing a sound event detection (SED) model for the DCASE 2024 Challenge Task 4. First, we propose an auxiliary decoder attached to the final convolutional block to improve feature extraction capabilities while reducing dependency on embeddings from pre-trained large models. The proposed auxiliary decoder operates independently from the main decoder, enhancing performance of the convolutional block during the initial training stages by assigning a different weight strategy between main and auxiliary decoder losses. Next, to address the time interval issue between the DESED and MAESTRO datasets, we propose maximum probability aggregation (MPA) during the training step. The proposed MPA method enables the model's output to be aligned with soft labels of 1 s in the MAESTRO dataset. Finally, we propose a multi-channel input feature that employs various versions of logmel and MFCC features to generate time-frequency pattern. The experimental results demonstrate the efficacy of these proposed methods in a view of improving SED performance by achieving a balanced enhancement across different datasets and label types. Ultimately, this approach presents a significant step forward in developing more robust and flexible SED models, Comment: DCASE 2024 challenge Task4, 4 pages

Recent developments in multimodal large language models (MLLMs) have spurred significant interest in their potential applications across various medical imaging domains. On the one hand, there is a temptation to use these generative models to synthesize realistic-looking medical image data, while on the other hand, the ability to identify synthetic image data in a pool of data is also significantly important. In this study, we explore the potential of the Gemini (\textit{gemini-1.0-pro-vision-latest}) and GPT-4V (gpt-4-vision-preview) models for medical image analysis using two modalities of medical image data. Utilizing synthetic and real imaging data, both Gemini AI and GPT-4V are first used to classify real versus synthetic images, followed by an interpretation and analysis of the input images. Experimental results demonstrate that both Gemini and GPT-4 could perform some interpretation of the input images. In this specific experiment, Gemini was able to perform slightly better than the GPT-4V on the classification task. In contrast, responses associated with GPT-4V were mostly generic in nature. Our early investigation presented in this work provides insights into the potential of MLLMs to assist with the classification and interpretation of retinal fundoscopy and lung X-ray images. We also identify key limitations associated with the early investigation study on MLLMs for specialized tasks in medical image analysis., Comment: Accepted in Fifth IEEE Workshop on Artificial Intelligence for HealthCare, IEEE 25th International Conference on Information Reuse and Integration for Data Science

Text-to-speech (TTS) development for African languages such as Luganda is still limited, primarily due to the scarcity of high-quality, single-speaker recordings essential for training TTS models. Prior work has focused on utilizing the Luganda Common Voice recordings of multiple speakers aged between 20-49. Although the generated speech is intelligible, it is still of lower quality than the model trained on studio-grade recordings. This is due to the insufficient data preprocessing methods applied to improve the quality of the Common Voice recordings. Furthermore, speech convergence is more difficult to achieve due to varying intonations, as well as background noise. In this paper, we show that the quality of Luganda TTS from Common Voice can improve by training on multiple speakers of close intonation in addition to further preprocessing of the training data. Specifically, we selected six female speakers with close intonation determined by subjectively listening and comparing their voice recordings. In addition to trimming out silent portions from the beginning and end of the recordings, we applied a pre-trained speech enhancement model to reduce background noise and enhance audio quality. We also utilized a pre-trained, non-intrusive, self-supervised Mean Opinion Score (MOS) estimation model to filter recordings with an estimated MOS over 3.5, indicating high perceived quality. Subjective MOS evaluations from nine native Luganda speakers demonstrate that our TTS model achieves a significantly better MOS of 3.55 compared to the reported 2.5 MOS of the existing model. Moreover, for a fair comparison, our model trained on six speakers outperforms models trained on a single-speaker (3.13 MOS) or two speakers (3.22 MOS). This showcases the effectiveness of compensating for the lack of data from one speaker with data from multiple speakers of close intonation to improve TTS quality., Comment: Presented at the AfricaNLP workshop at ICLR 2024

Vibrations of damaged bearings are manifested as modulations in the amplitude of the generated vibration signal, making envelope analysis an effective approach for discriminating between healthy and abnormal vibration patterns. Motivated by this, we introduce a low-complexity method for vibration-based condition monitoring (VBCM) of rolling bearings based on envelope analysis. In the proposed method, the instantaneous amplitude (envelope) and instantaneous frequency of the vibration signal are jointly utilized to facilitate three novel envelope representations: instantaneous amplitude-frequency mapping (IAFM), instantaneous amplitude-frequency correlation (IAFC), and instantaneous energy-frequency distribution (IEFD). Maintaining temporal information, these representations effectively capture energy-frequency variations that are unique to the condition of the bearing, thereby enabling the extraction of discriminative features with high sensitivity to variations in operational conditions. Accordingly, six new highly discriminative features are engineered from these representations, capturing and characterizing their shapes. The experimental results show outstanding performance in detecting and diagnosing various fault types, demonstrating the effectiveness of the proposed method in capturing unique variations in energy and frequency between healthy and faulty bearings. Moreover, the proposed method has moderate computational complexity, meeting the requirements of real-time applications. Further, the Python code of the proposed method is made public to support collaborative research efforts and ensure the reproducibility of the presented work

The encounter between the Jovian co-rotating plasma and Ganymede gives rise to electromagnetic waves that propagate along the magnetic field lines and accelerate particles by resonant or non-resonant wave-particle interaction. They ultimately precipitate into Jupiter's atmosphere and trigger auroral emissions. In this study, we use Juno/JADE, Juno/UVS data, and magnetic field line tracing to characterize the properties of electrons accelerated by the Ganymede-magnetosphere interaction in the far-field region. We show that the precipitating energy flux exhibits an exponential decay as a function of downtail distance from the moon, with an e-folding value of 29{\deg}, consistent with previous UV observations from the Hubble Space Telescope (HST). We characterize the electron energy distributions and show that two distributions exist. Electrons creating the Main Alfv\'en Wing (MAW) spot and the auroral tail always have broadband distribution and a mean characteristic energy of 2.2 keV while in the region connected to the Transhemispheric Electron Beam (TEB) spot the electrons are distributed non-monotonically, with a higher characteristic energy above 10 keV. Based on the observation of bidirectional electron beams, we suggest that Juno was located within the acceleration region during the 11 observations reported. We thus estimate that the acceleration region is extended, at least, between an altitude of 0.5 and 1.3 Jupiter radius above the 1-bar surface. Finally, we estimate the size of the interaction region in the Ganymede orbital plane using far-field measurements. These observations provide important insights for the study of particle acceleration processes involved in moon-magnetosphere interactions., Comment: Accepted for publication in JGR: Space Physics

PCPDTBT nanostructures have been synthesized via template-assisted method and polymer-melt technique. The morphological, optical and structural properties of the PCPDTBT have been investigated. Melting polymer was used as a driving force to infiltrate the Anodic Aluminum Oxide (AAO) template in which the applied temperatures are 200, 250, 300, 350, 400 and 450 Celsius respectively. The melting time duration is set constant for 30 minutes for each of those melting temperatures. Nanowires constructions have been produced at all melting temperature however based the morphological investigation, only the first two melting temperatures, 200 and 250, that can serve the structural without any broken noticed on the Raman measurement. The optical and structural properties are also confirm these facts., Comment: 25 pages

Blood cell classification and counting are vital for the diagnosis of various blood-related diseases, such as anemia, leukemia, and thrombocytopenia. The manual process of blood cell classification and counting is time-consuming, prone to errors, and labor-intensive. Therefore, we have proposed a DL based automated system for blood cell classification and counting from microscopic blood smear images. We classify total of nine types of blood cells, including Erythrocyte, Erythroblast, Neutrophil, Basophil, Eosinophil, Lymphocyte, Monocyte, Immature Granulocytes, and Platelet. Several preprocessing steps like image resizing, rescaling, contrast enhancement and augmentation are utilized. To segment the blood cells from the entire microscopic images, we employed the U-Net model. This segmentation technique aids in extracting the region of interest (ROI) by removing complex and noisy background elements. Both pixel-level metrics such as accuracy, precision, and sensitivity, and object-level evaluation metrics like Intersection over Union (IOU) and Dice coefficient are considered to comprehensively evaluate the performance of the U-Net model. The segmentation model achieved impressive performance metrics, including 98.23% accuracy, 98.40% precision, 98.25% sensitivity, 95.97% Intersection over Union (IOU), and 97.92% Dice coefficient. Subsequently, a watershed algorithm is applied to the segmented images to separate overlapped blood cells and extract individual cells. We have proposed a BloodCell-Net approach incorporated with custom light weight convolutional neural network (LWCNN) for classifying individual blood cells into nine types. Comprehensive evaluation of the classifier's performance is conducted using metrics including accuracy, precision, recall, and F1 score. The classifier achieved an average accuracy of 97.10%, precision of 97.19%, recall of 97.01%, and F1 score of 97.10%., Comment: 24 pages, 7 tables and 13 Figures