Search

Rapid diagnostic tests are crucial for timely disease detection and management, yet accurate interpretation of test results remains challenging. In this study, we propose a novel approach to enhance the accuracy and reliability of rapid diagnostic test result interpretation by integrating artificial intelligence (AI) algorithms, including convolutional neural networks (CNN), within a smartphone-based application. The app enables users to take pictures of their test kits, which YOLOv8 then processes to precisely crop and extract the membrane region, even if the test kit is not centered in the frame or is positioned at the very edge of the image. This capability offers greater accessibility, allowing even visually impaired individuals to capture test images without needing perfect alignment, thus promoting user independence and inclusivity. The extracted image is analyzed by an additional CNN classifier that determines if the results are positive, negative, or invalid, providing users with the results and a confidence level. Through validation experiments with commonly used rapid test kits across various diagnostic applications, our results demonstrate that the synergistic integration of AI significantly improves sensitivity and specificity in test result interpretation. This improvement can be attributed to the extraction of the membrane zones from the test kit images using the state-of-the-art YOLO algorithm. Additionally, we performed SHapley Additive exPlanations (SHAP) analysis to investigate the factors influencing the model's decisions, identifying reasons behind both correct and incorrect classifications. By facilitating the differentiation of genuine test lines from background noise and providing valuable insights into test line intensity and uniformity, our approach offers a robust solution to challenges in rapid test interpretation.

Data is the main fuel of a successful machine learning model. A dataset may contain sensitive individual records e.g. personal health records, financial data, industrial information, etc. Training a model using this sensitive data has become a new privacy concern when someone uses third-party cloud computing. Trained models also suffer privacy attacks which leads to the leaking of sensitive information of the training data. This study is conducted to preserve the privacy of training data in the context of customer churn prediction modeling for the telecommunications industry (TCI). In this work, we propose a framework for privacy-preserving customer churn prediction (PPCCP) model in the cloud environment. We have proposed a novel approach which is a combination of Generative Adversarial Networks (GANs) and adaptive Weight-of-Evidence (aWOE). Synthetic data is generated from GANs, and aWOE is applied on the synthetic training dataset before feeding the data to the classification algorithms. Our experiments were carried out using eight different machine learning (ML) classifiers on three openly accessible datasets from the telecommunication sector. We then evaluated the performance using six commonly employed evaluation metrics. In addition to presenting a data privacy analysis, we also performed a statistical significance test. The training and prediction processes achieve data privacy and the prediction classifiers achieve high prediction performance (87.1\% in terms of F-Measure for GANs-aWOE based Na\"{\i}ve Bayes model). In contrast to earlier studies, our suggested approach demonstrates a prediction enhancement of up to 28.9\% and 27.9\% in terms of accuracy and F-measure, respectively., Comment: 26 pages, 14 tables, 13 figures

Two strings are considered to have parameterized matching when there exists a bijection of the parameterized alphabet onto itself such that it transforms one string to another. Parameterized matching has application in software duplication detection, image processing, and computational biology. We consider the problem for which a pattern $p$, a text $t$ and a mismatch tolerance limit $k$ is given and the goal is to find all positions in text $t$, for which pattern $p$, parameterized matches with $|p|$ length substrings of $t$ with at most $k$ mismatches. Our main result is an algorithm for this problem with $O(\alpha^2 n\log n + n \alpha^2 \sqrt{\alpha} \log \left( n \alpha \right))$ time complexity, where $n = |t|$ and $\alpha = |\Sigma|$ which is improving for $k=\tilde{\Omega}(|\Sigma|^{5/3})$ the algorithm by Hazay, Lewenstein and Sokol. We also present a hashing based probabilistic algorithm for this problem when $k = 1$ with $O \left( n \log n \right)$ time complexity, which we believe is algorithmically beautiful., Comment: 17 pages, 2 figures

This paper extends a previous model for p-i-n GaAs quantum dot solar cells (QDSC) by revising the equation of photocarrier generation rate in quantum dots (QDs) inside the intrinsic region. In our model, we address a notable discrepancy that arose from the previous model where they did not consider the volume of QDs within the intrinsic region, leading to an overestimation of the photocarrier generation rate. Our present model rectifies this by incorporating the volume of quantum dots, resulting in adjustments to the photocarrier generation rate. Additionally, we determine the absorption coefficient of the QDs based on Mie theory for different diameter sizes considering the constant volume fraction of the total number of QDs in the intrinsic region. We observe in our analysis that the absorption spectra of the QDs and host material may overlap in certain cases, although the previous model assumed no overlap. This finding suggests the need for caution when evaluating spectral overlap: if the spectra do not overlap, both the previous and current modified models can be reliably applied. However, in cases of overlap, careful consideration is required to ensure accurate predictions of photocarrier generation. Furthermore, investigating the effect of QD diameter size on the photocarrier generation rate in the intrinsic region, we find that smaller QD sizes result in a higher absorption coefficient as well as a higher generation rate for a constant volume of QDs in the region. Moreover, we establish the optimization of the QDs array size by varying the size and the total volume of QDs to improve the generation rate. Our analysis reveals that a higher volume of QDs and a smaller size of QDs result in the maximum generation rate. From an experimental perspective, we propose that the optimal arrangement of QDs in such solar cells is a 0.5 volume fraction with a QD diameter of 2 nm., Comment: 22 pages, 6 figures

We explore red stellar populations toward the W3 giant molecular cloud through the use of optical-to-infrared (IR) photometry and Gaia DR 3 data, simultaneously characterizing stellar content and properties of dust in the molecular medium. We use a Rayleigh-Jeans Color Excess (RJCE) method modified to de-redden stellar observations of both red giants (RGs) and OB stars, and construct an IR Hertzsprung-Russell diagram validated against the Besanccon Galactic model. Taking advantage of the near-universal IR interstellar extinction law and precise Gaia measurements, we develop a method for obtaining the spectral classification, foreground extinction, and distance moduli of stars, validated by spectroscopically-confirmed OB stars. We constrain the observed parallax and proper motion of OB stars in W3, demonstrating the importance of considering systematic effects in the parallax bias, and assign parallax- and proper motion-based cloud membership to our stellar samples. While it has been assumed that all spectroscopic OB stars are inside the W3 cloud, we find evidence of seven background B stars and three potential runaway OB stars. The methods developed here based on known stellar populations enable us to identify 82 new OB candidates that are confidently within the cloud. We quantify several dust-to-dust empirical correlations, in particular the IR color excess $E(H-[4.5])$ and the optical depth $\tau_1$ of submillimeter dust emission at 1 THz using RGs behind W3, measuring a best fit of $E(H-[4.5]) = (1.07 \pm 0.04) \times 10^3 \, \tau_{1,\,\mathrm{HOTT}} + (0.00 \pm 0.02)$ mags., Comment: accepted for publication in ApJ, 39 pages, 20 figures

Cross-lingual summarization (CLS) is a sophisticated branch in Natural Language Processing that demands models to accurately translate and summarize articles from different source languages. Despite the improvement of the subsequent studies, This area still needs data-efficient solutions along with effective training methodologies. To the best of our knowledge, there is no feasible solution for CLS when there is no available high-quality CLS data. In this paper, we propose a novel data-efficient approach, ConVerSum, for CLS leveraging the power of contrastive learning, generating versatile candidate summaries in different languages based on the given source document and contrasting these summaries with reference summaries concerning the given documents. After that, we train the model with a contrastive ranking loss. Then, we rigorously evaluate the proposed approach against current methodologies and compare it to powerful Large Language Models (LLMs)- Gemini, GPT 3.5, and GPT 4o proving our model performs better for low-resource languages' CLS. These findings represent a substantial improvement in the area, opening the door to more efficient and accurate cross-lingual summarizing techniques.

DNA methylation is a crucial epigenetic marker used in various clocks to predict epigenetic age. However, many existing clocks fail to account for crucial information about CpG sites and their interrelationships, such as co-methylation patterns. We present a novel approach to represent methylation data as a graph, using methylation values and relevant information about CpG sites as nodes, and relationships like co-methylation, same gene, and same chromosome as edges. We then use a Graph Neural Network (GNN) to predict age. Thus our model, GraphAge, leverages both structural and positional information for prediction as well as better interpretation. Although we had to train in a constrained compute setting, GraphAge still showed competitive performance with a Mean Absolute Error (MAE) of 3.207 and a Mean Squared Error (MSE) of 25.277, slightly outperforming the current state of the art. Perhaps more importantly, we utilized GNN explainer for interpretation purposes and were able to unearth interesting insights (e.g., key CpG sites, pathways, and their relationships through Methylation Regulated Networks in the context of aging), which were not possible to 'decode' without leveraging the unique capability of GraphAge to 'encode' various structural relationships. GraphAge has the potential to consume and utilize all relevant information (if available) about an individual that relates to the complex process of aging. So, in that sense, it is one of its kind and can be seen as the first benchmark for a multimodal model that can incorporate all this information in order to close the gap in our understanding of the true nature of aging.

Compared with an extensive list of automotive radar datasets that support autonomous driving, indoor radar datasets are scarce at a smaller scale in the format of low-resolution radar point clouds and usually under an open-space single-room setting. In this paper, we scale up indoor radar data collection using multi-view high-resolution radar heatmap in a multi-day, multi-room, and multi-subject setting, with an emphasis on the diversity of environment and subjects. Referred to as the millimeter-wave multi-view radar (MMVR) dataset, it consists of $345$K multi-view radar frames collected from $25$ human subjects over $6$ different rooms, $446$K annotated bounding boxes/segmentation instances, and $7.59$ million annotated keypoints to support three major perception tasks of object detection, pose estimation, and instance segmentation, respectively. For each task, we report performance benchmarks under two protocols: a single subject in an open space and multiple subjects in several cluttered rooms with two data splits: random split and cross-environment split over $395$ 1-min data segments. We anticipate that MMVR facilitates indoor radar perception development for indoor vehicle (robot/humanoid) navigation, building energy management, and elderly care for better efficiency, user experience, and safety. The MMVR dataset is available at https://doi.org/10.5281/zenodo.12611978., Comment: 26 pages, 25 figures, 10 tables; See https://doi.org/10.5281/zenodo.12611978 to access the MMVR dataset

Parkinson's disease (PD) is a neuro-degenerative disorder that affects movement, speech, and coordination. Timely diagnosis and treatment can improve the quality of life for PD patients. However, access to clinical diagnosis is limited in low and middle income countries (LMICs). Therefore, development of automated screening tools for PD can have a huge social impact, particularly in the public health sector. In this paper, we present PULSAR, a novel method to screen for PD from webcam-recorded videos of the finger-tapping task from the Movement Disorder Society - Unified Parkinson's Disease Rating Scale (MDS-UPDRS). PULSAR is trained and evaluated on data collected from 382 participants (183 self-reported as PD patients). We used an adaptive graph convolutional neural network to dynamically learn the spatio temporal graph edges specific to the finger-tapping task. We enhanced this idea with a multi stream adaptive convolution model to learn features from different modalities of data critical to detect PD, such as relative location of the finger joints, velocity and acceleration of tapping. As the labels of the videos are self-reported, there could be cases of undiagnosed PD in the non-PD labeled samples. We leveraged the idea of Positive Unlabeled (PU) Learning that does not need labeled negative data. Our experiments show clear benefit of modeling the problem in this way. PULSAR achieved 80.95% accuracy in validation set and a mean accuracy of 71.29% (2.49% standard deviation) in independent test, despite being trained with limited amount of data. This is specially promising as labeled data is scarce in health care sector. We hope PULSAR will make PD screening more accessible to everyone. The proposed techniques could be extended for assessment of other movement disorders, such as ataxia, and Huntington's disease.

In this paper, we outline our approach to identify ophthalmic biomarkers from Optical Coherence Tomography (OCT) images presented in the OLIVES dataset, obtained from a diverse range of patients. Using robust augmentations and 5-fold cross-validation, we trained two vision transformer-based models: MaxViT and EVA-02, and ensembled them at inference time. We find MaxViT's use of convolution layers followed by strided attention to be better suited for local feature detection while EVA-02's use of normal attention mechanism and knowledge distillation is better for detecting global features. Our solution brought us the champion title of the IEEE SPS Video and Image Processing (VIP) Cup 2023, achieving a patient-wise F1 score of 0.814 in the first phase and 0.8527 in the second and final phase of the competition, scoring 3.8% higher than the next best solution., Comment: Ablation study results leveraging pseudolabels added in section 3.9