Cognitive and neurological impairments are very common, but only a small proportion of affected individuals are diagnosed and treated, partly because of the high costs associated with frequent screening. Detecting pre-illness stages and analyzing the progression of neurological disorders through effective and efficient intelligent systems can be beneficial for timely diagnosis and early intervention. We propose using Large Language Models to extract features from free dialogues to detect cognitive decline. These features comprise high-level reasoning content-independent features (such as comprehension, decreased awareness, increased distraction, and memory problems). Our solution comprises (i) preprocessing, (ii) feature engineering via Natural Language Processing techniques and prompt engineering, (iii) feature analysis and selection to optimize performance, and (iv) classification, supported by automatic explainability. We also explore how to improve Chatgpt's direct cognitive impairment prediction capabilities using the best features in our models. Evaluation metrics obtained endorse the effectiveness of a mixed approach combining feature extraction with Chatgpt and a specialized Machine Learning model to detect cognitive decline within free-form conversational dialogues with older adults. Ultimately, our work may facilitate the development of an inexpensive, non-invasive, and rapid means of detecting and explaining cognitive decline.
相關內容
Iris recognition is widely acknowledged for its exceptional accuracy in biometric authentication, traditionally relying on near-infrared (NIR) imaging. Recently, visible spectrum (VIS) imaging via accessible smartphone cameras has been explored for biometric capture. However, a thorough study of iris recognition using smartphone-captured 'High-Quality' VIS images and cross-spectral matching with previously enrolled NIR images has not been conducted. The primary challenge lies in capturing high-quality biometrics, a known limitation of smartphone cameras. This study introduces a novel Android application designed to consistently capture high-quality VIS iris images through automated focus and zoom adjustments. The application integrates a YOLOv3-tiny model for precise eye and iris detection and a lightweight Ghost-Attention U-Net (G-ATTU-Net) for segmentation, while adhering to ISO/IEC 29794-6 standards for image quality. The approach was validated using smartphone-captured VIS and NIR iris images from 47 subjects, achieving a True Acceptance Rate (TAR) of 96.57% for VIS images and 97.95% for NIR images, with consistent performance across various capture distances and iris colors. This robust solution is expected to significantly advance the field of iris biometrics, with important implications for enhancing smartphone security.
Cross-sectional incidence estimation based on recency testing has become a widely used tool in HIV research. Recently, this method has gained prominence in HIV prevention trials to estimate the "placebo" incidence that participants might experience without preventive treatment. The application of this approach faces challenges due to non-representative sampling, as individuals aware of their HIV-positive status may be less likely to participate in screening for an HIV prevention trial. To address this, a recent phase 3 trial excluded individuals based on whether they have had a recent HIV test. To the best of our knowledge, the validity of this approach has yet to be studied. In our work, we investigate the performance of cross-sectional HIV incidence estimation when excluding individuals based on prior HIV tests in realistic trial settings. We develop a statistical framework that incorporates a testing-based criterion and possible non-representative sampling. We introduce a metric we call the effective mean duration of recent infection (MDRI) that mathematically quantifies bias in incidence estimation. We conduct an extensive simulation study to evaluate incidence estimator performance under various scenarios. Our findings reveal that when screening attendance is affected by knowledge of HIV status, incidence estimators become unreliable unless all individuals with recent HIV tests are excluded. Additionally, we identified a trade-off between bias and variability: excluding more individuals reduces bias from non-representative sampling but in many cases increases the variability of incidence estimates. These findings highlight the need for caution when applying testing-based criteria and emphasize the importance of refining incidence estimation methods to improve the design and evaluation of future HIV prevention trials.
Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adaptable class-agnostic strategies. However, these strategies come with their own set of limitations, such as the need for manual exemplar input and multiple passes for multiple categories, resulting in significant inefficiencies. This paper introduces a more practical approach enabling simultaneous counting of multiple object categories using an open-vocabulary framework. Our solution, OmniCount, stands out by using semantic and geometric insights (priors) from pre-trained models to count multiple categories of objects as specified by users, all without additional training. OmniCount distinguishes itself by generating precise object masks and leveraging varied interactive prompts via the Segment Anything Model for efficient counting. To evaluate OmniCount, we created the OmniCount-191 benchmark, a first-of-its-kind dataset with multi-label object counts, including points, bounding boxes, and VQA annotations. Our comprehensive evaluation in OmniCount-191, alongside other leading benchmarks, demonstrates OmniCount's exceptional performance, significantly outpacing existing solutions. The project webpage is available at //mondalanindya.github.io/OmniCount.
Individual fairness guarantees are often desirable properties to have, but they become hard to formalize when the dataset contains outliers. Here, we investigate the problem of developing an individually fair $k$-means clustering algorithm for datasets that contain outliers. That is, given $n$ points and $k$ centers, we want that for each point which is not an outlier, there must be a center within the $\frac{n}{k}$ nearest neighbours of the given point. While a few of the recent works have looked into individually fair clustering, this is the first work that explores this problem in the presence of outliers for $k$-means clustering. For this purpose, we define and solve a linear program (LP) that helps us identify the outliers. We exclude these outliers from the dataset and apply a rounding algorithm that computes the $k$ centers, such that the fairness constraint of the remaining points is satisfied. We also provide theoretical guarantees that our method leads to a guaranteed approximation of the fair radius as well as the clustering cost. We also demonstrate our techniques empirically on real-world datasets.
Batch effects are inevitable in large-scale metabolomics. Prior to formal data analysis, batch effect correction (BEC) is applied to prevent from obscuring biological variations, and batch effect evaluation (BEE) is used for correction assessment. However, existing BEE algorithms neglect covariances between the variables, and existing BEC algorithms might fail to adequately correct the covariances. Therefore, we resort to recent advancements in high-dimensional statistics, and respectively propose "quality control-based simultaneous tests (QC-ST)" and "covariance correction (CoCo)". Validated by the simulation data, QC-ST can simultaneously detect the statistical significance of QC samples' mean vectors and covariance matrices across different batches, and has a satisfactory statistical performance in empirical sizes, empirical powers, and computational speed. Then, we apply four QC-based BEC algorithms to two large cohort datasets, and find that extreme gradient boost (XGBoost) performs best in relative standard deviation (RSD) and dispersion-ratio (D-ratio). After prepositive BEC, if QC-ST still suggests that batch effects between some two batches are significant, CoCo should be implemented. And after CoCo (if necessary), the four metrics (i.e., RSD, D-ratio, classification performance, and QC-ST) might be further improved. In summary, under the guidance of QC-ST, we can develop a matching strategy to integrate multiple BEC algorithms more rationally and flexibly, and minimize batch effects for reliable biological conclusions.
Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-grained entity types. In this paper, we argue that the implicitly entailed extrinsic and intrinsic dependencies between labels can provide critical knowledge to tackle the above challenges. To this end, we propose \emph{Label Reasoning Network(LRN)}, which sequentially reasons fine-grained entity labels by discovering and exploiting label dependencies knowledge entailed in the data. Specifically, LRN utilizes an auto-regressive network to conduct deductive reasoning and a bipartite attribute graph to conduct inductive reasoning between labels, which can effectively model, learn and reason complex label dependencies in a sequence-to-set, end-to-end manner. Experiments show that LRN achieves the state-of-the-art performance on standard ultra fine-grained entity typing benchmarks, and can also resolve the long tail label problem effectively.
Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific behaviors. Inspired by principles of behavioral testing in software engineering, we introduce CheckList, a task-agnostic methodology for testing NLP models. CheckList includes a matrix of general linguistic capabilities and test types that facilitate comprehensive test ideation, as well as a software tool to generate a large and diverse number of test cases quickly. We illustrate the utility of CheckList with tests for three tasks, identifying critical failures in both commercial and state-of-art models. In a user study, a team responsible for a commercial sentiment analysis model found new and actionable bugs in an extensively tested model. In another user study, NLP practitioners with CheckList created twice as many tests, and found almost three times as many bugs as users without it.
For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target language, in this paper, we propose to fine-tune the learned model with a few similar examples given a test case, which could benefit the prediction by leveraging the structural and semantic information conveyed in such similar examples. To this end, we present a meta-learning algorithm to find a good model parameter initialization that could fast adapt to the given test case and propose to construct multiple pseudo-NER tasks for meta-training by computing sentence similarities. To further improve the model's generalization ability across different languages, we introduce a masking scheme and augment the loss function with an additional maximum term during meta-training. We conduct extensive experiments on cross-lingual named entity recognition with minimal resources over five target languages. The results show that our approach significantly outperforms existing state-of-the-art methods across the board.
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convolutional filters on 2D reshapings of entity and relation embeddings in order to capture rich interactions between their components. However, the number of interactions that ConvE can capture is limited. In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE. InteractE is based on three key ideas -- feature permutation, a novel feature reshaping, and circular convolution. Through extensive experiments, we find that InteractE outperforms state-of-the-art convolutional link prediction baselines on FB15k-237. Further, InteractE achieves an MRR score that is 9%, 7.5%, and 23% better than ConvE on the FB15k-237, WN18RR and YAGO3-10 datasets respectively. The results validate our central hypothesis -- that increasing feature interaction is beneficial to link prediction performance. We make the source code of InteractE available to encourage reproducible research.
Events are happening in real-world and real-time, which can be planned and organized occasions involving multiple people and objects. Social media platforms publish a lot of text messages containing public events with comprehensive topics. However, mining social events is challenging due to the heterogeneous event elements in texts and explicit and implicit social network structures. In this paper, we design an event meta-schema to characterize the semantic relatedness of social events and build an event-based heterogeneous information network (HIN) integrating information from external knowledge base, and propose a novel Pair-wise Popularity Graph Convolutional Network (PP-GCN) based fine-grained social event categorization model. We propose a Knowledgeable meta-paths Instances based social Event Similarity (KIES) between events and build a weighted adjacent matrix as input to the PP-GCN model. Comprehensive experiments on real data collections are conducted to compare various social event detection and clustering tasks. Experimental results demonstrate that our proposed framework outperforms other alternative social event categorization techniques.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191