Search

This article explores the use of natural language processing (NLP) techniques to identify incarceration status in electronic health records (EHR) in emergency department settings. The study developed and validated NLP models to accurately identify incarceration status from clinical notes, which could potentially help address health disparities and tailor interventions for individuals with a history of incarceration. The study found that the Clinical-Longformer NLP model was effective in accurately identifying incarceration history, although it had limitations in distinguishing temporal labels. It is important to approach patients in a non-judgmental manner and confirm incarceration history before offering resources to avoid stigma. The NLP model can serve as a screening tool, but manual confirmation is recommended to avoid false positives or misplacements of electronic labels in patient files. [Extracted from the article]

Background: Chat Generative Pre-trained Transformer (ChatGPT) is a 175-billion-parameter natural language processing model that can generate conversation-style responses to user input. Objective: This study aimed to evaluate the performance of ChatGPT on questions within the scope of the United States Medical Licensing Examination Step 1 and Step 2 exams, as well as to analyze responses for user interpretability. Methods: We used 2 sets of multiple-choice questions to evaluate ChatGPT's performance, each with questions pertaining to Step 1 and Step 2. The first set was derived from AMBOSS, a commonly used question bank for medical students, which also provides statistics on question difficulty and the performance on an exam relative to the user base. The second set was the National Board of Medical Examiners (NBME) free 120 questions. ChatGPT's performance was compared to 2 other large language models, GPT-3 and InstructGPT. The text output of each ChatGPT response was evaluated across 3 qualitative metrics: logical justification of the answer selected, presence of information internal to the question, and presence of information external to the question. Results: Of the 4 data sets, AMBOSS-Step1, AMBOSS-Step2, NBME-Free-Step1, and NBME-Free-Step2, ChatGPT achieved accuracies of 44% (44/100), 42% (42/100), 64.4% (56/87), and 57.8% (59/102), respectively. ChatGPT outperformed InstructGPT by 8.15% on average across all data sets, and GPT-3 performed similarly to random chance. The model demonstrated a significant decrease in performance as question difficulty increased (P=.01) within the AMBOSS-Step1 data set. We found that logical justification for ChatGPT's answer selection was present in 100% of outputs of the NBME data sets. Internal information to the question was present in 96.8% (183/189) of all questions. The presence of information external to the question was 44.5% and 27% lower for incorrect answers relative to correct answers on the NBME-Free-Step1 (P<.001) and NBME-Free-Step2 (P=.001) data sets, respectively. Conclusions: ChatGPT marks a significant improvement in natural language processing models on the tasks of medical question answering. By performing at a greater than 60% threshold on the NBME-Free-Step-1 data set, we show that the model achieves the equivalent of a passing score for a third-year medical student. Additionally, we highlight ChatGPT's capacity to provide logic and informational context across the majority of answers. These facts taken together make a compelling case for the potential applications of ChatGPT as an interactive medical education tool to support learning. [ABSTRACT FROM AUTHOR]

Current search engines in most geospatial data portals tend to induce users to focus on one single-data characteristic dimension (e.g. popularity and release date). This approach largely fails to take account of users’ multidimensional preferences for geospatial data, and hence may likely result in a less than optimal user experience in discovering the most applicable dataset. This study reports a machine learning framework to address the ranking challenge, the fundamental obstacle in geospatial data discovery, by (1) identifying a number of ranking features of geospatial data to represent users’ multidimensional preferences by considering semantics, user behavior, spatial similarity, and static dataset metadata attributes; (2) applying a machine learning method to automatically learn a ranking function; and (3) proposing a system architecture to combine existing search-oriented open source software, semantic knowledge base, ranking feature extraction, and machine learning algorithm. Results show that the machine learning approach outperforms other methods, in terms of both precision at K and normalized discounted cumulative gain. As an early attempt of utilizing machine learning to improve the search ranking in the geospatial domain, we expect this work to set an example for further research and open the door towards intelligent geospatial data discovery. [ABSTRACT FROM AUTHOR]

It is challenging to find relevant data for research and development purposes in the geospatial big data era. One long-standing problem in data discovery is locating, assimilating and utilizing the semantic context for a given query. Most research in the geospatial domain has approached this problem in one of two ways: building a domain-specific ontology manually or discovering automatically, semantic relationships using metadata and machine learning techniques. The former relies on rich expert knowledge but is static, costly and labor intensive, whereas the second is automatic and prone to noise. An emerging trend in information science takes advantage of large-scale user search histories, which are dynamic but subject to user- and crawler-generated noise. Leveraging the benefits of these three approaches and avoiding their weaknesses, a novel methodology is proposed to (1) discover vocabulary-based semantic relationships from user search histories and clickstreams, (2) refine the similarity calculation methods from existing ontologies and (3) integrate the results of ontology, metadata, user search history and clickstream analysis to better determine their semantic relationships. An accuracy assessment by domain experts for the similarity values indicates an 83% overall accuracy for the top 10 related terms over randomly selected sample queries. This research functions as an example for building vocabulary-based semantic relationships for different geographical domains to improve various aspects of data discovery, including the accuracy of the vocabulary relationships of commonly used search terms. [ABSTRACT FROM PUBLISHER]

The problem of similarity learning is relevant to many data mining applications, such as recommender systems, classification, and retrieval. This problem is particularly challenging in the context of networks, which contain different aspects such as the topological structure, content, and user supervision. These different aspects need to be combined effectively, in order to create a holistic similarity function. In particular, while most similarity learning methods in networks such as SimRank utilize the topological structure, the user supervision and content are rarely considered. In this paper, a factorized similarity learning (FSL) is proposed to integrate the link, node content, and user supervision into a uniform framework. This is learned by using matrix factorization, and the final similarities are approximated by the span of low-rank matrices. The proposed framework is further extended to a noise-tolerant version by adopting a hinge loss alternatively. To facilitate efficient computation on large-scale data, a parallel extension is developed. Experiments are conducted on the DBLP and CoRA data sets. The results show that FSL is robust and efficient and outperforms the state of the art. The code for the learning algorithm used in our experiments is available at . [ABSTRACT FROM AUTHOR]

We present a semisupervised method for single-pixel classification of hyperspectral images. The proposed method is designed to address the special problematic characteristics of hyperspectral images, namely, high dimensionality of hyperspectral pixels, lack of labeled samples, and spatial variability of spectral signatures. To alleviate these problems, the proposed method features the following components. First, being a semisupervised approach, it exploits the wealth of unlabeled samples in the image by evaluating the confidence probability of the predicted labels, for each unlabeled sample. Second, we propose to jointly optimize the classifier parameters and the dictionary atoms by a task-driven formulation, to ensure that the learned features (sparse codes) are optimal for the trained classifier. Finally, it incorporates spatial information through adding a Laplacian smoothness regularization to the output of the classifier, rather than the sparse codes, making the spatial constraint more flexible. The proposed method is compared with a few comparable methods for classification of several popular data sets, and it produces significantly better classification results. [ABSTRACT FROM PUBLISHER]

The graph construction procedure essentially determines the potentials of those graph-oriented learning algorithms for image analysis. In this paper, we propose a process to build the so-called directed l¹-graph, in which the vertices involve all the samples and the in-going edge weights to each vertex describe its l¹-norm driven reconstruction from the remaining samples and the noise. Then, a series of new algorithms for various machine learning tasks, e.g., data clustering, subspace learning, and semisupervised learning, are derived upon the l¹-graphs. Compared with the conventional k-nearest-neighbor graph and ε-ball graph, the l¹-graph possesses the advantages: 1) greater robustness to data noise, 2) automatic sparsity, and 3) adaptive neighborhood for individual datum. Extensive experiments on three real-world datasets show the consistent superiority of l¹-graph over those classic graphs in data clustering, subspace learning, and semi-supervised learning tasks. [ABSTRACT FROM AUTHOR]

We present a supervised learning approach for object-category specific restoration, recognition, and segmentation of images which are blurred using an unknown kernel. The novelty of this work is a multilayer graphical model which unifies the lowlevel vision task of restoration and the high-level vision task of recognition in a cooperative framework. The graphical model is an interconnected two-layer Markov random field. The restoration layer accounts for the compatibility between sharp and blurred images and models the association between adjacent patches in the sharp image. The recognition layer encodes the entity class and its location in the underlying scene. The potentials are represented using nonparametric kernel densities and are learnt from training data. Inference is performed using nonparametric belief propagation. Experiments demonstrate the effectiveness of our model for the restoration and recognition of blurred license plates as well as face images. [ABSTRACT FROM AUTHOR]

Discusses how reliance on powerful pattern recognition and machine learning techniques is increasing in the field of multimedia retrieval. State of the art in multimedia database management; Association of multimedia content with semantic concepts; Knowledge representations for multimedia content.

Nonnegative matrix factorization (NMF) is a popular technique for finding parts-based, linear representations of nonnegative data. It has been successfully applied in a wide range of applications such as pattern recognition, information retrieval, and computer vision. However, NMF is essentially an unsupervised method and cannot make use of label information. In this paper, we propose a novel semi-supervised matrix decomposition method, called Constrained Nonnegative Matrix Factorization (CNMF), which incorporates the label information as additional constraints. Specifically, we show how explicitly combining label information improves the discriminating power of the resulting matrix decomposition. We explore the proposed CNMF method with two cost function formulations and provide the corresponding update solutions for the optimization problems. Empirical experiments demonstrate the effectiveness of our novel algorithm in comparison to the state-of-the-art approaches through a set of evaluations based on real-world applications. [ABSTRACT FROM PUBLISHER]

Abstract: In this paper, we propose a multiple-metric learning algorithm to learn jointly a set of optimal homogenous/heterogeneous metrics in order to fuse the data collected from multiple sensors for joint classification. The learned metrics have the potential to perform better than the conventional Euclidean metric for classification. Moreover, in the case of heterogenous sensors, the learned multiple metrics can be quite different, which are adapted to each type of sensor. By learning the multiple metrics jointly within a single unified optimization framework, we can learn better metrics to fuse the multi-sensor data for a joint classification. Furthermore, we also exploit multi-metric learning in a kernel induced feature space to capture the non-linearity in the original feature space via kernel mapping. [Copyright &y& Elsevier]

Abstract: We present a novel Gaussianized vector representation for scene images by an unsupervised approach. Each image is first encoded as an ensemble of orderless bag of features. A global Gaussian Mixture Model (GMM) learned from all images is then used to randomly distribute each feature into one Gaussian component by a multinomial trial. The posteriors of the feature on all the Gaussian components serve as the parameters of the multinomial distribution. Finally, the normalized means of the features distributed in every Gaussian component are concatenated to form a supervector, which is a compact representation for each scene image. We prove that these supervectors observe the standard normal distribution. The Gaussianized vector representation is a more generalized form of the widely used histogram representation. Our experiments on scene categorization tasks using this vector representation show significantly improved performance compared with the histogram-of-features representation. This paper is an extended version of our work that won the IBM Best Student Paper Award at the 2008 International Conference on Pattern Recognition (ICPR 2008) (). [Copyright &y& Elsevier]

Abstract: For learning-based tasks such as image classification, the feature dimension is usually very high. The learning is afflicted by the curse of dimensionality as the search space grows exponentially with the dimension. Discriminant-EM (DEM) proposed a framework by applying self-supervised learning in a discriminating subspace. This paper extends the linear DEM to a nonlinear kernel algorithm, Kernel DEM (KDEM), and evaluates KDEM extensively on benchmark image databases and synthetic data. Various comparisons with other state-of-the-art learning techniques are investigated for several tasks of image classification. Extensive results show the effectiveness of our approach. [Copyright &y& Elsevier]

Finding geospatial data has been a big challenge regarding the data size and heterogeneity across various domains. Previous work has explored using machine learning to improve geospatial data search ranking, but it usually relies on training data labelled by subject matter experts, which makes it laborious and costly to apply to scenarios in which data relevancy to a query can change over time. When a user interacts with a search engine, plenteous information is recorded in the log file, which is essentially free, sustainable and up-to-the-minute. In this research, we propose a deep learning-based search ranking framework that can expeditiously update the ranking model through capturing real-time user clickstream data. The contributions of the proposed framework consist of 1) a log parser that can ingest and parse Web logs that record users' behavior in a real-time manner; 2) a set of hypotheses of modelling the relative relevance of data; and 3) a deep learning based ranking model which can be updated dynamically with the increment of user behavior data. Quantitative comparison with a few other machine learning algorithms suggests substantial improvement. • A framework supports real time ranking. • A log processor that can ingest and process from Web logs in a real-time manner. • A set of hypotheses of modelling the relative relevance of data. • A deep learning based ranking algorithm that can be trained incrementally using user behavior data. [ABSTRACT FROM AUTHOR]