Document-level information extraction (IE) tasks have recently begun to be revisited in earnest using the end-to-end neural network techniques that have been successful on their sentence-level IE counterparts. Evaluation of the approaches, however, has been limited in a number of dimensions. In particular, the precision/recall/F1 scores typically reported provide few insights on the range of errors the models make. We build on the work of Kummerfeld and Klein (2013) to propose a transformation-based framework for automating error analysis in document-level event and (N-ary) relation extraction. We employ our framework to compare two state-of-the-art document-level template-filling approaches on datasets from three domains; and then, to gauge progress in IE since its inception 30 years ago, vs. four systems from the MUC-4 (1992) evaluation.

Given a discriminating neural network, the problem of fairness improvement is to systematically reduce discrimination without significantly scarifies its performance (i.e., accuracy). Multiple categories of fairness improving methods have been proposed for neural networks, including pre-processing, in-processing and post-processing. Our empirical study however shows that these methods are not always effective (e.g., they may improve fairness by paying the price of huge accuracy drop) or even not helpful (e.g., they may even worsen both fairness and accuracy). In this work, we propose an approach which adaptively chooses the fairness improving method based on causality analysis. That is, we choose the method based on how the neurons and attributes responsible for unfairness are distributed among the input attributes and the hidden neurons. Our experimental evaluation shows that our approach is effective (i.e., always identify the best fairness improving method) and efficient (i.e., with an average time overhead of 5 minutes).

The Medical Internet of Things, a recent technological advancement in medicine, is incredibly helpful in providing real-time monitoring of health metrics. This paper presents a non-invasive IoT system that tracks patients' emotions, especially those with an autism spectrum disorder. With a few affordable sensors and cloud computing services, the individual's heart rates are monitored and analyzed to study the effects of change in sweat and heartbeats per minute for different emotions. Under normal resting conditions of the individual, the proposed system could detect the right emotion using machine learning algorithms with a performance of up to 92% accuracy. The result of the proposed approach is comparable with the state-of-the-art solutions in medical IoT.

Research articles are being shared in increasing numbers on multiple online platforms. Although the scholarly impact of these articles has been widely studied, the online interest determined by how long the research articles are shared online remains unclear. Being cognizant of how long a research article is mentioned online could be valuable information to the researchers. In this paper, we analyzed multiple social media platforms on which users share and/or discuss scholarly articles. We built three clusters for papers, based on the number of yearly online mentions having publication dates ranging from the year 1920 to 2016. Using the online social media metrics for each of these three clusters, we built machine learning models to predict the long-term online interest in research articles. We addressed the prediction task with two different approaches: regression and classification. For the regression approach, the Multi-Layer Perceptron model performed best, and for the classification approach, the tree-based models performed better than other models. We found that old articles are most evident in the contexts of economics and industry (i.e., patents). In contrast, recently published articles are most evident in research platforms (i.e., Mendeley) followed by social media platforms (i.e., Twitter).

More than 50 million people worldwide are living with different types of neurodegenerative dementias including Alzheimer's Disease (AD), Vascular Dementia, Lewy Body Dementia, and Frontotemporal Lobar Dementia [1]. These are among the leading global neurodegenerative diseases and have notable economic impacts on individuals and societies [2]. To mitigate the impact of neurodegenerative dementias on older adults and help them plan for the future [3], early detection of dementia is necessary. It would help older adults at the early stages of the disease seek out different intervention programs [4], including psycho-social interventions (e.g., walking programs and art therapy) [5], non-pharmaceutical intervention programs (e.g., music interventions [6]) as well as clinical interventions so that they can maintain their quality of life [7] at the normal level and slow down disease progression.

The rise of social media platforms provides an unbounded, infinitely rich source of aggregate knowledge of the world around us, both historic and real-time, from a human perspective. The greatest challenge we face is how to process and understand this raw and unstructured data, go beyond individual observations and see the "big picture"--the domain of Situation Awareness. We provide an extensive survey of Artificial Intelligence research, focusing on microblog social media data with applications to Situation Awareness, that gives the seminal work and state-of-the-art approaches across six thematic areas: Crime, Disasters, Finance, Physical Environment, Politics, and Health and Population. We provide a novel, unified methodological perspective, identify key results and challenges, and present ongoing research directions.

In detecting malicious websites, a common approach is the use of blacklists which are not exhaustive in themselves and are unable to generalize to new malicious sites. Detecting newly encountered malicious websites automatically will help reduce the vulnerability to this form of attack. In this study, we explored the use of ten machine learning models to classify malicious websites based on lexical features and understand how they generalize across datasets. Specifically, we trained, validated, and tested these models on different sets of datasets and then carried out a cross-datasets analysis. From our analysis, we found that K-Nearest Neighbor is the only model that performs consistently high across datasets. Other models such as Random Forest, Decision Trees, Logistic Regression, and Support Vector Machines also consistently outperform a baseline model of predicting every link as malicious across all metrics and datasets. Also, we found no evidence that any subset of lexical features generalizes across models or datasets. This research should be relevant to cybersecurity professionals and academic researchers as it could form the basis for real-life detection systems or further research work.

Sequential manipulation tasks require a robot to perceive the state of an environment and plan a sequence of actions leading to a desired goal state. In such tasks, the ability to reason about spatial relations among object entities from raw sensor inputs is crucial in order to determine when a task has been completed and which actions can be executed. In this work, we propose SORNet (Spatial Object-Centric Representation Network), a framework for learning object-centric representations from RGB images conditioned on a set of object queries, represented as image patches called canonical object views. With only a single canonical view per object and no annotation, SORNet generalizes zero-shot to object entities whose shape and texture are both unseen during training. We evaluate SORNet on various spatial reasoning tasks such as spatial relation classification and relative direction regression in complex tabletop manipulation scenarios and show that SORNet significantly outperforms baselines including state-of-the-art representation learning techniques. We also demonstrate the application of the representation learned by SORNet on visual-servoing and task planning for sequential manipulation on a real robot.

Place recognition is key to Simultaneous Localization and Mapping (SLAM) and spatial perception. However, a place recognition in the wild often suffers from erroneous predictions due to image variations, e.g., changing viewpoints and street appearance. Integrating uncertainty estimation into the life cycle of place recognition is a promising method to mitigate the impact of variations on place recognition performance. However, existing uncertainty estimation approaches in this vein are either computationally inefficient (e.g., Monte Carlo dropout) or at the cost of dropped accuracy. This paper proposes STUN, a self-teaching framework that learns to simultaneously predict the place and estimate the prediction uncertainty given an input image. To this end, we first train a teacher net using a standard metric learning pipeline to produce embedding priors. Then, supervised by the pretrained teacher net, a student net with an additional variance branch is trained to finetune the embedding priors and estimate the uncertainty sample by sample. During the online inference phase, we only use the student net to generate a place prediction in conjunction with the uncertainty. When compared with place recognition systems that are ignorant to the uncertainty, our framework features the uncertainty estimation for free without sacrificing any prediction accuracy. Our experimental results on the large-scale Pittsburgh30k dataset demonstrate that STUN outperforms the state-of-the-art methods in both recognition accuracy and the quality of uncertainty estimation.

Telemedicine utilization was accelerated during the COVID-19 pandemic, and skin conditions were a common use case. However, the quality of photographs sent by patients remains a major limitation. To address this issue, we developed TrueImage 2.0, an artificial intelligence (AI) model for assessing patient photo quality for telemedicine and providing real-time feedback to patients for photo quality improvement. TrueImage 2.0 was trained on 1700 telemedicine images annotated by clinicians for photo quality. On a retrospective dataset of 357 telemedicine images, TrueImage 2.0 effectively identified poor quality images (Receiver operator curve area under the curve (ROC-AUC) =0.78) and the reason for poor quality (Blurry ROC-AUC=0.84, Lighting issues ROC-AUC=0.70). The performance is consistent across age, gender, and skin tone. Next, we assessed whether patient-TrueImage 2.0 interaction led to an improvement in submitted photo quality through a prospective clinical pilot study with 98 patients. TrueImage 2.0 reduced the number of patients with a poor-quality image by 68.0%.