Improved Digital Therapy for Developmental Pediatrics using Domain-Specific Artificial Intelligence: Machine Learning Study (Preprint)

2020 ◽  
Author(s):  
Peter Washington ◽  
Haik Kalantarian ◽  
Jack Kent ◽  
Arman Husic ◽  
Aaron Kline ◽  
...  
Keyword(s):  
State Of The Art ◽  
Video Data ◽  
Emotion Detection ◽  
Emotion Classification ◽  
Web Interface ◽  
Single Class ◽  
Domain Specific ◽  
Precision Health ◽  
Digital Healthcare ◽  
Behavioral Conditions

BACKGROUND Automated emotion classification could aid those who struggle to recognize emotion, including children with developmental behavioral conditions such as autism. However, most computer vision emotion recognition models are trained on adult affect and therefore underperform when used on child faces. OBJECTIVE We designed a strategy to gamify the collection and the labeling of child affect data in an effort to boost the performance of automatic child emotion detection to a level closer to what will be needed for digital healthcare approaches. METHODS We leveraged our prototype therapeutic smartphone game, GuessWhat, which was designed in large part for children with developmental and behavioral conditions, to gamify the secure collection of video data of children expressing a variety of emotions prompted by the game. Independently, we created a secure web interface to gamify the human labeling effort HollywoodSquares, tailored for use by any qualified labeler. We gathered and labeled 2,155 videos, 39,968 emotion frames, and 106,001 labels on all images. With this drastically expanded pediatric emotion centric database (>30x larger than existing public pediatric affect datasets), we trained a pediatric emotion classification convolutional neural network (CNN) classifier of happy, sad, surprised, fearful, angry, disgust, and neutral expressions in children. RESULTS The classifier achieved 66.9% balanced accuracy and 67.4% F1-score on the entirety of CAFE as well as 79.1% balanced accuracy and 78.0% F1-score on CAFE Subset A, a subset containing at least 60% human agreement on emotions labels. This performance is at least 10% higher than all previously published classifiers, the best of which reached 56.0% balanced accuracy even when combining “anger” and “disgust” into a single class. CONCLUSIONS This work validates that mobile games designed for pediatric therapies can generate high volumes of domain-relevant datasets to train state of the art classifiers to perform tasks highly relevant to precision health efforts.

scholarly journals DialogueRNN: An Attentive RNN for Emotion Detection in Conversations

2019 ◽  
Vol 33 ◽  
pp. 6818-6825 ◽  
Author(s):  
Navonil Majumder ◽  
Soujanya Poria ◽  
Devamanyu Hazarika ◽  
Rada Mihalcea ◽  
Alexander Gelbukh ◽  
...  
Keyword(s):  
Neural Networks ◽  
Social Media ◽  
Recurrent Neural Networks ◽  
Opinion Mining ◽  
State Of The Art ◽  
Emotion Detection ◽  
Emotion Classification ◽  
Argumentation Mining ◽  
Consumer Feedback ◽  
The Individual

Emotion detection in conversations is a necessary step for a number of applications, including opinion mining over chat history, social media threads, debates, argumentation mining, understanding consumer feedback in live conversations, and so on. Currently systems do not treat the parties in the conversation individually by adapting to the speaker of each utterance. In this paper, we describe a new method based on recurrent neural networks that keeps track of the individual party states throughout the conversation and uses this information for emotion classification. Our model outperforms the state-of-the-art by a significant margin on two different datasets.

scholarly journals Digi-HTA: Health technology assessment framework for digital healthcare services

2019 ◽  
Vol 11 (4) ◽  
Author(s):  
Jari Haverinen ◽  
Niina Keränen ◽  
Petra Falkenbach ◽  
Anna Maijala ◽  
Timo Kolehmainen ◽  
...  
Keyword(s):  
Health Technology Assessment ◽  
Technology Assessment ◽  
State Of The Art ◽  
Health Technology ◽  
Healthcare Services ◽  
The State ◽  
Systematic Evaluation ◽  
Health Technologies ◽  
Digital Healthcare ◽  
And Robotics

Health technology assessment (HTA) refers to the systematic evaluation of the properties, effects, and/or impacts of health technology. The main purpose of the assessment is to inform decisionmakers in order to better support the introduction of new health technologies. New digital healthcare solutions like mHealth, artificial intelligence (AI), and robotics have brought with them a great potential to further develop healthcare services, but their introduction should follow the same criteria as that of other healthcare methods. They must provide evidence-based benefits and be safe to use, and their impacts on patients and organizations need to be clarified. The first objective of this study was to describe the state-of-the-art HTA methods for mHealth, AI, and robotics. The second objective of this study was to evaluate the domains needed in the assessment. The final aim was to develop an HTA framework for digital healthcare services to support the introduction of novel technologies into Finnish healthcare. In this study, the state-of-the-art HTA methods were evaluated using a literature review and interviews. It was noted that some good practices already existed, but the overall picture showed that further development is still needed, especially in the AI and robotics fields. With the cooperation of professionals, key aspects and domains that should be taken into account to make fast but comprehensive assessments were identified. Based on this information, we created a new framework which supports the HTA process for digital healthcare services. The framework was named Digi-HTA.

scholarly journals BioALBERT: A Simple and Effective Pre-trained Language Model for Biomedical Named Entity Recognition

2020 ◽  
Author(s):  
Usman Naseem ◽  
Matloob Khushi ◽  
Vinay Reddy ◽  
Sakthivel Rajendran ◽  
Imran Razzak ◽  
...  
Keyword(s):  
State Of The Art ◽  
Language Model ◽  
Named Entity Recognition ◽  
Training Data ◽  
Entity Recognition ◽  
Future Research ◽  
Named Entity ◽  
Domain Specific ◽  
Context Dependent ◽  
Biomedical Named Entity Recognition

Abstract Background: In recent years, with the growing amount of biomedical documents, coupled with advancement in natural language processing algorithms, the research on biomedical named entity recognition (BioNER) has increased exponentially. However, BioNER research is challenging as NER in the biomedical domain are: (i) often restricted due to limited amount of training data, (ii) an entity can refer to multiple types and concepts depending on its context and, (iii) heavy reliance on acronyms that are sub-domain specific. Existing BioNER approaches often neglect these issues and directly adopt the state-of-the-art (SOTA) models trained in general corpora which often yields unsatisfactory results. Results: We propose biomedical ALBERT (A Lite Bidirectional Encoder Representations from Transformers for Biomedical Text Mining) - bioALBERT - an effective domain-specific pre-trained language model trained on huge biomedical corpus designed to capture biomedical context-dependent NER. We adopted self-supervised loss function used in ALBERT that targets on modelling inter-sentence coherence to better learn context-dependent representations and incorporated parameter reduction strategies to minimise memory usage and enhance the training time in BioNER. In our experiments, BioALBERT outperformed comparative SOTA BioNER models on eight biomedical NER benchmark datasets with four different entity types. The performance is increased for; (i) disease type corpora by 7.47% (NCBI-disease) and 10.63% (BC5CDR-disease); (ii) drug-chem type corpora by 4.61% (BC5CDR-Chem) and 3.89 (BC4CHEMD); (iii) gene-protein type corpora by 12.25% (BC2GM) and 6.42% (JNLPBA); and (iv) Species type corpora by 6.19% (LINNAEUS) and 23.71% (Species-800) is observed which leads to a state-of-the-art results. Conclusions: The performance of proposed model on four different biomedical entity types shows that our model is robust and generalizable in recognizing biomedical entities in text. We trained four different variants of BioALBERT models which are available for the research community to be used in future research.

Feature Matching-based Approaches to Improve the Robustness of Android Visual GUI Testing

2022 ◽  
Vol 31 (2) ◽  
pp. 1-32
Author(s):  
Luca Ardito ◽  
Andrea Bottino ◽  
Riccardo Coppola ◽  
Fabrizio Lamberti ◽  
Francesco Manigrasso ◽  
...  
Keyword(s):  
Computer Vision ◽  
Feature Matching ◽  
State Of The Art ◽  
Design Of Algorithms ◽  
Computational Burden ◽  
Domain Specific ◽  
Gui Testing ◽  
Wide Range ◽  
Full Screen ◽  
Feature Based

In automated Visual GUI Testing (VGT) for Android devices, the available tools often suffer from low robustness to mobile fragmentation, leading to incorrect results when running the same tests on different devices. To soften these issues, we evaluate two feature matching-based approaches for widget detection in VGT scripts, which use, respectively, the complete full-screen snapshot of the application ( Fullscreen ) and the cropped images of its widgets ( Cropped ) as visual locators to match on emulated devices. Our analysis includes validating the portability of different feature-based visual locators over various apps and devices and evaluating their robustness in terms of cross-device portability and correctly executed interactions. We assessed our results through a comparison with two state-of-the-art tools, EyeAutomate and Sikuli. Despite a limited increase in the computational burden, our Fullscreen approach outperformed state-of-the-art tools in terms of correctly identified locators across a wide range of devices and led to a 30% increase in passing tests. Our work shows that VGT tools’ dependability can be improved by bridging the testing and computer vision communities. This connection enables the design of algorithms targeted to domain-specific needs and thus inherently more usable and robust.

Word Sense Disambiguation

2013 ◽  
pp. 22-51
Author(s):  
Pushpak Bhattacharyya ◽  
Mitesh Khapra
Keyword(s):  
State Of The Art ◽  
Word Sense Disambiguation ◽  
Current Trend ◽  
General Purpose ◽  
Word Sense ◽  
Domain Specific ◽  
Knowledge Based ◽  
Current State ◽  
Sense Disambiguation ◽  
State Of Affairs

This chapter discusses the basic concepts of Word Sense Disambiguation (WSD) and the approaches to solving this problem. Both general purpose WSD and domain specific WSD are presented. The first part of the discussion focuses on existing approaches for WSD, including knowledge-based, supervised, semi-supervised, unsupervised, hybrid, and bilingual approaches. The accuracy value for general purpose WSD as the current state of affairs seems to be pegged at around 65%. This has motivated investigations into domain specific WSD, which is the current trend in the field. In the latter part of the chapter, we present a greedy neural network inspired algorithm for domain specific WSD and compare its performance with other state-of-the-art algorithms for WSD. Our experiments suggest that for domain-specific WSD, simply selecting the most frequent sense of a word does as well as any state-of-the-art algorithm.

scholarly journals State of the Art of Underwater Active Optical 3D Scanners

Sensors ◽  
2019 ◽  
Vol 19 (23) ◽  
pp. 5161 ◽  
Author(s):  
Miguel Castillón ◽  
Albert Palomer ◽  
Josep Forest ◽  
Pere Ridao
Keyword(s):  
State Of The Art ◽  
Robotic Systems ◽  
Underwater Imaging ◽  
Maintenance And Repair ◽  
Safety Issues ◽  
Domain Specific ◽  
Light Sensing ◽  
Vision Sensors ◽  
3D Scanners ◽  
Quantitative Performance

Underwater inspection, maintenance and repair (IMR) operations are being increasingly robotized in order to reduce safety issues and costs. These robotic systems rely on vision sensors to perform fundamental tasks, such as navigation and object recognition and manipulation. Especially, active optical 3D scanners are commonly used due to the domain-specific challenges of underwater imaging. This paper presents an exhaustive survey on the state of the art of optical 3D underwater scanners. A literature review on light projection and light-sensing technologies is presented. Moreover, quantitative performance comparisons of underwater 3D scanners present in the literature and commercial products are carried out.

Image Features from Morphological Scale-Spaces

2011 ◽  
pp. 32-79
Author(s):  
Sébastien Lefèvre
Keyword(s):  
Data Mining ◽  
Performance Evaluation ◽  
Video Processing ◽  
State Of The Art ◽  
Image Features ◽  
Video Data ◽  
Multimedia Data ◽  
Multimedia Data Mining ◽  
Shot Detection ◽  
Scale Spaces

Video processing and segmentation are important stages for multimedia data mining, especially with the advance and diversity of video data available. The aim of this chapter is to introduce researchers, especially new ones, to the “video representation, processing, and segmentation techniques”. This includes an easy and smooth introduction, followed by principles of video structure and representation, and then a state-of-the-art of the segmentation techniques focusing on the shot-detection. Performance evaluation and common issues are also discussed before concluding the chapter.

scholarly journals A user-centered approach for detecting emotions with low-cost sensors

2020 ◽  
Vol 79 (47-48) ◽  
pp. 35885-35907
Author(s):  
Rita Francese ◽  
Michele Risi ◽  
Genoveffa Tortora
Keyword(s):  
Artificial Intelligence ◽  
Detection System ◽  
Low Cost ◽  
Affective State ◽  
Classification Performance ◽  
Emotion Detection ◽  
Emotion Classification ◽  
User Perceptions ◽  
Machine Learning Classifiers ◽  
User Centered

AbstractDetecting emotions is very useful in many fields, from health-care to human-computer interaction. In this paper, we propose an iterative user-centered methodology for supporting the development of an emotion detection system based on low-cost sensors. Artificial Intelligence techniques have been adopted for emotion classification. Different kind of Machine Learning classifiers have been experimentally trained on the users’ biometrics data, such as hearth rate, movement and audio. The system has been developed in two iterations and, at the end of each of them, the performance of classifiers (MLP, CNN, LSTM, Bidirectional-LSTM and Decision Tree) has been compared. After the experiment, the SAM questionnaire is proposed to evaluate the user’s affective state when using the system. In the first experiment we gathered data from 47 participants, in the second one an improved version of the system has been trained and validated by 107 people. The emotional analysis conducted at the end of each iteration suggests that reducing the device invasiveness may affect the user perceptions and also improve the classification performance.

scholarly journals A RESTful middleware for AI controlled sensors, actuators and smart devices

2019 ◽  
Vol 11 (7) ◽  
pp. 2963-2986 ◽  
Author(s):  
Nikos Dipsis ◽  
Kostas Stathis
Keyword(s):  
Smart Home ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Smart Devices ◽  
Machine Learning Algorithm ◽  
Concrete Case ◽  
Domain Specific ◽  
Sensor Actuator ◽  
Current State

Abstract The numerous applications of internet of things (IoT) and sensor networks combined with specialized devices used in each has led to a proliferation of domain specific middleware, which in turn creates interoperability issues between the corresponding architectures and the technologies used. But what if we wanted to use a machine learning algorithm to an IoT application so that it adapts intelligently to changes of the environment, or enable a software agent to enrich with artificial intelligence (AI) a smart home consisting of multiple and possibly incompatible technologies? In this work we answer these questions by studying a framework that explores how to simplify the incorporation of AI capabilities to existing sensor-actuator networks or IoT infrastructures making the services offered in such settings smarter. Towards this goal we present eVATAR+, a middleware that implements the interactions within the context of such integrations systematically and transparently from the developers’ perspective. It also provides a simple and easy to use interface for developers to use. eVATAR+ uses JAVA server technologies enhanced by mediator functionality providing interoperability, maintainability and heterogeneity support. We exemplify eVATAR+ with a concrete case study and we evaluate the relative merits of our approach by comparing our work with the current state of the art.

Current and future methodologies for quantitative analysis of information transfer in sign language and gesture data

2017 ◽  
Vol 40 ◽  
Author(s):  
Evie Malaia
Keyword(s):  
Quantitative Analysis ◽  
Data Collection ◽  
Sign Language ◽  
Motion Capture ◽  
Information Transfer ◽  
State Of The Art ◽  
Video Data ◽  
Noninvasive Methods ◽  
Video Recordings ◽  
Biological Differentiation

AbstractState-of-the-art methods of analysis of video data now include motion capture and optical flow from video recordings. These techniques allow for biological differentiation between visual communication and noncommunicative motion, enabling further inquiry into neural bases of communication. The requirements for additional noninvasive methods of data collection and automatic analysis of natural gesture and sign language are discussed.

Sign in / Sign up

Export Citation Format

Share Document