Search

Objective: Pain assessment is of great importance in both clinical research and patient care. Facial expression analysis is becoming a key part of pain detection because it is convenient, automatic, and real-time. The aim of this study is to present a cold pain intensity estimation experiment, investigate the importance of the spatial-temporal information on facial expression based cold pain, and study the performance of the personalized model as well as the generalized model. Methods: A cold pain experiment was carried out and facial expressions from 29 subjects were extracted. Three different architectures (Inception V3, VGG-LSTM, and Convolutional LSTM) were used to estimate three intensities of cold pain: No pain, Moderate pain, and Severe Pain. Architectures with Sequential information were compared with single-frame architecture, showing the importance of spatial-temporal information on pain estimation. The performances of the personalized model and the generalized model were also compared. Results: A mean F1 score of 79.48% was achieved using Convolutional LSTM based on the personalized model. Conclusion: This study demonstrates the potential for the estimation of cold pain intensity from facial expression analysis and shows that the personalized spatial-temporal framework has better performance in cold pain intensity estimation. Significance: This cold pain intensity estimator could allow convenient, automatic, and real-time use to provide continuous objective pain intensity estimations of subjects and patients.

Pain is a health problem of vast dimension that requires prompt diagnosis. However, the evaluation criteria currently used in clinical settings are based on self-rating scales, which are subjective and prone to error. This may cause administering of improper analgesic treatments, either in dosage or in duration. For the scope of providing objective measures of pain and help devising effective therapeutic choices, we designed a personalized platform for sensing and monitoring pain. As input to the platform, visual, speech and physiological clues expressed by the patient during the pain experience are non-invasively measured, then sent to a cloud server to be integrated and analyzed. In this work, preliminary results obtained with the vision-based block of the platform are presented. Because the pain perceived by each individual is highly subjective, once the data are collected from each subject, quantitative descriptors are extracted and personalized selection of relevant features is performed to train a subject-specific regression model. Video sequences of genuine pain felt were tested and weighted accuracy values of 0.81 (0.19) and 0.84 (0.10) were obtained, respectively, for three-class and two-class scenarios, showing benefits and drawbacks of the proposed personalized platform.

This paper concerns personalized sentiment analysis, which aims at improving the prediction of the sentiment expressed in a piece of text by considering individualities. Mostly, this is done by relating to a person’s past expressions (or opinions), however the time gaps between the messages are not considered in the existing works. We argue that the opinion at a specific time point is affected more by recent opinions that contain related content than the earlier or unrelated ones, thus a sentiment model ought to include such information in the analysis. By using a recurrent neural network with an attention layer as a basic model, we introduce three cases to integrate time gaps in the model. Evaluated on Twitter data with frequent users, we have found that the performance is improved the most by including the time information in the Hawkes process, and it is also more effective to add the time information in the attention layer than at the input.

People use different words when expressing their opinions. Sentiment analysis as a way to automatically detect and categorize people’s opinions in text, needs to reflect this diversity and individuality. One possible approach to analyze such traits is to take a person’s past opinions into consideration. In practice, such a model can suffer from the data sparsity issue, thus it is difficult to develop. In this article, we take texts from social platforms and propose a preliminary model for evaluating the effectiveness of including user information from the past, and offer a solution for the data sparsity. Furthermore, we present a finer-designed, enhanced model that focuses on frequent users and offers to capture the decay of past opinions using various gaps between the creation time of the text. An attention-based Hawkes process on top of a recurrent neural network is applied for this purpose, and the performance of the model is evaluated with Twitter data. With the proposed framework, positive results are shown which opens up new perspectives for future research.

INTRODUCTION: Machine learning algorithms and in silico models for the COVID-19 have been used to classify infectious people and predict their condition in time. OBJECTIVES: This study aims at creating a personalized model that combines machine learning and finite element simulation approach in order to predict development of COVID-19 infection in patients. METHODS: The methodology combines several aspects (1) classification of patients into several classes of clinical condition (2) segmentation of human lungs in X ray images (3) finite element simulation to investigate the spreading of SARS-COV-2 virion in the lungs. RESULTS: The findings show accuracy larger than 90% in all aspects of methodology. FE simulation has revealed that the distribution of airflow in the lung changes in time with the infection. CONCLUSION: The key benefit of our proposed method is that it combines several methods that will be further improved in order to create a truly unique combined methodology for predictive models in patients infected with COVID-19.

Thermal comfort and sensation are important aspects of building design and indoor climate control, as modern man spends most of the day indoors. Conventional indoor climate design and control approaches are based on static thermal comfort/sensation models that view the building occupants as passive recipients of their thermal environment. To overcome the disadvantages of static models, adaptive thermal comfort models aim to provide opportunity for personalized climate control and thermal comfort enhancement. Recent advances in wearable technologies contributed to new possibilities in controlling and monitoring health conditions and human wellbeing in daily life. The generated streaming data generated from wearable sensors are providing a unique opportunity to develop a real-time monitor of an individual&rsquo, s thermal state. The main goal of this work is to introduce a personalized adaptive model to predict individual&rsquo, s thermal sensation based on non-intrusive and easily measured variables, which could be obtained from already available wearable sensors. In this paper, a personalized classification model for individual thermal sensation with a reduced-dimension input-space, including 12 features extracted from easily measured variables, which are obtained from wearable sensors, was developed using least-squares support vector machine algorithm. The developed classification model predicted the individual&rsquo, s thermal sensation with an overall average accuracy of 86%. Additionally, we introduced the main framework of streaming algorithm for personalized classification model to predict an individual&rsquo, s thermal sensation based on streaming data obtained from wearable sensors.