Explainable Agents as Static Web Pages: UAV Simulation Example
Ontology highlight
ABSTRACT:
SUBMITTER: Calvaresi D
PROVIDER: S-EPMC7338151 | biostudies-literature | 2020 Jun
REPOSITORIES: biostudies-literature
Similar Datasets
Project description: Not available
| S-EPMC9459905 | biostudies-literature
Project description:The identification and mapping of trees via remotely sensed data for application in forest management is an active area of research. Previously proposed methods using airborne and hyperspectral sensors can identify tree species with high accuracy but are costly and are thus unsuitable for small-scale forest managers. In this work, we constructed a machine vision system for tree identification and mapping using Red-Green-Blue (RGB) image taken by an unmanned aerial vehicle (UAV) and a convolutional neural network (CNN). In this system, we first calculated the slope from the three-dimensional model obtained by the UAV, and segmented the UAV RGB photograph of the forest into several tree crown objects automatically using colour and three-dimensional information and the slope model, and lastly applied object-based CNN classification for each crown image. This system succeeded in classifying seven tree classes, including several tree species with more than 90% accuracy. The guided gradient-weighted class activation mapping (Guided Grad-CAM) showed that the CNN classified trees according to their shapes and leaf contrasts, which enhances the potential of the system for classifying individual trees with similar colours in a cost-effective manner-a useful feature for forest management.
| S-EPMC7806907 | biostudies-literature
Project description:OBJECTIVE:The objective of the present study was to evaluate the quality of general health information in Spanish language web pages, and the official Regional Services web pages from the different Autonomous Regions. DESIGN:It is a cross-sectional study. We have used a previously validated questionnaire to study the present state of the health information on Internet for a lay-user point of view. PARTICIPANTS AND INTERVENTIONS:By mean of PageRank (Google®), we obtained a group of webs, including a total of 65 health web pages. We applied some exclusion criteria, and finally obtained a total of 36 webs. We also analyzed the official web pages from the different Health Services in Spain (19 webs), making a total of 54 health web pages. RESULTS:In the light of our data, we observed that, the quality of the general information health web pages was generally rather low, especially regarding the information quality. Not one page reached the maximum score (19 points). The mean score of the web pages was of 9.8±2.8. CONCLUSIONS:In conclusion, to avoid the problems arising from the lack of quality, health professionals should design advertising campaigns and other media to teach the lay-user how to evaluate the information quality.
| S-EPMC7024504 | biostudies-literature
Project description:Objective.This work aims to generate realistic anatomical deformations from static patient scans. Specifically, we present a method to generate these deformations/augmentations via deep learning driven respiratory motion simulation that provides the ground truth for validating deformable image registration (DIR) algorithms and driving more accurate deep learning based DIR.Approach.We present a novel 3D Seq2Seq deep learning respiratory motion simulator (RMSim) that learns from 4D-CT images and predicts future breathing phases given a static CT image. The predicted respiratory patterns, represented by time-varying displacement vector fields (DVFs) at different breathing phases, are modulated through auxiliary inputs of 1D breathing traces so that a larger amplitude in the trace results in more significant predicted deformation. Stacked 3D-ConvLSTMs are used to capture the spatial-temporal respiration patterns. Training loss includes a smoothness loss in the DVF and mean-squared error between the predicted and ground truth phase images. A spatial transformer deforms the static CT with the predicted DVF to generate the predicted phase image. 10-phase 4D-CTs of 140 internal patients were used to train and test RMSim. The trained RMSim was then used to augment a public DIR challenge dataset for training VoxelMorph to show the effectiveness of RMSim-generated deformation augmentation.Main results.We validated our RMSim output with both private and public benchmark datasets (healthy and cancer patients). The structure similarity index measure (SSIM) for predicted breathing phases and ground truth 4D CT images was 0.92 ± 0.04, demonstrating RMSim's potential to generate realistic respiratory motion. Moreover, the landmark registration error in a public DIR dataset was improved from 8.12 ± 5.78 mm to 6.58mm ± 6.38 mm using RMSim-augmented training data.Significance.The proposed approach can be used for validating DIR algorithms as well as for patient-specific augmentations to improve deep learning DIR algorithms. The code, pretrained models, and augmented DIR validation datasets will be released athttps://github.com/nadeemlab/SeqX2Y.
| S-EPMC10202019 | biostudies-literature
Project description:BackgroundThe balance of the benefits and risks of long term use of hormone replacement therapy (HRT) have been a matter of debate for decades. In Europe, HRT requires medical prescription and its advertising is only permitted when aimed at health professionals (direct to consumer advertising is allowed in some non European countries). The objective of this study is to analyse the appropriateness and quality of Internet advertising about HRT in Spain.MethodsA search was carried out on the Internet (January 2009) using the eight best-selling HRT drugs in Spain. The brand name of each drug was entered into Google's search engine. The web sites appearing on the first page of results and the corresponding companies were analysed using the European Code of Good Practice as the reference point.ResultsFive corporate web pages: none of them included bibliographic references or measures to ensure that the advertising was only accessible by health professionals. Regarding non-corporate web pages (n = 27): 41% did not include the company name or address, 44% made no distinction between patient and health professional information, 7% contained bibliographic references, 26% provided unspecific information for the use of HRT for osteoporosis and 19% included menstrual cycle regulation or boosting feminity as an indication. Two online pharmacies sold HRT drugs which could be bought online in Spain, did not include the name or contact details of the registered company, nor did they stipulate the need for a medical prescription or differentiate between patient and health professional information.ConclusionsEven though pharmaceutical companies have committed themselves to compliance with codes of good practice, deficiencies were observed regarding the identification, information and promotion of HRT medications on their web pages. Unaffected by legislation, non-corporate web pages are an ideal place for indirect HRT advertising, but they often contain misleading information. HRT can be bought online from Spain, without a medical consultation or prescription constituting a serious issue for public health. In our information society, it is the right and obligation of public health bodies to ensure that such information is not misleading.
| S-EPMC2850342 | biostudies-literature
Project description:BackgroundSupportive care Prioritization, Assessment and Recommendations for Kids (SPARK) is a web-based application that facilitates symptom screening and access to supportive care clinical practice guidelines (CPGs) for children and adolescents receiving cancer treatments. Objective was to develop SPARK family member web pages for pediatric patient family members accessing: (1) proxy symptom screening and symptom reports, and (2) care recommendations for symptom management based on CPGs.MethodsSPARK family member web pages were developed and included access to symptom screening and care recommendations sections. Care recommendations for fatigue and mucositis were created. These were iteratively refined based upon cognitive interviews with English-speaking family members ≥16 years of age until less than two participants incorrectly understood sections as adjudicated by two independent raters.ResultsA total of 100 family members were enrolled who evaluated the SPARK family member web pages (n = 40), fatigue care recommendation (n = 30) and mucositis prevention care recommendation (n = 30). Among the last 10 participants, none said that the SPARK family member web pages were hard or very hard to use, one incorrectly understood one web page, none said either care recommendation was hard to understand and none were incorrect in their understanding of the care recommendations.ConclusionsWe successfully developed SPARK web pages for use by family members of pediatric patients receiving cancer treatments. We also developed a process for translating CPG recommendations designed for healthcare professionals to lay language. The utility of SPARK family member web pages after clinical implementation could be a focus for future research.
| S-EPMC7519510 | biostudies-literature
Project description:PurposeOnline information can influence attitudes toward vaccination. The aim of the present study was to provide a systematic evaluation of the search engine ranking, quality, and content of Web pages that are critical versus noncritical of human papillomavirus (HPV) vaccination.MethodsWe identified HPV vaccine-related Web pages with the Google search engine by entering 20 terms. We then assessed each Web page for critical versus noncritical bias and for the following quality indicators: authorship disclosure, source disclosure, attribution of at least one reference, currency, exclusion of testimonial accounts, and readability level less than ninth grade. We also determined Web page comprehensiveness in terms of mention of 14 HPV vaccine-relevant topics.ResultsTwenty searches yielded 116 unique Web pages. HPV vaccine-critical Web pages comprised roughly a third of the top, top 5- and top 10-ranking Web pages. The prevalence of HPV vaccine-critical Web pages was higher for queries that included term modifiers in addition to root terms. Compared with noncritical Web pages, Web pages critical of HPV vaccine overall had a lower quality score than those with a noncritical bias (p < .01) and covered fewer important HPV-related topics (p < .001). Critical Web pages required viewers to have higher reading skills, were less likely to include an author byline, and were more likely to include testimonial accounts. They also were more likely to raise unsubstantiated concerns about vaccination.ConclusionsWeb pages critical of HPV vaccine may be frequently returned and highly ranked by search engine queries despite being of lower quality and less comprehensive than noncritical Web pages.
| S-EPMC4695228 | biostudies-literature
Project description:BackgroundMany computer studies have employed either dynamic simulation or metabolic flux analysis (MFA) to predict the behaviour of biochemical pathways. Dynamic simulation determines the time evolution of pathway properties in response to environmental changes, whereas MFA provides only a snapshot of pathway properties within a particular set of environmental conditions. However, owing to the large amount of kinetic data required for dynamic simulation, MFA, which requires less information, has been used to manipulate large-scale pathways to determine metabolic outcomes.ResultsHere we describe a simulation method based on cooperation between kinetics-based dynamic models and MFA-based static models. This hybrid method enables quasi-dynamic simulations of large-scale metabolic pathways, while drastically reducing the number of kinetics assays needed for dynamic simulations. The dynamic behaviour of metabolic pathways predicted by our method is almost identical to that determined by dynamic kinetic simulation.ConclusionThe discrepancies between the dynamic and the hybrid models were sufficiently small to prove that an MFA-based static module is capable of performing dynamic simulations as accurately as kinetic models. Our hybrid method reduces the number of biochemical experiments required for dynamic models of large-scale metabolic pathways by replacing suitable enzyme reactions with a static module.
| S-EPMC1262783 | biostudies-literature
Project description:SummaryWhile cause-and-effect knowledge assembly models encoded in Biological Expression Language are able to support generation of mechanistic hypotheses, they are static and limited in their ability to encode temporality. Here, we present BEL2ABM, a software for producing continuous, dynamic, executable agent-based models from BEL templates.Availability and implementationThe tool has been developed in Java and NetLogo. Code, data and documentation are available under the Apache 2.0 License at https://github.com/pybel/bel2abm.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6022644 | biostudies-literature
Project description:An increasing number of ion channel structures are being determined. This generates a need for computational tools to enable functional annotation of channel structures. However, several studies of ion channel and model pores have indicated that the physical dimensions of a pore are not always a reliable indicator of its conductive status. This is due to the unusual behavior of water within nano-confined spaces, resulting in a phenomenon referred to as "hydrophobic gating". We have recently demonstrated how simulating the behavior of water within an ion channel pore can be used to predict its conductive status. In this addendum to our study, we apply this method to compare the recently solved structure of a mutant of the bestrophin chloride channel BEST1 with that of the wild-type channel. Our results support the hypothesis of a hydrophobic gate within the narrow neck of BEST1. This provides further validation that this simulation approach provides the basis for an accurate and computationally efficient tool for the functional annotation of ion channel structures.
| S-EPMC5555266 | biostudies-literature