Dataset Information

Introducing Depth Information Into Generative Target Tracking.

ABSTRACT: Common visual features used in target tracking, including colour and grayscale, are prone to failure in a confusingly similar-looking background. As the technology of three-dimensional visual information acquisition has gradually gained ground in recent years, the conditions for the wide use of depth information in target tracking has been made available. This study focuses on discussing the possible ways to introduce depth information into the generative target tracking methods based on a kernel density estimation as well as the performance of different methods of introduction, thereby providing a reference for the use of depth information in actual target tracking systems. First, an analysis of the mean-shift technical framework, a typical algorithm used for generative target tracking, is described, and four methods of introducing the depth information are proposed, i.e., the thresholding of the data source, thresholding of the density distribution of the dataset applied, weighting of the data source, and weighting of the density distribution of the dataset. Details of an experimental study conducted to evaluate the validity, characteristics, and advantages of each method are then described. The experimental results showed that the four methods can improve the validity of the basic method to a certain extent and meet the requirements of real-time target tracking in a confusingly similar background. The method of weighting the density distribution of the dataset, into which depth information is introduced, is the prime choice in engineering practise because it delivers an excellent comprehensive performance and the highest level of accuracy, whereas methods such as the thresholding of both the data sources and the density distribution of the dataset are less time-consuming. The performance in comparison with that of a state-of-the-art tracker further verifies the practicality of the proposed approach. Finally, the research results also provide a reference for improvements in other target tracking methods in which depth information can be introduced.

SUBMITTER: Sun D

PROVIDER: S-EPMC8442731 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Can reproductive life plan (RLP)-based information in contraceptive counselling before pregnancy increase women's knowledge of reproduction, and of the importance of folic acid intake in particular?The RLP-based information increased women's knowledge of reproduction including knowledge of folic acid intake.Many women have insufficient knowledge of reproduction, including a health-promoting lifestyle prior to conception, and highly educated women in particular postpone childbearing until an age when their fertile capacity has started to decrease.The study was an randomized controlled trial with one intervention group (IG) and two control groups (CG1, CG2). A sample size calculation indicated that 82 women per group would be adequate. Recruitment took place during 3 months in 2012 and 299 women were included. The women were randomized in blocks of three. All groups received standard care (contraceptive counselling, Chlamydia testing, cervical screening). In addition, women in the IG were given oral and written RLP-based information about reproduction.A total of 299 out of 338 (88%) Swedish-speaking women visiting a Student Health Centre were included (mean age 23 years); response rate was 88%. Before the counselling, women in the IG and the CG1 completed a baseline questionnaire, including questions about lifestyle changes in connection to pregnancy planning, family planning intentions and knowledge of reproduction (e.g. the fecundity of an ovum). At follow-up 2 months after inclusion, a structured telephone interview was performed in all groups (n = 262, 88% participation rate).There was no difference between the groups regarding the mean knowledge score at baseline. The IG scored higher at follow-up than at baseline (P < 0.001); the mean increased from 6.4 to 9.0 out of a maximum 20 points. The women in the CG1 scored no differently at follow-up than at baseline. The difference in the knowledge score between the IG and the two CGs was significant (P < 0.001), whereas no difference was shown between the two CGs. There was no difference between the groups at baseline regarding how many women could mention folic acid intake among the things to do when planning to get pregnant. At follow-up, 22% in the IG, 3% in CG1 and 1% in CG2 mentioned folic acid intake (P < 0.001). At follow-up, more women in the IG also wished to have their last child earlier in life (P < 0.001) than at baseline, while there was no difference in the CG1.As the study sample consisted of university students, it is possible that the effect of the intervention was connected to a high level of education and conclusions for all women of reproductive age should be drawn with caution.The provision of RLP-based information seems to be a feasible tool for promoting reproductive health.Study funding was received from the Faculty of Medicine, Uppsala University, Sweden. There are no conflicts of interest.ClinicalTrial.gov Identifier NCT01739101.

Project description:BackgroundUnderstanding the multifaceted nature of health outcomes requires a comprehensive examination of the social, economic, and environmental determinants that shape individual well-being. Among these determinants, behavioral factors play a crucial role, particularly the consumption patterns of psychoactive substances, which have important implications on public health. The Global Burden of Disease Study shows a growing impact in disability-adjusted life years due to substance use. The successful identification of patients' substance use information equips clinical care teams to address substance-related issues more effectively, enabling targeted support and ultimately improving patient outcomes.ObjectiveTraditional natural language processing methods face limitations in accurately parsing diverse clinical language associated with substance use. Large language models offer promise in overcoming these challenges by adapting to diverse language patterns. This study investigates the application of the generative pretrained transformer (GPT) model in specific GPT-3.5 for extracting tobacco, alcohol, and substance use information from patient discharge summaries in zero-shot and few-shot learning settings. This study contributes to the evolving landscape of health care informatics by showcasing the potential of advanced language models in extracting nuanced information critical for enhancing patient care.MethodsThe main data source for analysis in this paper is Medical Information Mart for Intensive Care III data set. Among all notes in this data set, we focused on discharge summaries. Prompt engineering was undertaken, involving an iterative exploration of diverse prompts. Leveraging carefully curated examples and refined prompts, we investigate the model's proficiency through zero-shot as well as few-shot prompting strategies.ResultsResults show GPT's varying effectiveness in identifying mentions of tobacco, alcohol, and substance use across learning scenarios. Zero-shot learning showed high accuracy in identifying substance use, whereas few-shot learning reduced accuracy but improved in identifying substance use status, enhancing recall and F1-score at the expense of lower precision.ConclusionsExcellence of zero-shot learning in precisely extracting text span mentioning substance use demonstrates its effectiveness in situations in which comprehensive recall is important. Conversely, few-shot learning offers advantages when accurately determining the status of substance use is the primary focus, even if it involves a trade-off in precision. The results contribute to enhancement of early detection and intervention strategies, tailor treatment plans with greater precision, and ultimately, contribute to a holistic understanding of patient health profiles. By integrating these artificial intelligence-driven methods into electronic health record systems, clinicians can gain immediate, comprehensive insights into substance use that results in shaping interventions that are not only timely but also more personalized and effective.

Dataset Information

Introducing Depth Information Into Generative Target Tracking.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets