PubMed Health⌕ Search

Biomedical subjects

Weiming Hu

Publications and source records attributed to Weiming Hu.

11 recordsLinked to original sources
PubMed2006

A system for learning statistical motion patterns.

Analysis of motion patterns is an effective approach for anomaly detection and behavior prediction. Current approaches for the analysis of motion patterns depend on known scenes, where objects move in predefined ways. It is highly desirable to automatically construct object motion patterns which reflect the knowledge of the scene. In this paper, we present a system for automatically learning motion patterns for anomaly detection and behavior prediction based on a proposed algorithm for robustly tracking multiple objects. In the tracking algorithm, foreground pixels are clustered using a fast accurate fuzzy K-means algorithm. Growing and prediction of the cluster centroids of foreground pixels ensure that each cluster centroid is associated with a moving object in the scene. In the algorithm for learning motion patterns, trajectories are clustered hierarchically using spatial and temporal information and then each motion pattern is represented with a chain of Gaussian distributions. Based on the learned statistical motion patterns, statistical methods are used to detect anomalies and predict behaviors. Our system is tested using image sequences acquired, respectively, from a crowded real traffic scene and a model traffic scene. Experimental results show the robustness of the tracking algorithm, the efficiency of the algorithm for learning motion patterns, and the encouraging performance of algorithms for anomaly detection and behavior prediction.

Algorithms↗
PubMed2006

Principal axis-based correspondence between multiple cameras for people tracking.

Visual surveillance using multiple cameras has attracted increasing interest in recent years. Correspondence between multiple cameras is one of the most important and basic problems which visual surveillance using multiple cameras brings. In this paper, we propose a simple and robust method, based on principal axes of people, to match people across multiple cameras. The correspondence likelihood reflecting the similarity of pairs of principal axes of people is constructed according to the relationship between "ground-points" of people detected in each camera view and the intersections of principal axes detected in different camera views and transformed to the same view. Our method has the following desirable properties: 1) Camera calibration is not needed. 2) Accurate motion detection and segmentation are less critical due to the robustness of the principal axis-based feature to noise. 3) Based on the fused data derived from correspondence results, positions of people in each camera view can be accurately located even when the people are partially occluded in all views. The experimental results on several real video sequences from outdoor environments have demonstrated the effectiveness, efficiency, and robustness of our method.

Algorithms↗
PubMed2005

Tobacco-cessation services and patient satisfaction in nine nonprofit HMOs.

BACKGROUND: The U.S. Public Health Service clinical practice guideline calls for clinicians and healthcare organizations to identify and treat every tobacco user seen in a healthcare setting. There is little information on the extent of compliance with the guideline's treatment model described by the "5A's" (Ask, Advise, Assess, Assist, Arrange). METHODS: In 1999-2000 a survey was mailed to 64,764 members aged 25 to 75 years, of nine nonprofit HMOs participating in the National Cancer Institute-funded Cancer Research Network. These plans provide medical care to more than 8 million Americans including a minority enrollment of 30%. Smokers were asked about tobacco-cessation treatments received during primary care visits in the past year. RESULTS: A 70% response rate identified a smoking prevalence of 10% (n=4207). Results indicated that 90% of smokers were asked about smoking, 71% were advised to quit, 56% were assessed for their willingness to quit, 49% received assistance interventions, and 9% had follow-up arranged. Treatment was provided more often to smokers who asked for help and/or intended to quit. Few and only modest associations were found between other patient characteristics and receipt of 5A's cessation services. In contrast to widely reported concerns about smokers' resistance to tobacco interventions, smokers who received treatment were more satisfied with health plan services. CONCLUSIONS: Results demonstrate substantial clinician compliance with the first two steps-Ask and Advise. Greater efforts are needed in providing the more effective tobacco treatments-Assist and Arrange. Compliance with the guideline is associated with greater patient satisfaction.

Adult↗
PubMed2005

3-D model-based vehicle tracking.

This paper aims at tracking vehicles from monocular intensity image sequences and presents an efficient and robust approach to three-dimensional (3-D) model-based vehicle tracking. Under the weak perspective assumption and the ground-plane constraint, the movements of model projection in the two-dimensional image plane can be decomposed into two motions: translation and rotation. They are the results of the corresponding movements of 3-D translation on the ground plane (GP) and rotation around the normal of the GP, which can be determined separately. A new metric based on point-to-line segment distance is proposed to evaluate the similarity between an image region and an instantiation of a 3-D vehicle model under a given pose. Based on this, we provide an efficient pose refinement method to refine the vehicle's pose parameters. An improved EKF is also proposed to track and to predict vehicle motion with a precise kinematics model. Experimental results with both indoor and outdoor data show that the algorithm obtains desirable performance even under severe occlusion and clutter.

Algorithms↗
PubMed2004

Design, synthesis, and evaluation of a new class of noncyclic 1,3-dicarbonyl compounds as PPARalpha selective activators.

Lipid accumulation in nonadipose tissues is increasingly linked to the development of type 2 diabetes in obese individuals. We report here the design, synthesis, and evaluation of a series of novel PPARalpha selective activators containing 1,3-dicarbonyl moieties. Structure-activity relationship studies led to the identification of PPARalpha selective activators (compounds 10, 14, 17, 18, and 21) with stronger potency and efficacy to activate PPARalpha over PPARgamma and PPARdelta. Experiments in vivo showed that compounds 10, 14, and 17 had blood glucose lowering effect in diabetic db/db mouse model after two weeks oral dosing. The data strongly support further testing of these lead compounds in other relevant disease animal models to evaluate their potential therapeutic benefits.

Adipose Tissue↗
PubMed2004

Evaluation of the impact of an HMO's varicella vaccination program on incidence of varicella.

The impact of a varicella vaccination program on disease in a large HMO population during 1996-1999 was assessed by multiple cross-sectional analyses of automated database records of vaccinations and varicella diagnoses for children (0-18 years). The cumulative proportion of the population vaccinated reached 73% among 2-year-olds, and 22% overall. An overall 49.7% reduction in varicella incidence was estimated to be attributable to an 18.5% point increase in the proportion of the population vaccinated.

Adolescent↗
PubMed2004

A hierarchical self-organizing approach for learning the patterns of motion trajectories.

The understanding and description of object behaviors is a hot topic in computer vision. Trajectory analysis is one of the basic problems in behavior understanding, and the learning of trajectory patterns that can be used to detect anomalies and predict object trajectories is an interesting and important problem in trajectory analysis. In this paper, we present a hierarchical self-organizing neural network model and its application to the learning of trajectory distribution patterns for event recognition. The distribution patterns of trajectories are learnt using a hierarchical self-organizing neural network. Using the learned patterns, we consider anomaly detection as well as object behavior prediction. Compared with the existing neural network structures that are used to learn patterns of trajectories, our network structure has smaller scale and faster learning speed, and is thus more effective. Experimental results using two different sets of data demonstrate the accuracy and speed of our hierarchical self-organizing neural network in learning the distribution patterns of object trajectories.

Learning↗
PubMed2004

Quantitative structure-activity relationship study of histone deacetylase inhibitors.

Histone deacetylases (HDACs) play a critical role in gene transcription and have become a novel target for the discovery of drugs against cancer and other diseases. During the past several years there have been extensive efforts in the identification and optimization of histone deacetylase inhibitors (HDACIs) as novel anticancer drugs. Here we report a comprehensive quantitative structure-activity relationship (QSAR) study of HDACIs in the hope of identifying the structural determinants for anticancer activity. We have identified, collected, and verified the structural and biological activity data for 124 compounds from various literature sources and performed an extensive QSAR study on this comprehensive data set by using various QSAR and classification methods. A highly predictive QSAR model with R(2) of 0.76 and leave-one-out cross-validated R(2) of 0.73 was obtained. The overall rate of cross-validated correct prediction of the classification model is around 92%. The QSAR and classification models provided direct guidance to our internal programs of identifying and optimizing HDAC inhibitors. Limitations of the models were also discussed.

Animals↗
PubMed2003

[Establishment of whole pancreaticoduodenal allotransplantation model with jejunum drainage and portal venous drainage in pigs].

OBJECTIVE: To establish a pig model of pancreaticoduodenal transplantation with jejunum drainage and portal venous drainage. METHODS: Forty pigs were randomly divided into the donor group and recipient group. University of Wisconsin (UW) solution was used for both in situ flush and storage of all organs under cold storage conditions. Whole pancreaticoduodenal graft was harvested with segments of abdominal aorta and portal vein and shaped under cold UW solution. Then, the end-to-end anastomosis was performed with the donor iliac artery bifurcation Y graft to the recipient superior mesenteric arteries and celiac artery. Furthermore, type I diabetes model was made by removal of the recipient pancreas The venous anastomosis was reconstructed between the donor portal vein and the recipient superior mesenteric vein. Meanwhile, the end-to-side anastomosis was performed with the donor common iliac artery bifurcation Y graft to the recipient abdomial aorta, and the side-to-side intestinal anastomosis between the donor duodenum and the recipient jejunum was performed. RESULTS: Twenty piges were subjected to pancreaticoduodenal transplantation, in which 1 died from respiratory depression because of anesthesia, and 2 had thrombus and infarction in the pancreatic graft after transplantation. 17 cases showed normal blood sugar in peripheral circulation 24 hours after operation, the mean survival of the graft was 18.6 +/- 2.6 days. CONCLUSION: The technique of duodenal transplantation with jejunum drainage and portal venous drainage may pave the way for the further development of pancreas transplantation in clinical practice. It can be utilized in basic research of pancreas transplantation.

Anastomosis, Surgical↗
PubMed2002

[An in vivo study of reseeding endothelial cell for attenuation of hyperacute rejection after xenotransplantation].

UNLABELLED: To investigate the possible significance and usefulness of reseeding the endothelial cell of recipient for the prevention of hyperacute rejection (HAR) resulting from the xenograft. METHODS: Discordant xenotransplantation model (guinea pig-to-rat) was adopted in this study. Firstly endothelial cells from rat abdominal aorta were separated and cultured. Secondly the guinea pig abdominal aorta of which the endothelium had been removed was cultured with the suspension containing rat endothelial cells (4 x 10(6)/ml). The viability of cultured vessel was assessed using light microscopy and transmission electron microscopy. Thirdly, the guinea pig vessels reseeded with rat endothelial cells were transplanted to rat in vivo. The thrombrosis time was observed. The condition of deposit of IgM and C3 in the recipient's transplanted vessel endothelium was examined by immuno-fluorescence staining assay. RESULTS: The thrombrosis time of the guinea pig vessel reseeded with rat endothelial cells (20.3 + 4.42 h) was significantly prolonged as compared with that of the normal guinea pig vessel (0.35 + 0.284 h) and the guinea pig vessel that had been deprived of endothelium (0.165 + 0.77 h). No deposit of IgM and C3 was seen in the new endothelium of guinea pig vessel in the treated group, whereas deposit of IgM and C3 was observed in the untreated normal guinea pig aorta. CONCLUSION: Donor vessels reseeded with endothelial cells from the recipient will undergo less severe rejection and this technique may be very useful in the attenuation of HAR.

Animals↗