3241 Using infant exertion to tailor treadmill intervention

Abstract With the rapid growth of the volume of video data and the development of multimedia technologies, it has become necessary to have the ability to accurately and quickly browse and search through information stored in large multimedia databases. For this purpose, content-based video retrieval ( CBVR ) has become an active area of research over the last decade. In this paper, We propose a content-based video retrieval system providing similar videos from a large multimedia data-set based on a query video. The approach uses vector motion-based signatures to describe the visual content and uses machine learning techniques to extract key-frames for rapid browsing and efficient video indexing. We have implemented the proposed approach on both, single machine and real-time distributed cluster to evaluate the real-time performance aspect, especially when the number and size of videos are large. Experiments are performed using various benchmark action and activity recognition data-sets and the results reveal the effectiveness of the proposed method in both accuracy and processing time compared to state-of-the-art methods.

Download Full-text

Localizing the Accessory Pathway in Ventricular Preexcitation Patients Using a Score Based Algorithm

Methods of Information in Medicine ◽

10.3414/me11-01-0046 ◽

2012 ◽

Vol 51 (01) ◽

pp. 3-12 ◽

Cited By ~ 3

Author(s):

M. C. Stühlinger ◽

C. N. Nowak ◽

K. Spuller ◽

K. Etsadashvili ◽

X. Stühlinger ◽

...

Keyword(s):

Cardiac Electrophysiology ◽

Accessory Pathway ◽

Positive Likelihood Ratio ◽

Original Study ◽

Data Sets ◽

Standardized Residuals ◽

Study Population ◽

A Prospective Study ◽

Ventricular Preexcitation ◽

Better Than

SummaryObjectives: Clinical data was analyzed to find an efficient way to localize the accessory pathway in patients with ventricular preexcitation.Methods: The delta wave morphologies and ablation sites of 186 patients who underwent catheter ablation were analyzed and an algorithm (“locAP”) to localize the accessory pathway was developed from the 84 data sets with a PQ interval ≤ 0.12 s and a QRS width ≥ 0.12 s. Fifty additional patients were included for a prospective validation. The locAP algorithm ranks 13 locations according to the likelihood that the accessory pathway is localized there. The algorithm is based on the locAP score which uses the standardized residuals of the available data sets.Results: The locAP algorithm’s accuracy is 0.54 for 13 locations, with a sensitivity of 0.84, a specificity of 0.97, and a positive likelihood ratio of 24.94. If the two most likely locations are regarded, the accuracy rises to 0.79, for the three most likely locations combined the accuracy is 0.82. This new algorithm performs better than Milstein’s, Fitzpatrick’s, and Arruda’s algorithm both in the original study population as well as in a prospective study.Conclusions: The locAP algorithm is a valid and valuable tool for clinical practice in a cardiac electrophysiology laboratory. It could be shown that use of the locAP algorithm is favorable over the localizing algorithms that are in clinical use today.

Download Full-text

Video Data Mining

Encyclopedia of Data Warehousing and Mining ◽

10.4018/978-1-59140-557-3.ch223 ◽

2011 ◽

pp. 1185-1189 ◽

Cited By ~ 2

Author(s):

Jung Hwan Oh ◽

Jeong Kyu Lee ◽

Sae Hwang

Keyword(s):

Data Mining ◽

Research Area ◽

Multimedia Databases ◽

Video Data ◽

Multimedia Data ◽

Data Sets ◽

Data Set ◽

Useful Knowledge ◽

Active Research ◽

Diverse Data

Data mining, which is defined as the process of extracting previously unknown knowledge and detecting interesting patterns from a massive set of data, has been an active research area. As a result, several commercial products and research prototypes are available nowadays. However, most of these studies have focused on corporate data — typically in an alpha-numeric database, and relatively less work has been pursued for the mining of multimedia data (Zaïane, Han, & Zhu, 2000). Digital multimedia differs from previous forms of combined media in that the bits representing texts, images, audios, and videos can be treated as data by computer programs (Simoff, Djeraba, & Zaïane, 2002). One facet of these diverse data in terms of underlying models and formats is that they are synchronized and integrated hence, can be treated as integrated data records. The collection of such integral data records constitutes a multimedia data set. The challenge of extracting meaningful patterns from such data sets has lead to research and development in the area of multimedia data mining. This is a challenging field due to the non-structured nature of multimedia data. Such ubiquitous data is required in many applications such as financial, medical, advertising and Command, Control, Communications and Intelligence (C3I) (Thuraisingham, Clifton, Maurer, & Ceruti, 2001). Multimedia databases are widespread and multimedia data sets are extremely large. There are tools for managing and searching within such collections, but the need for tools to extract hidden and useful knowledge embedded within multimedia data is becoming critical for many decision-making applications.

Download Full-text

Assessing the Effect of Pedestrians’ Use of Cell Phones on Their Walking Behavior: A Study Based on Automated Video Analysis

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/0361198118780708 ◽

2018 ◽

Vol 2672 (35) ◽

pp. 46-57 ◽

Cited By ~ 9

Author(s):

Rushdi Alsaleh ◽

Tarek Sayed ◽

Mohamed H. Zaki

Keyword(s):

Cognitive Abilities ◽

Cell Phones ◽

Step Length ◽

Video Data ◽

Health Science ◽

Automated System ◽

Step Frequency ◽

Data Set ◽

Walking Behavior ◽

And Control

The objective of the study is to assess the effect of the use of cell phones while walking at urban crosswalks. The methodology uses recent findings in health science concerning the relationship between tempo-spatial characteristics of gait and the cognitive abilities of pedestrians. Gait measures are shown to be affected by the complexity of the task (e.g., talking and texting) performed during walking. This study focuses on the effect of distraction states, distraction types (visual such as texting/reading and auditory such as talking/listening), and pedestrian-vehicle interactions on the gait parameters of pedestrians at crosswalks. Experiments are performed on a video data set near a college campus in the city of Kamloops, British Columbia. The analysis relies on automated video-based data collection using a computer vision technique. The benefits of such an automated system include the ability to capture the natural movement of pedestrians and minimizing the risk of disturbing their behavior. Results show that pedestrians distracted by texting/reading (visually) or talking/listening (auditory) while walking tend to reduce and control their walking speed by adjusting their step length or step frequency, respectively. Pedestrians distracted by texting/reading (visually) have significantly lower step length and are less stable in walking. Distracted pedestrians involved in interactions with approaching vehicles tend to reduce and control their walking speeds by adjusting their step frequencies. This research can find applications in pedestrian facility design, modeling and calibrating pedestrian simulations, and pedestrian safety intervention programs and legislative actions.

Download Full-text

Investigation of Pig Activity Based on Video Data and Semi-Supervised Neural Networks

AgriEngineering ◽

10.3390/agriengineering2040039 ◽

2020 ◽

Vol 2 (4) ◽

pp. 581-595

Author(s):

Martin Wutke ◽

Armin Otto Schmitt ◽

Imke Traulsen ◽

Mehmet Gültas

Keyword(s):

Neural Networks ◽

Early Warning Systems ◽

The State ◽

Video Data ◽

Activity Level ◽

Data Sets ◽

Complex Scene ◽

Data Set ◽

Stress Indicator ◽

Tail Biting

The activity level of pigs is an important stress indicator which can be associated to tail-biting, a major issue for animal welfare of domestic pigs in conventional housing systems. Although the consideration of the animal activity could be essential to detect tail-biting before an outbreak occurs, it is often manually assessed and therefore labor intense, cost intensive and impracticable on a commercial scale. Recent advances of semi- and unsupervised convolutional neural networks (CNNs) have made them to the state of art technology for detecting anomalous behavior patterns in a variety of complex scene environments. In this study we apply such a CNN for anomaly detection to identify varying levels of activity in a multi-pen problem setup. By applying a two-stage approach we first trained the CNN to detect anomalies in the form of extreme activity behavior. Second, we trained a classifier to categorize the detected anomaly scores by learning the potential activity range of each pen. We evaluated our framework by analyzing 82 manually rated videos and achieved a success rate of 91%. Furthermore, we compared our model with a motion history image (MHI) approach and a binary image approach using two benchmark data sets, i.e., the well established pedestrian data sets published by the University of California, San Diego (UCSD) and our pig data set. The results show the effectiveness of our framework, which can be applied without the need of a labor intense manual annotation process and can be utilized for the assessment of the pig activity in a variety of applications like early warning systems to detect changes in the state of health.

Download Full-text

Video Data Mining

Data Warehousing and Mining ◽

10.4018/978-1-59904-951-9.ch094 ◽

2008 ◽

pp. 1631-1637

Author(s):

Jung Hwan Oh ◽

Jeong Kyu Lee ◽

Sae Hwang

Keyword(s):

Data Mining ◽

Research Area ◽

Multimedia Databases ◽

Video Data ◽

Multimedia Data ◽

Data Sets ◽

Data Set ◽

Useful Knowledge ◽

Active Research ◽

Diverse Data

Data mining, which is defined as the process of extracting previously unknown knowledge and detecting interesting patterns from a massive set of data, has been an active research area. As a result, several commercial products and research prototypes are available nowadays. However, most of these studies have focused on corporate data — typically in an alpha-numeric database, and relatively less work has been pursued for the mining of multimedia data (Zaïane, Han, & Zhu, 2000). Digital multimedia differs from previous forms of combined media in that the bits representing texts, images, audios, and videos can be treated as data by computer programs (Simoff, Djeraba, & Zaïane, 2002). One facet of these diverse data in terms of underlying models and formats is that they are synchronized and integrated hence, can be treated as integrated data records. The collection of such integral data records constitutes a multimedia data set. The challenge of extracting meaningful patterns from such data sets has lead to research and development in the area of multimedia data mining. This is a challenging field due to the non-structured nature of multimedia data. Such ubiquitous data is required in many applications such as financial, medical, advertising and Command, Control, Communications and Intelligence (C3I) (Thuraisingham, Clifton, Maurer, & Ceruti, 2001). Multimedia databases are widespread and multimedia data sets are extremely large. There are tools for managing and searching within such collections, but the need for tools to extract hidden and useful knowledge embedded within multimedia data is becoming critical for many decision-making applications.

Download Full-text

Behavior Analysis Using a Multilevel Motion Pattern Learning Framework

Transportation Research Record Journal of the Transportation Research Board ◽

10.3141/2528-13 ◽

2015 ◽

Vol 2528 (1) ◽

pp. 116-127 ◽

Cited By ~ 3

Author(s):

Mohamed Gomaa Mohamed ◽

Nicolas Saunier

Keyword(s):

Gaussian Mixture ◽

Video Data ◽

Road User ◽

Pattern Learning ◽

Data Sets ◽

Motion Pattern ◽

Trajectory Data ◽

Data Set ◽

Learning Framework ◽

Road Users

The increasing availability of video data, through existing traffic cameras or dedicated field data collection, and the development of computer vision techniques pave the way for the collection of massive data sets about the microscopic behavior of road users. Analysis of such data sets helps in understanding normal road user behavior and can be used for realistic prediction of motion and computation of surrogate safety indicators. A multilevel motion pattern learning framework was developed to enable automated scene interpretation, anomalous behavior detection, and surrogate safety analysis. First, points of interest (POIs) were learned on the basis of the Gaussian mixture model and the expectation maximization algorithm and then used to form activity paths (APs). Second, motion patterns, represented by trajectory prototypes, were learned from road users' trajectories in each AP by using a two-stage trajectory clustering method based on spatial then temporal (speed) information. Finally, motion prediction relied on matching at each instant partial trajectories to the learned prototypes to evaluate potential for collision by using computing indicators. An intersection case study demonstrates the framework's ability in many ways: it helps reduce the computation cost up to 90%; it cleans the trajectory data set from tracking outliers; it uses actual trajectories as prototypes without any pre- and postprocessing; and it predicts future motion realistically to compute surrogate safety indicators.

Download Full-text

Video Data Mining

Encyclopedia of Data Warehousing and Mining, Second Edition ◽

10.4018/978-1-60566-010-3.ch312 ◽

2011 ◽

pp. 2042-2047

Author(s):

JungHwan Oh

Keyword(s):

Data Mining ◽

Research Area ◽

Multimedia Databases ◽

Video Data ◽

Multimedia Data ◽

Data Sets ◽

Data Set ◽

Useful Knowledge ◽

Active Research ◽

Diverse Data

Data mining, which is defined as the process of extracting previously unknown knowledge and detecting interesting patterns from a massive set of data, has been an active research area. As a result, several commercial products and research prototypes are available nowadays. However, most of these studies have focused on corporate data — typically in an alpha-numeric database, and relatively less work has been pursued for the mining of multimedia data (Zaïane, Han, & Zhu, 2000). Digital multimedia differs from previous forms of combined media in that the bits representing texts, images, audios, and videos can be treated as data by computer programs (Simoff, Djeraba, & Zaïane, 2002). One facet of these diverse data in terms of underlying models and formats is that they are synchronized and integrated hence, can be treated as integrated data records. The collection of such integral data records constitutes a multimedia data set. The challenge of extracting meaningful patterns from such data sets has lead to research and development in the area of multimedia data mining. This is a challenging field due to the non-structured nature of multimedia data. Such ubiquitous data is required in many applications such as financial, medical, advertising and Command, Control, Communications and Intelligence (C3I) (Thuraisingham, Clifton, Maurer, & Ceruti, 2001). Multimedia databases are widespread and multimedia data sets are extremely large. There are tools for managing and searching within such collections, but the need for tools to extract hidden and useful knowledge embedded within multimedia data is becoming critical for many decision-making applications.

Download Full-text

Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections

Applied Sciences ◽

10.3390/app10093079 ◽

2020 ◽

Vol 10 (9) ◽

pp. 3079 ◽

Cited By ~ 10

Author(s):

Yi-Qi Huang ◽

Jia-Chun Zheng ◽

Shi-Dan Sun ◽

Cheng-Fu Yang ◽

Jing Liu

Keyword(s):

Real Time ◽

Video Data ◽

Detection Accuracy ◽

Data Sets ◽

Traffic Flows ◽

Data Set ◽

Traffic System ◽

Network Training ◽

Intelligent Traffic System ◽

Spatial Pyramid Pooling

In the intelligent traffic system, real-time and accurate detections of vehicles in images and video data are very important and challenging work. Especially in situations with complex scenes, different models, and high density, it is difficult to accurately locate and classify these vehicles during traffic flows. Therefore, we propose a single-stage deep neural network YOLOv3-DL, which is based on the Tensorflow framework to improve this problem. The network structure is optimized by introducing the idea of spatial pyramid pooling, then the loss function is redefined, and a weight regularization method is introduced, for that, the real-time detections and statistics of traffic flows can be implemented effectively. The optimization algorithm we use is the DL-CAR data set for end-to-end network training and experiments with data sets under different scenarios and weathers. The analyses of experimental data show that the optimized algorithm can improve the vehicles’ detection accuracy on the test set by 3.86%. Experiments on test sets in different environments have improved the detection accuracy rate by 4.53%, indicating that the algorithm has high robustness. At the same time, the detection accuracy and speed of the investigated algorithm are higher than other algorithms, indicating that the algorithm has higher detection performance.

Download Full-text

2053

Journal of Clinical and Translational Science ◽

10.1017/cts.2017.156 ◽

2017 ◽

Vol 1 (S1) ◽

pp. 43-43

Author(s):

Yue Zang ◽

Tom Greene ◽

Trent Matheson ◽

Erin Rothwell

Keyword(s):

Statistical Power ◽

Sensitivity Analyses ◽

Initial Contact ◽

Data Sets ◽

Data Set ◽

Academic Promotion ◽

University Of Utah ◽

School Of Medicine ◽

Study Population ◽

The University

OBJECTIVES/SPECIFIC AIMS: In this study, we propose to investigate effectiveness of 2 core services provided by the Center for Clinical and Translational Science (CCTS), home for CTSA program in the School of Medicine at the University of Utah. METHODS/STUDY POPULATION: We will apply a longitudinal database of research and tenure track faculty (n>600) in the School of Medicine at the University of Utah from 2006 to 2016 to estimate the effect of initial usage of the biostatistics and clinical services cores of the University of Utah CCTS on the probability of (a) ≥1 peer reviewed publication, (b) external grant funding, and (c) academic promotion within 1, 2, and 3 years after the initial contact. We will apply a “new users” design (Hernan et al., Epidemiology, 2008; 19: 766–779) to compare the outcomes of faculty initiating use of the 2 CCTS cores Versus faculty without prior use of these cores in a series of cohorts defined by the calendar year of initial contract with the 2 cores, with covariate adjustment performed within each cohort to account for measured confounders. Separate outcome models will be specified for each cohort, but the statistical models will be fit to stacked augmented data sets which include the data from each cohort. Using the stacked data set, results will be pooled across each of the cohorts to increase statistical power. Robust sandwich estimates of standard errors will be used to account for the inclusion of multiple assessments for each faculty member. RESULTS/ANTICIPATED RESULTS: Estimates of the effect of initiation of new CTSA usage on academic productivity outcomes will be obtained, and provided in conjunction with sensitivity analyses to address the potential impact of uncontrolled confounding. DISCUSSION/SIGNIFICANCE OF IMPACT: The proposed evaluation strategy should overcome some of the biases inherent in typical metrics for effectiveness of CTSA programs, and will be applied to evaluate success of future initiatives.

Download Full-text