scholarly journals MSBOTS: a multiple small biological organism tracking system robust against non-ideal detection and segmentation conditions

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e11750
Author(s):  
Xiaoying Wang ◽  
Eva Cheng ◽  
Ian S. Burnett
Keyword(s):  
Standard Deviation ◽  
State Of The Art ◽  
Tracking System ◽  
Pharmaceutical Research ◽  
Research Use ◽  
Public Research ◽  
Biological Organism ◽  
Movement Trajectories ◽  
Imaging Conditions ◽  
Biological Organisms

Accurately tracking a group of small biological organisms using algorithms to obtain their movement trajectories is essential to biomedical and pharmaceutical research. However, object mis-detection, segmentation errors and overlapped individual trajectories are particularly common issues that restrict the development of automatic multiple small organism tracking research. Extending on previous work, this paper presents an accurate and generalised Multiple Small Biological Organism Tracking System (MSBOTS), whose general feasibility is tested on three types of organisms. Evaluated on zebrafish, Artemia and Daphnia video datasets with a wide variety of imaging conditions, the proposed system exhibited decreased overall Multiple Object Tracking Precision (MOTP) errors of up to 77.59%. Moreover, MSBOTS obtained more reliable tracking trajectories with a decreased standard deviation of up to 47.68 pixels compared with the state-of-the-art idTracker system. This paper also presents a behaviour analysis module to study the locomotive characteristics of individual organisms from the obtained tracking trajectories. The developed MSBOTS with the locomotive analysis module and the tested video datasets are made freely available online for public research use.

scholarly journals MINING EFFORT DATA FROM THE OSS REPOSITORY OF DEVELOPER’S BUG FIX ACTIVITY

2016 ◽  
Vol 3 (1) ◽  
pp. 107-128
Author(s):  
Syed Nadeem Ahsan ◽  
Muhammad Tanvir Afzal ◽  
Safdar Zaman ◽  
Christian Gütel ◽  
Franz Wotawa
Keyword(s):  
Open Source ◽  
Open Source Software ◽  
State Of The Art ◽  
Tracking System ◽  
Previous History ◽  
Effort Estimation ◽  
Estimation Model ◽  
Activity Data ◽  
Actual Time ◽  
History Of

During the evolution of any software, efforts are made to fix bugs or to add new features in software. In software engineering, previous history of effort data is required to build an effort estimation model, which estimates the cost and complexity of any software. Therefore, the role of effort data is indispensable to build state-of-the-art effort estimation models. Most of the Open Source Software does not maintain any effort related information. Consequently there is no state-of-the-art effort estimation model for Open Source Software, whereas most of the existing effort models are for commercial software. In this paper we present an approach to build an effort estimation model for Open Source Software. For this purpose we suggest to mine effort data from the history of the developer’s bug fix activities. Our approach determines the actual time spend to fix a bug, and considers it as an estimated effort. Initially, we use the developer’s bug-fix-activity data to construct the developer’s activity log-book. The log-book is used to store the actual time elapsed to fix a bug. Subsequently, the log-book information is used to mine the bug fix effort data. Furthermore, the developer’s bug fix activity data is used to define three different measures for the developer’s contribution or expertise level. Finally, we used the bug-fix-activity data to visualize the developer’s collaborations and the involved source files. In order to perform an experiment we selected the Mozilla open source project and downloaded 93,607 bug reports from the Mozilla project bug tracking system i.e., Bugzilla. We also downloaded the available CVS-log data from the Mozilla project repository. In this study we reveal that in case of Mozilla only 4.9% developers have been involved in fixing 71.5% of the reported bugs.

Viewpoint: Waking up in a digital dawn: are we there yet?1

2002 ◽  
Vol 27 (3) ◽  
pp. 3-6
Author(s):  
Elisa Lanzi
Keyword(s):  
Faculty Member ◽  
Physical Environment ◽  
State Of The Art ◽  
Fine Arts ◽  
Digital Content ◽  
Research Use ◽  
Imaging Center ◽  
User Expectations ◽  
Waking Up ◽  
Building Project

A new state-of-the-art fine arts complex for our College will soon open and it includes an Imaging Center: a physical environment that will support activities related to the teaching and research use of images. A parallel building project is happening simultaneously: the development of digital content and tools to enable imaging across the campus. The bricks and mortar effort will soon result in a spectacular sunrise. As far as content and tools go, we’re still in the deepest dark before dawn, i.e. we’re not there yet. As one faculty member put it, ‘That’s nice, but now what I really need …’. These few words speak volumes about user expectations and the extraordinary effort it takes to meet them.

scholarly journals Visual Tracking Using Wang–Landau Reinforcement Sampler

2020 ◽  
Vol 10 (21) ◽  
pp. 7780
Author(s):  
Dokyeong Kwon ◽  
Junseok Kwon
Keyword(s):  
Visual Tracking ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Tracking System ◽  
Network Architectures ◽  
Tracking Accuracy ◽  
Algorithm Performance ◽  
Q Learning ◽  
Number Of Visits

In this study, we present a novel tracking system, in which the tracking accuracy can be considerably enhanced by state prediction. Accordingly, we present a new Q-learning-based reinforcement method, augmented by Wang–Landau sampling. In the proposed method, reinforcement learning is used to predict a target configuration for the subsequent frame, while Wang–Landau sampler balances the exploitation and exploration degrees of the prediction. Our method can adapt to control the randomness of policy, using statistics on the number of visits in a particular state. Thus, our method considerably enhances conventional Q-learning algorithm performance, which also enhances visual tracking performance. Numerical results demonstrate that our method substantially outperforms other state-of-the-art visual trackers and runs in realtime because our method contains no complicated deep neural network architectures.

A Layer-Wise Ensemble Technique for Binary Neural Network

2021 ◽  
pp. 2152011
Author(s):  
Jiazhen Xi ◽  
Hiroyuki Yamauchi
Keyword(s):  
Standard Deviation ◽  
Prediction Error ◽  
State Of The Art ◽  
Error Reduction ◽  
Ensemble Technique ◽  
Stability Performance ◽  
Comparison Results ◽  
Binary Neural Network ◽  
Memory Footprint ◽  
Selection For

Binary neural networks (BNNs) have drawn much attention because of the most promising techniques to meet the desired memory footprint and inference speed requirements. However, they still suffer from the severe intrinsic instability of the error convergence, resulting in increase in prediction error and its standard deviation, which is mostly caused by the inherently poor representation with only two possible values of [Formula: see text]1 and [Formula: see text]1. In this work, we have proposed a cost-aware layer-wise ensemble method to address the above issue without incurring any excessive costs, which is characterized by (1) layer-wise bagging and (2) cost-aware layer selection for the bagging. One of the experimental results has shown that the proposed method reduces the error and its standard deviation by 15% and 54% on CIFAR-10, respectively, compared to the BNN serving as a baseline. This paper demonstrated and discussed such error reduction and stability performance with high versatility based on the comparison results under the various cases of combinations of the network base model with the proposed and the state-of-the-art prior techniques while changing the network sizes and datasets of CIFAR-10, SVHN, and MNIST for the evaluation.

Research of the Gaze during Perception of Textbook’s Page Elements in Bulgarian

2021 ◽  
Vol 63 (5) ◽  
pp. 467-474
Author(s):  
Despina Vasileva ◽  
Keyword(s):  
Statistical Analysis ◽  
Standard Deviation ◽  
Tracking System ◽  
Field Of View ◽  
Right Visual Field ◽  
Critical Ratio ◽  
The Gaze ◽  
Two Samples ◽  
Left And Right ◽  
The Right

A study about perception of a page from a textbook of Bulgarian is presented in the article. Participants in the experiment are 30 students of age 15 to 19 from high schools in Sofia. The study is realized through an eye tracking system. For the purposes of the study 8 stimuli (textbook pages) were constructed, containing the components as follows: “text”, “image”, and “diagram”. In each stimulus the quantity of the components differs. All possible pairs in a combination in the left and in the right field of view are presented in the stimuli. The goal of the research is to be examined the fixation of the gaze on each elements of a textbook page. To assess the characteristic of the gaze was calculated the number of saccades in the left and right visual field of the slides. The data are organized in spreadsheets. Statistical analysis is performed in two-group t-test (two samples with different variances). Mean number of saccades, standard deviation, standard error, critical ratio are calculated.

A Practical Approach for Dynamic Taint Tracking with Control-flow Relationships

2022 ◽  
Vol 31 (2) ◽  
pp. 1-43
Author(s):  
Katherine Hough ◽  
Jonathan Bell
Keyword(s):  
Tracking Control ◽  
State Of The Art ◽  
Tracking System ◽  
Control Flow ◽  
Tracking Systems ◽  
Alternative Semantics ◽  
Automated Debugging ◽  
Data Flows ◽  
Taint Tracking

Dynamic taint tracking, a technique that traces relationships between values as a program executes, has been used to support a variety of software engineering tasks. Some taint tracking systems only consider data flows and ignore control flows. As a result, relationships between some values are not reflected by the analysis. Many applications of taint tracking either benefit from or rely on these relationships being traced, but past works have found that tracking control flows resulted in over-tainting, dramatically reducing the precision of the taint tracking system. In this article, we introduce Conflux , alternative semantics for propagating taint tags along control flows. Conflux aims to reduce over-tainting by decreasing the scope of control flows and providing a heuristic for reducing loop-related over-tainting. We created a Java implementation of Conflux and performed a case study exploring the effect of Conflux on a concrete application of taint tracking, automated debugging. In addition to this case study, we evaluated Conflux ’s accuracy using a novel benchmark consisting of popular, real-world programs. We compared Conflux against existing taint propagation policies, including a state-of-the-art approach for reducing control-flow-related over-tainting, finding that Conflux had the highest F1 score on 43 out of the 48 total tests.

scholarly journals Deep Learning Based Surveillance System for Open Critical Areas

Inventions ◽  
2018 ◽  
Vol 3 (4) ◽  
pp. 69 ◽  
Author(s):  
Francesco Turchini ◽  
Lorenzo Seidenari ◽  
Tiberio Uricchio ◽  
Alberto Del Bimbo
Keyword(s):  
Anomaly Detection ◽  
State Of The Art ◽  
Detection System ◽  
Tracking System ◽  
Critical Areas ◽  
Parking Lot ◽  
Recent Computer ◽  
Quantitative Results ◽  
Public Dataset ◽  
Statistical Anomaly Detection

How to automatically monitor wide critical open areas is a challenge to be addressed. Recent computer vision algorithms can be exploited to avoid the deployment of a large amount of expensive sensors. In this work, we propose our object tracking system which, combined with our recently developed anomaly detection system. can provide intelligence and protection for critical areas. In this work. we report two case studies: an international pier and a city parking lot. We acquire sequences to evaluate the effectiveness of the approach in challenging conditions. We report quantitative results for object counting, detection, parking analysis, and anomaly detection. Moreover, we report state-of-the-art results for statistical anomaly detection on a public dataset.

scholarly journals Feasibility of Collecting Vulvar Pain Variability and Its Correlates Using Prospective Collection with Smartphones

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Ruby H. N. Nguyen ◽  
Rachael M. Turner ◽  
Jared Sieling ◽  
David A. Williams ◽  
James S. Hodges ◽  
...  
Keyword(s):  
Standard Deviation ◽  
Tracking System ◽  
Population Based ◽  
Pain Level ◽  
Vulvar Pain ◽  
Population Based Study ◽  
Prospective Data ◽  
Pain Ratings ◽  
Average Pain ◽  
Treatment Use

Context. Vulvar pain level may fluctuate in women with vulvodynia even in the absence of therapy; however, there is little evidence suggesting which factors may be associated with variability. Objective. Determine the feasibility of using smartphones to collect prospective data on vulvar pain and factors that may influence vulvar pain level. Methods. 24 clinically confirmed women were enrolled from a population-based study and asked to answer five questions using their smartphones each week for one month. Questions assessed vulvar pain level (0–10), presence of pain upon wakening, pain elsewhere in their body, treatment use, and intercourse. Results. Women completed 100% of their scheduled surveys, with acceptability measures highly endorsed. Vulvar pain ratings had a standard deviation within women of 1.6, with greater variation on average among those with higher average pain levels (P<0.001). On the weeks when a woman reported waking with pain, her vulvar pain level was higher by 1.82 on average (P<0.001). Overall, average vulvar pain level was not significantly associated with the frequency of reporting other body pains (P=0.64). Conclusion. Our smartphone tracking system promoted excellent compliance with weekly tracking of factors that are otherwise difficult to recall, some of which were highly associated with vulvar pain level.

State-of-the-Art Lentiviral Vectors for Research Use: Risk Assessment and Biosafety Recommendations

2009 ◽  
Vol 9 (6) ◽  
pp. 459-474 ◽  
Author(s):  
Katia Pauwels ◽  
Rik Gijsbers ◽  
Jaan Toelen ◽  
Axel Schambach ◽  
Karen Willard-Gallo ◽  
...  
Keyword(s):  
Risk Assessment ◽  
State Of The Art ◽  
Lentiviral Vectors ◽  
Research Use
Sign in / Sign up

Export Citation Format

Share Document