Method of fragment based tracking of displacement of a large areal object in images

Automation of technological processes using computer vision systems necessitates fragment based tracking of the displacement of a large areal object in images. Examples of such processes are monitoring mooring operations, loading and unloading operations, analyzing the environment from the vessel’s bridge, and tracking berthing. These processes are cyclical in the maritime transport industry and thus require methods for automatic data analysis in 24×7 mode. The paper proposes a method of fragment based tracking of the displacement of a large areal object in images in real time. The algorithm that underlies the method enables tracking the object fragment using convolution of pixel matrices and ensures data processing by frequency methods, including computational operations using Fourier images. The developed method is applicable for real-time tracking the object in images, even when it can be hardly distinguished from the background. The method of tracking the displacement of a large areal object proposed in the study can be used in software and hardware meters for longitudinal and vertical displacement, which are used in the maritime transport industry.

gcProfileMakeR: An R Package for Automatic Classification of Constitutive and Non-Constitutive Metabolites

Metabolomes comprise constitutive and non-constitutive metabolites produced due to physiological, genetic or environmental effects. However, finding constitutive metabolites and non-constitutive metabolites in large datasets is technically challenging. We developed gcProfileMakeR, an R package using standard Excel output files from an Agilent Chemstation GC-MS for automatic data analysis using CAS numbers. gcProfileMakeR has two filters for data preprocessing removing contaminants and low-quality peaks. The first function NormalizeWithinFiles, samples assigning retention times to CAS. The second function NormalizeBetweenFiles, reaches a consensus between files where compounds in close retention times are grouped together. The third function getGroups, establishes what is considered as Constitutive Profile, Non-constitutive by Frequency i.e., not present in all samples and Non-constitutive by Quality. Results can be plotted with the plotGroup function. We used it to analyse floral scent emissions in four snapdragon genotypes. These included a wild type, Deficiens nicotianoides and compacta affecting floral identity and RNAi:AmLHY targeting a circadian clock gene. We identified differences in scent constitutive and non-constitutive profiles as well as in timing of emission. gcProfileMakeR is a very useful tool to define constitutive and non-constitutive scent profiles. It also allows to analyse genotypes and circadian datasets to identify differing metabolites.

How to Engage Followers: Classifying Fashion Brands According to Their Instagram Profiles, Posts and Comments

In this article we show how fashion brands communicate with their follower on Instagram. We use a continuously update dataset of 68 brands, more than 300,000 posts and more than 40,000,000 comments. Starting with descriptive statistics, we uncover different behavior and success of the various brands. It turns out that there are patterns specific to luxury, mass-market and sportswear brands. Posting volume is extremely brand dependent as is the number of comments and the engagement of the community. Having understood the statistics, we turn to machine learning techniques to measure the response of the community via comments. Topic models help us understand the structure of their respective community and uncover insights regarding the response to campaigns. Having up-to-date content is essential for this kind of analysis, as the market is highly volatile. Furthermore, automatic data analysis is crucial to measure the success of campaigns and adjust them accordingly for maximum effect.

Automatic classification of single-molecule charge transport data with an unsupervised machine-learning algorithm

Based on unsupervised deep learning algorithms, an automatic data analysis method for single-molecule charge transport data is developed, which offers an opportunity to reveal more physical and chemical phenomena at the single-molecule level.

Quantitative Approach for the Analysis of Fusional Convergence Using Eye-Tracking and SacLab Toolbox

Fusional vergence is a disjunctive movement of the eyes that is made in order to obtain single vision. The aim of the study was to provide a quantitative and objective approach for analyzing the fusional convergence response using eye tracking (ET) technology and automatic data analysis provided by the intuitive SacLab toolbox previously developed by our group. We evaluated the proposed approach in a population of 26 subjects with normal binocular vision, who were tested with base-out prisms (magnitudes 4Δ, 6Δ, and 10Δ) in order to elicit fusional convergence response. Eye movements were recorded using the Viewpoint ET and analyzed using SacLab. Parameters describing both the vergence and the version components of the fusional response (convergence duration, CD; peak convergence velocity, PCV; number of intrusive saccades, NS; and mean saccadic amplitude, MSA) were automatically calculated and provided to clinicians for an objective evaluation. Results showed that the number of subjects achieving fusional convergence decreased with prism magnitude. For subjects achieving fusion CD and PCV increased significantly (p<0.05) when increasing the prism magnitude. For NS and MSA, there were no significant changes when passing to 6Δ, but a significant increase resulted when passing to 10Δ (p<0.05). Noninvasive ET associated with the intuitive SacLab toolbox may represent a valid option to objectively characterize the fusional vergence response in clinical setting. The analysis may be extended to patients with vergence disorders.