scholarly journals Selfee: Self-supervised Features Extraction of animal behaviors

2021 ◽  
Author(s):  
Yinjun Jia ◽  
Shuai-shuai Li ◽  
Xuan Guo ◽  
Junqiang Hu ◽  
Xiao-Hong Xu ◽  
...  
Keyword(s):  
Animal Behavior ◽  
Temporal Dynamics ◽  
Video Recordings ◽  
Animal Behaviors ◽  
Video Frames ◽  
Neuroscience Research ◽  
Depth Analysis ◽  
Time Series Analyses ◽  
Supervised Feature Extraction

Fast and accurately characterizing animal behaviors is crucial for neuroscience research. Deep learning models are efficiently used in the laboratories for behavior analysis. However, it has not been achieved to use a fully unsupervised method to extract comprehensive and discriminative features directly from raw behavior video frames for annotation and analysis purposes. Here, we report a self supervised feature extraction (Selfee) convolutional neural network with multiple downstream applications to process video frames of animal behavior in an end to end way. Visualization and classification of the extracted features (Meta representations) validate that Selfee processes animal behaviors in a comparable way of human understanding. We demonstrate that Meta representations can be efficiently used to detect anomalous behaviors that are indiscernible to human observation and hint in depth analysis. Furthermore, time series analyses of Meta representations reveal the temporal dynamics of animal behaviors. In conclusion, we present a self supervised learning approach to extract comprehensive and discriminative features directly from raw video recordings of animal behaviors and demonstrate its potential usage for various downstream applications.

scholarly journals Classification and Measurement of the Firms’ Resources and Capabilities Applied to Eco-Innovation Projects from a Resource-Based View Perspective

2018 ◽  
Vol 10 (9) ◽  
pp. 3161 ◽  
Author(s):  
Pilar Portillo-Tarragona ◽  
Sabina Scarpellini ◽  
Jose Moneva ◽  
Jesus Valero-Gil ◽  
Alfonso Aranda-Usón
Keyword(s):  
Natural Resources ◽  
Conceptual Framework ◽  
Case Studies ◽  
Corporate Sustainability ◽  
Policy Makers ◽  
Resource Based View ◽  
Depth Analysis ◽  
Innovation Projects ◽  
Resources And Capabilities

Interest from academics, policy–makers and practitioners in eco-innovation has increased as it enables the optimization of the use of natural resources improving competitiveness and it provides a conceptual framework for corporate sustainability. In this context, this paper provides an in-depth analysis and a wide classification of the specific indicators for the integrated measurement of eco-innovation projects in business from a resource-based view (RBV). The specific metrics were tested to measure the economic-financial and environmental resources and capabilities applied by five Spanish firms to eco-innovation projects, selected as case studies.

Permutation Min-Entropy and Statistical Complexity Analysis of Electricity Spot Price

2015 ◽  
Vol 14 (04) ◽  
pp. 1550040 ◽  
Author(s):  
Qingju Fan ◽  
Dan Li
Keyword(s):  
Temporal Dynamics ◽  
Complexity Analysis ◽  
Spot Price ◽  
Temporal Correlations ◽  
Price Series ◽  
Statistical Complexity ◽  
Electricity Spot Price ◽  
Insight Into ◽  
Refined Classification

In this study, we investigate the subtle temporal dynamics of California 1999–2000 spot price series based on permutation min-entropy (PME) and complexity-entropy causality plane. The dynamical transitions of price series are captured and the temporal correlations of price series are also discriminated by the recently introduced PME. Moreover, utilizing the CECP, we provide a refined classification of the monthly price dynamics and obtain an insight into the stochastic nature of price series. The results uncover that the spot price signal presents diverse temporal correlations and exhibits a higher stochastic behavior during the periods of crisis.

scholarly journals SIPEC: the deep-learning Swiss knife for behavioral data analysis

2020 ◽  
Author(s):  
Markus Marks ◽  
Jin Qiuhan ◽  
Oliver Sturman ◽  
Lukas von Ziegler ◽  
Sepp Kollmorgen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Animal Behavior ◽  
Home Cage ◽  
Complex Environments ◽  
Or Groups ◽  
Multiple Behaviors ◽  
Freely Moving ◽  
Using Data

ABSTRACTAnalysing the behavior of individuals or groups of animals in complex environments is an important, yet difficult computer vision task. Here we present a novel deep learning architecture for classifying animal behavior and demonstrate how this end-to-end approach can significantly outperform pose estimation-based approaches, whilst requiring no intervention after minimal training. Our behavioral classifier is embedded in a first-of-its-kind pipeline (SIPEC) which performs segmentation, identification, pose-estimation and classification of behavior all automatically. SIPEC successfully recognizes multiple behaviors of freely moving mice as well as socially interacting nonhuman primates in 3D, using data only from simple mono-vision cameras in home-cage setups.

scholarly journals Classification of Action Based Video using Heterogeneous Feature Extraction and SVM

2019 ◽  
Vol 8 (11) ◽  
pp. 1887-1892
Keyword(s):  
Optical Flow ◽  
Video Sequence ◽  
Human Action ◽  
Video Data ◽  
Support Vector ◽  
Svm Classifier ◽  
Video Frames ◽  
Integral Role ◽  
Heterogeneous Feature

Action recognition (AR) plays a fundamental role in computer vision and video analysis. We are witnessing an astronomical increase of video data on the web and it is difficult to recognize the action in video due to different view point of camera. For AR in video sequence, it depends upon appearance in frame and optical flow in frames of video. In video spatial and temporal components of video frames features play integral role for better classification of action in videos. In the proposed system, RGB frames and optical flow frames are used for AR with the help of Convolutional Neural Network (CNN) pre-trained model Alex-Net extract features from fc7 layer. Support vector machine (SVM) classifier is used for the classification of AR in videos. For classification purpose, HMDB51 dataset have been used which includes 51 Classes of human action. The dataset is divided into 51 action categories. Using SVM classifier, extracted features are used for classification and achieved best result 95.6% accuracy as compared to other techniques of the state-of- art.v

scholarly journals Towards a better understanding of the low recall of insertion variants with short-read based variant callers

2020 ◽  
Author(s):  
Wesley Delage ◽  
Julien Thevenon ◽  
Claire Lemaitre
Keyword(s):  
Gold Standard ◽  
Insertion Site ◽  
Structural Variants ◽  
Genomic Context ◽  
Breakpoint Junction ◽  
Short Read ◽  
Depth Analysis ◽  
Long Read ◽  
The Impact

AbstractSince 2009, numerous tools have been developed to detect structural variants (SVs) using short read technologies. Insertions >50 bp are one of the hardest type to discover and are drastically underrepresented in gold standard variant callsets. The advent of long read technologies has completely changed the situation. In 2019, two independent cross technologies studies have published the most complete variant callsets with sequence resolved insertions in human individuals. Among the reported insertions, only 17 to 37% could be discovered with short-read based tools. In this work, we performed an in-depth analysis of these unprecedented insertion callsets in order to investigate the causes of such failures. We have first established a precise classification of insertion variants according to four layers of characterization: the nature and size of the inserted sequence, the genomic context of the insertion site and the breakpoint junction complexity. Because these levels are intertwined, we then used simulations to characterize the impact of each complexity factor on the recall of several SV callers. Simulations showed that the most impacting factor was the insertion type rather than the genomic context, with various difficulties being handled differently among the tested SV callers, and they highlighted the lack of sequence resolution for most insertion calls. Our results explain the low recall by pointing out several difficulty factors among the observed insertion features and provide avenues for improving SV caller algorithms and their [email protected]

scholarly journals Watching a Small Portion could be as Good as Watching All: Towards Efficient Video Classification

2018 ◽  
Author(s):  
Hehe Fan ◽  
Zhongwen Xu ◽  
Linchao Zhu ◽  
Chenggang Yan ◽  
Jianjun Ge ◽  
...  
Keyword(s):  
Large Scale ◽  
Sampling Rate ◽  
Computational Cost ◽  
Confidence Score ◽  
Video Content ◽  
Video Classification ◽  
Video Frames ◽  
Similar Accuracy ◽  
Efficient Video

We aim to significantly reduce the computational cost for classification of temporally untrimmed videos while retaining similar accuracy. Existing video classification methods sample frames with a predefined frequency over entire video. Differently, we propose an end-to-end deep reinforcement approach which enables an agent to classify videos by watching a very small portion of frames like what we do. We make two main contributions. First, information is not equally distributed in video frames along time. An agent needs to watch more carefully when a clip is informative and skip the frames if they are redundant or irrelevant. The proposed approach enables the agent to adapt sampling rate to video content and skip most of the frames without the loss of information. Second, in order to have a confident decision, the number of frames that should be watched by an agent varies greatly from one video to another. We incorporate an adaptive stop network to measure confidence score and generate timely trigger to stop the agent watching videos, which improves efficiency without loss of accuracy. Our approach reduces the computational cost significantly for the large-scale YouTube-8M dataset, while the accuracy remains the same.

Classification of Biological Sequences

Data Mining ◽  
2013 ◽  
pp. 1019-1042
Author(s):  
Pratibha Rani ◽  
Vikram Pudi
Keyword(s):  
Naive Bayes ◽  
Analysis Data ◽  
Naïve Bayes ◽  
Biological Data ◽  
Rapid Progress ◽  
Biological Data Analysis ◽  
Depth Analysis ◽  
Iterative Scaling ◽  
Mining Methods

The rapid progress of computational biology, biotechnology, and bioinformatics in the last two decades has led to the accumulation of tremendous amounts of biological data that demands in-depth analysis. Data mining methods have been applied successfully for analyzing this data. An important problem in biological data analysis is to classify a newly discovered sequence like a protein or DNA sequence based on their important features and functions, using the collection of available sequences. In this chapter, we study this problem and present two Bayesian classifiers RBNBC (Rani & Pudi, 2008a) and REBMEC (Rani & Pudi, 2008c). The algorithms used in these classifiers incorporate repeated occurrences of subsequences within each sequence (Rani, 2008). Specifically, Repeat Based Naive Bayes Classifier (RBNBC) uses a novel formulation of Naive Bayes, and the second classifier, Repeat Based Maximum Entropy Classifier (REBMEC) uses a novel framework based on the classical Generalized Iterative Scaling (GIS) algorithm.

Community Detection Approaches in Real World Networks

2014 ◽  
Vol 6 (1) ◽  
pp. 35-51 ◽  
Author(s):  
Pooja Wadhwa ◽  
M.P.S Bhatia
Keyword(s):  
Community Detection ◽  
Online Social Networks ◽  
Temporal Dynamics ◽  
Detection Methods ◽  
Unified Approach ◽  
Detection Algorithms ◽  
Dynamic Community Detection ◽  
Dynamic Communities ◽  
Dynamic Community

Online social networks have been continuously evolving and one of their prominent features is the evolution of communities which can be characterized as a group of people who share a common relationship among themselves. Earlier studies on social network analysis focused on static network structures rather than dynamic processes, however, with the passage of time, the networks have also evolved and the researchers have started to focus on the aspect of studying dynamic behavior of networks. This paper aims to present an overview of community detection approaches graduating from static community detection methods towards the methods to identify dynamic communities in networks. The authors also present a classification of the existing dynamic community detection algorithms along the dimension of studying the evolution as either a two-step approach comprising of community detection via static methods and then applying temporal dynamics or a unified approach which comprises of dynamic detection of communities along with their evolutionary characteristics.

E-Marketplace Emergence

2012 ◽  
Vol 10 (1) ◽  
pp. 14-32 ◽  
Author(s):  
Bahar Miri Movahedi ◽  
Kayvan Miri Lavassani ◽  
Vinod Kumar
Keyword(s):  
Future Trends ◽  
Electronic Marketplaces ◽  
Dimensional Classification ◽  
Depth Analysis ◽  
Comprehensive Classification

The present paper provides a comprehensive multi-dimensional classification of Electronic Marketplaces (EM). The paper opens the discussion by investigating the early utilizations of the concept of EM and makes some original references to the early uses of the technology in marketplaces. After an in-depth analysis of the concept of EM, the developments and application of the EM as an intra- and inter-organizational electronic platform is explicitly described. Finally, a comprehensive classification of EMs is presented followed by a discussion of future trends in study and utilization of EMs.

Liquidity of financial markets: a review

2019 ◽  
Vol 37 (2) ◽  
pp. 201-227 ◽  
Author(s):  
Abhinava Tripathi ◽  
Alok Dixit ◽  
Vipul Vipul
Keyword(s):  
Emerging Markets ◽  
Financial Markets ◽  
Return Predictability ◽  
Research Papers ◽  
Ongoing Research ◽  
Content Type ◽  
Research Areas ◽  
Comprehensive Collection ◽  
Depth Analysis

Purpose The purpose of this study is to systematically review and analyze the literature in the area of liquidity of financial markets. The study summarizes the key findings and approaches and highlights the research gaps in the extant literature. Design/methodology/approach A variety of reputed databases are utilized to select 100 research papers, from a large pool of nearly 3,000 research papers spanning between 1972 and 2018 using systematic literature review methodology. The selected research papers are organized to provide an in-depth analysis and an account of the ongoing research in the area of liquidity. The study uses bibliometric network visualization and word-cloud analyses to compile and analyze the literature. Findings The study summarizes the recent approaches in the liquidity research on aspects such as methodologies followed, variables applied, sub-areas covered, and the types of economies and markets covered. The article shows that the literature on liquidity in the emerging markets (e.g. China and India) is deficient. Overall, the following research areas related to liquidity need further exploration in the context of emerging markets: liquidity beyond the best bid-ask quotes, intraday return predictability using microstructure variables (e.g. order imbalances), impact of algorithmic-trading and volatility of liquidity. Originality/value To the best of authors’ knowledge, in the recent past, a detailed account of the literature on liquidity has not been published. It provides a comprehensive collection and classification of the literature on the liquidity of financial markets. This would be helpful to the future researchers, academics and practitioners in the area of financial markets.

Sign in / Sign up

Export Citation Format

Share Document