Human Interaction Dataset Research Articles

Intronic small nucleolar RNAs regulate host gene splicing through base pairing with their adjacent intronic sequences

BackgroundSmall nucleolar RNAs (snoRNAs) are abundant noncoding RNAs best known for their involvement in ribosomal RNA maturation. In mammals, most expressed snoRNAs are embedded in introns of longer genes and produced through transcription and splicing of their host. Intronic snoRNAs were long viewed as inert passengers with little effect on host expression. However, a recent study reported a snoRNA influencing the splicing and ultimate output of its host gene. Overall, the general contribution of intronic snoRNAs to host expression remains unclear.ResultsComputational analysis of large-scale human RNA-RNA interaction datasets indicates that 30% of detected snoRNAs interact with their host transcripts. Many snoRNA-host duplexes are located near alternatively spliced exons and display high sequence conservation suggesting a possible role in splicing regulation. The study of the model SNORD2-EIF4A2 duplex indicates that the snoRNA interaction with the host intronic sequence conceals the branch point leading to decreased inclusion of the adjacent alternative exon. Extended SNORD2 sequence containing the interacting intronic region accumulates in sequencing datasets in a cell-type-specific manner. Antisense oligonucleotides and mutations that disrupt the formation of the snoRNA-intron structure promote the splicing of the alternative exon, shifting the EIF4A2 transcript ratio away from nonsense-mediated decay.ConclusionsMany snoRNAs form RNA duplexes near alternative exons of their host transcripts, placing them in optimal positions to control host output as shown for the SNORD2-EIF4A2 model system. Overall, our study supports a more widespread role for intronic snoRNAs in the regulation of their host transcript maturation.

Complex Prediction in Large PPI Networks Using Expansion and Stripe of Core Cliques.

The widespread availability and importance of large-scale protein-protein interaction (PPI) data demand a flurry of research efforts to understand the organisation of a cell and its functionality by analysing these data at the network level. In the bioinformatics and data mining fields, network clustering acquired a lot of attraction to examine a PPI network's topological and functional aspects. The clustering of PPI networks has been proven to be an excellent method for discovering functional modules, disclosing functions of unknown proteins, and other tasks in numerous research over the last decade. This research proposes a unique graph mining approach to detect protein complexes using dense neighbourhoods (highly connected regions) in an interaction graph. Our technique first finds size-3 cliques associated with each edge (protein interaction), and then these core cliques are expanded to form high-density subgraphs. Loosely connected proteins are stripped out from these subgraphs to produce a potential protein complex. Finally, the redundancy is removed based on the Jaccard coefficient. Computational results are presented on the yeast and human protein interaction dataset to highlight our proposed technique's efficiency. Predicted protein complexes of the proposed approach have a significantly higher score of similarity to those used as gold standards in the CYC-2008 and CORUM benchmark databases than other existing approaches.

FT-HID: a large-scale RGB-D dataset for first- and third-person human interaction analysis

Analysis of human interaction is one important research topic of human motion analysis. It has been studied either using first-person vision (FPV) or third-person vision (TPV). However, the joint learning of both types of vision has so far attracted little attention. One of the reasons is the lack of suitable datasets that cover both FPV and TPV. In addition, existing benchmark datasets of either FPV or TPV have several limitations, including the limited number of samples, participant subjects, interaction categories, and modalities. In this work, we contribute a large-scale human interaction dataset, namely FT-HID dataset. FT-HID contains pair-aligned samples of first-person and third-person visions. The dataset was collected from 109 distinct subjects and has more than 90K samples for three modalities. The dataset has been validated by using several existing action recognition methods. In addition, we introduce a novel multi-view interaction mechanism for skeleton sequences, and a joint learning multi-stream framework for first-person and third-person visions. Both methods yield promising results on the FT-HID dataset. It is expected that the introduction of this vision-aligned large-scale dataset will promote the development of both FPV and TPV, and their joint learning techniques for human action analysis.

Hybrid approach for disease comorbidity and disease gene prediction using heterogeneous dataset

High throughput analysis and large scale integration of biological data led to leading researches in the field of bioinformatics. Recent years witnessed the development of various methods for disease associated gene prediction and disease comorbidity predictions. Most of the existing techniques use network-based approaches and similarity-based approaches for these predictions. Even though network-based approaches have better performance, these methods rely on text data from OMIM records and PubMed abstracts. In this method, a novel algorithm (HDCDGP) is proposed for disease comorbidity prediction and disease associated gene prediction. Disease comorbidity network and disease gene network were constructed using data from gene ontology (GO), human phenotype ontology (HPO), protein-protein interaction (PPI) and pathway dataset. Modified random walk restart algorithm was applied on these networks for extracting novel disease-gene associations. Experimental results showed that the hybrid approach has better performance compared to existing systems with an overall accuracy around 85%.

AIR-Act2Act: Human–human interaction dataset for teaching non-verbal social behaviors to robots

To better interact with users, a social robot should understand the users’ behavior, infer the intention, and respond appropriately. Machine learning is one way of implementing robot intelligence. It provides the ability to automatically learn and improve from experience instead of explicitly telling the robot what to do. Social skills can also be learned through watching human–human interaction videos. However, human–human interaction datasets are relatively scarce to learn interactions that occur in various situations. Moreover, we aim to use service robots in the elderly care domain; however, there has been no interaction dataset collected for this domain. For this reason, we introduce a human–human interaction dataset for teaching non-verbal social behaviors to robots. It is the only interaction dataset that elderly people have participated in as performers. We recruited 100 elderly people and 2 college students to perform 10 interactions in an indoor environment. The entire dataset has 5,000 interaction samples, each of which contains depth maps, body indexes, and 3D skeletal data that are captured with three Microsoft Kinect v2 sensors. In addition, we provide the joint angles of a humanoid NAO robot which are converted from the human behavior that robots need to learn. The dataset and useful Python scripts are available for download at https://github.com/ai4r/AIR-Act2Act. It can be used to not only teach social skills to robots but also benchmark action recognition algorithms.

A Coordinated Approach by Public Domain Bioinformatics Resources to Aid the Fight Against Alzheimer's Disease Through Expert Curation of Key Protein Targets.

Background:The analysis and interpretation of data generated from patient-derived clinical samples relies on access to high-quality bioinformatics resources. These are maintained and updated by expert curators extracting knowledge from unstructured biological data described in free-text journal articles and converting this into more structured, computationally-accessible forms. This enables analyses such as functional enrichment of sets of genes/proteins using the Gene Ontology, and makes the searching of data more productive by managing issues such as gene/protein name synonyms, identifier mapping, and data quality.Objective:To undertake a coordinated annotation update of key public-domain resources to better support Alzheimer’s disease research.Methods:We have systematically identified target proteins critical to disease process, in part by accessing informed input from the clinical research community.Results:Data from 954 papers have been added to the UniProtKB, Gene Ontology, and the International Molecular Exchange Consortium (IMEx) databases, with 299 human proteins and 279 orthologs updated in UniProtKB. 745 binary interactions were added to the IMEx human molecular interaction dataset.Conclusion:This represents a significant enhancement in the expert curated data pertinent to Alzheimer’s disease available in a number of biomedical databases. Relevant protein entries have been updated in UniProtKB and concomitantly in the Gene Ontology. Molecular interaction networks have been significantly extended in the IMEx Consortium dataset and a set of reference protein complexes created. All the resources described are open-source and freely available to the research community and we provide examples of how these data could be exploited by researchers.

A Multi-Feature Representation of Skeleton Sequences for Human Interaction Recognition

Inspired from the promising performances achieved by recurrent neural networks (RNN) and convolutional neural networks (CNN) in action recognition based on skeleton, this paper presents a deep network structure which combines both CNN for classification and RNN to achieve attention mechanism for human interaction recognition. Specifically, the attention module in this structure is utilized to give various levels of attention to various frames by different weights, and the CNN is employed to extract the high-level spatial and temporal information of skeleton data. These two modules seamlessly form a single network architecture. In addition, to eliminate the impact of different locations and orientations, a coordinate transformation is conducted from the original coordinate system to the human-centric coordinate system. Furthermore, three different features are extracted from the skeleton data as the inputs of three subnetworks, respectively. Eventually, these subnetworks fed with different features are fused as an integrated network. The experimental result shows the validity of the proposed approach on two widely used human interaction datasets.

An Efficient Classifier using Machine Learning Technique for Individual Action Identification

Human action recognition is an important branch of computer vision and is getting increasing attention from researchers. It has been applied in many areas including surveillance, healthcare, sports and computer games. This proposed work focuses on designing a human action recognition system for a human interaction dataset. Literature research is conducted to determine suitable algorithms for action recognition. In this proposed work, three machine learning models are implemented as the classifiers for human actions. An image processing method and a projection-based feature extraction algorithm are presented to generate training examples for the classifier. The action recognition task is divided into two parts: 4-class human posture recognition and 5-class human motion recognition. Classifiers are trained to classify input data into one of the posture or motion classes. Performance evaluations of the classifiers are carried out to assess validation accuracy and test accuracy for action recognition. The architecture designs for the centralized and distributed recognition systems are presented. Later these designed architectures are simulated on the sensor network to evaluate feasibility and recognition performance. Overall, the designed classifiers show a promising performance for action recognition.

Multiple human upper bodies detection via candidate-region convolutional neural network

Upper body detection on images is a challenging task in practical application scenarios and shares all the difficulties of object detection. This paper focuses on the problems of the multiple upper bodies, including the diversity of appearances, the various object scales, and the frequent occlusions. To address these problems, we divide the upper body detection into two stages to form a Candidate-Region Convolutional Neural Network(CR-CNN). In the upper body candidate generation stage, a deep hierarchical model is proposed. This model is built by a graphical model that contains the appearance model and deformable model. The appearance model is built based on the feature maps in a CNN, and the deformable model is defined by each pair of connected parts to compute the relative spatial information in the graphical model. In the upper body candidate refining stage, the detected bounding boxes serve as the candidate regions and refined in the CR-CNN. Moreover, multiple convolutional features are introduced into the CR-CNN to provide the local information and contextual information. The proposed method is compared with the state of the art on the TV Human Interaction (TVHI) dataset and HollywoodHeads dataset. The experimental results demonstrate the effectiveness of the proposed method.

A structured multi-feature representation for recognizing human action and interaction

Abstract Active research has been carried out for human action recognition using 3D human skeleton joints with the release of cost-efficient RGB-D sensors. However, extracting discriminative features from noisy skeleton sequences to effectively distinguish various human action or interaction categories still remains challenging. This paper proposes a structured multi-feature representation for human action and interaction recognition. Specifically, a novel kernel enhanced bag of semantic words (BSW) is designed to represent the dynamic property of skeleton trajectories. By aggregating BSW with the geometric feature, a GBSW representation is constructed for human action recognition. For human interaction recognition where the cooperation of each subject matters, a GBSWC representation is proposed via combining the GBSW feature with a correlation feature which addresses the intrinsic relationship between interactive persons. Experimental results on several human action and interaction datasets demonstrate the superior performances of the proposed features over the state-of-the-art methods.

Position Matters: Network Centrality Considerably Impacts Rates of Protein Evolution in the Human Protein-Protein Interaction Network.

The proteins of any organism evolve at disparate rates. A long list of factors affecting rates of protein evolution have been identified. However, the relative importance of each factor in determining rates of protein evolution remains unresolved. The prevailing view is that evolutionary rates are dominantly determined by gene expression, and that other factors such as network centrality have only a marginal effect, if any. However, this view is largely based on analyses in yeasts, and accurately measuring the importance of the determinants of rates of protein evolution is complicated by the fact that the different factors are often correlated with each other, and by the relatively poor quality of available functional genomics data sets. Here, we use correlation, partial correlation and principal component regression analyses to measure the contributions of several factors to the variability of the rates of evolution of human proteins. For this purpose, we analyzed the entire human protein–protein interaction data set and the human signal transduction network—a network data set of exceptionally high quality, obtained by manual curation, which is expected to be virtually free from false positives. In contrast with the prevailing view, we observe that network centrality (measured as the number of physical and nonphysical interactions, betweenness, and closeness) has a considerable impact on rates of protein evolution. Surprisingly, the impact of centrality on rates of protein evolution seems to be comparable, or even superior according to some analyses, to that of gene expression. Our observations seem to be independent of potentially confounding factors and from the limitations (biases and errors) of interactomic data sets.

Human Activity Recognition Based On 2d Texture Signal Pattern Analysis

Human activity recognition is an important research area of computer vision which dictates the need to automatically detect and retrieve semantic events in videos based on video contents. In this paper, we attempt to extract the foreground object from the video clip using color model and generate a unique signal pattern for the detected foreground (human). Signal pattern is generated for the extracted 2D texture features and the most significant features are selected using feature selection method. For each detected object, we can study its corresponding motion pattern, entry/exist points, and behavior patterns. Based on this information, it is efficient to improve the object detection and track the abnormal event occurrence. Experiments were performed on KTH dataset, High-Level Human interaction dataset and real time video dataset. The empirical results show that 85% of accuracy based on precision/recall measure was obtained, and the ability to recognize the activities in real time shows the promise for applied use.

Supervised framework for automatic recognition and retrieval of interaction: a framework for classification and retrieving videos with similar human interactions

This study presents supervised framework for automatic recognition and retrieval of interactions (SAFARRIs), a supervised learning framework to recognise interactions such as pushing, punching, and hugging, between a pair of human performers in a video shot. The primary contribution of the study is to extend the vectors of locally aggregated descriptors (VLADs) as a compact and discriminative video encoding representation, to solve the complex class partitioning problem of recognising human interaction. An initial codebook is generated from the training set of video shots, by extracting feature descriptors around the spatiotemporal interest points computed across frames. A bag of action words is generated by encoding the first‐order statistics of the visual words using VLAD. Support vector machine classifiers (1 against all) are trained using these codebooks. The authors have verified SAFARRI's accuracy for classification and retrieval (query by example). SAFARRI is free from tracking or recognition of body parts and capable of identifying the region of interaction in video shots. It gives superior retrieval and classification performances over recently proposed methods, on two publicly available human interaction datasets.

A bioinformatic survey of RNA-binding proteins in Plasmodium.

BackgroundThe malaria parasites in the genus Plasmodium have a very complicated life cycle involving an invertebrate vector and a vertebrate host. RNA-binding proteins (RBPs) are critical factors involved in every aspect of the development of these parasites. However, very few RBPs have been functionally characterized to date in the human parasite Plasmodium falciparum.MethodsUsing different bioinformatic methods and tools we searched P. falciparum genome to list and annotate RBPs. A representative 3D models for each of the RBD domain identified in P. falciparum was created using I-TESSAR and SWISS-MODEL. Microarray and RNAseq data analysis pertaining PfRBPs was performed using MeV software. Finally, Cytoscape was used to create protein-protein interaction network for CITH-Dozi and Caf1-CCR4-Not complexes.ResultsWe report the identification of 189 putative RBP genes belonging to 13 different families in Plasmodium, which comprise 3.5 % of all annotated genes. Almost 90 % (169/189) of these genes belong to six prominent RBP classes, namely RNA recognition motifs, DEAD/H-box RNA helicases, K homology, Zinc finger, Puf and Alba gene families. Interestingly, almost all of the identified RNA-binding helicases and KH genes have cognate homologs in model species, suggesting their evolutionary conservation. Exploration of the existing P. falciparum blood-stage transcriptomes revealed that most RBPs have peak mRNA expression levels early during the intraerythrocytic development cycle, which taper off in later stages. Nearly 27 % of RBPs have elevated expression in gametocytes, while 47 and 24 % have elevated mRNA expression in ookinete and asexual stages. Comparative interactome analyses using human and Plasmodium protein-protein interaction datasets suggest extensive conservation of the PfCITH/PfDOZI and PfCaf1-CCR4-NOT complexes.ConclusionsThe Plasmodium parasites possess a large number of putative RBPs belonging to most of RBP families identified so far, suggesting the presence of extensive post-transcriptional regulation in these parasites. Taken together, in silico identification of these putative RBPs provides a foundation for future functional studies aimed at defining a unique network of post-transcriptional regulation in P. falciparum.Electronic supplementary materialThe online version of this article (doi:10.1186/s12864-015-2092-1) contains supplementary material, which is available to authorized users.

Lung Lesion Extraction Using a Toboggan Based Growing Automatic Segmentation Approach.

The accurate segmentation of lung lesions from computed tomography (CT) scans is important for lung cancer research and can offer valuable information for clinical diagnosis and treatment. However, it is challenging to achieve a fully automatic lesion detection and segmentation with acceptable accuracy due to the heterogeneity of lung lesions. Here, we propose a novel toboggan based growing automatic segmentation approach (TBGA) with a three-step framework, which are automatic initial seed point selection, multi-constraints 3D lesion extraction and the final lesion refinement. The new approach does not require any human interaction or training dataset for lesion detection, yet it can provide a high lesion detection sensitivity (96.35%) and a comparable segmentation accuracy with manual segmentation (P > 0.05), which was proved by a series assessments using the LIDC-IDRI dataset (850 lesions) and in-house clinical dataset (121 lesions). We also compared TBGA with commonly used level set and skeleton graph cut methods, respectively. The results indicated a significant improvement of segmentation accuracy . Furthermore, the average time consumption for one lesion segmentation was under 8 s using our new method. In conclusion, we believe that the novel TBGA can achieve robust, efficient and accurate lung lesion segmentation in CT images automatically.

When susceptible-infectious-susceptible contagion meets time-varying networks with identical infectivity

Transmission of infectious diseases among populations can be modelled as contagion processes on contact networks. These contact networks are highly evolved in time and are represented by time-varying networks. The agents in contagion processes may have finite infectivity independently of their connectivity. Here we present an analytical framework of the susceptible-infectious-susceptible contagion process on time-varying networks, namely activity-driven networks with identical infectivity. We derive the critical epidemic thresholds and immunization thresholds as a function of infectivity, and prove that targeted immunizations are more efficient than random immunizations independently of the infectivity. We validate our conclusions in a large-scale human indoor interaction data set. Finally, we assess the effects of finite size.

Large-scale protein-protein interactions detection by integrating big biosensing data with computational model.

Protein-protein interactions are the basis of biological functions, and studying these interactions on a molecular level is of crucial importance for understanding the functionality of a living cell. During the past decade, biosensors have emerged as an important tool for the high-throughput identification of proteins and their interactions. However, the high-throughput experimental methods for identifying PPIs are both time-consuming and expensive. On the other hand, high-throughput PPI data are often associated with high false-positive and high false-negative rates. Targeting at these problems, we propose a method for PPI detection by integrating biosensor-based PPI data with a novel computational model. This method was developed based on the algorithm of extreme learning machine combined with a novel representation of protein sequence descriptor. When performed on the large-scale human protein interaction dataset, the proposed method achieved 84.8% prediction accuracy with 84.08% sensitivity at the specificity of 85.53%. We conducted more extensive experiments to compare the proposed method with the state-of-the-art techniques, support vector machine. The achieved results demonstrate that our approach is very promising for detecting new PPIs, and it can be a helpful supplement for biosensor-based PPI data detection.

Prediction of regulation relationship between protein interactions in signaling networks

The discovery of regulation relationship of protein interactions is crucial for the mechanism research in signaling network. Bioinformatics methods can be used to accelerate the discovery of regulation relationship between protein interactions, to distinguish the activation relations from inhibition relations. In this paper, we describe a novel method to predict the regulation relations of protein interactions in the signaling network. We detected 4,417 domain pairs that were significantly enriched in the activation or inhibition dataset. Three machine learning methods, logistic regression, support vector machines(SVMs), and naïve bayes, were explored in the classifier models. The prediction power of three different models was evaluated by 5-fold cross-validation and the independent test dataset. The area under the receiver operating characteristic curve for logistic regression, SVM, and naïve bayes models was 0.946, 0.905 and 0.809, respectively. Finally, the logistic regression classifier was applied to the human proteome-wide interaction dataset, and 2,591 interactions were predicted with their regulation relations, with 2,048 in activation and 543 in inhibition. This model based on domains can be used to identify the regulation relations between protein interactions and furthermore reconstruct signaling pathways.

Improving Functional Modules Discovery by Enriching Interaction Networks with Gene Profiles

Recent advances in proteomic and transcriptomic technologies resulted in the accumulation of vast amount of high-throughput data that span multiple biological processes and characteristics in different organisms. Much of the data come in the form of interaction networks and mRNA expression arrays. An important task in systems biology is functional modules discovery where the goal is to uncover well-connected sub-networks (modules). These discovered modules help to unravel the underlying mechanisms of the observed biological processes. While most of the existing module discovery methods use only the interaction data, in this work we propose, CLARM, which discovers biological modules by incorporating gene profiles data with protein-protein interaction networks. We demonstrate the effectiveness of CLARM on Yeast and Human interaction datasets, and gene expression and molecular function profiles. Experiments on these real datasets show that the CLARM approach is competitive to well established functional module discovery methods. Keywords: Biological processes, CLARM, expression arrays, functional modules, interaction proteomic, sub-networks.

Human Pose Estimation and Activity Recognition From Multi-View Videos: Comparative Explorations of Recent Developments

This paper presents a review and comparative study of recent multi-view approaches for human 3D pose estimation and activity recognition. We discuss the application domain of human pose estimation and activity recognition and the associated requirements, covering: advanced human–computer interaction (HCI), assisted living, gesture-based interactive games, intelligent driver assistance systems, movies, 3D TV and animation, physical therapy, autonomous mental development, smart environments, sport motion analysis, video surveillance, and video annotation. Next, we review and categorize recent approaches which have been proposed to comply with these requirements. We report a comparison of the most promising methods for multi-view human action recognition using two publicly available datasets: the INRIA Xmas Motion Acquisition Sequences (IXMAS) Multi-View Human Action Dataset, and the i3DPost Multi-View Human Action and Interaction Dataset. To compare the proposed methods, we give a qualitative assessment of methods which cannot be compared quantitatively, and analyze some prominent 3D pose estimation techniques for application, where not only the performed action needs to be identified but a more detailed description of the body pose and joint configuration. Finally, we discuss some of the shortcomings of multi-view camera setups and outline our thoughts on future directions of 3D body pose estimation and human action recognition.