Automatic Domain Research Articles

Automatic Recognition Method of Broken Transmission Line Defect Image Based on Deep Transfer Learning

The material of ACSR in transmission line is prone to local damage, which leads to broken strand defect and reducing power consumption safety. Therefore, an automatic recognition method of broken strand defect image of transmission line based on deep transfer learning is designed to improve the automatic recognition effect of broken strand defect image. The multi-scale algorithm is used to enhance the image. In the feature extraction part of the depth transfer learning framework in the confusion domain, the multi-source domain transfer and dual flow fusion algorithm are used to extract the features of the enhanced image, and the Euclidean distance between the feature vector and the template image feature vector is used to correct the image features; using the corrected image feature training network propagated to the automatic defect recognition part and the domain classification part, the loss function and back propagation algorithm are used to reduce the loss of feature extraction and automatic defect recognition part, and the optimal results of automatic defect recognition and domain classification are obtained. The experimental results show that the method can enhance the image effectively with high definition. At different image angles, the recognition accuracy of this method is as high as 0.96, which has better automatic recognition effect of defect image.

Sensitivity analysis of the orbital motion around 469219 Kamo’oalewa (2016 HO3) to uncertainties on asteroid mass and solar radiation pressure

• Apply Automatic domain splitting (ADS) to identify motion robustness considering model uncertainties. • Polar orbits are more robust than the equatorial and the inclined ones. • Solar terminator orbit has the best robustness among all the polar orbits. • Robust motion exists even for very small bodies with weak gravity fields. • ADS could provide fast estimation of the state bounds. This study investigates the robustness of orbital motion in the vicinity of the asteroid 469219 Kamo'oalewa (2016 HO 3 ) considering the uncertainties of its mass and the solar radiation pressure. By applying the automatic domain splitting algorithm, these uncertainties are propagated and their effects on orbits with different geometries are investigated. Moreover, the bounds of the state flow are also evaluated along the propagation as an indicator of the motion sensitivity to uncertainties. An analysis of the results obtained shows that polar orbits are more robust to these uncertainties than equatorial and inclined orbits. Specifically, the solar terminator orbit is bounded within a small range and has the best robustness among all the polar orbits, thus can be used for practical mission purposes. Our studies prove that robust orbits exist even for very small bodies with weak gravity fields. Therefore, this work contributes to systematically identifying robust motions near an asteroid when uncertainties of the gravity and the SRP are simultaneously considered, addressing the challenge of real mission operations.

An Unsupervised Approach to Structuring and Analyzing Repetitive Semantic Structures in Free Text of Electronic Medical Records.

Electronic medical records (EMRs) include many valuable data about patients, which is, however, unstructured. Therefore, there is a lack of both labeled medical text data in Russian and tools for automatic annotation. As a result, today, it is hardly feasible for researchers to utilize text data of EMRs in training machine learning models in the biomedical domain. We present an unsupervised approach to medical data annotation. Syntactic trees are produced from initial sentences using morphological and syntactical analyses. In retrieved trees, similar subtrees are grouped using Node2Vec and Word2Vec and labeled using domain vocabularies and Wikidata categories. The usage of Wikidata categories increased the fraction of labeled sentences 5.5 times compared to labeling with domain vocabularies only. We show on a validation dataset that the proposed labeling method generates meaningful labels correctly for 92.7% of groups. Annotation with domain vocabularies and Wikidata categories covered more than 82% of sentences of the corpus, extended with timestamp and event labels 97% of sentences got covered. The obtained method can be used to label EMRs in Russian automatically. Additionally, the proposed methodology can be applied to other languages, which lack resources for automatic labeling and domain vocabulary.

Robot obstacle avoidance system using deep reinforcement learning

PurposeMost manufacturing plants choose the easy way of completely separating human operators from robots to prevent accidents, but as a result, it dramatically affects the overall quality and speed that is expected from human–robot collaboration. It is not an easy task to ensure human safety when he/she has entered a robot’s workspace, and the unstructured nature of those working environments makes it even harder. The purpose of this paper is to propose a real-time robot collision avoidance method to alleviate this problem.Design/methodology/approachIn this paper, a model is trained to learn the direct control commands from the raw depth images through self-supervised reinforcement learning algorithm. To reduce the effect of sample inefficiency and safety during initial training, a virtual reality platform is used to simulate a natural working environment and generate obstacle avoidance data for training. To ensure a smooth transfer to a real robot, the automatic domain randomization technique is used to generate randomly distributed environmental parameters through the obstacle avoidance simulation of virtual robots in the virtual environment, contributing to better performance in the natural environment.FindingsThe method has been tested in both simulations with a real UR3 robot for several practical applications. The results of this paper indicate that the proposed approach can effectively make the robot safety-aware and learn how to divert its trajectory to avoid accidents with humans within the workspace.Research limitations/implicationsThe method has been tested in both simulations with a real UR3 robot in several practical applications. The results indicate that the proposed approach can effectively make the robot be aware of safety and learn how to change its trajectory to avoid accidents with persons within the workspace.Originality/valueThis paper provides a novel collision avoidance framework that allows robots to work alongside human operators in unstructured and complex environments. The method uses end-to-end policy training to directly extract the optimal path from the visual inputs for the scene.

An Unsupervised Approach to Structuring and Analyzing Repetitive Semantic Structures in Free Text of Electronic Medical Records.

Electronic Medical Records (EMR) contain a lot of valuable data about patients, which is however unstructured. There is a lack of labeled medical text data in Russian and there are no tools for automatic annotation. We present an unsupervised approach to medical data annotation. Morphological and syntactical analyses of initial sentences produce syntactic trees, from which similar subtrees are then grouped by Word2Vec and labeled using dictionaries and Wikidata categories. This method can be used to automatically label EMRs in Russian and proposed methodology can be applied to other languages, which lack resources for automatic labeling and domain vocabularies.

Automatic online multi-source domain adaptation

Knowledge transfer across several streaming processes remain challenging problem not only because of different distributions of each stream but also because of rapidly changing and never-ending environments of data streams. Albeit growing research achievements in this area, most of existing works are developed for a single source domain which limits its resilience to exploit multi-source domains being beneficial to recover from concept drifts quickly and to avoid the negative transfer problem. An online domain adaptation technique under multi-source streaming processes, namely automatic online multi-source domain adaptation (AOMSDA), is proposed in this paper. The online domain adaptation strategy of AOMSDA is formulated under a coupled generative and discriminative approach of denoising autoencoder (DAE) where the central moment discrepancy (CMD)-based regularizer is integrated to handle the existence of multi-source domains thereby taking advantage of complementary information sources. The asynchronous concept drifts taking place at different time periods are addressed by a self-organizing structure and a node re-weighting strategy. Our numerical study demonstrates that AOMSDA is capable of outperforming its counterparts in 5 of 8 study cases while the ablation study depicts the advantage of each learning component. In addition, AOMSDA is general for any number of source streams. The source code of AOMSDA is shared publicly inhttps://github.com/Renchunzi-Xie/AOMSDA.git.

Domain Usability Evaluation

Contemporary software systems focus on usability and accessibility from the point of view of effectiveness and ergonomics. However, the correct usage of the domain dictionary and the description of domain relations and properties via their user interfaces are often neglected. We use the term domain usability (DU) to describe the aspects of the user interface related to the terminology and domain. Our experience showed that poor domain usability reduces the memorability and effectiveness of user interfaces. To address this problem, we describe a method called ADUE (Automatic Domain Usability Evaluation) for the automated evaluation of selected DU properties on existing user interfaces. As a prerequisite to the method, metrics for formal evaluation of domain usability, a form stereotype recognition algorithm, and general application terms filtering algorithm have been proposed. We executed ADUE on several real-world Java applications and report our findings. We also provide proposals to modify existing manual usability evaluation techniques for the purpose of domain usability evaluation.

VPP Coupling High-Fidelity Analyses and Analytical Formulations for Multihulls Sails and Appendages Optimization

A procedure for the optimization of a catamaran’s sail plan able to provide a preliminary optimal appendages configuration is described. The method integrates a sail parametric CAD model, an automatic computational domain generator and a Velocity Prediction Program (VPP) based on a combination of sail RANS computations and analytical models. The sailing speed and course angle are obtained, with an iterative process, solving the forces and moment equilibrium system of equations. Analytical formulations for the hull forces were developed and tuned against a matrix of CFD solutions. The appendages aerodynamic polars are estimated by applying preliminary design criteria from aerospace literature. The procedure permits us to find the combination of appendages configuration, rudders setting, sail planform, shape and trim that maximise the VMG (Velocity Made Good). Two versions of the sail analysis module were implemented: one adopting commercial software and one based on the use of only Open-Source codes. The solutions of the two modules were compared to evaluate advantages and limitations of the two approaches.

Dynamical structure of the motion around asteroids with uncertain gravity and solar radiation pressure

For a rendezvous space mission to a small body, the gravity field is usually modeled with large uncertainty in the preliminary mission design. Consequently, the orbital motion in the vicinity of the body cannot be predicted accurately. In this research, the automatic domain splitting (ADS) method is applied as an indicator to characterize the dynamical structure and nonlinearity of the orbital motion from a new perspective, which is instrumental in robust mission design. The uncertainties of the C20 and C22 terms in the gravitational potential are considered as these harmonic terms are usually dominant. Asteroid Steins is taken as an example. The relation among the required accuracy, the expansion order and the integration time by applying ADS is firstly investigated. Then the effects of the uncertainties of both the gravity and the solar radiation pressure (SRP) perturbation on orbits with different geometries are studied. The orbital motion is found to be more sensitive to the uncertainty of the C22 term than that of the C20 term. SRP has a significant effect on the high-altitude motion. Moreover, the bounds of the state flow over the uncertainties are also evaluated along with the propagation. The results are validated against numerical integrations and Monte Carlo simulations.

3D spatial domain gravity inversion with growing multiple polygonal cross-sections and exponential mass density contrast

An automatic 3D spatial domain inversion technique is developed to estimate basement depths of sedimentary basins from observed gravity anomalies using a prescribed exponential mass density contrast. A collage of vertical polygonal cross-sections, each one with unit thickness, in which the density contrast differs exponentially with depth describes the model space. The proposed technique estimates the optimum depth ordinates of the vertices of polygonal cross-sections from a given set of gravity anomalies following predefined convergence criteria. Initial depths to basement interface at plurality of observations are calculated presuming that the density contrast within the Bouguer slab at each observation is also varying exponentially with depth. A previously reported algorithm that make use of both analytic and numeric approaches to compute the gravity response of such 3D model space with exponential mass density contrast is adopted for forward modelling. The proposed inversion is efficient even when the gravity anomalies are available at non-uniform spatial grid intervals. Recovery of basement depths with modest error from a set of gravity anomalies attributable to a synthetic model in the presence of pseudorandom noise and also the fact that the estimated depth structure of the Almazan Basin in NE Spain correlates reasonably well with the information derived from seismic data demonstrates the applicability of the proposed inversion method. The snags associated with other existing density models in the analysis of gravity anomalies are demonstrated on both synthetic and real field anomalies.

A SYNTACTIC-BASED SENTENCE VALIDATION TECHNIQUE FOR MALAY TEXT SUMMARIZER

In the Automatic Text Summarization domain, a Sentence Compression (SC) technique is applied to the summary sentence to remove unnecessary words or phrases. The purpose of SC is to preserve the important information in the sentence and to remove the unnecessary ones without sacrificing the sentence's grammar. The existing development of Malay Natural Language Processing (NLP) tools is still under study with limited open access. The issue is the lack of a benchmark dataset in the Malay language to evaluate the quality of the summaries and to validate the compressed sentence produced by the summarizer model. Hence, our paper outlines a Syntactic-based Sentence Validation technique for Malay sentences by referring to the Malay Grammar Pattern. In this work, we propose a new derivation set of Syntactic Rules based on the Malay main Word Class to validate a Malay sentence that undergoes the SC procedure. We experimented using the Malay dataset of 100 new articles covering the Natural Disaster and Events domain to find the optimal compression rate and its effect on the summary content. An automatic evaluation using ROUGE (Recall-Oriented Understudy for Gisting Evaluation) produced a result with an average F-measure of 0.5826 and an average Recall value of 0.5925 with an optimum compression rate of 0.5 Confidence Conf value. Furthermore, a manual summary evaluation by a group of Malay experts on the grammaticality of the compressed summary sentence produced a good result of 4.11 and a readability score of 4.12 out of 5. This depicts the reliability of the proposed technique to validate the Malay sentence with promising summary content and readability results.

Inhibitory control and impulsive responses in neurodevelopmental disorders.

The impairment of inhibitory control is often assumed to be the core deficit of several neurodevelopmental disorders characterized by poor impulse control. However, could the same deficit explain different clinical phenotypes? Evidence from behavioural studies is very mixed. This is partly because inhibition is a highly complex executive function. Thus, the different types of tasks that generically tap into inhibitory control are likely to provide different outcomes. Additionally, sample inhomogeneity in terms of age, comorbidity, and medical treatment are confounding factors. Therefore, to make a reliable assessment of the deficit of inhibitory control in a given disorder, the same task and samples with similar characteristics must be employed. This article reviews and discusses studies on five neurodevelopmental disorders with impaired impulse control where these criteria have been used: Tourette syndrome; obsessive-compulsive disorder; attention-deficit/hyperactivity disorder; primary motor stereotypies; and autism spectrum disorder. Overall, they suggest that the mechanisms underlying the inability to control urges are extremely heterogeneous and cannot be ascribed to a general impairment of inhibition. These findings do not support the hypothesis that inhibitory deficits represent a transdiagnostic feature of neurodevelopmental disorders with poor impulse control. WHAT THIS PAPER ADDS: The mechanisms underlying the inability to control urges in neurodevelopmental disorders are heterogeneous. Inhibition impairments cannot generally explain all neurodevelopmental disorders characterized by poor urge control.

β-Strand-mediated interactions of protein domains.

Protein domains exist by themselves or in combination with other domains to form complex multidomain proteins. Defining domain boundaries in proteins is essential for understanding their evolution and function but is not trivial. More specifically, partitioning domains that interact by forming a single β-sheet is known to be particularly troublesome for automatic structure-based domain decomposition pipelines. Here, we study edge-to-edge β-strand interactions between domains in a protein chain, to help define the boundaries for some more difficult cases where a single β-sheet spanning over two domains gives an appearance of one. We give a number of examples where β-strands belonging to a single β-sheet do not belong to a single domain and highlight the difficulties of automatic domain parsers on these examples. This work can be used as a baseline for defining domain boundaries in homologous proteins or proteins with similar domain interactions in the future.

ADOL: a novel framework for automatic domain ontology learning

Ontology, as a semantic representation of a shared conceptualization, makes knowledge machine-readable and easy to spread. One of its typical applications is used to develop e-learning systems with Educational Ontology. Ontology can help students master knowledge architecture of required subjects and make scattered courseware more systematic. A big challenge is how to construct Educational Ontology to describe systematic knowledge of different subjects automatically. Currently, most of the ontologies are developed and extended manually, which requires the developers to possess certain professional knowledge and is time-consuming. In this paper, a framework to construct and extend Educational Ontology automatically is proposed.2 The proposed ontology learning framework, called ‘ADOL,’ can convert domain textbooks into a corresponding ontology automatically and efficiently. A case study on High School Physics shows that our approach is feasible and efficient.

Probabilistic data association: the orbit set

This paper presents a novel method to obtain the solution to the initial orbit determination problem for optical observations as a continuum of orbits—namely the orbit set—that fits the set of acquired observations within a prescribed accuracy. Differential algebra is exploited to analytically link the uncertainty in the observations to the state of the orbiting body with truncated power series, thus allowing for a compact analytical description of the orbit set. The automatic domain splitting tool controls the truncation error of the polynomial approximation by patching the uncertainty domain with different polynomial expansions, effectively creating a mesh. The algorithm is tested for different observing strategies to understand the working boundaries, thus defining the region for which the admissible region is necessary to extract meaningful information from observations and highlight where the new method can achieve a smaller uncertainty region, effectively showing that for some observing strategies it is possible to extract more information from a tracklet than the attributable. Consequently, the method enables comparison of orbit sets avoiding sampling when looking for correlation of different observations. Linear regression is also implemented to improve the uncertainty estimation and study the influence of the confidence level on the orbit set size. This is shown both for simulated and real observations obtained from the TFRM observatory.

A boundary element-based automatic domain partitioning approach for semi-structured quad mesh generation

In this paper, a boundary element-based approach is proposed for partitioning a planar domain automatically into a set of 4-sided regions, which is suitable for semi-structured quad mesh generation. The basic idea is to generate a smooth cross-field via solving PDEs with the boundary element method and then partition the input domain by extracting singular structures of the cross-field. Firstly, a cross is configured at each boundary vertex of the input domain. Then, two Laplacian equations are selected as the governing equation to smoothly propagate the crosses defined on the boundary into the interior of the domain. To obtain an accurate cross-field, the boundary element method is used to solve the governing equations. Then the singular vertices are identified by analyzing the structure of the cross-field, and the streamlines emanating from these points are traced and simplified as segmentation curves to partition the domain. Finally, to demonstrate the efficiency and effectiveness of the proposed approach, some quad mesh generation examples and comparison with previous approaches are presented.

An application of the automatic domain updating to the Tonle Sap Lake, Cambodia

An application of the automatic domain updating to the Tonle Sap Lake, Cambodia

Automatic domain modeling for human–robot interaction

This paper introduces an approach to automatic domain modeling for human–robot interaction. The proposed approach is symbolic and intended for semantically unconstrained task-oriented human–robot interaction domains. At the specification level, it is cognitively inspired, addressing selected cognitive mechanisms of the human memory system (e.g., integration, semantic categorization, associative learning, etc.) that are relevant for natural language human–robot interaction. We discuss a corpus-based validation of the introduced approach and report on its particular implementation within the conversational agent integrated with a human-like robot.

Representationalism and cognitive culturalism: riders on elephants on turtles all the way down

This article examines the influx of neurocognitive concepts in cultural sociology and this development’s consequences for representationalism. In the first part, I examine representationalism in two research programs that have shaped cultural sociology from the cultural turn to the present: Jeffrey Alexander’s “strong program” and Ann Swidler’s “tool kit” theory. I also briefly discuss the mixed and contradictory findings presented in one of sociology’s most-cited cognitive works, Paul DiMaggio’s (Annu Rev Sociol 23:263–87, 1997) programmatic statement on cognitive psychology’s potential contributions to sociology, which catalyzed the discipline’s cognitive turn. In part two, I demonstrate how in working with and against these three pillars in cultural sociology, figures such as Omar Lizardo, Steven Vaisey, and John Levi Martin have drawn on the cognitive neurosciences to re-conceptualize culture in ways that may have profound consequences for representationalism as it is practiced in the field. I conclude by arguing that representationalism is present but suppressed in cognitive cultural theory and its empirical investigations; that representationalism finds support in the neurocognitive sources that cognitive culturalists cite; and by asserting that future general theories of action will be predicated on a more interactive relationship between automatic and deliberative cognitive domains than the cognitive culturalists currently allow.

Automatic User Domain Classification Based on Support Vector Machine (SVM)

Finding domain of a research paper and a researcher is a crucial task and would be highly appreciable in order to provide personalized search results to the user. An automatic user domain classification technique based on SVM has been proposed in this paper in order to determine the domain of a user based on her publications. In this technique, for a given user, his specific area of domain is determined by classifying the keywords from his publication works. It consists of two phases: keyword extraction and domain classification. In keyword extraction phase, the list of publications corresponding to a user mail id is retrieved by using publish or perish tool. From each of the published papers, the keywords are extracted. In domain classification, SVM classifier is applied to determine the domain of the user. This is performed by training standard keywords from each domain into the SVM classifier. If a user belongs to more than one domain, then the primary domain with more publications will be considered.