Search results

In computational chemistry, the chemical bond energy (pKa) is essential, but most pKa-related data are submerged in scientific papers, with only a few data that have been extracted by domain experts manually. The loss of scientific data does not contribute to in-depth and innovative scientific data analysis. To address this problem, this study aims to utilize natural language processing methods to extract pKa-related scientific data in chemical papers.

Based on the previous Bert-CRF model combined with dictionaries and rules to resolve the problem of a large number of unknown words of professional vocabulary, in this paper, the authors proposed an end-to-end Bert-CRF model with inputting constructed domain wordpiece tokens using text mining methods. The authors use standard high-frequency string extraction techniques to construct domain wordpiece tokens for specific domains. And in the subsequent deep learning work, domain features are added to the input.

The experiments show that the end-to-end Bert-CRF model could have a relatively good result and can be easily transferred to other domains because it reduces the requirements for experts by using automatic high-frequency wordpiece tokens extraction techniques to construct the domain wordpiece tokenization rules and then input domain features to the Bert model.

By decomposing lots of unknown words with domain feature-based wordpiece tokens, the authors manage to resolve the problem of a large amount of professional vocabulary and achieve a relatively ideal extraction result compared to the baseline model. The end-to-end model explores low-cost migration for entity and relation extraction in professional fields, reducing the requirements for experts.

This paper aims to present the classification, representation and extraction of adhesively bonded assembly features (ABAFs) from the computer-aided design (CAD) model.

The ABAFs are represented as a set of faces with a characteristic arrangement among the faces among parts in proximity suitable for adhesive bonding. The characteristics combination of the faying surfaces and their topological relationships help in classification of ABAFs. The ABAFs are classified into elementary and compound types based on the number of assembly features exist at the joint location.

A set of algorithms is developed to extract and identify the ABAFs from CAD model. Typical automotive and aerospace CAD assembly models have been used to illustrate and validate the proposed approach.

New classification and extraction methods for ABAFs are proposed, which are useful for variant design.

Entity relation extraction is an important research direction to obtain structured information. However, most of the current methods are to determine the relations between entities in a given sentence based on a stepwise method, seldom considering entities and relations into a unified framework. The joint learning method is an optimal solution that combines relations and entities. This paper aims to optimize hierarchical reinforcement learning framework and provide an efficient model to extract entity relation.

This paper is based on the hierarchical reinforcement learning framework of joint learning and combines the model with BERT, the best language representation model, to optimize the word embedding and encoding process. Besides, this paper adjusts some punctuation marks to make the data set more standardized, and introduces positional information to improve the performance of the model.

Experiments show that the model proposed in this paper outperforms the baseline model with a 13% improvement, and achieve 0.742 in F1 score in NYT10 data set. This model can effectively extract entities and relations in large-scale unstructured text and can be applied to the fields of multi-domain information retrieval, intelligent understanding and intelligent interaction.

The research provides an efficient solution for researchers in a different domain to make use of artificial intelligence (AI) technologies to process their unstructured text more accurately.

As a means of data acquisition for the situation awareness, computer vision-based motion capture technologies have increased the potential to observe and assess manual activities for the prevention of accidents and injuries in construction. This study thus aims to present a computationally efficient and robust method of human motion data capture for the on-site motion sensing and analysis.

This study investigated a tracking approach to three-dimensional (3D) human skeleton extraction from stereo video streams. Instead of detecting body joints on each image, the proposed method tracks locations of the body joints over all the successive frames by learning from the initialized body posture. The corresponding body joints to the ones tracked are then identified and matched on the image sequences from the other lens and reconstructed in a 3D space through triangulation to build 3D skeleton models. For validation, a lab test is conducted to evaluate the accuracy and working ranges of the proposed method, respectively.

Results of the test reveal that the tracking approach produces accurate outcomes at a distance, with nearly real-time computational processing, and can be potentially used for site data collection. Thus, the proposed approach has a potential for various field analyses for construction workers’ safety and ergonomics.

Recently, motion capture technologies have rapidly been developed and studied in construction. However, existing sensing technologies are not yet readily applicable to construction environments. This study explores two smartphones as stereo cameras as a potentially suitable means of data collection in construction for the less operational constrains (e.g. no on-body sensor required, less sensitivity to sunlight, and flexible ranges of operations).

Statistical modeling has been successfully applied to integrated circuit (IC) solder joint inspection. However, there are some inherent problems in previous statistical modeling methods. This paper aims to propose an adaptive statistical modeling method to further improve the inspection performance for IC solder joints.

First, different pixels in the IC solder joint image were modeled by different templates, each of which was composed of the hue value of the pixel and a proposed template significance factor. Then, the potential defect image was obtained by adaptive template matching and the potential defect threshold for each pixel. It was noted that the number of templates, matching distance threshold, potential defect threshold and updating rate were adaptively updated during model training. Finally, the trained statistical model was used to inspect the IC solder joints by means of defect degree.

Experimental results indicated that the proposed adaptive schemes greatly contributed to the inspection performance of statistical modeling. Also, the proposed inspection method achieved better performance compared with some state-of-the-art inspection methods.

The proposed method offers a promising approach for IC solder joint inspection, which establishes different numbers of templates constructed by pixel values and template significance factors for different pixels. Also, some important parameters were adaptively updated with the updating of the model, which contributed to the inspection performance of the model.

Recent years have witnessed the rapid development of massive open online courses (MOOCs). With more and more courses being produced by instructors and being participated by learners all over the world, unprecedented massive educational resources are aggregated. The educational resources include videos, subtitles, lecture notes, quizzes, etc., on the teaching side, and forum contents, Wiki, log of learning behavior, log of homework, etc., on the learning side. However, the data are both unstructured and diverse. To facilitate knowledge management and mining on MOOCs, extracting keywords from the resources is important. This paper aims to adapt the state-of-the-art techniques to MOOC settings and evaluate the effectiveness on real data. In terms of practice, this paper also tries to answer the questions for the first time that to what extend can the MOOC resources support keyword extraction models, and how many human efforts are required to make the models work well.

Based on which side generates the data, i.e instructors or learners, the data are classified to teaching resources and learning resources, respectively. The approach used on teaching resources is based on machine learning models with labels, while the approach used on learning resources is based on graph model without labels.

From the teaching resources, the methods used by the authors can accurately extract keywords with only 10 per cent labeled data. The authors find a characteristic of the data that the resources of various forms, e.g. subtitles and PPTs, should be separately considered because they have the different model ability. From the learning resources, the keywords extracted from MOOC forums are not as domain-specific as those extracted from teaching resources, but they can reflect the topics which are lively discussed in forums. Then instructors can get feedback from the indication. The authors implement two applications with the extracted keywords: generating concept map and generating learning path. The visual demos show they have the potential to improve learning efficiency when they are integrated into a real MOOC platform.

Conducting keyword extraction on MOOC resources is quite difficult because teaching resources are hard to be obtained due to copyrights. Also, getting labeled data is tough because usually expertise of the corresponding domain is required.

The experiment results support that MOOC resources are good enough for building models of keyword extraction, and an acceptable balance between human efforts and model accuracy can be achieved.

This paper presents a pioneer study on keyword extraction on MOOC resources and obtains some new findings.

Automatic optical inspection (AOI) systems have been widely used in many fields to evaluate the qualities of products at the end of the production line. The purpose of this paper is to propose a local-to-global ensemble learning method for the AOI system based on to inspect integrated circuit (IC) solder joints defects.

In the proposed method, the locally statistically modeling stage and the globally ensemble learning stage are involved to tackle the inspection problem. At the former stage, the improved visual background extraction–based algorithm is used for locally statistically modeling to grasp tiny appearance differences between the IC solder joints to achieve potential defect images for the subsequent stage. At the latter stage, mean unqualified probability is introduced based on a novel ensemble learning, in which an adaptive weighted strategy is proposed for revealing different contributions of the base classifier to the inspection performance.

Experimental results demonstrate that the proposed method achieves better inspection performance with an acceptable inspection time compared with some state-of-the-art methods.

The approach is a promising method for IC solder joint inspection, which can simultaneously grasp the local characteristics of IC solder joints and reveal inherently global relationships between IC solder joints.

The weld region obtained during friction stir welding (FSW) of metallic materials (including aluminum alloys) contains typically well-defined zones, each characterized by fairly unique microstructure and properties. The purpose of this paper is to carry out combined experimental and numerical investigations of the mechanical properties of materials residing in different weld zones of FSW joints of thick AA2139-T8 plates.

Within the experimental investigation, the following has been conducted: first, optical-microscopy characterization of the transverse sections of the FSW joints, in order to help identify and delineate weld zones; second, micro hardness field generation over the same transverse section in order to reconfirm the location and the extent of various weld zones; third, extraction of miniature tensile specimens from different weld zones and their experimental testing; and finally, extraction of a larger size tensile specimen spanning transversely the FSW weld and its testing. Within the computational investigation, an effort was made to: first, validate the mechanical properties obtained using the miniature tensile specimens; and second, demonstrate the need for the use of the miniature tensile specimens.

It is argued that the availability of weld-zone material mechanical properties is critical since: first, these properties are often inferior relative to their base-metal counterparts; second, the width of the weld in thick metallic-armor is often comparable to the armor thickness, and therefore may represent a significant portion of the armor exposed-surface area; and finally, modeling of the weld-material structural response under loading requires the availability of high-fidelity/validated material constitutive models, and the development of such models requires knowledge of the weld-material mechanical properties.

The importance of determining the mechanical properties of the material in different parts of the weld zone with sufficient accuracy is demonstrated.

This paper aims to present a natural human–robot teleoperation system, which capitalizes on the latest advancements of monocular human pose estimation to simplify scenario requirements on heterogeneous robot arm teleoperation.

Several optimizations in the joint extraction process are carried on to better balance the performance of the pose estimation network. To bridge the gap between human joint pose in Cartesian space and heterogeneous robot joint angle pose in Radian space, a routinized mapping procedure is proposed.

The effectiveness of the developed methods on joint extraction is verified via qualitative and quantitative experiments. The teleoperation experiments on different robots validate the feasibility of the system controlling.

The proposed system provides an intuitive and efficient human–robot teleoperation method with low-cost devices. It also enhances the controllability and flexibility of robot arms by releasing human operator from motion constraints, paving a new way for effective robot teleoperation.

In this paper we give a synoptic view of the growth of the text processing technology of information extraction (IE) whose function is to extract information about a pre‐specified set of entities, relations or events from natural language texts and to record this information in structured representations called templates. Here we describe the nature of the IE task, review the history of the area from its origins in AI work in the 1960s and 70s till the present, discuss the techniques being used to carry out the task, describe application areas where IE systems are or are about to be at work, and conclude with a discussion of the challenges facing the area. What emerges is a picture of an exciting new text processing technology with a host of new applications, both on its own and in conjunction with other technologies, such as information retrieval, machine translation and data mining.