Use Of Domain Knowledge Research Articles

Basketball Tactics Analysis Based on Improved Openpose Algorithm and Its Application

The use of information technology has currently resulted in a change in people's production and lifestyles as well as a catalyst for the sports industry's evolution. Currently, there is a growing use of digitization in the sports industry's basketball realm. Using 2D posture estimation, a novel lightweight deep learning architecture (LDLA) is built to accomplish the automatic analysis of basketball game footage. We offer a real-time method to identify numerous people's 2D poses in a video. Additionally, it examines how 2D pose estimation might be used to analyse basketball shooting videos. First, group and global motion features are extracted to represent semantic events. A full basketball game video is broken down into three stages: clip-based segmentation, classification of semantics occurrences utilizing audio and video, and temporal sequence characteristics employing GRU CNN. Video is first processed to create some basic video categorization and segmentation using the visual, movement, and auditory data. Further use of domain knowledge is made to find important events in the basketball video. Shot and image threshold recognition algorithms for videos have used both optical and kinematic prediction information; scene classification comes next. The placements of probable semantic events, such as "fouling" and "shooting at the basket," are then discovered by comparing the multidimensional data with supplementary domain expertise. Experimental results demonstrate the proposed LDLA method achieves 99.6% of accuracy, 93.2% of precision, 93.5% of recall and 89.5% of F1-score.

Local machine learning model-based multi-objective optimization for managing system interdependencies in production: A case study from the ironmaking industry

Modeling interdependencies in a production process is a vital aspect of process engineering. Being built on the fundamental understanding of the process and capturing underlying physical and chemical mechanisms, this task is traditionally carried out through first-principle modeling. However, due to various assumptions and parameter approximation, such approach sometimes struggles to accurately model process dynamics. This is partially due to the requirements for process stability in mission-critical scenarios, where it is not viable to conduct extensive experiments that would enable the development of comprehensive models, and hence, the process control is still partially dependent on the experience of the process operator. In this paper, a data-driven approach based on production data is introduced to address the challenge of discovering, understanding, and modeling interdependencies in a production process by constructing a constrained multi-objective optimization problem. The applicability of the proposed approach is demonstrated through a case study in the ironmaking industry, whereby a set of Machine Learning and causality-based methods is provided while highlighting the significance of transparency and use of domain knowledge in the development of data-driven models. Based on the real data from a Sintering plant, interdependencies are quantified between five key process parameters, which, when supplemented with other control parameters, result in a higher overall process output leading to reductions in operational costs and environmental impact. Such approach shows potential for applications in a broader context across other fields of science and engineering, where it can be used to improve the discovery of interdependencies in complex real-world industrial settings.

Double-Constrained Consensus Clustering with Application to Online Anti-Counterfeiting

Semi-supervised consensus clustering is a promising strategy to compensate for the subjectivity of clustering and its sensitivity to design factors, with various techniques being recently proposed to integrate domain knowledge and multiple clustering partitions. In this article, we present a new approach that makes double use of domain knowledge, namely to build the initial partitions, as well as to combine them. In particular, we show how to model and integrate must-link and cannot-link constraints into the objective function of a generic consensus clustering (CC) framework that maximizes the similarity between the consensus partition and the input partitions, which have, in turn, been enriched with the same constraints. In addition, borrowing from the theory of functional dependencies, the integrated framework exploits the notions of deductive closure and minimal cover to take full advantage of the logical implication between constraints. Using standard UCI benchmarks, we found that the resulting algorithm, termed CCC double-constrained consensus clustering), was more effective than plain CC at combining base-constrained partitions, with an average performance improvement of 5.54%. We then argue that CCC is especially well-suited for profiling counterfeit e-commerce websites, as constraints can be acquired by leveraging specific domain features, and demonstrate its potential for detecting affiliate marketing programs. Taken together, our experiments suggest that CCC makes the process of clustering more robust and able to withstand changes in clustering algorithms, datasets, and features, with a remarkable improvement in average performance.

Knowledge Adaptive Multi-Way Matching Network for Biomedical Named Entity Recognition via Machine Reading Comprehension.

Rapid and effective utilization of biomedical literature is paramount to combat diseases like COVID19. Biomedical named entity recognition (BioNER) is a fundamental task in text mining that can help physicians accelerate knowledge discovery to curb the spread of the COVID-19 epidemic. Recent approaches have shown that casting entity extraction as the machine reading comprehension task can significantly improve model performance. However, two major drawbacks impede higher success in identifying entities (1) ignoring the use of domain knowledge to capture the context beyond sentences and (2) lacking the ability to deeper understand the intent of questions. In this paper, to remedy this, we introduce and explore external domain knowledge which cannot be implicitly learned in text sequence. Previous works have focused more on text sequence and explored little of the domain knowledge. To better incorporate domain knowledge, a multi-way matching reader mechanism is devised to model representations of interaction between sequence, question and knowledge retrieved from Unified Medical Language System (UMLS). Benefiting from these, our model can better understand the intent of questions in complex contexts. Experimental results indicate that incorporating domain knowledge can help to obtain competitive results across 10 BioNER datasets, achieving absolute improvement of up to 2.02% in the f1 score.

Energy-aware intelligent scheduling for deadline-constrained workflows in sustainable cloud computing

It is challenging to handle the non-linear power consumption model, complex workflow structures, and diverse user-defined deadlines for energy-efficient workflow scheduling in sustainable cloud computing. Although metaheuristics are very attractive to solve this problem, most of the existing work regards the problem as a black-box and ignores the use of domain knowledge. To make up for their shortcomings, this paper tailors an energy-aware intelligent scheduling algorithm (EIS) with three new mechanisms. First, we derive the optimal execution time that minimizes energy consumption for each task on a given resource. Second, based on the optimal execution time of each workflow task, the EIS distributes the workflow slack time (difference between its completion time and deadline) to reduce the voltages and frequencies of task executions for energy saving. Third, the EIS mines the idle time gaps caused by task precedence constraints to further reduce dynamic energy consumption whilst satisfying workflows’ deadline constraints. To measure the performance of the EIS, we conduct extensive comparison experiments based on actual workflow applications. The results demonstrate that the energy consumption of the EIS is much lower than that of the competitors under different deadlines, and has a faster descend rate with the evolution process.

Early portfolio pruning: a scalable approach to hybrid portfolio selection

Driving the decisions of stock market investors is among the most challenging financial research problems. Markowitz’s approach to portfolio selection models stock profitability and risk level through a mean–variance model, which involves estimating a very large number of parameters. In addition to requiring considerable computational effort, this raises serious concerns about the reliability of the model in real-world scenarios. This paper presents a hybrid approach that combines itemset extraction with portfolio selection. We propose to adapt Markowitz’s model logic to deal with sets of candidate portfolios rather than with single stocks. We overcome some of the known issues of the Markovitz model as follows: (i) Complexity: we reduce the model complexity, in terms of parameter estimation, by studying the interactions among stocks within a shortlist of candidate stock portfolios previously selected by an itemset mining algorithm. (ii) Portfolio-level constraints: we not only perform stock-level selection, but also support the enforcement of arbitrary constraints at the portfolio level, including the properties of diversification and the fundamental indicators. (iii) Usability: we simplify the decision-maker’s work by proposing a decision support system that enables flexible use of domain knowledge and human-in-the-loop feedback. The experimental results, achieved on the US stock market, confirm the proposed approach’s flexibility, effectiveness, and scalability.

A scoping review on the use of natural language processing in research on political polarization: trends and research prospects

As part of the “text-as-data” movement, Natural Language Processing (NLP) provides a computational way to examine political polarization. We conducted a methodological scoping review of studies published since 2010 (n = 154) to clarify how NLP research has conceptualized and measured political polarization, and to characterize the degree of integration of the two different research paradigms that meet in this research area. We identified biases toward US context (59%), Twitter data (43%) and machine learning approach (33%). Research covers different layers of the political public sphere (politicians, experts, media, or the lay public), however, very few studies involved more than one layer. Results indicate that only a few studies made use of domain knowledge and a high proportion of the studies were not interdisciplinary. Those studies that made efforts to interpret the results demonstrated that the characteristics of political texts depend not only on the political position of their authors, but also on other often-overlooked factors. Ignoring these factors may lead to overly optimistic performance measures. Also, spurious results may be obtained when causal relations are inferred from textual data. Our paper provides arguments for the integration of explanatory and predictive modeling paradigms, and for a more interdisciplinary approach to polarization research.

On the use of domain knowledge for process model repair

Process models are important for supporting organizations in documenting, understanding and monitoring their business. When these process models become outdated, they need to be revised to accurately describe the new status quo of the processes in the organization. Process model repair techniques help at automatically revising the existing model from behavior traced in event logs. So far, such techniques have focused on identifying which parts of the model to change and how to change them, but they do not use knowledge from practitioners to inform the revision. As a consequence, fragments of the model may change in a way that defies existing regulations or represents outdated information that was wrongly considered from the event log. This paper uses concepts from theory revision to provide formal foundations for process model repair that exploits domain knowledge. Specifically, it conceptualizes (1) what are unchangeable fragments in the model and (2) the role that various traces in the event log should play when it comes to model repair. A scenario of use is presented that demonstrates the benefits of this conceptualization. The current state of existing process model repair techniques is compared against the proposed concepts. The results show that only two existing techniques partially consider the concepts presented in this paper for model repair.

A Strategic Approach to Machine Learning for Material Science: How to Tackle Real-World Challenges and Avoid Pitfalls

The exponential growth and success of machine learning (ML) has resulted in its application in all scientific domains including material science. Advancement in experimental techniques has led to an increase in the volume of material science data encouraging material scientists to investigate data-driven solutions to scientific problems. While the resources available to get started with ML are ever increasing, there is little literature on traversing through the space of decisions that need to be made to implement a robust and trustworthy ML solution. A lack of such resources leads to researchers wading through articles and papers trying to determine the best approach for their problem and sometimes also falling prey to pitfalls in a real-world scenario. This paper aims to act as a guide for researchers who want to strategically approach a ML solution to their problem through the use of domain knowledge and systematic evaluation of the major aspects of a ML pipeline. We focus on four aspects of the ML pipeline: (1) problem formulation, (2) data curation, (3) feature representation and model selection, and (4) model generalizability and real-world performance. In each case, we discuss the space of decisions, provide examples from scientific literature, and illustrate how different choices can affect the outcome through a case study of predicting compressive strength of uniaxially pressed molecular solid, 2,4,6-triamino-1,3,5-trinitrobenzene (TATB) samples. Using a similar approach of critical thinking along with rigorous evaluation and diagnostics, researchers can be assured of the reliability of predictions from their ML models.

Systematic literature review of domain-oriented specification techniques

Context:The popularity of domain-specific languages and model driven development has made the tacit use of domain knowledge in system development more tangible. Our vision is a development process where a (software) system specification is based on multiple domain models, and where the specification method is built from cognitive concepts, presumably derived from natural language. Goal:To realize this vision, we evaluate and reflect upon the existing literature in domain-oriented specification techniques. Method:We designed and conducted a systematic literature review on domain-oriented specification techniques. Results:We identified 53 primary studies, populated the classification framework for each study, and summarized our findings per classification aspect. We found many approaches for creating domain models or domain-specific languages. Observations include: (i) most methods are defined incompletely; (ii) none offers methodical support for the use of domain models or domain-specific languages to create other specifications; (iii) there are specification techniques to integrate models in general, but no study offers methodical support for multiple domain models. Conclusion:The results indicate which topics need further research and which can instead be reused to realize our vision on system development.Editor’s note: Open Science material was validated by the Journal of Systems and Software Open Science Board.

Analysis of the Reform Effectiveness of Vocational Skill Identification Based on the New Social Training Model in the New Era under Deep Learning Assessment.

In order to be able to make full use of domain knowledge to improve the performance of skill word extraction, this paper proposes a skill word extraction method based on a combination of deep learning and corpus features. Skill word extraction is transformed into a sequence annotation problem, and based on the basic model of sequence annotation, Bi-LSTM-CRF, corpus features are added to the input layer, and the output of the input layer is connected with the Bi-LSTM output as the input of the CRF layer. The experimental results show timely updating of the question bank, paying attention to the quality of vocational skill identification, and strictly managing the issuance of vocational qualification false certificates.

Metacognition and the development of self‐directed learning in a problem‐based engineering curriculum

AbstractBackgroundDeveloping self‐directed learning (SDL) skills in engineering students is critical to support life‐long learning. This research was conducted at Iron Range Engineering (IRE), an innovative, problem‐based learning (PBL) engineering program, which has suffused the concept of metacognition throughout its curriculum.Purpose/Hypotheses Using measures of metacognition obtained from think‐aloud problem‐solving activities, to what extent do students change their use of SDL strategies from the beginning of their junior year to the end of their senior year of the 2‐year PBL engineering program? Using evidence obtained from interview data, how do students' conceptualizations of metacognition and use of SDL strategies change from the beginning of their junior year to the end of their senior year of the 2‐year PBL engineering program? What is the relationship between think‐aloud and interview measures of metacognition, and how could the two types of measures better inform us about the potential impact of the IRE program on students' use of SDL strategies? Design/MethodTwelve students participated in both think‐aloud problem‐solving tasks and interviews.ResultsData from think‐aloud problem‐solving activities showed that nearly one‐half of students' verbalizations were metacognitive and that they talked more about strategies and made more use of domain knowledge by the end of their program. Interview data showed that one‐half of the students showed an increase in the complexity of their understanding of SDL.ConclusionsOur data show an increased use of strategies during problem‐solving at the end of the program. The results are promising, but further research is needed to understand the development of SDL in engineering students.

Who is winning? A comparison of humans versus computers for calibration model building

AbstractIncreasing awareness of the ability to transform data into knowledge has steered more focus on data science within the educational system as well as the development of machine learning methods capable of handling complex problems with minimal or no human interaction. In principle, this raises the question on where human–computer interaction is superior in building good models in contrast to fully automated algorithms. In this study, we investigated modeling performance by using bachelor students, master students, and a fully automated procedure on three near‐infrared (NIR) calibration tasks of increasing complexity. From a total of 107 student and +5000 automated models, it is evident that simple calibration tasks can be automated to achieve similar or better performance, whereas for the more complicated tasks, the human–computer interaction is superior. Indeed, teaching data science and chemometrics should focus on tools for fundamental data understanding and emphasize the use of domain knowledge and critical thinking in the analysis of data.

Knowledge-Based Structure Optimization Design for Boom of Excavator

During the design optimization of the excavator boom, there are many design variables and complicated processes. The original optimization methods mainly focused on the optimization of mathematical models, and they lacked consideration in the use of domain knowledge, design-specification knowledge, expert experience knowledge, and historical examples. In order to comprehensively utilize the domain knowledge and expert experience knowledge, this study uses the optimization process analysis, uses knowledge expression and coding processing technology to encode the boom structure, builds an optimal design coding system based on knowledge guidance, and realizes the automatic optimization design of the boom structure. In the process of constructing the knowledge-oriented optimization system, to realize the reuse of the knowledge of the boom structure design in the numerical optimization iteration, a knowledge processing flowchart of the boom structure design is constructed. The concept of “shape distance” is proposed to judge the similarity feature matrix of the boom structure coding. To evaluate whether the stress distribution is uniform, a fast prediction model based on stress characteristic regions is constructed. The research results show that, under the comprehensive consideration of the four working conditions, the knowledge-guided optimization of the boom structure can avoid the deformity in the optimization process, accelerate the calculation speed of the optimization model, and improve the optimization quality of the model.

Task-Aware Waypoint Sampling for Robotic Planning

To achieve a complex task, a robot often needs to navigate in a physical space in order to complete activities in different locations. For example, it may need to inspect several structures, making multiple observations of each structure from different perspectives. Typically, the positions from which these activities can be performed are represented as waypoints – discrete positions that are sampled from the continuous physical space and used to find a task plan. Existing approaches to waypoint selection either iteratively consider the entire space or use domain knowledge to consider each activity separately. This can lead to task planning problems that are more complex than is necessary or to plans of compromised quality. Moreover, all previous approaches only consider geometric constraints that can be imposed on the waypoint selection process. We present Task-Aware Waypoint Sampling (TAWS), which offers two key novelties. First, it is an anytime approach that combines the benefits of random sampling with the use of domain knowledge in waypoint selection by performing a one-time computation of the connectivity graph from which waypoints are sampled. In addition, TAWS is the first approach that accounts for performance preferences, which are preferences a system operator may have about the generated task plan. These can account, for example, for areas near doorways where it is preferable that the robot does not stop to perform activities. We demonstrate the performance benefits of our approach on simulated automated manufacturing tasks.

Entity summarization: State of the art and future challenges

The increasing availability of semantic data has substantially enhanced Web applications. Semantic data such as RDF data is commonly represented as entity-property-value triples. The magnitude of semantic data, in particular the large number of triples describing an entity, could overload users with excessive amounts of information. This has motivated fruitful research on automated generation of summaries for entity descriptions to satisfy users’ information needs efficiently and effectively. We focus on this prominent topic of entity summarization, and our research objective is to present the first comprehensive survey of entity summarization research. Rather than separately reviewing each method, our contributions include (1) identifying and classifying technical features of existing methods to form a high-level overview, (2) identifying and classifying frameworks for combining multiple technical features adopted by existing methods, (3) collecting known benchmarks for intrinsic evaluation and efforts for extrinsic evaluation, and (4) suggesting research directions for future work. By investigating the literature, we synthesized two hierarchies of techniques. The first hierarchy categories generic technical features into several perspectives: frequency and centrality, informativeness, and diversity and coverage. In the second hierarchy we present domain-specific and task-specific technical features, including the use of domain knowledge, context awareness, and personalization. Our review demonstrated that existing methods are mainly unsupervised and they combine multiple technical features using various frameworks: random surfer models, similarity-based grouping, MMR-like re-ranking, or combinatorial optimization. We also found a few deep learning based methods in recent research. Current evaluation results and our case study showed that the problem of entity summarization is still far from being solved. Based on the limitations of existing methods revealed in the review, we identified several future directions: the use of semantics, human factors, machine and deep learning, non-extractive methods, and interactive methods.

Entity Summarization: State of the Art and Future Challenges

The increasing availability of semantic data has substantially enhanced Web applications. Semantic data such as RDF data is commonly represented as entity-property-value triples. The magnitude of semantic data, in particular the large number of triples describing an entity, could overload users with excessive amounts of information. This has motivated fruitful research on automated generation of summaries for entity descriptions to satisfy users' information needs efficiently and effectively. We focus on this prominent topic of entity summarization, and our research objective is to present the first comprehensive survey of entity summarization research. Rather than separately reviewing each method, our contributions include (1) identifying and classifying technical features of existing methods to form a high-level overview, (2) identifying and classifying frameworks for combining multiple technical features adopted by existing methods, (3) collecting known benchmarks for intrinsic evaluation and efforts for extrinsic evaluation, and (4) suggesting research directions for future work. By investigating the literature, we synthesized two hierarchies of techniques. The first hierarchy categories generic technical features into several perspectives: frequency and cen-trality, informativeness, and diversity and coverage. In the second hierarchy we present domain-specific and task-specific technical features, including the use of domain knowledge, context awareness, and personalization. Our review demonstrated that existing methods are mainly unsupervised and they combine multiple technical features using various frameworks: random surfer models, similarity-based grouping, MMR-like re-ranking, or combinatorial optimization. We also found a few deep learning based methods in recent research. Current evaluation results and our case study showed that the problem of entity summarization is still far from being solved. Based on the limitations of existing methods revealed in the review, we identified several future directions: the use of semantics, human factors, machine and deep learning, non-extractive methods, and interactive methods.

Entity Summarization: State of the Art and Future Challenges

The increasing availability of semantic data has substantially enhanced Web applications. Semantic data such as RDF data is commonly represented as entity-property-value triples. The magnitude of semantic data, in particular the large number of triples describing an entity, could overload users with excessive amounts of information. This has motivated fruitful research on automated generation of summaries for entity descriptions to satisfy users' information needs efficiently and effectively. We focus on this prominent topic of entity summarization, and our research objective is to present the first comprehensive survey of entity summarization research. Rather than separately reviewing each method, our contributions include (1) identifying and classifying technical features of existing methods to form a high-level overview, (2) identifying and classifying frameworks for combining multiple technical features adopted by existing methods, (3) collecting known benchmarks for intrinsic evaluation and efforts for extrinsic evaluation, and (4) suggesting research directions for future work. By investigating the literature, we synthesized two hierarchies of techniques. The first hierarchy categories generic technical features into several perspectives: frequency and centrality, informativeness, and diversity and coverage. In the second hierarchy we present domain-specific and task-specific technical features, including the use of domain knowledge, context awareness, and personalization. Our review demonstrated that existing methods are mainly unsupervised and they combine multiple technical features using various frameworks: random surfer models, similarity-based grouping, MMR-like re-ranking, or combinatorial optimization. We also found a few deep learning based methods in recent research.

Intelligent Interactive Beam Training for Millimeter Wave Communications

Millimeter wave communications, equipped with large-scale antenna arrays, are able to provide Gbps data rates by exploring abundant spectrum resources. However, the use of a large number of antennas along with narrow beams causes a large overhead in obtaining channel state information (CSI) via beam training, especially for fast-changing channels. To reduce beam training overhead, in this paper we develop an interactive learning design paradigm (ILDP) that makes full use of domain knowledge of wireless communications (WCs) and adaptive learning ability of machine learning (ML). Specifically, the ILDP is fulfilled via deep reinforcement learning (DRL), which yields DRL-ILDP, and consists of communication model (CM) module and adaptive learning (AL) module, which work in an interactive manner. Then, we exploit the DRL-ILDP to design efficient beam training algorithms for both multi-user and user-centric cooperative communications. The proposed DRL-ILDP based algorithms enjoy three folds of advantages. Firstly, ILDP takes full advantages of the existing WC models and methods. Secondly, ILDP integrates powerful ML elements, which facilitates extracting interested statistical and probabilistic information from environments. Thirdly, via the interaction between the CM and AL modules, the algorithms are able to collect samples and extract information in real-time and sufficiently adapt to the ever-changing environments. Simulation results demonstrate the effectiveness and superiority of the designed algorithms.

The 2019 National Natural language processing (NLP) Clinical Challenges (n2c2)/Open Health NLP (OHNLP) shared task on clinical concept normalization for clinical records.

The 2019 National Natural language processing (NLP) Clinical Challenges (n2c2)/Open Health NLP (OHNLP) shared task track 3, focused on medical concept normalization (MCN) in clinical records. This track aimed to assess the state of the art in identifying and matching salient medical concepts to a controlled vocabulary. In this paper, we describe the task, describe the data set used, compare the participating systems, present results, identify the strengths and limitations of the current state of the art, and identify directions for future research. Participating teams were provided with narrative discharge summaries in which text spans corresponding to medical concepts were identified. This paper refers to these text spans as mentions. Teams were tasked with normalizing these mentions to concepts, represented by concept unique identifiers, within the Unified Medical Language System. Submitted systems represented 4 broad categories of approaches: cascading dictionary matching, cosine distance, deep learning, and retrieve-and-rank systems. Disambiguation modules were common across all approaches. A total of 33 teams participated in the MCN task. The best-performing team achieved an accuracy of 0.8526. The median and mean performances among all teams were 0.7733 and 0.7426, respectively. Overall performance among the top 10 teams was high. However, several mention types were challenging for all teams. These included mentions requiring disambiguation of misspelled words, acronyms, abbreviations, and mentions with more than 1 possible semantic type. Also challenging were complex mentions of long, multi-word terms that may require new ways of extracting and representing mention meaning, the use of domain knowledge, parse trees, or hand-crafted rules.