Showing papers on "Domain knowledge published in 2018"

Deep learning for healthcare: review, opportunities and challenges.

Abstract: Gaining knowledge and actionable insights from complex, high-dimensional and heterogeneous biomedical data remains a key challenge in transforming health care. Various types of data have been emerging in modern biomedical research, including electronic health records, imaging, -omics, sensor data and text, which are complex, heterogeneous, poorly annotated and generally unstructured. Traditional data mining and statistical learning approaches typically need to first perform feature engineering to obtain effective and more robust features from those data, and then build prediction or clustering models on top of them. There are lots of challenges on both steps in a scenario of complicated data and lacking of sufficient domain knowledge. The latest advances in deep learning technologies provide new effective paradigms to obtain end-to-end learning models from complex data. In this article, we review the recent literature on applying deep learning technologies to advance the health care domain. Based on the analyzed work, we suggest that deep learning approaches could be the vehicle for translating big biomedical data into improved human health. However, we also note limitations and needs for improved methods development and applications, especially in terms of ease-of-understanding for domain experts and citizen scientists. We discuss such challenges and suggest developing holistic and meaningful interpretable architectures to bridge deep learning models and human interpretability.

Neural scene representation and rendering

Abstract: Scene representation-the process of converting visual sensory data into concise descriptions-is a requirement for intelligent behavior. Recent work has shown that neural networks excel at this task when provided with large, labeled datasets. However, removing the reliance on human labeling remains an important open problem. To this end, we introduce the Generative Query Network (GQN), a framework within which machines learn to represent scenes using only their own sensors. The GQN takes as input images of a scene taken from different viewpoints, constructs an internal representation, and uses this representation to predict the appearance of that scene from previously unobserved viewpoints. The GQN demonstrates representation learning without human labels or domain knowledge, paving the way toward machines that autonomously learn to understand the world around them.

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

Abstract: Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make & model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem in large scale FGVC. Our method won first place in iNaturalist 2017 large scale species classification challenge. Central to the success of our approach is a training scheme that uses higher image resolution and deals with the long-tailed distribution of training data. Next, we study transfer learning via fine-tuning from large scale datasets to small scale, domain-specific FGVC datasets. We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure. Our proposed transfer learning outperforms ImageNet pre-training and obtains state-of-the-art results on multiple commonly used FGVC datasets.

ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition.

Abstract: Conventional machine learning approaches for predicting material properties from elemental compositions have emphasized the importance of leveraging domain knowledge when designing model inputs. Here, we demonstrate that by using a deep learning approach, we can bypass such manual feature engineering requiring domain knowledge and achieve much better results, even with only a few thousand training samples. We present the design and implementation of a deep neural network model referred to as ElemNet; it automatically captures the physical and chemical interactions and similarities between different elements using artificial intelligence which allows it to predict the materials properties with better accuracy and speed. The speed and best-in-class accuracy of ElemNet enable us to perform a fast and robust screening for new material candidates in a huge combinatorial space; where we predict hundreds of thousands of chemical systems that could contain yet-undiscovered compounds.

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning.

Abstract: Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make and model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem in large scale FGVC. Our method won first place in iNaturalist 2017 large scale species classification challenge. Central to the success of our approach is a training scheme that uses higher image resolution and deals with the long-tailed distribution of training data. Next, we study transfer learning via fine-tuning from large scale datasets to small scale, domain-specific FGVC datasets. We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure. Our proposed transfer learning outperforms ImageNet pre-training and obtains state-of-the-art results on multiple commonly used FGVC datasets.

Recurrent knowledge graph embedding for effective recommendation

Abstract: Knowledge graphs (KGs) have proven to be effective to improve recommendation. Existing methods mainly rely on hand-engineered features from KGs (e.g., meta paths), which requires domain knowledge. This paper presents RKGE, a KG embedding approach that automatically learns semantic representations of both entities and paths between entities for characterizing user preferences towards items. Specifically, RKGE employs a novel recurrent network architecture that contains a batch of recurrent networks to model the semantics of paths linking a same entity pair, which are seamlessly fused into recommendation. It further employs a pooling operator to discriminate the saliency of different paths in characterizing user preferences towards items. Extensive validation on real-world datasets shows the superiority of RKGE against state-of-the-art methods. Furthermore, we show that RKGE provides meaningful explanations for recommendation results.

A Review of User Interface Design for Interactive Machine Learning

Abstract: Interactive Machine Learning (IML) seeks to complement human perception and intelligence by tightly integrating these strengths with the computational power and speed of computers. The interactive process is designed to involve input from the user but does not require the background knowledge or experience that might be necessary to work with more traditional machine learning techniques. Under the IML process, non-experts can apply their domain knowledge and insight over otherwise unwieldy datasets to find patterns of interest or develop complex data-driven applications. This process is co-adaptive in nature and relies on careful management of the interaction between human and machine. User interface design is fundamental to the success of this approach, yet there is a lack of consolidated principles on how such an interface should be implemented. This article presents a detailed review and characterisation of Interactive Machine Learning from an interactive systems perspective. We propose and describe a structural and behavioural model of a generalised IML system and identify solution principles for building effective interfaces for IML. Where possible, these emergent solution principles are contextualised by reference to the broader human-computer interaction literature. Finally, we identify strands of user interface research key to unlocking more efficient and productive non-expert interactive machine learning applications.

A Survey of Data Mining and Deep Learning in Bioinformatics

Abstract: The fields of medicine science and health informatics have made great progress recently and have led to in-depth analytics that is demanded by generation, collection and accumulation of massive data. Meanwhile, we are entering a new period where novel technologies are starting to analyze and explore knowledge from tremendous amount of data, bringing limitless potential for information growth. One fact that cannot be ignored is that the techniques of machine learning and deep learning applications play a more significant role in the success of bioinformatics exploration from biological data point of view, and a linkage is emphasized and established to bridge these two data analytics techniques and bioinformatics in both industry and academia. This survey concentrates on the review of recent researches using data mining and deep learning approaches for analyzing the specific domain knowledge of bioinformatics. The authors give a brief but pithy summarization of numerous data mining algorithms used for preprocessing, classification and clustering as well as various optimized neural network architectures in deep learning methods, and their advantages and disadvantages in the practical applications are also discussed and compared in terms of their industrial usage. It is believed that in this review paper, valuable insights are provided for those who are dedicated to start using data analytics methods in bioinformatics.

Lessons from Natural Language Inference in the Clinical Domain

Abstract: State of the art models using deep neural networks have become very good in learning an accurate mapping from inputs to outputs. However, they still lack generalization capabilities in conditions that differ from the ones encountered during training. This is even more challenging in specialized, and knowledge intensive domains, where training data is limited. To address this gap, we introduce MedNLI - a dataset annotated by doctors, performing a natural language inference task (NLI), grounded in the medical history of patients. We present strategies to: 1) leverage transfer learning using datasets from the open domain, (e.g. SNLI) and 2) incorporate domain knowledge from external data and lexical sources (e.g. medical terminologies). Our results demonstrate performance gains using both strategies.

Re-weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation

Abstract: Unsupervised Domain Adaptation (UDA) aims to transfer domain knowledge from existing well-defined tasks to new ones where labels are unavailable. In the real-world applications, as the domain (task) discrepancies are usually uncontrollable, it is significantly motivated to match the feature distributions even if the domain discrepancies are disparate. Additionally, as no label is available in the target domain, how to successfully adapt the classifier from the source to the target domain still remains an open question. In this paper, we propose the Re-weighted Adversarial Adaptation Network (RAAN) to reduce the feature distribution divergence and adapt the classifier when domain discrepancies are disparate. Specifically, to alleviate the need of common supports in matching the feature distribution, we choose to minimize optimal transport (OT) based Earth-Mover (EM) distance and reformulate it to a minimax objective function. Utilizing this, RAAN can be trained in an end-to-end and adversarial manner. To further adapt the classifier, we propose to match the label distribution and embed it into the adversarial training. Finally, after extensive evaluation of our method using UDA datasets of varying difficulty, RAAN achieved the state-of-the-art results and outperformed other methods by a large margin when the domain shifts are disparate.

Incorporating Prior Domain Knowledge into Deep Neural Networks

Abstract: In recent years, the large amount of labeled data available has also helped tend research toward using minimal domain knowledge, e.g., in deep neural network research. However, in many situations, data is limited and of poor quality. Can domain knowledge be useful in such a setting? In this paper, we propose domain adapted neural networks (DANN) to explore how domain knowledge can be integrated into model training for deep networks. In particular, we incorporate loss terms for knowledge available as monotonicity constraints and approximation constraints. We evaluate our model on both synthetic data generated using the popular Bohachevsky function and a real-world dataset for predicting oxygen solubility in water. In both situations, we find that our DANN model outperforms its domain-agnostic counterpart yielding an overall mean performance improvement of 19.5% with a worst- and best-case performance improvement of 4% and 42.7%, respectively.

Knowledge-aware Multimodal Dialogue Systems

Abstract: By offering a natural way for information seeking, multimodal dialogue systems are attracting increasing attention in several domains such as retail, travel etc. However, most existing dialogue systems are limited to textual modality, which cannot be easily extended to capture the rich semantics in visual modality such as product images. For example, in fashion domain, the visual appearance of clothes and matching styles play a crucial role in understanding the user's intention. Without considering these, the dialogue agent may fail to generate desirable responses for users. In this paper, we present a Knowledge-aware Multimodal Dialogue (KMD) model to address the limitation of text-based dialogue systems. It gives special consideration to the semantics and domain knowledge revealed in visual content, and is featured with three key components. First, we build a taxonomy-based learning module to capture the fine-grained semantics in images the category and attributes of a product). Second, we propose an end-to-end neural conversational model to generate responses based on the conversation history, visual semantics, and domain knowledge. Lastly, to avoid inconsistent dialogues, we adopt a deep reinforcement learning method which accounts for future rewards to optimize the neural conversational model. We perform extensive evaluation on a multi-turn task-oriented dialogue dataset in fashion domain. Experiment results show that our method significantly outperforms state-of-the-art methods, demonstrating the efficacy of modeling visual modality and domain knowledge for dialogue systems.

Neural Compatibility Modeling with Attentive Knowledge Distillation

Abstract: Recently, the booming fashion sector and its huge potential benefits have attracted tremendous attention from many research communities. In particular, increasing research efforts have been dedicated to the complementary clothing matching as matching clothes to make a suitable outfit has become a daily headache for many people, especially those who do not have the sense of aesthetics. Thanks to the remarkable success of neural networks in various applications such as the image classification and speech recognition, the researchers are enabled to adopt the data-driven learning methods to analyze fashion items. Nevertheless, existing studies overlook the rich valuable knowledge (rules) accumulated in fashion domain, especially the rules regarding clothing matching. Towards this end, in this work, we shed light on the complementary clothing matching by integrating the advanced deep neural networks and the rich fashion domain knowledge. Considering that the rules can be fuzzy and different rules may have different confidence levels to different samples, we present a neural compatibility modeling scheme with attentive knowledge distillation based on the teacher-student network scheme. Extensive experiments on the real-world dataset show the superiority of our model over several state-of-the-art methods. Based upon the comparisons, we observe certain fashion insights that can add value to the fashion matching study. As a byproduct, we released the codes, and involved parameters to benefit other researchers.

Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation

Abstract: Unsupervised domain adaptation has caught appealing attentions as it facilitates the unlabeled target learning by borrowing existing well-established source domain knowledge. Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain to better solve cross-domain distribution divergences. However, existing approaches separate target label optimization and domain-invariant feature learning as different steps. To address that issue, we develop a novel Graph Adaptive Knowledge Transfer (GAKT) model to jointly optimize target labels and domain-free features in a unified framework. Specifically, semi-supervised knowledge adaptation and label propagation on target data are coupled to benefit each other, and hence the marginal and conditional disparities across different domains will be better alleviated. Experimental evaluation on two cross-domain visual datasets demonstrates the effectiveness of our designed approach on facilitating the unlabeled target task learning, compared to the state-of-the-art domain adaptation approaches.

A retrospective of knowledge graphs

Abstract: Information on the Internet is fragmented and presented in different data sources, which makes automatic knowledge harvesting and understanding formidable for machines, and even for humans. Knowledge graphs have become prevalent in both of industry and academic circles these years, to be one of the most efficient and effective knowledge integration approaches. Techniques for knowledge graph construction can mine information from either structured, semi-structured, or even unstructured data sources, and finally integrate the information into knowledge, represented in a graph. Furthermore, knowledge graph is able to organize information in an easy-to-maintain, easy-to-understand and easy-to-use manner. In this paper, we give a summarization of techniques for constructing knowledge graphs. We review the existing knowledge graph systems developed by both academia and industry. We discuss in detail about the process of building knowledge graphs, and survey state-of-the-art techniques for automatic knowledge graph checking and expansion via logical inferring and reasoning. We also review the issues of graph data management by introducing the knowledge data models and graph databases, especially from a NoSQL point of view. Finally, we overview current knowledge graph systems and discuss the future research directions.

Glaucoma diagnosis based on both hidden features and domain knowledge through deep learning models

Abstract: Glaucoma is one of the leading causes of blindness in the world and there is no cure for it yet. But it is very meaningful to detect it early as earlier detection makes it possible to stop further loss of visions. Although deep learning models have proved their advantages in natural image analysis, they usually rely on large datasets to learn to extract hidden features, thus limiting its application in medical areas where data is hard to get. Consequently, it is meaningful and challenging to design a deep learning model for disease diagnosis with relatively fewer data. In this paper, we study how to use deep learning model to combine domain knowledge with retinal fundus images for automatic glaucoma diagnosis. The domain knowledge includes measures important for glaucoma diagnosis and important region of the image which contains much information. To make full use of this domain knowledge and extract hidden features from image simultaneously, we design a multi-branch neural network (MB-NN) model with methods to automatically extract important areas of images and obtain domain knowledge features. We evaluate the effectiveness of the proposed model on real datasets and achieve an accuracy of 0.9151, sensitivity of 0.9233, and specificity of 0.9090, which is better than the state-of-the-art models.

Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation

Abstract: Unsupervised domain adaptation has caught appealing attentions as it facilitates the unlabeled target learning by borrowing existing well-established source domain knowledge. Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain to better solve cross-domain distribution divergences. However, existing approaches separate target label optimization and domain-invariant feature learning as different steps. To address that issue, we develop a novel Graph Adaptive Knowledge Transfer (GAKT) model to jointly optimize target labels and domain-free features in a unified framework. Specifically, semi-supervised knowledge adaptation and label propagation on target data are coupled to benefit each other, and hence the marginal and conditional disparities across different domains will be better alleviated. Experimental evaluation on two cross-domain visual datasets demonstrates the effectiveness of our designed approach on facilitating the unlabeled target task learning, compared to the state-of-the-art domain adaptation approaches.

Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction

Abstract: With access to large datasets, deep neural networks (DNN) have achieved human-level accuracy in image and speech recognition tasks. However, in chemistry data is inherently small and fragmented. In this work, we develop an approach of using rule-based knowledge for training ChemNet, a transferable and generalizable deep neural network for chemical property prediction that learns in a weak-supervised manner from large unlabeled chemical databases. When coupled with transfer learning approaches to predict other smaller datasets for chemical properties that it was not originally trained on, we show that ChemNet's accuracy outperforms contemporary DNN models that were trained using conventional supervised learning. Furthermore, we demonstrate that the ChemNet pre-training approach is equally effective on both CNN (Chemception) and RNN (SMILES2vec) models, indicating that this approach is network architecture agnostic and is effective across multiple data modalities. Our results indicate a pre-trained ChemNet that incorporates chemistry domain knowledge and enables the development of generalizable neural networks for more accurate prediction of novel chemical properties.

CliCR: a Dataset of Clinical Case Reports for Machine Reading Comprehension

Abstract: We present a new dataset for machine comprehension in the medical domain. Our dataset uses clinical case reports with around 100,000 gap-filling queries about these cases. We apply several baselines and state-of-the-art neural readers to the dataset, and observe a considerable gap in performance (20% F1) between the best human and machine readers. We analyze the skills required for successful answering and show how reader performance varies depending on the applicable skills. We find that inferences using domain knowledge and object tracking are the most frequently required skills, and that recognizing omitted information and spatio-temporal reasoning are the most difficult for the machines.

Autostacker: a compositional evolutionary learning system

Abstract: In this work, an automatic machine learning (AutoML) modeling architecture called Autostacker is introduced. Autostacker combines an innovative hierarchical stacking architecture and an evolutionary algorithm (EA) to perform efficient parameter search without the need for prior domain knowledge about the data or feature preprocessing. Using EA, Autostacker quickly evolves candidate pipelines with high predictive accuracy. These pipelines can be used in their given form, or serve as a starting point for further augmentation and refinement by human experts. Autostacker finds innovative machine learning model combinations and structures, rather than selecting a single model and optimizing its hyperparameters. When its performance on fifteen datasets is compared with that of other AutoML systems, Autostacker produces superior or competitive results in terms of both test accuracy and time cost.

Bayesian Optimization Using Domain Knowledge on the ATRIAS Biped

Abstract: Robotics controllers often consist of expert-designed heuristics, which can be hard to tune in higher dimensions. Simulation can aid in optimizing these controllers if parameters learned in simulation transfer to hardware. Unfortunately, this is often not the case in legged locomotion, necessitating learning directly on hardware. This motivates using data-efficient learning techniques like Bayesian Optimization (BO) to minimize collecting expensive data samples. BO is a black-box data-efficient optimization scheme, though its performance typically degrades in higher dimensions. We aim to overcome this problem by incorporating domain knowledge, with a focus on bipedal locomotion. In our previous work, we proposed a feature transformation that projected a 16-dimensional locomotion controller to a 1-dimensional space using knowledge of human walking. When optimizing a human-inspired neuromuscular controller in simulation, this feature transformation enhanced sample efficiency of BO over traditional BO with a Squared Exponential kernel. In this paper, we present a generalized feature transform applicable to non-humanoid robot morphologies and evaluate it on the ATRIAS bipedal robot, in both simulation and hardware. We present three different walking controllers and two are evaluated on the real robot. Our results show that this feature transform captures important aspects of walking and accelerates learning on hardware and simulation, as compared to traditional BO.

A domain keyword analysis approach extending Term Frequency-Keyword Active Index with Google Word2Vec model

Abstract: In bibliometric research, keyword analysis of publications provides an effective way not only to investigate the knowledge structure of research domains, but also to explore the developing trends within domains. To identify the most representative keywords, many approaches have been proposed. Most of them focus on using statistical regularities, syntax, grammar, or network-based characteristics to select representative keywords for the domain analysis. In this paper, we argue that the domain knowledge is reflected by the semantic meanings behind keywords rather than the keywords themselves. We apply the Google Word2Vec model, a model of a word distribution using deep learning, to represent the semantic meanings of the keywords. Based on this work, we propose a new domain knowledge approach, the Semantic Frequency-Semantic Active Index, similar to Term Frequency-Inverse Document Frequency, to link domain and background information and identify infrequent but important keywords. We adopt a semantic similarity measuring process before statistical computation to compute the frequencies of “semantic units” rather than keyword frequencies. Semantic units are generated by word vector clustering, while the Inverse Document Frequency is extended to include the semantic inverse document frequency; thus only words in the inverse documents with a certain similarity will be counted. Taking geographical natural hazards as the domain and natural hazards as the background discipline, we identify the domain-specific knowledge that distinguishes geographical natural hazards from other types of natural hazards. We compare and discuss the advantages and disadvantages of the proposed method in relation to existing methods, finding that by introducing the semantic meaning of the keywords, our method supports more effective domain knowledge analysis.

Interpretable Multimodal Retrieval for Fashion Products

Abstract: Deep learning methods have been successfully applied to fashion retrieval. However, the latent meaning of learned feature vectors hinders the explanation of retrieval results and integration of user feedback. Fortunately, there are many online shopping websites organizing fashion items into hierarchical structures based on product taxonomy and domain knowledge. Such structures help to reveal how human perceive the relatedness among fashion products. Nevertheless, incorporating structural knowledge for deep learning remains a challenging problem. This paper presents techniques for organizing and utilizing the fashion hierarchies in deep learning to facilitate the reasoning of search results and user intent. The novelty of our work originates from the development of an EI (Exclusive & Independent) tree that can cooperate with deep models for end-to-end multimodal learning. EI tree organizes the fashion concepts into multiple semantic levels and augments the tree structure with exclusive as well as independent constraints. It describes the different relationships among sibling concepts and guides the end-to-end learning of multi-level fashion semantics. From EI tree, we learn an explicit hierarchical similarity function to characterize the semantic similarities among fashion products. It facilitates the interpretable retrieval scheme that can integrate the concept-level feedback. Experiment results on two large fashion datasets show that the proposed approach can characterize the semantic similarities among fashion items accurately and capture user's search intent precisely, leading to more accurate search results as compared to the state-of-the-art methods.

FEMOSAA: Feature-Guided and Knee-Driven Multi-Objective Optimization for Self-Adaptive Software

Abstract: Self-Adaptive Software (SAS) can reconfigure itself to adapt to the changing environment at runtime, aiming to continually optimize conflicted nonfunctional objectives (e.g., response time, energy consumption, throughput, cost, etc.). In this article, we present Feature-guided and knEe-driven Multi-Objective optimization for Self-Adaptive softwAre (FEMOSAA), a novel framework that automatically synergizes the feature model and Multi-Objective Evolutionary Algorithm (MOEA) to optimize SAS at runtime. FEMOSAA operates in two phases: at design time, FEMOSAA automatically transposes the engineers’ design of SAS, expressed as a feature model, to fit the MOEA, creating new chromosome representation and reproduction operators. At runtime, FEMOSAA utilizes the feature model as domain knowledge to guide the search and further extend the MOEA, providing a larger chance for finding better solutions. In addition, we have designed a new method to search for the knee solutions, which can achieve a balanced tradeoff. We comprehensively evaluated FEMOSAA on two running SAS: One is a highly complex SAS with various adaptable real-world software under the realistic workload trace; another is a service-oriented SAS that can be dynamically composed from services. In particular, we compared the effectiveness and overhead of FEMOSAA against four of its variants and three other search-based frameworks for SAS under various scenarios, including three commonly applied MOEAs, two workload patterns, and diverse conflicting quality objectives. The results reveal the effectiveness of FEMOSAA and its superiority over the others with high statistical significance and nontrivial effect sizes.

Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning

Abstract: Space-based missions such as Kepler, and soon TESS, provide large datasets that must be analyzed efficiently and systematically. Recent work by Shallue & Vanderburg (2018) successfully used stateof-the-art deep learning models to automatically classify Kepler transit signals as either exoplanets or false positives; our application of their model yielded 95.8% accuracy and 95.5% average precision. Here we expand upon that work by including additional scientific domain knowledge into the network architecture and input representations to significantly increase overall model performance to 97.5% accuracy and 98.0% average precision. Notably, we achieve 15–20% gains in recall for the lowest signal-to-noise transits that can correspond to rocky planets in the habitable zone. We input into the network centroid time-series information derived from Kepler data plus key stellar parameters taken from the Kepler DR25 and Gaia DR2 catalogues. We also implement data augmentation techniques to alleviate model over-fitting. These improvements allow us to drastically reduce the size of the model, while still maintaining improved performance; smaller models are better for generalization, for example from Kepler to TESS data. This work illustrates the importance of including expert domain knowledge in even state-of-the-art deep learning models when applying them to scientific research problems that seek to identify weak signals in noisy data. This classification tool will be especially useful for upcoming space-based photometry missions focused on finding small planets, such as TESS and PLATO.

Challenges of Domain-Driven Microservice Design: A Model-Driven Perspective

Abstract: Domain-driven design (DDD) is a model-driven methodology to capture relevant domain knowledge for software design. It provides the means to isolate domain concepts and identify concept relationships. This makes DDD particularly appropriate for designing microservice architectures, because functional microservices focus on realizing distinct business capabilities. This article explores the challenges of domain-driven microservice design and presents ways to cope with them based on model-driven development.

Knowledge graph based on domain ontology and natural language processing technology for Chinese intangible cultural heritage

Abstract: Intangible cultural heritage (ICH) is a precious historical and cultural resource of a country. Protection and inheritance of ICH is important to the sustainable development of national culture. There are many different intangible cultural heritage items in China. With the development of information technology, ICH database resources were built by government departments or public cultural services institutions, but most databases were widely dispersed. Certain traditional database systems are disadvantageous to storage, management and analysis of massive data. At the same time, a large quantity of data has been produced, accompanied by digital intangible cultural heritage development. The public is unable to grasp key knowledge quickly because of the massive and fragmented nature of the data. To solve these problems, we proposed the intangible cultural heritage knowledge graph to assist knowledge management and provide a service to the public. ICH domain ontology was defined with the help of intangible cultural heritage experts and knowledge engineers to regulate the concept, attribute and relationship of ICH knowledge. In this study, massive ICH data were obtained, and domain knowledge was extracted from ICH text data using the Natural Language Processing (NLP) technology. A knowledge base based on domain ontology and instances for Chinese intangible cultural heritage was constructed, and the knowledge graph was developed. The pattern and characteristics behind the intangible cultural heritage were presented based on the ICH knowledge graph. The knowledge graph for ICH could foster support for organization, management and protection of the intangible cultural heritage knowledge. The public can also obtain the ICH knowledge quickly and discover the linked knowledge. The knowledge graph is helpful for the protection and inheritance of intangible cultural heritage.

Role of search for domain knowledge and architectural knowledge in alliance partner selection

Abstract: Research Summary: The literature on technological alliances emphasizes that search for knowledge drives alliance formation. However, in conceptualizing technological knowledge, prior work on alliances has not made a distinction between domain knowledge—knowledge that firms possess in distinct technological domains—and architectural knowledge—knowledge that firms possess about how to combine elements from different technological domains. We argue that firms seek partners that are similar in domain knowledge to deepen their knowledge, and partners that are dissimilar in architectural knowledge to broaden their knowledge. Our results indicate that the likelihood of alliance formation increases when two firms are similar in domain knowledge and dissimilar in architectural knowledge. Further, our results show that these effects are positively moderated by the degree of decomposability of a firm's knowledge base. Managerial Summary: In dynamic environments, companies need to continually deepen and broaden their technological knowledge, and they often look for alliance partners who can provide them that knowledge. For knowledge deepening, companies are more likely to form alliances with those companies that have expertise in similar technological fields. For knowledge broadening, they are more likely to form alliances with those companies that have expertise in the same technological fields, but have different recipes for combining knowledge from those fields. Furthermore, a company with a modular knowledge base is more likely to seek a partner that has expertise in similar technological fields or whose recipes for combining knowledge from different technological fields are different from the recipes it has.