Domain Expert Knowledge Research Articles

Web-based Platform for Data Analysis and Monitoring

With the increasing number of sensors installed in production systems and the associated amount of recorded data, a high potential for optimizing manufacturing processes is offered. Based on the gathered information, data analyzing methods can be used to identify correlations and thus, optimize complex multi-stage production systems with the goal of zero-defect manufacturing. For this purpose, multiple statistical methods have to be applied, which is often a time-consuming task and currently requires trained and experienced specialists. Furthermore, the investigated data must be kept up to date for the early recognition of changes possibly leading to cost-intensive scrap and production downtimes. To address these issues, a web-based platform with an intuitive user interface was developed. The platform can access and process various data sources using modular methods. In addition, as part of continuous monitoring, the results of these analyzing steps can be dynamically calculated. The aim of the platform is to make complex analysis processes accessible to machine operators and thus to combine domain expertise and statistical knowledge. The paper describes the underlying architecture and the relevant interfaces of the platform.

Future of Artificial Intelligence in Anesthetics and Pain Management

The potential of the second wave of Artificial Intelligence (AI) to change our lives beyond recognition is both exciting and challenging. AI has been around for over three decades, and this new approach of artificial intelligence, due to enhancements in technology, both software, and hardware, has resulted in the fact that human decision-making is considered inferior and erratic in many fields: none more so than medicine. Machine learning algorithms with access to large data sets can be trained to outperform clinicians in many respects. AI’s effectiveness in accurate diagnosis of various medical conditions and medical image interpretation is well documented. Modern AI technology has the potential to transform medicine to a level never seen before in terms of efficiency and accuracy; but is also potentially highly disruptive, creating insecurity and allowing the transfer of expert domain knowledge to machines. Anesthetics is a complex medical discipline and assuming AI can easily replace experienced and knowledgeable medical practitioners is a very unrealistic expectation. AI can be used in anesthetics to develop, in some respects, more advanced clinical decision support tools based on machine learning. This paper focuses on the complexity of both AI developments, deep learning, neural networks, etc. and opportunities of AI in anesthetics for the future. It will review current advances in AI tools and hardware technologies as well as outlining how these can be used in the field of anesthetics.

Efficient Biosignal Processing Using Hyperdimensional Computing: Network Templates for Combined Learning and Classification of ExG Signals

Recognizing the very size of the brain’s circuits, hyperdimensional (HD) computing can model neural activity patterns with points in a HD space, that is, with HD vectors. Key examined properties of HD computing include: a versatile set of arithmetic operations on HD vectors, generality, scalability, analyzability, one-shot learning, and energy efficiency. These make it a prime candidate for efficient biosignal processing where signals are noisy and nonstationary, training data sets are not huge, individual variability is significant, and energy-efficiency constraints are tight. Purely based on native HD computing operators, we describe a combined method for multiclass learning and classification of various ExG biosignals such as electromyography (EMG), electroencephalography (EEG), and electrocorticography (ECoG). We develop a full set of HD network templates that comprehensively encode body potentials and brain neural activity recorded from different electrodes into a single HD vector without requiring domain expert knowledge or ad hoc electrode selection process. Such encoded HD vector is processed as a single unit for fast one-shot learning, and robust classification. It can be interpreted to identify the most useful features as well. Compared to state-of-the-art counterparts, HD computing enables online, incremental, and fast learning as it demands less than a third as much training data as well as less preprocessing.

Visual Analysis of Collective Anomalies Using Faceted High-Order Correlation Graphs

Successfully detecting, analyzing, and reasoning about collective anomalies is important for many real-life application domains (e.g., intrusion detection, fraud analysis, software security). The primary challenges to achieving this goal include the overwhelming number of low-risk events and their multimodal relationships, the diversity of collective anomalies by various data and anomaly types, and the difficulty in incorporating the domain knowledge of experts. In this paper, we propose the novel concept of the faceted High-Order Correlation Graph (HOCG). Compared with previous, low-order correlation graphs, HOCG achieves better user interactivity, computational scalability, and domain generality through synthesizing heterogeneous types of objects, their anomalies, and the multimodal relationships, all in a single graph. We design elaborate visual metaphors, interaction models, and the coordinated multiple view based interface to allow users to fully unleash the visual analytics power of the HOCG. We conduct case studies for three application domains and collect feedback from domain experts who apply our method to these scenarios. The results demonstrate the effectiveness of the HOCG in the overview of point anomalies, the detection of collective anomalies, and the reasoning process of root cause analyses.

A Fibrosis Diagnosis Clinical Decision Support System Using Fuzzy Knowledge

Liver cirrhosis, the end stage of chronic liver disease, is one of the major risk factors for the development of liver cancer, and may result in premature death. This research proposes a fuzzy fibrosis decision support (F2DS) system. It is a fuzzy knowledge-based expert system for liver fibrosis stage prediction. F2DS is carefully based on a set of knowledge acquisition and machine learning techniques. In addition, the system depends on domain expert knowledge for designing the membership functions and validating the fuzzy knowledge base. It depends on a suitable list of 17 symptoms, and laboratory test features that can accurately and significantly describe fibrosis patients. The experimental results of the expert system were obtained using a real dataset from the Liver Institute, Mansoura University, Egypt, of 119 patients infected by chronic viral hepatitis C. The performance of the system was evaluated with many metrics, achieving a testing accuracy of 95.7%. The evaluation of proposed fuzzy expert system shows its capability of diagnosing the stages of liver fibrosis with a high degree of accuracy, and it can be embedded as a component in a healthcare system to assist physicians in their daily practice. In addition, students training in medicine can benefit from this system.

Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning

Abstract Space-based missions such as Kepler, and soon the Transiting Exoplanet Survey Satellite (TESS), provide large data sets that must be analyzed efficiently and systematically. Recent work by Shallue & Vanderburg successfully used state-of-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 data release 25 catalog. 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 Letter 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.

ResumeVis

Massive public resume data emerging on the internet indicates individual-related characteristics in terms of profile and career experiences. Resume Analysis (RA) provides opportunities for many applications, such as recruitment trend predict, talent seeking and evaluation. Existing RA studies either largely rely on the knowledge of domain experts, or leverage classic statistical or data mining models to identify and filter explicit attributes based on pre-defined rules. However, they fail to discover the latent semantic information from semi-structured resume text, i.e., individual career progress trajectory and social-relations, which are otherwise vital to comprehensive understanding of people’s career evolving patterns. Besides, when dealing with large numbers of resumes, how to properly visualize such semantic information to reduce the information load and to support better human cognition is also challenging. To tackle these issues, we propose a visual analytics system called ResumeVis to mine and visualize resume data. First, a text mining-based approach is presented to extract semantic information. Then, a set of visualizations are devised to represent the semantic information in multiple perspectives. Through interactive exploration on ResumeVis performed by domain experts, the following tasks can be accomplished: to trace individual career evolving trajectory; to mine latent social-relations among individuals; and to hold the full picture of massive resumes’ collective mobility. Case studies with over 2,500 government officer resumes demonstrate the effectiveness of our system.

A New Geospatial Model Integrating a Fuzzy Rule-Based System in a GIS Platform to Partition a Complex Urban System in Homogeneous Urban Contexts

Here, we present a new unsupervised method aimed at obtaining a partition of a complex urban system in homogenous urban areas, called urban contexts. Our model integrates spatial analysis processes and a fuzzy rule-based system applied to manage the knowledge of domain experts; it is implemented using a GIS platform. The area of study is initially partitioned in microzones, homogeneous portions of the urban system, which are the atomic reference elements for the census data. With the contribution of domain experts, we identify the physical, morphological, environmental, and socio-economic indicators needed to identify synthetic characteristics of urban contexts and create the fuzzy rule set necessary for determining the type of urban context. We implement the set of spatial analysis processes required to calculate the indicators for the microzones and apply a Mamdani fuzzy rule system to classify the microzones. Finally, the partition of the area of study in urban contexts is obtained by dissolving continuous microzones belonging to the same type of urban context. Tests are performed on the Municipality of Pozzuoli (Naples, Italy); the reliability of the out model is measured by comparing the results with the ones obtained through a detailed analysis.

Semantic Modelling and Publishing of Traditional Data Collection Questionnaires and Answers

Extensive collections of data of linguistic, historical and socio-cultural importance are stored in libraries, museums and national archives with enormous potential to support research. However, a sizable portion of the data remains underutilised because of a lack of the required knowledge to model the data semantically and convert it into a format suitable for the semantic web. Although many institutions have produced digital versions of their collection, semantic enrichment, interlinking and exploration are still missing from digitised versions. In this paper, we present a model that provides structure and semantics to a non-standard linguistic and historical data collection on the example of the Bavarian dialects in Austria at the Austrian Academy of Sciences. We followed a semantic modelling approach that utilises the knowledge of domain experts and the corresponding schema produced during the data collection process. The model is used to enrich, interlink and publish the collection semantically. The dataset includes questionnaires and answers as well as supplementary information about the circumstances of the data collection (person, location, time, etc.). The semantic uplift is demonstrated by converting a subset of the collection to a Linked Open Data (LOD) format, where domain experts evaluated the model and the resulting dataset for its support of user queries.

Constraint-based discriminative dimension selection for high-dimensional stream clustering

Clustering data streams is one of active research topic in data mining. However, runtime of the existing stream clustering algorithms increases and their performance drop in the face of large number of dimensions. Complexity of the stream clustering methods is increased when perform on data with large number of dimensions. In order to reduce the clustering complexity, one possible solution consists in determining the appropriate subset of cluster dimensions via dimension projection. SED-Stream is an efficient clustering algorithm that supports high dimension data streams. The aim of this paper is to increase performance of SED-Stream in terms of both clustering quality and execution-time. In order to improve the clustering process, background or domain expert knowledge are integrated as “constraints” in SEDC-Stream. The new algorithm, SEDC-Stream, supports the evolving characteristics of the dynamic constraints which are activation, fading, outdating and prioritization. SEDC-Stream algorithm is able to reduce cluster splitting time, and place new incoming points to their suitable clusters. Compared to SED-Stream on the three real-world streams datasets, SEDC-Stream is able to generate a better clustering performance in terms of both purity and f-measure.

Efficient design of hardware-enabled reservoir computing in FPGAs

In this work, we propose a new approach toward the efficient optimization and implementation of reservoir computing hardware, reducing the required domain-expert knowledge and optimization effort. First, we introduce a self-adapting reservoir input mask to the structure of the data via linear autoencoders. We, therefore, incorporate the advantages of dimensionality reduction and dimensionality expansion achieved by conventional algorithmically-efficient linear algebra procedures of principal component analysis. Second, we employ evolutionary-inspired genetic algorithm techniques resulting in a highly efficient optimization of reservoir dynamics with a dramatically reduced number of evaluations comparing to exhaustive search. We illustrate the method on the so-called single-node reservoir computing architecture, especially suitable for implementation in ultrahigh-speed hardware. The combination of both methods and the resulting reduction of time required for performance optimization of a hardware system establish a strategy toward machine learning hardware capable of self-adaption to optimally solve specific problems. We confirm the validity of those principles building reservoir computing hardware based on a field-programmable gate array.

RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records.

We have recently seen many successful applications of recurrent neural networks (RNNs) on electronic medical records (EMRs), which contain histories of patients' diagnoses, medications, and other various events, in order to predict the current and future states of patients. Despite the strong performance of RNNs, it is often challenging for users to understand why the model makes a particular prediction. Such black-box nature of RNNs can impede its wide adoption in clinical practice. Furthermore, we have no established methods to interactively leverage users' domain expertise and prior knowledge as inputs for steering the model. Therefore, our design study aims to provide a visual analytics solution to increase interpretability and interactivity of RNNs via a joint effort of medical experts, artificial intelligence scientists, and visual analytics researchers. Following the iterative design process between the experts, we design, implement, and evaluate a visual analytics tool called RetainVis, which couples a newly improved, interpretable, and interactive RNN-based model called RetainEX and visualizations for users' exploration of EMR data in the context of prediction tasks. Our study shows the effective use of RetainVis for gaining insights into how individual medical codes contribute to making risk predictions, using EMRs of patients with heart failure and cataract symptoms. Our study also demonstrates how we made substantial changes to the state-of-the-art RNN model called RETAIN in order to make use of temporal information and increase interactivity. This study will provide a useful guideline for researchers that aim to design an interpretable and interactive visual analytics tool for RNNs.

A multivariate encoder information based convolutional neural network for intelligent fault diagnosis of planetary gearboxes

Rotary encoder signal, as the built-in position information, possesses a wide variety of advantages over vibration signal and has aroused great interest in the field of health monitoring for rotating machinery. However, there are two major issues when attempting to detect and diagnose failures with encoder information. First of all, a series of proper signal processing methods need to be designed for fault feature extraction, which largely relies on the expert experience and domain knowledge. Furthermore, existing studies primarily concentrate on a single transform, such as instantaneous angular speed, which neglects the diversity of encoder information. In view of above deficiencies, a multivariate encoder information based convolutional neural network (MEI-CNN) is proposed for intelligent diagnosis in this paper. In this framework, three different types of dynamic encoder information are firstly acquired by analyzing and processing the raw position sequence, after that multivariate encoder information (MEI) data are constructed by data fusion. Finally, a concise and effective convolutional neural network is designed to extract discriminating features and provide diagnosis results. The proposed method not only overcomes drawbacks of traditional techniques based on vibration analysis, but also provides an intelligent way to achieve satisfactory diagnosis results. The effectiveness and superiority of MEI-CNN are validated by experimental data from a planetary gearbox test rig. The results also indicate that the proposed method may offer a promising tool for intelligent diagnosis of rotating machinery.

A Blade Defect Diagnosis Method by Fusing Blade Tip Timing and Tip Clearance Information

Blade tip timing (BTT) technology is considered the most promising method for blade vibration measurements due to the advantages of its simplicity and non-contact measurement capacity. Nevertheless, BTT technology still suffers from two problems, which are (1) the requirements of domain expertise and prior knowledge of BTT signals analysis due to severe under-sampling; and (2) that the traditional BTT method can only judge whether there is a defect in the blade but it cannot judge the severity and the location of the defect. Thus, how to overcome the above drawbacks has become a big challenge. Aiming at under-sampled BTT signals, a feature learning method using a convolutional neural network (CNN) is introduced. In this way, some new fault-sensitive features can be adaptively learned from raw under-sampled data and it is therefore no longer necessary to rely on prior knowledge. At the same time, research has found that tip clearance (TC) is also very sensitive to the blade state, especially regarding defect severity and location. A novel analysis method fusing TC and BTT signals is proposed in this paper. The goal of this approach is to integrate tip clearance information with tip timing information for blade fault detection. The method consists of four key steps: First, we extract the TC and BTT signals from raw pulse data; second, TC statistical features and BTT deep learning features will be extracted and fused using the kernel principal component analysis (KPCA) method; then, model training and selection are carried out; and finally, 16 sets of experiments are carried out to validate the feasibility of the proposed method and the classification accuracy achieves 95%, which is far higher than the traditional diagnostic method.

Fujitsu HIKARI, a Healthcare Decision Support System based on Biomedical Knowledge

Fujitsu HIKARI is an artificial intelligence solution to assist clinicians in medical decision making, developed in the context of a joint collaboration project between Fujitsu Laboratories of Europe and Hospital Clínico San Carlos. This decision support system leverages on data analytics combined with healthcare semantic information to provide health estimations for patients, improving care quality and personalized treatment. Fujitsu HIKARI stands on the shoulders of biomedical knowledge, which includes (i) theoretical knowledge extracted from scientific literature, domain expert knowledge, and health standards; and (ii) empirical knowledge extracted from real patient electronic health records. The theoretical knowledge combines a theoretical knowledge graph (TKG) and a biomedical document repository (BDR). The empirical knowledge is encoded in an empirical knowledge graph (EKG). One of the main functionalities of Fujitsu HIKARI is the patient mental health risks assessment, which is based on the exploitation of its underlying Biomedical Knowledge.

Towards improving diagnosis of skin diseases by combining deep neural network and human knowledge

BackgroundThe emergence of the deep convolutional neural network (CNN) greatly improves the quality of computer-aided supporting systems. However, due to the challenges of generating reliable and timely results, clinical adoption of computer-aided diagnosis systems is still limited. Recent informatics research indicates that machine learning algorithms need to be combined with sufficient clinical expertise in order to achieve an optimal result.MethodsIn this research, we used deep learning algorithms to help diagnose four common cutaneous diseases based on dermoscopic images. In order to facilitate decision-making and improve the accuracy of our algorithm, we summarized classification/diagnosis scenarios based on domain expert knowledge and semantically represented them in a hierarchical structure.ResultsOur algorithm achieved an accuracy of 87.25 ± 2.24% in our test dataset with 1067 images. The semantic summarization of diagnosis scenarios can help further improve the algorithm to facilitate future computer-aided decision support.ConclusionsIn this paper, we applied deep neural network algorithm to classify dermoscopic images of four common skin diseases and archived promising results. Based on the results, we further summarized the diagnosis/classification scenarios, which reflect the importance of combining the efforts of both human expertise and computer algorithms in dermatologic diagnoses.

Deep learning at the shallow end: Malware classification for non-domain experts

Current malware detection and classification approaches generally rely on time consuming and knowledge intensive processes to extract patterns (signatures) and behaviors from malware, which are then used for identification. Moreover, these signatures are often limited to local, contiguous sequences within the data whilst ignoring their context in relation to each other and throughout the malware file as a whole. We present a Deep Learning based malware classification approach that requires no expert domain knowledge and is based on a purely data driven approach for complex pattern and feature identification.

Testing Indicators of Translation Expertise in an Intralingual Task

Massey/Ehrensberger-Dow (2014) showed that the focused use of external resources, more frequent but shorter pauses, and fast text production speed correlated with the level of translation experience in participants translating a text from English into German. This paper aims to: (1) investigate whether these indicators distinguish professional translators from trainees and language students who translated from English into Polish, and (2) test which indicators are also present in an intralingual task, i.e., when paraphrasing a text. Additionally, task duration and the quality of the target texts produced by the three groups are compared with a view to expand the list of indicators of translation expertise. The data discussed here come from the ParaTrans research project in which professional translators, translation trainees and language students translated and paraphrased comparable texts. The results confirm that the less frequent use of external resources, shorter problem-solving pauses, fast text production and high quality target texts are strong indicators of expertise in translation. The number of problem-solving pauses was the only parameter found to distinguish professionals from trainees and language students in the paraphrasing task. This suggests that translation expertise perceived as a general construct can be seen as encompassing task expertise: the ability to reformulate meaning (transferable to a paraphrasing task) and the domain knowledge expertise inclusive of the ability to efficiently use bilingual knowledge when producing a translation

A Systematic Review on Healthcare Analytics: Application and Theoretical Perspective of Data Mining.

The growing healthcare industry is generating a large volume of useful data on patient demographics, treatment plans, payment, and insurance coverage—attracting the attention of clinicians and scientists alike. In recent years, a number of peer-reviewed articles have addressed different dimensions of data mining application in healthcare. However, the lack of a comprehensive and systematic narrative motivated us to construct a literature review on this topic. In this paper, we present a review of the literature on healthcare analytics using data mining and big data. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we conducted a database search between 2005 and 2016. Critical elements of the selected studies—healthcare sub-areas, data mining techniques, types of analytics, data, and data sources—were extracted to provide a systematic view of development in this field and possible future directions. We found that the existing literature mostly examines analytics in clinical and administrative decision-making. Use of human-generated data is predominant considering the wide adoption of Electronic Medical Record in clinical care. However, analytics based on website and social media data has been increasing in recent years. Lack of prescriptive analytics in practice and integration of domain expert knowledge in the decision-making process emphasizes the necessity of future research.

Evolution of Project Management Research and Industry-focused Innovations

In this paper, we have investigated the quantity and quality of worldwide research production in the field of “project management” over the past 35 years. We conducted bibliometric analysis using the Scopus database between 1980 and 2014 to develop an understanding of the evolution of project management as a field of endeavour. Using the knowledge of a domain expert in the field of “project management”, we first developed a set of reliable keywords which represent the field. Secondly, we developed a data extraction strategy for searching on the phrase “project management” in the title or keyword or abstract of publications by limiting our sources to journals in English. We observed the evolution of this field by analysing not only the quantity of publications, but also their quality (citations) per year and compared their growth trend in four periods to track the evolutionary trends over the last 35 years. The results of our analysis confirm that both the research themes or topics and the active parties involved in project management research are changing over time. It appears that over the four study periods, the understanding of project management as a research and scientific field has broadened substantially to include human factors, strategy and organisational dynamics and complexity management.