Level Of Domain Knowledge Research Articles

Informating and Automating in Systems Design: Extending the Zuboffian View of Technology Ready-to-Use vs. Technology Unintuitive-to-Use

ABSTRACT Previous literature has treated software functionalities as a binary choice between informating and automating, based on Zuboff’s definitions. We suggest that the space between the role of a user engaging with a system (informate) and what the system can accomplish for the user (automate) has increasingly become blurred, moving toward a more nuanced continuum. We present a user-system interaction framework that analyzes this continuum with a focus on the user’s perspective. Using cases from archival data, this paper provides an analysis of what goes well and badly in the locus of control handoff between users and systems, highlighting the implications of software that is created in one region but used globally. The paper contributes to the literature by extending Zuboff’s informate vs. automate discussion and identifying design decisions that could help to avoid potentially catastrophic design errors. Using the interaction framework, we argue that it would be beneficial for system designers to move toward the informate end of the continuum, when designing systems for users with a high level of domain knowledge and expertise, and when there are significant differences between the environment in which the system is designed and the one in which the system is used.

As Teachers Not Tourists: Creating Knowledge During a Short-Term Study Abroad Program

Here, I address the call for teacher education programs to feature international elements to help pre-service teachers craft powerful classroom instruction and successfully work with students from culturally diverse backgrounds. I share a qualitative investigation of participants’ experiences during a short-term study abroad program in Japan that explored contemporary disaster preparedness as a result of the Great East Japan Earthquake and Tsunami. The program sponsors, the Japanese Ministry of Foreign Affairs, hoped participants would develop an appreciation for the people and culture of Japan while they learned about disaster preparedness. I wondered if collecting curriculum items during a short-term study abroad program could help social studies pre-service teachers create—not just receive—historical domain knowledge? In Japan, participants collected items to use as featured resources around which they designed classroom activities for secondary students. Their activities demonstrated three levels of second-order historical domain knowledge and two elements of civic competence. This study suggests that pre-service teachers with no previous international experience may require explicit modeling and scaffolding to translate their short-term study abroad participation into dynamic learning. Another implication is that participants need strong support to consider the photographs they capture as artifacts of contemporary material culture.

Combining uncertainty information with AI recommendations supports calibration with domain knowledge

The use of Artificial Intelligence (AI) decision support is increasing in high-stakes contexts, such as healthcare, defense, and finance. Uncertainty information may help users better leverage AI predictions, especially when combined with their domain knowledge. We conducted a human-subject experiment with an online sample to examine the effects of presenting uncertainty information with AI recommendations. The experimental stimuli and task, which included identifying plant and animal images, are from an existing image recognition deep learning model, a popular approach to AI. The uncertainty information was predicted probabilities for whether each label was the true label. This information was presented numerically and visually. In the study, we tested the effect of AI recommendations in a within-subject comparison and uncertainty information in a between-subject comparison. The results suggest that AI recommendations increased both participants’ accuracy and confidence. Further, providing uncertainty information significantly increased accuracy but not confidence, suggesting that it may be effective for reducing overconfidence. In this task, participants tended to have higher domain knowledge for animals than plants based on a self-reported measure of domain knowledge. Participants with more domain knowledge were appropriately less confident when uncertainty information was provided. This suggests that people use AI and uncertainty information differently, such as an expert versus second opinion, depending on their level of domain knowledge. These results suggest that if presented appropriately, uncertainty information can potentially decrease overconfidence that is induced by using AI recommendations.

Auto Encoder Fixed-Target Training Features Extraction Approach for Binary Classification Problems

The main issues with machine learning-based feature extraction techniques are the requirement of extensive domain-level knowledge, experience, and the need to be supported by large amounts of data that are sometimes not available. Moreover, it is often difficult to apply domain-level knowledge to extract the necessary features for building a machine-learning classifier. Therefore, it is significantly important to find and develop feature extraction techniques that depend mainly on the training data and don’t require or depend on domain-level knowledge and experience. To address these issues for binary classification problems, a novel feature extraction approach, AE-FT(Fixed Target) for extracting common features using a Deep Belief Network (DBN)-based Autoencoder (AE) is proposed in this paper. In this approach, common features are extracted by a DBN trained on a dataset sample’s binary using the Fixed Target training approach.
 The proposed common features extraction approach is tested and evaluated on two different data sets. For each dataset, the extracted features are used to train seven of the common machine learning binary classification algorithms and compared their performances. Moreover, the number of extracted features is very small compared to other existing feature extraction methods. Therefore, the proposed common features extraction method improves the performance of the binary classification algorithms by reducing the number of features reducing laborious processes, and increasing the recognition accuracy effectively.
 The results show that the proposed common features extraction approach, without any domain-level knowledge or human expertise, provides a very good performance compared to other feature extraction techniques.

Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings

Building upon prior research that highlighted the need for standardizing environments for building control research, and inspired by recently introduced challenges for real life reinforcement learning (RL) control, here we propose a non-exhaustive set of nine real world challenges for RL control in grid-interactive buildings (GIBs). We argue that research in this area should be expressed in this framework in addition to providing a standardized environment for repeatability. Advanced controllers such as model predictive control (MPC) and RL control have both advantages and disadvantages that prevent them from being implemented in real world problems. Comparisons between the two are rare, and often biased. By focusing on the challenges, we can investigate the performance of the controllers under a variety of situations and generate a fair comparison. As a demonstration, we implement the offline learning challenge in CityLearn, an OpenAI Gym environment for the easy implementation of RL agents in a demand response setting to reshape the aggregated curve of electricity demand by controlling the energy storage of a diverse set of buildings in a district. We use CityLearn to study the impact of different levels of domain knowledge and complexity of RL algorithms and show that the sequence of operations (SOOs) utilized in a rule based controller (RBC) that provides fixed logs to RL agents during offline training affect the performance of the agents when evaluated on a set of four energy flexibility metrics. Longer offline training from an optimized RBC leads to improved performance in the long run. RL agents that train on the logs from a simplified RBC risk poorer performance as the offline training period increases. We also observe no impact on performance from information sharing amongst agents. We call for a more interdisciplinary effort of the research community to address the real world challenges, and unlock the potential of GIB controllers.

Empirical investigation of the domain knowledge and team advertising creativity typology: The case of Nescafe coffee

This study proposes and tests a typology of domain knowledge and team creativity by empirically assessing the effects of varying levels of domain knowledge on the creative outcomes of the team members. Two separate studies were conducted to address this inquiry. Study one aimed at determining the level of domain knowledge of each team member in the teams. Eleven groups comprising of thirty-three business students designed eleven advertisements for the products of their own choices. Utilizing the situation judgment test and the grade earned in the advertising course, four teams were formed comprising two balanced and two imbalanced domain knowledge teams. To test the hypotheses of the study, these teams were asked to develop a print advertisement for Nescafe for the summer season (Study Two). Upon creativity assessment of the final ads by twenty-six independent creative personnel in a total of seven advertising agencies in Pakistan, the results revealed that a balanced team with low domain knowledge outperformed the other balanced team with high domain knowledge. Further, unexpectedly, one of the imbalanced domain knowledge teams also outperformed the balanced high domain knowledge team. The study in the light of extant literature presents worthwhile implications for academia and practitioners.

Decision-based virtual metrology for advanced process control to empower smart production and an empirical study for semiconductor manufacturing

Virtual metrology (VM) has been employed to improve the performance of advanced process control for semiconductor manufacturing. A number of VM models have been proposed to predict the quality characteristics for the wafers that have not been sampled and measured. However, little research has been done to address the interrelations between the VM model and associated decisions for advanced process control and yield enhancement. There is a research need for developing a framework that can integrate the confidence level of VM prediction and domain knowledge to derive appropriate decisions for real-time control. To fill the gaps, this study aims to develop a decision-based virtual metrology framework that integrates clustering and regression models to enhance the prediction and ensure the decision quality for the R2R controller. In particular, Isolation Forest is employed to cluster the data group for multi-recipes and multi-tools. Random Forest Regression is developed for the prediction model for each category respectively to enhance the accuracy of predicted results. Furthermore, this approach designs an overall confidence score based on data integrity and predicted results to suggest the optimal decision rules for R2R control in real time. This approach is validated with an empirical study in a leading semiconductor manufacturing company in Taiwan. Indeed, the results have demonstrated practical viability and the developed solution has been implemented.

OntoSLAM: An Ontology for Representing Location and Simultaneous Mapping Information for Autonomous Robots

Autonomous robots are playing an important role to solve the Simultaneous Localization and Mapping (SLAM) problem in different domains. To generate flexible, intelligent, and interoperable solutions for SLAM, it is a must to model the complex knowledge managed in these scenarios (i.e., robots characteristics and capabilities, maps information, locations of robots and landmarks, etc.) with a standard and formal representation. Some studies have proposed ontologies as the standard representation of such knowledge; however, most of them only cover partial aspects of the information managed by SLAM solutions. In this context, the main contribution of this work is a complete ontology, called OntoSLAM, to model all aspects related to autonomous robots and the SLAM problem, towards the standardization needed in robotics, which is not reached until now with the existing SLAM ontologies. A comparative evaluation of OntoSLAM with state-of-the-art SLAM ontologies is performed, to show how OntoSLAM covers the gaps of the existing SLAM knowledge representation models. Results show the superiority of OntoSLAM at the Domain Knowledge level and similarities with other ontologies at Lexical and Structural levels. Additionally, OntoSLAM is integrated into the Robot Operating System (ROS) and Gazebo simulator to test it with Pepper robots and demonstrate its suitability, applicability, and flexibility. Experiments show how OntoSLAM provides semantic benefits to autonomous robots, such as the capability of inferring data from organized knowledge representation, without compromising the information for the application and becoming closer to the standardization needed in robotics.

Detection of alcoholism using EEG signals and a CNN-LSTM-ATTN network

Alcoholism is a serious disorder that poses a problem for modern society, but the detection of alcoholism has no widely accepted standard tests or procedures. If alcoholism goes undetected at its early stages, it can create havoc in the patient's life. An electroencephalography (EEG) is a method used to measure the brain's electrical activity and can detect alcoholism. EEG signals are complex and multi-channel and thus can be difficult to interpret manually. Several previous works have tried to classify a subject as alcoholic or control (non-alcoholic) based on EEG signals. Such works have mainly used machine learning or statistical techniques along with handcrafted features such as entropy, correlation dimension, Hurst exponent. With the growth in computational power and data volume worldwide, deep learning models have recently been gaining momentum in various fields. However, only a few studies are available on the application of deep learning models for the classification of alcoholism using EEG signals. This paper proposes a deep learning architecture that uses a combination of fast Fourier transform (FFT), a convolution neural network (CNN), long short-term memory (LSTM), and a recently proposed attention mechanism for extracting Spatio-temporal features from multi-channel EEG signals. The proposed architecture can classify a subject as an alcoholic or control with a high degree of accuracy by analyzing EEG signals of that subject and can be used for automating alcoholism detection. The analytical results using the proposed architecture show a 98.83% accuracy, making it better than most state-of-the-art algorithms.

Application of a methodological approach to compare ontologies

PurposeThis study aims to the OQuaRE quality model to the developed methodology.Design/methodology/approachOntologies are formal, well-defined and flexible representations of knowledge related to a specific domain. They provide the base to develop efficient and interoperable solutions. Hence, a proliferation of ontologies in many domains is unleashed. Then, it is necessary to define how to compare such ontologies to decide which one is the most suitable for the specific needs of users/developers. As the emerging development of ontologies, several studies have proposed criteria to evaluate them.FindingsIn a previous study, the authors propose a methodological process to qualitatively and quantitatively compare ontologies at Lexical, Structural and Domain Knowledge levels, considering correctness and quality perspectives. As the evaluation methods of the proposal are based on a golden-standard, it can be customized to compare ontologies in any domain.Practical implicationsTo show the suitability of the proposal, the authors apply the methodological approach to conduct comparative studies of ontologies in two different domains, one in the robotic area, in particular for the simultaneous localization and mapping (SLAM) problem; and the other one, in the cultural heritage domain. With these cases of study, the authors demonstrate that with this methodological comparative process, we are able to identify the strengths and weaknesses of ontologies, as well as the gaps still needed to fill in the target domains.Originality/valueUsing these metrics and the quality model from OQuaRE, the authors are incorporating a standard of software engineering at the quality validation into the Semantic Web.

Towards histopathological stain invariance by Unsupervised Domain Augmentation using generative adversarial networks

The application of supervised deep learning methods in digital pathology is limited due to their sensitivity to domain shift. Digital Pathology is an area prone to high variability due to many sources, including the common practice of evaluating several consecutive tissue sections stained with different staining protocols. Obtaining labels for each stain is very expensive and time consuming as it requires a high level of domain knowledge. In this article, we propose an unsupervised augmentation approach based on adversarial image-to-image translation, which facilitates the training of stain invariant supervised convolutional neural networks. By training the network on one commonly used staining modality and applying it to images that include corresponding, but differently stained, tissue structures, the presented method demonstrates significant improvements over other approaches. These benefits are illustrated in the problem of glomeruli segmentation in seven different staining modalities (PAS, Jones H&E, CD68, Sirius Red, CD34, H&E and CD3) and analysis of the learned representations demonstrate their stain invariance.

Conceptual Model for Integrated Production and Maintenance Planning with Automated Prognostic Method Selection

Abstract With increasing digitalization, manufacturing systems provide data to describe their current condition, allowing for a digital representation of the physical system. This enables a transition to more efficient maintenance and production planning approaches. In this context, selecting suitable prognostic methods is crucial and requires a high level of expertise and domain knowledge. This paper proposes a conceptional model for an integrated approach to solve these problems that are usually treated separately. Following an introduction of enablers for advanced maintenance strategies and prognostic methods, the conceptional model is presented. Concurrently, the state of the research of the modules is outlined. To conclude, open research questions are summarized.

Model-Agnostic Post-Processing Based on Recursive Feedback for Medical Image Segmentation

In medical image segmentation, post-processing can effectively improve the performance of a segmentation model. Existing post-processing methods generally require additional training of a post-processing model using training data or designing a post-processing procedure based on a high level of domain knowledge. Their application is limited in many real-world situations due to the lack of prerequisites. In this study, we present a post-processing method that can be applied to any existing segmentation model without requiring the use of training data or domain knowledge. Given a segmentation model of any type, the proposed method improves its prediction based on the recursive feedback mechanism. For a query image, we first obtain its prediction mask by using the segmentation model. Based on the prediction mask, we modify the original image by selectively blurring the area in which the target object is expected to be absent. Subsequently, the modified image is fed again into the model to acquire a refined prediction mask. We repeat this process to obtain multiple prediction masks, which are then combined to yield the final prediction. We verified the effectiveness of the proposed method through experiments using real-world medical datasets.

Immersive virtual reality for supporting complex scientific knowledge: Augmenting our understanding with physiological monitoring

AbstractEducators are recognizing the potential power of immersive virtual reality (IVR) to allow learners to experience previously intangible firsthand phenomena, such as atoms and molecules. In this study, an IVR simulation of a complex gene regulation system was co‐designed with an undergraduate microbiology course instructor. The course, with 234 students, was taught using active learning strategies, including peer instruction and exposure to a two‐dimensional computer simulation. Thirty‐four students from the course participated in an interactive IVR experience using head‐mounted displays. We assess students' conceptual understanding using tests, multimodal data collected during the IVR sessions (including video analysis in combination with physiological sensor data and eye‐tracking data) as well as semi‐structured interviews. We found that students who were seated while in IVR demonstrated significantly higher conceptual understanding of gene regulation at the end of the course and higher overall course outcomes, as compared to students who experienced the course as originally designed (control). However, students who experienced IVR in a standing position performed similarly to the control group. In addition, learning gain appears to be influenced by a combination of prior knowledge and how IVR is experienced (ie, sitting vs. standing). Learning implications for the connections between sensorimotor systems and cognition in IVR are discussed. Practitioner NotesWhat is already known about this topic Research on the educational applications of IVR for K‐12 and higher education emerged in the nineties, which can be summarized by several key reviews and meta‐reviews surveying the field but the answer to questions about the “added‐value” of IVR is often mixed (Dede, Jacobson, & Richards, 2017; Merchant, Goetz, Cifuentes, Keeney‐Kennicutt, & Davis, 2014)—we turn to the question of when IVR is effective for student learning. A common issue reported by researchers is that cognitive overload can hinder learning in IVR (Makransky & Lilleholt, 2018; Moreno & Mayer, 2004). Research considering the contribution of body positioning and sensorimotor perception on cognitive load is just emerging (Funk et al., 2012; Nerhood & Thompson, 2016). What this paper adds Our finding that learning outcome is influenced by a combination of how IVR is experienced (ie, sitting vs. standing position) and students’ level of prior domain knowledge, builds on earlier findings that suggest IVR experiences to be taxing on cognitive resources and further suggests that body position and prior knowledge are related mitigating factors for learning outcomes in an IVR experience—thus a more nuanced relationship exists between cognitive resources, prior knowledge and learning outcomes in IVR. We offer a new approach for using multimodal physiological measures to gain insight into the conditions under which IVR impacts the learning experience. Implications for practice and/or policy Implications of our preliminary study suggest for a seated IVR learning experience for supporting students with lower levels of prior knowledge of complex concepts, while students with higher levels of prior knowledge could choose between either sitting or standing, full‐body experience.

Optimal LQI and PID Synthesis for Speed Control of Switched Reluctance Motor Using Metaheuristic Techniques

At present, switched reluctance motors (SRM) become very interesting for many industrial applications in variable speed control. For such systems, the linear quadratic regulator with integral action (LQI) method is commonly used when using plants in state spaces due to its robustness and easy adjustment. All methods from the linear quadratic regulator (LQR) project provide a weighting of the Q and R matrices, which are manually adjusted to achieve the desired performance. The manual fine tuning of LQI controller parameters is a difficult task that requires a high level of domain knowledge. In this work, metaheuristic algorithms are explored to design the LQI controller and a comprehensive comparison is made between these algorithms and Proportional-Integral-Derivative (PID) controller as well as to select the best technique for the LQI controller design and adjustment of the Q and R parameters in SR Motor. Simulation and experimental results on a setup prototype are shown to validate the proposed control schemes. This paper has as main contributions the weighting of the parameters of the LQI in an optimized way and adjustment of the gains of the controller more quickly and the hybrid controller (LQI + GA) becomes more powerful in the sense of a possible extension of the control of a multivariable system.

Random forest application on cognitive level classification of E-learning content

The e-learning is the primary method of learning for most learners after the regular academics studies. The knowledge delivery through e-learning technologies increased exponentially over the years because of the advancement in internet and e-learning technologies. Knowledge delivery to some people would never have been possible without the e-learning technologies. Most of the working professional do focused studies for carrier advancement, promotion or to improve the domain knowledge. These learner can find many free e-learning web sites from the internet easily in the domain of interest. However it is quite difficult to find the best e-learning content suitable for their learning based on their domain knowledge level. User spent most of the time figuring out the right content from a plethora of available content and end up learning nothing. An intelligent framework using machine learning algorithms with Random Forest Classifier is proposed to address this issue, which classifies the e-learning content based on its difficulty levels and provide the learner the best content suitable based on the knowledge level .The frame work is trained with the data set collected from multiple popular e-learning web sites. The model is tested with real time e-learning web sites links and found that the e-contents in the web sites are recommended to the user based on its difficulty levels as beginner level, intermediate level and advanced level.

Effects of divergent thinking training on students’ scientific creativity: The impact of individual creative potential and domain knowledge

Training on creative thinking, in particular divergent thinking has shown promising effects on improving creativity in higher education and organizational contexts. It’s unclear how school students’ scientific creativity can be enhanced through effective training and how individual differences might influence the training effects. This study examined the effects of a divergent thinking training program, which helped high school students to master a set of divergent thinking strategies and apply them in scientific creativity-related tasks. The results showed that students’ scientific creativity performance was improved after training. Moreover, students with either a high or low level of creative potential equally benefited from the training, whereas students with a higher level of domain knowledge profited more from the training than those with a lower level of domain knowledge. The interaction between training effects and domain knowledge implied the need for aligning the acquisition of domain knowledge with the training on divergent thinking for effective development of scientific creativity. Our results suggest that teaching domain knowledge and teaching domain general skills should not be opposed but work best when integrated together.

The role of domain knowledge in document selection from search results

It is a frequently seen scenario that when people are not familiar with their search topics, they use a simple keyword search, which leads to a large amount of search results in multiple pages. This makes it difficult for users to pick relevant documents, especially given that they are not knowledgeable of the topics. To explore how systems can better help users find relevant documents from search results, the current research analyzed document selection behaviors of users with different levels of domain knowledge (DK). Data were collected in a laboratory study with 35 participants each searching on four tasks in the genomics domain. The results show that users with high and low DK levels selected different sets of documents to view; those high in DK read more documents and gave higher relevance ratings for the viewed documents than those low in DK did. Users with low DK tended to select documents ranking toward the top of the search result lists, and those with high in DK tended to also select documents ranking down the search result lists. The findings help design search systems that can personalize search results to users with different levels of DK.

The usefulness of a Web-based Participatory Planning Support System in Wuhan, China

Public participation in urban planning has become a legal requirement in China since the 2008 Urban and Rural Planning Law prescribed to collect the opinions of the public in preparing plans. The way in which this participation is organized is left to local governments and current practices are still in a stage of experimentation. Drawing on Western experience various participatory tools have been explored, including in some instances Web-based planning support systems (PSS). The current literature has identified several potentials and shortcomings in the performance of PSS that define their usefulness. However, these have been identified in the context of democratic societies and communicative planning paradigms. To what extent do these potentials and shortcomings also pertain to the emerging practice in China? This paper aims to widen the understanding of the usefulness of Web-based PSS when these are applied in a Chinese context. To do so, the paper first presents a conceptual framework that divides usefulness into utility and usability, and thereafter, it analyzes the “East Lake greenway planning project” in Wuhan. The results show that the Wuhan PSS provides new functionalities in eliciting ideas from independent citizens in the early stage of the planning process. In terms of usability, the system meets many of the criteria, but requires a high level of computer experience and domain knowledge restricting its use to “professional citizens”. From the point of view of western planners this would seriously limit the usefulness as a participatory tool, but it is legitimate in China. Given the low level of computer literacy, limited access to the internet and a lacking tradition of public involvement in state affairs, it is nevertheless clear that there is a need to improve Web-based PSS and combine them with other participatory methods, both online and offline, to facilitate the participation of a diverse group of target users.

Leader-member exchange and innovative work behavior

PurposeThe purpose of this paper is to examine how leader–member exchange relates to subordinate’s innovative work behavior through core self-evaluation (CSE), domain knowledge and creative process engagement. On the basis of an interactional approach, this study hypothesized that there is an interaction between leader–member exchange, CSE and domain knowledge that affects innovative work behavior, such that leader–member exchange has the strongest positive relationship with innovative work behavior when subordinates have high levels of CSE and domain knowledge; and creative process engagement mediates the effect that this three-way interaction between leader–member exchange, CSE and domain knowledge has on innovative work behavior.Design/methodology/approachData were collected from 323 employees and their immediate supervisors (121) from automotive industry. First, subordinates completed measures of their leader–member exchange, CSE and domain knowledge. Then, the supervisors of these employees assessed their subordinates’ innovative work behavior.FindingsThe results showed that leader–member exchange, CSE and domain knowledge interacted to affect employee innovative work behavior in such a way that when CSE and domain knowledge were both high, leader–member exchange had the strongest positive relationship with innovative work behavior and creative process engagement mediated this relationship.Originality/valueThis study is the first of its kind to empirically examine the interactional perspective of leader–member exchange on innovative work behavior through domain knowledge, CSE and creative process engagement. Theoretical and practical implications and future area of research are discussed at the end.