Search

The complex traffic and road environment pose considerable challenges to the accuracy, timeliness, and adaptive ability of connected and autonomous vehicles (CAVs) in making driving decisions. This paper uses vehicle collaboration and integrates the adaptive learning capabilities of machine learning and the interpretation capabilities of expert systems (ESs) in a unified architecture to form a hybrid autonomous driving guidance system, which not only solves the ``bottleneck'' of knowledge acquisition during the construction of expert systems but also solves the ``black box'' phenomenon of machine learning in the decision-making process. First, an autonomous driving strategy based on deep reinforcement learning (DRL) is proposed for CAVs to make decisions and extract corresponding rules. Next, we design an ES knowledge base expansion method including rule extraction, rule sharing, and rule test. Particularly, vehicular blockchain is adopted to ensure user privacy and data security during the rule-sharing process. Third, hybrid autonomous driving guidance combining ES and machine learning is proposed for CAVs to make accurate and efficient decisions in different driving environments. Once the strategy is well trained, it can effectively guide CAVs to cope with the complex traffic environment. Extensive simulations validate the performance of our proposal in terms of decision-making accuracy, effectiveness, and safety.

Researchers and practitioners have long realized the importance of acquiring innovative knowledge from online innovation communities. However, it has still been a challenge to identify valuable information of interest from unstructured and noisy user-generated text. The extant research trying to solve this problem is limited by the generalizability issue and the lack of topic-level investigation. In this article, we proposed an automatic hybrid model to simultaneously extract knowledge topics and knowledge structures from free text in online innovation communities. By employing a topic model, one important contribution of this article is the elimination of manual intervention and addressing of the generalizability issue faced by existing supervised approaches. Another major contribution of this article is the design of a novel solution for knowledge structure construction by combining a topic model with association analysis; this solution addresses the weakness of the traditional topic model. We evaluate the validity of the proposed hybrid model in experiments with a real-world dataset. The results show that by providing a new angle for innovative knowledge acquisition and management, this proposed method is effective in extracting meaningful innovative knowledge and in uncovering knowledge structures.

Contribution: This article provides evidence on the effectiveness of game-based learning (GBL) for computer science education when using educational video games created by teachers using authoring tools. Background: Although teacher-oriented authoring tools for creating educational video games can help overcome the main barriers hampering the use and uptake of GBL, there is a lack of studies examining the effectiveness of educational video games authored by teachers using these authoring tools by means of rigorous scientific methods. Research Questions: Is GBL using teacher-authored games more effective than traditional teaching in terms of motivation for computer science students? Is GBL using teacher-authored games more effective than traditional teaching in terms of knowledge acquisition for computer science students? Methodology: Two randomized control trials with pretest, post-test, and one questionnaire were conducted to compare the effectiveness of traditional teaching and GBL in two computer science courses. The sample of the two experiments was composed by 75 and 49 students, respectively. Half of the students attended a traditional lecture, while the other half learned solely by playing teacher-authored educational video games. Findings: The results show that GBL using teacher-authored games was practically as effective as traditional teaching in terms of knowledge acquisition, but that it was emphatically successful in increasing student motivation. Students who learned by playing educational video games found the experience more motivating and fun than their counterparts, and a vast majority of them preferred the GBL approach over traditional teaching.

With the popularization of smart grids, patrol robots have become critical devices in the distribution networks to check the state of equipment. In order to enrich the knowledge of patrol robots in this complex scenario, this article presents the graph-based knowledge acquisition method with convolutional networks for distribution network patrol robots. The proposed method uses a graph convolutional network-based path-related embedding algorithm to complete the knowledge of the distribution network knowledge graph. The proposed algorithm generates the embeddings of entities and relations through aggregating the associated entities in the associated paths, instead of only the connected entities. The graph convolutional network consists of multiple graph convolution layers, and the message-passing process treats different entities discriminatorily according to the association strengths. For determining the plausibility of the knowledge, a scoring function is provided with the convolution operator. The experimental datasets are from a real grid company and contain four kinds of equipment. The experiments apply the proposed method to the equipment defects analysis, including the defect gradation, the coarse defect classification, and the fine defect classification. The proposed method is compared with some embedding methods. The experimental results verify that the proposed method outperforms the other methods for the real distribution network datasets, and the proposed method can analyze the defects effectively.

As COVID-19 hounds the world, the common cause of finding a swift solution to manage the pandemic has brought together researchers, institutions, governments, and society at large. The Internet of Things (IoT), Artificial Intelligence (AI) — including Machine Learning (ML) and Big Data analytics — as well as Robotics and Blockchain, are the four decisive areas of technological innovation that have been ingenuity harnessed to fight this pandemic and future ones. While these highly interrelated smart and connected health technologies cannot resolve the pandemic overnight and may not be the only answer to the crisis, they can provide greater insight into the disease and support frontline efforts to prevent and control the pandemic. This paper provides a blend of discussions on the contribution of these digital technologies, propose several complementary and multidisciplinary techniques to combat COVID-19, offer opportunities for more holistic studies, and accelerate knowledge acquisition and scientific discoveries in pandemic research. First, four areas where IoT can contribute are discussed, namely, i) tracking and tracing, ii) Remote Patient Monitoring (RPM) by Wearable IoT (WIoT), iii) Personal Digital Twins (PDT), and iv) real-life use case: ICT/IoT solution in Korea. Second, the role and novel applications of AI are explained, namely: i) diagnosis and prognosis, ii) risk prediction, iii) vaccine and drug development, iv) research dataset, v) early warnings and alerts, vi) social control and fake news detection, and vii) communication and chatbot. Third, the main uses of robotics and drone technology are analyzed, including i) crowd surveillance, ii) public announcements, iii) screening and diagnosis, and iv) essential supply delivery. Finally, we discuss how Distributed Ledger Technologies (DLTs), of which blockchain is a common example, can be combined with other technologies for tackling COVID-19.

Relation Extraction (RE) aims at harvesting relational facts from texts. A majority of existing research targets at knowledge acquisition from sentences, where subject-verb-object structures are usually treated as the signals of existence of relations. In contrast, relational facts expressed within noun phrases are highly implicit. Previous works mostly relies on human-compiled assertions and textual patterns in English to address noun phrase-based RE. For Chinese, the corresponding task is non-trivial because Chinese is a highly analytic language with flexible expressions. Additionally, noun phrases tend to be incomplete in grammatical structures, where clear mentions of predicates are often missing. In this article, we present an unsupervised Noun Phrase-based Open RE system for the Chinese language (NPORE), which employs a three-layer data-driven architecture. The system contains three components, i.e., Modifier-sensitive Phrase Segmenter, Candidate Relation Generator and Missing Relation Predicate Detector. It integrates with a graph clique mining algorithm to chunk Chinese noun phrases, considering how relations are expressed. We further propose a probabilistic method with knowledge priors and a hypergraph-based random walk process to detect missing relation predicates. Experiments over Chinese Wikipedia show NPORE outperforms state-of-the-art, capable of extracting 55.2 percent more relations than the most competitive baseline, with a comparable precision at 95.4 percent.

The objective of personalized learning is to design an effective knowledge acquisition track that matches the learner's strengths and bypasses her weaknesses to ultimately meet her desired goal. This concept emerged several years ago and is being adopted by a rapidly-growing number of educational institutions around the globe. In recent years, the boost of artificial intelligence (AI) and machine learning (ML), together with the advances in big data analysis, has unfolded novel perspectives to enhance personalized education in numerous dimensions. By taking advantage of AI/ML methods, the educational platform precisely acquires the student's characteristics. This is done, in part, by observing the past experiences as well as analyzing the available big data through exploring the learners' features and similarities. It can, for example, recommend the most appropriate content among numerous accessible ones, advise a well-designed long-term curriculum, connect appropriate learners by suggestion, accurate performance evaluation, and the like. Still, several aspects of AI-based personalized education remain unexplored. These include, among others, compensating for the adverse effects of the absence of peers, creating and maintaining motivations for learning, increasing diversity, removing the biases induced by the data and algorithms, and the like. In this paper, while providing a brief review of state-of-the-art research, we investigate the challenges of AI/ML-based personalized education and discuss potential solutions.

Contribution: This article presents the instruction of computer programming using adaptive learning activities considering students’ cognitive skills based on the learning theory of the Revised Bloom Taxonomy (RBT). To achieve this, the system converts students’ knowledge level to fuzzy weights, and using rule-based decision making, delivers adequate learning activities regarding their kind and complexity degree. Background: Tutoring through adaptive learning activities can be a powerful tool to support learners in practical courses, like computer programming. However, published results from pertinent literature are not oriented to the adaptivity of the domain knowledge in terms of the volume, kind, and complexity of the learning activities delivered to students. There is scope for a lot of improvement to this direction. Intended Outcomes: Combining learning theories with adaptive tutoring enhances student-centered learning, promotes student engagement, and improves knowledge acquisition. Application Design: An adaptive tutoring system was developed for supporting undergraduate students in the C# programming language course for an academic semester. The system delivers adaptive learning activities to students’ cognitive skills using the technology of fuzzy weights in a rule-based decision-making module and the learning theory of a RBT for designing the learning material. Findings: At the end of the academic semester, students’ data have been collected and a detailed evaluation was conducted. The results showed that the presented approach outperforms others which lack adaptivity in domain knowledge and learning theories, improving significantly the students’ learning outcomes.

The goal for a virtual reality (VR) training system is to enable trainees to acquire all the knowledge they need to perform effectively in a real environment. Such a system should provide an experience so authentic that no further real-world training is necessary, meaning that it is sufficient to train in VR. We evaluate the impact of a haptic thermal stimulus, which is of paramount importance to decision making, on trainees performance and knowledge acquisition. A thermal device was created to deliver the stimulus. As a proof of concept, a procedure from firefighter training is selected, in which sensing the temperature of a door with one's hand is essential. The sample consisted of 48 subjects divided among three experimental scenarios: one in which a virtual thermometer is used (visual stimulus), another in which the temperature is felt with the hand (thermal stimulus) and a third in which both methods are used (visual + thermal stimuli). For the performance evaluation, we measured the total time taken, the numbers of correctly executed procedures and identified neutral planes, the deviation from the target height, and the responses to a knowledge transfer questionnaire. Presence, cybersickness, and usability are measured to evaluate the impact of the haptic thermal stimulus. Considering the thermal stimulus condition as the baseline, we conclude that the significantly different results in the performance among the conditions indicate that the better performance in the visual-only condition is not representative of the real-life performance. Consequently, VR training applications need to deliver the correct stimuli for decision making.

The flexible combination of pervasive portable smart devices and omnipresent high-speed access infrastructures has revolutionized the data sensing and knowledge acquisition in mobile crowdsensing (MCS), underpinning fine-grained city management and highly customizable Internet service applications. However, MCS applications are still confronted with unsolved challenges, such as task assignment, privacy risks, and misbehavior detection. In light of this, this article proposes PETA, a privacy-preserving edge task assignment framework for MCS, leveraging the powerful edge servers deployed between users and the platform to cluster and manage users according to user attributes. Furthermore, group signature is employed by PETA to anonymize and verify user identities for privacy-preserving task assignments. The theoretical analysis and simulation results validate the performance of PETA on identity anonymity, malicious user detection, and task completion rate.

Extant systems engineering standards are so fragmented that the conceptualization of a cohesive body of knowledge is not easy. The discrepancies between different standards lead to misunderstanding and misinterpretation, making communication between stakeholders increasingly difficult. Moreover, these standards remain document centric, whereas systems engineering is transforming from paper-based to a model-based discipline. This requires the use of advanced information exchange schema and digital artifacts to enhance interoperability. Ontologies have been advocated as a mechanism to address these problems, as they can support the model-based transition and formalize the domain knowledge. However, manually creating ontologies is a time-consuming, error-prone, and tedious process. Little has been known about how to automate the development and little work has been conducted for building systems engineering ontologies. Therefore, in this article, we propose an ontology learning methodology to extract a systems engineering ontology from the extant standards. This methodology employs natural language processing techniques to carry out the lexical and morphological analyses on the standard documents. From the learning process, important terminologies, synonyms, concepts, and relations constructing the systems engineering body of knowledge are automatically recognized and classified. A formal and sophisticated system engineering ontology is achieved, which can be used to harmonize the extant standards, unify the languages, and improve the interoperability of the model-based systems engineering approach.

Process industries have the talent of emerging high levels of turbulent behaviors and uncertainties, such as the leakage of toxic substances and explosive materials. Resilience engineering, as a novel approach, can run the effects of such actions. Resilience engineering factors involve culture, change management, knowledge acquisition, risk assessment, readiness, plasticity, reportage, the obligation of a top manager, consciousness, safety procedures, incident survey, employee participation, and competence. The present study aims to investigate resilience engineering in process industries and analyze its efficiency using the data envelopment analysis (DEA) technique. Since there are high levels of uncertainty in the factors, Type-2 fuzzy sets that have a high capability of considering uncertainty is used to analyze the efficiency. The results of this work, which is the first case in evaluating the efficiency of resilience engineering in process industries by DEA and Type-2 fuzzy sets, indicate a robust approach for analyzing the efficiency and identifying the opportunities in process industries.

For offering proactive services to students in intelligent education, one of the fundamental tasks is predicting their performance (e.g., scores) on future exercises, where it is necessary to track each student's knowledge acquisition during her exercising activities. However, existing approaches can only exploit the exercising records of students, and the problem of extracting rich information existed in the exercise's materials (e.g., knowledge concepts, exercise content) to achieve both precise predictions of student performance and interpretable analysis of knowledge acquisition remains underexplored. In this paper, we present a holistic study of student performance prediction. To directly achieve the primary goal of prediction, we first propose a general Exercise-Enhanced Recurrent Neural Network (EERNN) framework by exploring both student's records and the exercise contents. In EERNN, we simply summarize each student's state into an integrated vector and trace it with a recurrent neural network, where we design a bidirectional LSTM to learn the encoding of each exercise's content. For making predictions, we propose two implementations under EERNN with different strategies, i.e., EERNNM with Markov property and EERNNA with Attention mechanism. Then, to explicitly track student's knowledge acquisition on multiple knowledge concepts, we extend EERNN to an explainable Exercise-aware Knowledge Tracing (EKT) by incorporating the knowledge concept effects, where the student's integrated state vector is extended to a knowledge state matrix. In EKT, we further develop a memory network for quantifying how much each exercise can affect the mastery of students on concepts during the exercising process. Finally, we conduct extensive experiments on large-scale real-world data. The results demonstrate the prediction effectiveness of two frameworks as well as the superior interpretability of EKT., Accepted by IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE)

Advancements in adaptive educational technologies, specifically the adaptive learning system, have made it possible to automatically optimize the sequencing of the pedagogical instructions according to the needs of individual learners. The crux of such systems lies in the instructional sequencing policy, which recommends personalized learning material based on the learning experiences of the learner to maximize their learning outcomes. However, limited available information such as cognitive, affective states, and competence levels of the learners ongoing knowledge points servers critical challenges to optimizing individual-specific pedagogical instructions in real-time. Moreover, making such decisions policy for every learner with a unique knowledge profile demands a trade-off between learner current knowledge and curiosity to learn next knowledge point. To address these challenges, this paper proposes a personalized adaptability knowledge extraction strategy (PAKES) using cognitive diagnosis and reinforcement learning (RL). We apply the general diagnostic model to track the current knowledge state of the learners. Subsequently, an RL-based Q-learning algorithm is employed to recommend optimal pedagogical instructions for individuals to meet their learning objectives while maintaining equilibrium among the learner-control and teaching trajectories. The results indicate that the learning analytics of the proposed framework can fairly deliver the optimal pedagogical paths for the learners based upon their learning profiles. A 62% learning progress score was achieved with the pedagogical paths recommended by the PAKES, showing a 20% improvement compared to the baseline model.

Online education is benefiting from advanced digital resources that now can offer interactive activities. Videos, animations, virtual and remote laboratories, and online games are just some examples of these activities. Educational standards and Virtual Learning Environments VLEs allow the integration of all these materials into learning objects that can be deployed in online courses or MOOCs. Virtual Laboratories provide an opportunity to train students and give to them the confidence for future interactions with real laboratory settings, with advantages such as: cost, portability, concurrency, and safety. Educational video games can improve the students’ knowledge acquisition and develop abilities such as: mental speed, reaction, connection between thoughts and movements and concentration. This paper shows the implementation of a virtual laboratory learning experience that includes the use of video games, multimedia content and virtual simulations. The objective of this resource is to help in the learning of wireless network planning problem and improve the students’ knowledge in the field of wireless networks key concepts. The virtual laboratory allows students to solve simple problems of antennas distribution and progressively increase the level by adding constraints and including new concepts in the design of the network.

Recently, ultrasound has been increasingly used in emergency departments (EDs) due to its promising noninvasive and portable characteristics. Traditional ultrasound training is a complex process that requires knowledge gain, development of psychomotor skills, and visual perception. However, it usually takes a long time for a novice sonographer to finish an ultrasound training program, and the training may target on limited applications. The e-learning, information, and communication technology on digital devices to support learning may overcome the limitations of the traditional ultrasound training. In this article, we design and implement a mobile e-learning platform for ultrasound training, namely MEUS, to address the abovementioned issues. The MEUS provides an interactive learning environment for teachers and learners. Teachers and learners can access MEUS and receive real-time feedback anywhere and anytime through a mobile device or desktop. We implement a multistage learning process. To evaluate the learning performance of using the platform, we add the MEUS platform as a part of the emergency ultrasound training course with the Post Graduate Year (PGY) program in the ED at the National Taiwan University Hospital. Our study shows that the MEUS platform can significantly increase the learning efficacy of the PGY students.

In this paper we describe an automated approach to enriching sentiment analysis with idiom–based features. Specifically, we automated the development of the supporting lexico–semantic resources, which include (1) a set of rules used to identify idioms in text and (2) their sentiment polarity classifications. Our method demonstrates how idiom dictionaries, which are readily available general pedagogical resources, can be adapted into purpose–specific computational resources automatically. These resources were then used to replace the manually engineered counterparts in an existing system, which originally outperformed the baseline sentiment analysis approaches by 17 percentage points on average, taking the F–measure from 40s into 60s. The new fully automated approach outperformed the baselines by 8 percentage points on average taking the F–measure from 40s into 50s. Although the latter improvement is not as high as the one achieved with the manually engineered features, it has got the advantage of being more general in a sense that it can readily utilize an arbitrary list of idioms without the knowledge acquisition overhead previously associated with this task, thereby fully automating the original approach.

The proposed Intelligent Medical Platform is a dialoguebased medical decision-making system that provides medical coaching and recommendation services, based on incremental learning methodology. The prototype demonstrates 90% accuracy for knowledge acquisition, 80% satisfaction level of user interaction with the system, and 95% accuracy for system integration with the legacy system.

To solve the problems of high time cost caused by the low efficiency of knowledge acquisition, this paper proposes a knowledge service framework based on case set. Three knowledge retrieval methods are designed based on parts keywords, customer orders and manufacturing processes. Additionally, a VSM-based (vetor space model) knowledge recommender method is proposed by using similarity matching algorithm to improve the efficiency of knowledge acquisition and transfer. Finally, application scenarios and evaluation of the proposed approach in a mechanical product design project are given to illustrate the application effect of knowledge service system.

The chemical terrorist attack is a type of unconventional terrorism that threatens the safety of cities. This kind of terrorist attack is highly concealed and difficult to be detected. Once the attack is successful, the consequences will be severe and the scope of impact will be enormous. Therefore, public security and emergency departments need to perform risk analysis and dynamic knowledge update to reduce risk or mitigate the effects of accidents. In order to quickly and effectively analyze the risk of chemical terrorist attacks, this article proposed a hybrid approach (B-R model) to analyze the risk of chemical terrorist attacks. First, a modular and customizable Bayesian network (BN) model library was built, which can satisfy users to select multi-dimensional risk factors. Based on the personalized BN, a risk knowledge graph (RKG) is constructed with multi-source data to realize the combination of risk analysis and knowledge acquisition. Then the threat degree of terrorist organizations, the strength of defensive forces, and the risk value of targets is calculated and displayed. The BN-RKG method provides data and theoretical support for defenders' resource allocation and emergency decision-making. Finally, a case study was conducted for a hypothetical scenario analysis. The result shows that the hybrid method can help with risk control and have the potential to support practical policymaking.

The use of recommendation systems has been extensively applied to different fields from the suggestion of multimedia content to other areas such as education. Thereof, the integration of affect-related information becomes a key factor to enhance the user experience and, when it comes to learning, it can be translated into the maximization of knowledge acquisition. The existence of affect-enhanced datasets is imperative when training a recommender learning system. This article introduces a new dataset gathered under realistic conditions, which includes affect-related information of 33 learners from different knowledge background interacting with an e-learning platform. Matrix factorization techniques were evaluated in order to prove the wealthiness of the dataset and to demonstrate that it could potentially replace the adaptation mechanism of the introduced platform and maximizing the learner's knowledge acquisition.

Smart manufacturing is targeted as the next generation of manufacturing by many national and international strategic development. The increasingly rich production data, the integration and extensive application of information technology, and the intelligent data processing and system modeling methods have collectively enabled smart manufacturing. Building upon them, manufacturing system modeling, knowledge acquisition, design, and real-time control are the key components [item 1) in the Appendix], [item 2) in the Appendix]. It is still one of the really huge challenges to gather data, transform them into information, and derive knowledge out of this information, especially given the requirement of knowledge that can be trusted as manufacturing systems may harm humans and the environment if they come to the wrong conclusion. Despite the learning and derivation of knowledge, it could be modeled beforehand and taken, for example, as an environmental model for online decisions like in deliberative agent-based systems. Nevertheless, for decisions during operation, real-time requirements, dependability, and security issues are to be guaranteed. Finally, for acceptance and trust, humans need to “understand” the reasons behind automated decisions; therefore, explainability or at least a white box description is an issue of such knowledge-based systems.

In recent years, e-learning systems such as massive open online courses (MOOC) have been widely employed in academic institutions and have shown its power in enhancing the students' learning ability. Automatic detection and classification of knowledge points in lecture video would significantly enhance the performance of the online learning platform. Most of the previously presented approach for knowledge discovery focused on the text and audio documents, whereas the identification of knowledge points in videos still remains a challenge. To bridge this gap, we proposed a novel convolutional neural network which was designed for the characteristics of lecture video. It could both extract the temporal-spatial and semantic information from the multimedia record. To evaluate the performance of the proposed technique, we conducted comparison experiments between the state-of-the-art methods and ours. The experimental results demonstrated that the presented approach outperformed the state-of-the-art techniques and could be potentially invaluable for the accurate discovery of knowledge points within videos.

To gain a comprehensive overview of new scientific findings with the enormous, ever-increasing amount of published information, we apply a new combinatorial approach that complements the process of reading scientific articles by supplementing artificial intelligence technologies. We present a combinatorial approach, which we illustrate in the form of a “double funnel of artificial intelligence.” Our approach suggests to largely increase the amount of data at the beginning of the data collection process and to subsequently clean and enrich the data set in order to gain much more knowledge at the end of the procedure compared to a “classical” literature review. We use natural language processing and text visualization techniques to uncover findings that are generally unbeknown to the human reader due to the inability to process very large amounts of text. By illustrating the individual steps using practical examples taken from use cases, we demonstrate the merits of our approach. With our methodology, we are able to reproduce findings from “regular” review papers; however, we discover additional and new findings in different fields, such as data science or medicine. We also point out the limitations of our approach. Finally, we make suggestions as to how the methodology could be further developed.

The Internet of Things has facilitated access to a large volume of sensitive information on each participating object in an ecosystem. This imposes many threats ranging from the risks of data management to the potential discrimination enabled by data analytics over delicate information such as locations, interests, and activities. To address these issues, the concept of trust is introduced as an important role in supporting both humans and services to overcome the perception of uncertainty and risks before making any decisions. However, establishing trust in a cyber world is a challenging task due to the volume of diversified influential factors from cyber-physical-systems. Hence, it is essential to have an intelligent trust computation model that is capable of generating accurate and intuitive trust values for prospective actors. Therefore, in this paper, a quantifiable trust assessment model is proposed. Built on this model, individual trust attributes are then calculated numerically. Moreover, a novel algorithm based on machine learning principles is devised to classify the extracted trust features and combine them to produce a final trust value to be used for decision making. Finally, our model's effectiveness is verified through a simulation. The results show that our method has advantages over other aggregation methods.

This paper introduces a method for automatic workflow extraction from texts using Process-Oriented Case-Based Reasoning (POCBR). While the current workflow management systems implement mostly different complicated graphical tasks based on advanced distributed solutions (e.g., cloud computing and grid computation), workflow knowledge acquisition from texts using case-based reasoning represents more expressive and semantic case representations. We propose in this context, an ontology-based workflow extraction framework to acquire processual knowledge from texts. Our methodology extends the classic NLP techniques to extract and disambiguate complex tasks and relations in texts. Using a graph-based representation of workflows and a domain ontology, our extraction process uses a context-aware approach to recognize workflow components in texts: data and control flows. We applied our framework in a technical domain in bioinformatics: i.e., phylogenetic analyses. An evaluation based on workflow semantic similarities in a gold standard proves that our approach provides promising results in the process extraction domain. Both data and implementation of our framework are available in: http://labo.bioinfo.uqam.ca/tgowler .

The exponential growth of the network elements and data traffic exchange in the last few years elevated the need of network providers for optimized and cost-efficient solutions regarding network management and monitorization. Solutions such as drive-tests (DTs) are becoming extremely expensive with the vast extension and complexity of nowadays mobile networks. Therefore, this paper provides a solution for optimized networkcontext knowledge acquisition, towards the self-organizing networks (SONs) concept. The presented framework incorporates an entire scheme for network Traces processing and positioning, based on network measurements and fingerprinting techniques. This framework enables a series of different use cases for network management and optimization, with real-time data processing capabilities within the network Traces collection interval (15 minutes), and achieving a median positioning error of 90 m.

If you want to be a professional developer, you’ll need to continuously invest substantial time to acquire highly specialized knowledge and develop diverse cognitive and interpersonal skills. A university can kindle your passion and provide incentives to expand your horizons, and your employer may support specialized training. But in the end, becoming a professional software developer is your decision and responsibility.

Autoencoder, which learns latent representations of samples in an unsupervised manner, has great potential in computer vision and signal processing. However, the diversity of samples makes learning a component autoencoder remaining a challenging task. This letter proposes a novel Self-Paced AutoEncoder (SPAE) for unsupervised feature extraction. The motivation behind this letter is to take samples gradually from simple to complex into consideration during training, which is similar to the mechanism of knowledge acquisition for humans. Under the unsupervised learning framework constructed on the autoencoder infrastructure, our SPAE first learns a weak autoencoder via samples with small losses and, then, elevates itself to a relatively strong autoencoder through samples with large losses. Then, the SPAE is generalized to a temporal domain, resulting to temporal SPAE (TSPAE), where the temporal information is explored and exploited to improve the performance. Typically, a TSPAE is capable of compressing temporal sequences into temporal-independent data. Experiments on the image classification and action recognition demonstrate the effectiveness of SPAE and TSPAE.

Creative cognitive systems are rarely assessed with the same tools as human creativity. In this paper, an approach is proposed for building cognitive systems which can solve human creativity tests. The importance of using cognitively viable processes, cognitive knowledge acquisition and organization, and cognitively comparable evaluation when implementing creative problem-solving systems is emphasized. Two case studies of artificial cognitive systems evaluated with human creativity tests are reviewed. A general approach is put forward. The applicability of this general approach to other creativity tests and artificial cognitive systems, together with ways of performing cognitive knowledge acquisition for these systems are then explored.

Data-driven knowledge acquisition is one of the key research fields in data mining. Dealing with large amounts of data has received a lot of attention in the field recently, and a number of methodologies have been proposed to extract insights from data in an automated or semi-automated manner. However, these methodologies generally target a specific aspect of the data mining process, such as data acquisition, data preprocessing, or data classification. However, a comprehensive knowledge acquisition method is crucial to support the end-to-end knowledge engineering process. In this paper, we introduce a knowledge acquisition system that covers all major phases of the cross-industry standard process for data mining. Acknowledging the importance of an end-to-end knowledge engineering process, we designed and developed an easy-to-use data-driven knowledge acquisition tool (DDKAT). The major features of the DDKAT are: (1) a novel unified features scoring approach for data selection; (2) a user-friendly data processing interface to improve the quality of the raw data; (3) an appropriate decision tree algorithm selection approach to build a classification model; and (4) the generation of production rules from various decision tree classification models in an automated manner. Furthermore, two diabetes studies were performed to assess the value of the DDKAT in terms of user experience. A total of 19 experts were involved in the first study and 102 students in the artificial intelligence domain were involved in the second study. The results showed that the overall user experience of the DDKAT was positive in terms of its attractiveness, as well as its pragmatic and hedonic quality factors.

In the past decade, advertising has rapidly become a major profit source for web-based businesses. One of the main challenges is the creation of effective and engaging ads that attract potential customers to product websites and eventual purchase. A promising solution is the combination of user preferences from the content provided on social media and the extraction of significant aspects discussed on review websites. The author proposes a three-phase model for content analysis on product review sites that considers in tandem the aspects discussed by users on review websites, the opinion polarities associated with such aspects, and user profiles on social networks, aiming to detect the most a#x201C;interestinga#x201D; aspects and use them to generate attractive messages. The effectiveness of the proposed approach has been validated in a real-world scenario by working with two Twitter seeds about domain-specific magazines and the data of their respective followers. Results demonstrate how the messages created by analyzing content (that is, product aspects and associated polarities) provided by a specific community improves the overall attractiveness of the generated advertisements.

Knowledge acquisition is an iterative process. Most previous work has focused on bootstrapping techniques based on syntactic patterns, that is, each iteration finds more syntactic patterns for subsequent extraction. However, syntactic bootstrapping is incapable of resolving the inherent ambiguities in the syntactic patterns. The precision of the extracted results is thus often poor. On the other hand, semantic bootstrapping bootstraps directly on knowledge rather than on syntactic patterns, that is, it uses existing knowledge to understand the text and acquire more knowledge. It has been shown that semantic bootstrapping can achieve superb precision while retaining good recall. Nonetheless, the working mechanism of semantic bootstrapping remains elusive. In this paper, we present a detailed analysis of semantic bootstrapping from a theoretical perspective. We show that the efficiency and effectiveness of semantic bootstrapping can be theoretically guaranteed. Our experimental evaluation results substantiate the theoretical analysis.

In the age of Web 2.0, community user contributed questions and answers provide an important alternative for knowledge acquisition through web search. Question retrieval in current community-based question answering (CQA) services do not, in general, work well for long and complex queries, such as the questions. The main reasons are the verboseness in natural language queries and the word mismatch between the queries and the candidate questions in the CQA archive during retrieval. To address these two problems, existing solutions try to refine the search queries by distinguishing the key concepts in the queries and expanding the queries with relevant content. However, using the existing query refinement approaches can only identify the key and non-key concepts, while the differences between the key concepts are overlooked. Moreover, the existing query expansion approaches, not only overlook the weights of key concepts in the queries, but also fail to consider concept level expansion for them. In this paper, we explore a key concept identification approach for query refinement and a pivot language translation based approach to explore key concept paraphrasing. We further propose a new question retrieval model which can seamlessly integrate the key concepts and their paraphrases. The experimental results demonstrate that the integrated retrieval model significantly outperforms the state-of-the-art models in question retrieval.

Self-organizing network (SON) mechanisms reduce operational expenditure in cellular networks while enhancing the offered quality of service. Within a SON, self-healing aims to autonomously solve problems in the radio access network and to minimize their impact on the user. Self-healing comprises automatic fault detection, root cause analysis, fault compensation, and recovery. This paper presents a root cause analysis system based on fuzzy logic. A genetic algorithm is proposed for learning the rule base. The proposed method is adapted to the way of reasoning of troubleshooting experts, which ease knowledge acquisition and system output interpretation. Results show that the obtained results are comparable or even better than those obtained when the troubleshooting experts define the rules, with the clear benefit of not requiring the experts to define the system. In addition, the system is robust, since fine tuning of its parameters is not mandatory.

Virtual environments can contribute to the effective learning of various subjects for people of all ages. Consequently, they assist in reducing the cost of maintaining physical structures of teaching, such as laboratories and classrooms. However, the measurement of how learners acquire knowledge in such environments is still incipient in the literature. This article presents a method to evaluate the knowledge acquisition in 3D virtual learning environments (3D VLEs) by using the learner's interactions in the VLE. Three experiments were conducted that demonstrate the viability of using this method and its computational implementation. The results suggest that it is possible to automatically assess learning in predetermined contexts and that some types of user interactions in 3D VLEs are correlated with the user's learning differential.

Taxonomy learning is an important task for knowledge acquisition, sharing, and classification as well as application development and utilization in various domains. To reduce human effort to build a taxonomy from scratch and improve the quality of the learned taxonomy, we propose a new taxonomy learning approach, named TaxoFinder . TaxoFinder takes three steps to automatically build a taxonomy. First, it identifies domain-specific concepts from a domain text corpus. Second, it builds a graph representing how such concepts are associated together based on their co-occurrences. As the key method in TaxoFinder, we propose a method for measuring associative strengths among the concepts, which quantify how strongly they are associated in the graph, using similarities between sentences and spatial distances between sentences. Lastly, TaxoFinder induces a taxonomy from the graph using a graph analytic algorithm. TaxoFinder aims to build a taxonomy in such a way that it maximizes the overall associative strengths among the concepts in the graph to build a taxonomy. We evaluate TaxoFinder using gold-standard evaluation on three different domains: emergency management for mass gatherings , autism research , and disease domains. In our evaluation, we compare TaxoFinder with a state-of-the-art subsumption method and show that TaxoFinder is an effective approach significantly outperforming the subsumption method.

The various responsibilities in intelligent systems design--responsibilities to acquire certain knowledge and skills--suggest strongly that effective interaction design is inherently interdisciplinary. As a consequence, gaps in knowledge acquisition and creativity on the part of design teams are bound to emerge as long as responsibilities are abrogated because they are tied to roles (such as cognitive systems engineers versus systems engineers). Communication, collaboration, and knowledge sharing are essential components of success, and a language that cuts across discipline-specific jargon is likely to make the development effort much more effective. This essay describes similarities between two related approaches to interaction design that resonate with each other and share principles: ecological interface design and human-centered computing. These similarities are emphasized by noting similarities between two different interfaces for computer network defense that were independently developed from each approach.

This paper proposes artificial neural network and fuzzy system-based extreme learning machines (ELM) for offline and online modeling of U-tube steam generators (UTSG). Water level of UTSG systems is predicted in a one-step-ahead fashion using nonlinear autoregressive with exogenous input (NARX) topology. Modeling data are generated using a well-known and widely accepted dynamic model reported in the literature. Model performances are analyzed with different number of neurons for the neural network and with different number of rules for the fuzzy system. UTSG models are built at different reactor power levels as well as full range that corresponds to all reactor operating powers. A quantitative comparison of the models are made using the root-mean-squared error (RMSE) and the minimum-descriptive-length (MDL) criteria. Furthermore, conventional back propagation learning-based neural and fuzzy models are also designed for comparing ELMs to classical artificial models. The advantages and disadvantages of the designed models are discussed. © 1963-2012 IEEE.

Virtual communities have become ubiquitous and vital in nearly all professions. These communities typically involve voluntary participation, and given that these communities are not organization specific, community members’ motivations for participation vary. In this study, we investigate the motivations of the members of a professional virtual community to engage in knowledge exchange. We synthesize social exchange theory and the theory of reasoned action to identify critical determinants of attitudes toward knowledge exchange in virtual communities, namely, trust among participants, anticipated reciprocal relationships, and the relevance of the community to participants’ jobs. Additionally, we posit that attitudes will influence the intention to use the virtual community and that this relationship will be moderated by the perceived quality of the information exchanged within the community. We test our research model using data compiled from a community of research scientists in South Korea. Our findings indicate that trust among participants has a positive influence on attitudes toward both sharing and acquiring knowledge. The anticipation of a reciprocal relationship has a positive effect on attitudes toward knowledge acquisition, and job relevance has a positive effect on attitudes toward knowledge sharing. Furthermore, attitudes toward knowledge acquisition affect attitudes toward knowledge sharing, and attitudes toward knowledge sharing positively influence intentions to use a virtual community. We also find that perceived information quality negatively moderates the relationship between attitudes toward knowledge sharing and user intentions to use a virtual community. We interpret and discuss these findings, and their implications for research and practice.

We present a robot cognitive framework based on (a) a memory-like architecture; and (b) the notion of “context”. We posit that relying solely on machine learning techniques may not be the right approach for a long-term, continuous knowledge acquisition. Since we are interested in long-term human-robot interaction, we focus on a scenario where a robot “remembers” relevant events happening in the environment. By visually sensing its surroundings, the robot is expected to infer and remember snapshots of events, and recall specific past events based on inputs and contextual information from humans. Using a COTS vision frameworks for the experiment, we show that the robot is able to form “memories” and recall related events based on cues and the context given during the human-robot interaction process.

Discovering hyponym relations among domain-specific terms is a fundamental task in taxonomy learning and knowledge acquisition. However, the great diversity of various domain corpora and the lack of labeled training sets make this task very challenging for conventional methods that are based on text content. The hyperlink structure of Wikipedia article pages was found to contain recurring network motifs in this study, indicating the probability of a hyperlink being a hyponym hyperlink. Hence, a novel hyponym relation extraction approach based on the network motifs of Wikipedia hyperlinks was proposed. This approach automatically constructs motif-based features from the hyperlink structure of a domain; every hyperlink is mapped to a 13-dimensional feature vector based on the 13 types of three-node motifs. The approach extracts structural information from Wikipedia and heuristically creates a labeled training set. Classification models were determined from the training sets for hyponym relation extraction. Two experiments were conducted to validate our approach based on seven domain-specific datasets obtained from Wikipedia. The first experiment, which utilized manually labeled data, verified the effectiveness of the motif-based features. The second experiment, which utilized an automatically labeled training set of different domains, showed that the proposed approach performs better than the approach based on lexico-syntactic patterns and achieves comparable result to the approach based on textual features. Experimental results show the practicability and fairly good domain scalability of the proposed approach.

This paper describes the construction and evaluation of a self-help skill training system for assisting student nurses in learning skills involving the transfer of patients from beds to wheelchairs. We have proposed a feedback method that is based on a checklist and video demonstrations. To help trainees efficiently check their performance and correct errors, the checklist was prepared with items specific to the performance of tasks related to individual body parts (e.g., the height of the waist). In this system, two Kinect RGB-D sensors were used for measuring the posture of the trainees and patients. An automatic skill evaluation method was used to designate the trainees’ performance against each evaluation item as correct or incorrect. Furthermore, the system's operation interface was designed to enable self-operation by trainees. Control tests were performed to measure the training effectiveness of the system. The results of the tests on a control group (n = 5) that used only a textbook and demonstration video but did not receive feedback were compared with those of the experimental group (n = 5) that used the proposed system. The results of both subjective and objective evaluation demonstrated that the experimental group showed greater improvement in performing patient transfer than the control group $(p .

This work proposes the use of bio-inspired knowledge acquisition for Fuzzy Systems founded on Swarm Intelligence-Particle Swarm Optimization (SI-PSO). Swarm-based models consider knowledge entities as particles that move in the space to reach the higher quality. Fuzzy Systems following SI-PSO for knowledge acquisition are categorized in this work as Swarm Fuzzy Systems (SFSs). Specifically, two learning methodologies, KASIA (using rule bases as particles in PSO) and KARP (using rules as particles in PSO) are introduced. SFSs performance is studied in a problem of practical importance nowadays with data sets, the learning of fuzzy meta-schedulers in computational grids. Fuzzy meta-schedulers are Fuzzy Systems doing intelligent allocation of jobs to improve the performance of the grid, such as the reduction of the execution time of workload. The scheduling decisions are taken based on the knowledge of the Fuzzy System and in this way, the relevance of their learning process are critical. In this work, compared results of the performance of the different SFSs and a comparison between SFSs and Genetic Fuzzy Systems are presented. Simulations results show that SFSs can achieve a faster convergence and higher quality with a reduced number of control parameters what makes them a good alternative to Genetic Fuzzy Systems.

Numerous consumer reviews of products are now available on the Internet. Consumer reviews contain rich and valuable knowledge for both firms and users. However, the reviews are often disorganized, leading to difficulties in information navigation and knowledge acquisition. This article proposes a product aspect ranking framework, which automatically identifies the important aspects of products from online consumer reviews, aiming at improving the usability of the numerous reviews. The important product aspects are identified based on two observations: 1) the important aspects are usually commented on by a large number of consumers and 2) consumer opinions on the important aspects greatly influence their overall opinions on the product. In particular, given the consumer reviews of a product, we first identify product aspects by a shallow dependency parser and determine consumer opinions on these aspects via a sentiment classifier. We then develop a probabilistic aspect ranking algorithm to infer the importance of aspects by simultaneously considering aspect frequency and the influence of consumer opinions given to each aspect over their overall opinions. The experimental results on a review corpus of 21 popular products in eight domains demonstrate the effectiveness of the proposed approach. Moreover, we apply product aspect ranking to two real-world applications, i.e., document-level sentiment classification and extractive review summarization, and achieve significant performance improvements, which demonstrate the capacity of product aspect ranking in facilitating real-world applications.

Educational software systems have an increasingly significant presence in engineering sciences. They aim to improve students' attitudes and knowledge acquisition typically through visual representation and simulation of complex algorithms and mechanisms or hardware systems that are often not available to the educational institutions. This paper presents a novel software system for CryptOgraphic ALgorithm visuAl representation (COALA), which was developed to support a Data Security course at the School of Electrical Engineering, University of Belgrade. The system allows users to follow the execution of several complex algorithms (DES, AES, RSA, and Diffie-Hellman) on real world examples in a step by step detailed view with the possibility of forward and backward navigation. Benefits of the COALA system for students are observed through the increase of the percentage of students who passed the exam and the average grade on the exams during one school year.

Given a collection of web images with the corresponding textual descriptions, in this paper, we propose a novel cross-domain learning method to classify these web multimedia objects by transferring the correlation knowledge among different information sources. Here, the knowledge is extracted from unlabeled objects through unsupervised learning and applied to perform supervised classification tasks. To mine more meaningful correlation knowledge, instead of using commonly used visual words in the traditional bag-of-visual-words (BoW) model, we discover higher level visual components (words and phrases) to incorporate the spatial and semantic information into our image representation model, i.e., bag-of-visual-phrases (BoP). By combining the enriched visual components with the textual words, we calculate the frequently co-occurring pairs among them to construct a cross-domain correlated graph in which the correlation knowledge is mined. After that, we investigate two different strategies to apply such knowledge to enrich the feature space where the supervised classification is performed. By transferring such knowledge, our cross-domain transfer learning method can not only handle large scale web multimedia objects, but also deal with the situation that the textual descriptions of a small portion of web images are missing. Empirical experiments on two different datasets of web multimedia objects are conducted to demonstrate the efficacy and effectiveness of our proposed cross-domain transfer learning method.

Enabling Subject Matter Experts (SMEs) to formulate knowledge without the intervention of Knowledge Engineers (KEs) requires providing SMEs with methods and tools that abstract the underlying knowledge representation and allow them to focus on modeling activities. Bridging the gap between SME-authored models and their representation is challenging, especially in the case of complex knowledge types like processes, where aspects like frame management, data, and control flow need to be addressed. In this paper, we describe how SME-authored process models can be provided with an operational semantics and grounded in a knowledge representation language like F-logic to support process-related reasoning. The main results of this work include a formalism for process representation and a mechanism for automatically translating process diagrams into executable code following such formalism. From all the process models authored by SMEs during evaluation 82 percent were well formed, all of which executed correctly. Additionally, the two optimizations applied to the code generation mechanism produced a performance improvement at reasoning time of 25 and 30 percent with respect to the base case, respectively.

The two most important issues of expert systems are the acquisition of domain experts' professional knowledge and the representation and reasoning of the knowledge rules that have been identified. First, during expert knowledge acquisition processes, the domain expert panel often demonstrates different experience and knowledge from one another and produces different types of knowledge information such as complete and incomplete, precise and imprecise, and known and unknown because of its cross-functional and multidisciplinary nature. Second, as a promising tool for knowledge representation and reasoning, fuzzy Petri nets (FPNs) still suffer a couple of deficiencies. The parameters in current FPN models could not accurately represent the increasingly complex knowledge-based systems, and the rules in most existing knowledge inference frameworks could not be dynamically adjustable according to propositions' variation as human cognition and thinking. In this paper, we present a knowledge acquisition and representation approach using the fuzzy evidential reasoning approach and dynamic adaptive FPNs to solve the problems mentioned above. As is illustrated by the numerical example, the proposed approach can well capture experts' diversity experience, enhance the knowledge representation power, and reason the rule-based knowledge more intelligently.

Data-intensive science is a scientific discovery process that is driven by knowledge extracted from large volumes of data rather than the traditional hypothesis driven discovery process. One of the key challenges in data-intensive science is development of enabling technologies to allow researchers to effectively utilize these large volumes of data in an effective manner. This paper introduces the concept of “data prospecting” to address the challenges of data intensive science. With data prospecting, we extend the familiar metaphor of data mining to describe an initial phase of data exploration used to determine promising areas for deeper analysis. Data prospecting enhances data selection through the use of interactive discovery engines. Interactive exploration enables a researcher to filter the data based on the “first look” analytics, discover interesting and previously unknown patterns to start new science investigations, verify the quality of the data, and corroborate whether patterns in the data match existing science theories or mental models. This paper describes our initial evaluation of the value of“data prospecting” to Earth Science researchers as part of their research process. The paper describes our discovery engine prototype to support data prospecting for specific data products along with its current limitations. Example science investigations from three different researchers using our prototype discovery engine to explore the Special Sensor Microwave/Imager and Sounder (SSM/I, SSMIS) data products are also presented.