Search

In corpus-based interpreting studies, typical challenges exist in the time-consuming and labour-intensive nature of transcribing spoken data and in identifying prosodic properties. This paper addresses these challenges by exploring methods for the automatic compilation of multimodal interpreting corpora, with a focus on English/Chinese Consecutive Interpreting. The results show that: 1) automatic transcription can achieve an accuracy rate of 95.3% in transcribing consecutive interpretations; 2) prosodic properties related to filled pauses, unfilled pauses, articulation rate, and mispronounced words can be automatically extracted using our rule-based programming; 3) mispronounced words can be effectively identified by employing Confidence Measure, with any word having a Confidence Measure lower than 0.321 considered as mispronounced; 4) automatic alignment can be achieved through the utilisation of automatic segmentation, sentence embedding, and alignment techniques. This study contributes to interpreting studies by broadening the empirical understanding of orality, enabling multimodal analyses of interpreting products, and providing a new methodological solution for the construction and utilisation of multimodal interpreting corpora. It also has implications in exploring applicability of new technologies in interpreting studies. [ABSTRACT FROM AUTHOR]

Expert knowledge is the key to modeling milling fault detection systems based on the belief rule base. The construction of an initial expert knowledge base seriously affects the accuracy and interpretability of the milling fault detection model. However, due to the complexity of the milling system structure and the uncertainty of the milling failure index, it is often impossible to construct model expert knowledge effectively. Therefore, a milling system fault detection method based on fault tree analysis and hierarchical BRB (FTBRB) is proposed. Firstly, the proposed method uses a fault tree and hierarchical BRB modeling. Through fault tree analysis (FTA), the logical correspondence between FTA and BRB is sorted out. This can effectively embed the FTA mechanism into the BRB expert knowledge base. The hierarchical BRB model is used to solve the problem of excessive indexes and avoid combinatorial explosion. Secondly, evidence reasoning (ER) is used to ensure the transparency of the model reasoning process. Thirdly, the projection covariance matrix adaptation evolutionary strategies (P-CMA-ES) is used to optimize the model. Finally, this paper verifies the validity model and the method's feasibility techniques for milling data sets. [ABSTRACT FROM AUTHOR]

We propose Information Lattice Learning (ILL) as a general framework to learn rules of a signal (e.g., an image or a probability distribution). In our definition, a rule is a coarsened signal used to help us gain one interpretable insight about the original signal. To make full sense of what might govern the signal's intrinsic structure, we seek multiple disentangled rules arranged in a hierarchy, called a lattice. Compared to representation/rule-learning models optimized for a specific task (e.g., classification), ILL focuses on explainability: it is designed to mimic human experiential learning and discover rules akin to those humans can distill and comprehend. This paper details the math and algorithms of ILL, and illustrates how it addresses the fundamental question "what makes X an X" by creating rule-based explanations designed to help humans understand. Our focus is on explaining X rather than (re)generating it. We present applications in knowledge discovery, using ILL to distill music theory from scores and chemical laws from molecules and further revealing connections between them. We show ILL's efficacy and interpretability on benchmarks and assessments, as well as a demonstration of ILL-enhanced classifiers achieving human-level digit recognition using only one or a few MNIST training examples (1-10 per class). [ABSTRACT FROM AUTHOR]

The variety and difference between domains for textual data require customization in the Natural Language Processing component especially in Named Entity Recognition where different domains contain several types of entities. The current NER model is deemed not fit to accurately extract entities from Quranic text due to its unique content. This paper describes the building of a rule-based Named Entity Recognition method to extract the entities that exist in the English translation to the meaning of the Quranic text and its performance evaluation. Named entity tagging, a common task in-text annotation, in which entities (nouns) in the unstructured text are identified and assigned a class. A few rules are built to extract several types of entities such as the name of prophets and people, creation, location, time, and the various names of God. The rules are built mainly using regular expressions and gazetteers. The rules that have been built result in high precision and recall as well as a satisfactory F-score of over 90%. The results from this experiment can be used as annotation in building a machine learning model to extract entities from the same type of domain specifically on the Quranic text or generally in the Islamic domain text. [ABSTRACT FROM AUTHOR]

In learning biologically inspired design (BID), the mapping process from problem to biological inspirations is crucial for generating novel ideas. This study determines the effects of knowledge representations related to design problems and inspirations on students' novelty of ideas generated in BID. Forty-four industrial design undergraduates were divided into four groups in four BID workshops. In each workshop, the design problem was represented in rule- and case-based formats while 220 biocards (inspirations were in concrete and abstract formats. Each group took turns to create ideas using one of four knowledge representation combinations of rule- or case-based design problems with concrete or abstract inspirations in each workshop and completed all of them throughout the workshops. Results showed that both ideas generated using the rule-based design problem with the concrete inspiration and the case-based design problem with the abstract inspiration had higher mean novelty scores than others. That implies that exclusively using highly structured representation in learning BID is not conducive to generating creative ideas. Accordingly, this study proposes a dual-track process for helping students achieve better innovation by balancing abstraction of knowledge representation in problem-solving. [ABSTRACT FROM AUTHOR]

Large-scale power-to‑hydrogen (P2H) stations with multi-stack configurations, are emerging as valuable flexible resources for the power grid. The energy management strategy (EMS) determines multi-stack operation statuses. Nonetheless, existing EMS focus on production without adequately addressing the implications for grid-side power factor (PF) and potential security concerns. This paper addresses this limitation by presenting a model that characterizes the PF of a multi-stack P2H system across varying operation statuses defined by current and temperature. Through this model, we highlight a clear trade-off between the PF constraint and production targets in multi-stack scheduling. Subsequently, we introduce an improved EMS framework for multi-stack P2H that seeks a balance between PF, production, and security. This EMS is organized as a two-layer execution structure to guarantee control accuracy and tractability, which includes a model-based robust multi-stack scheduling programming and a rule-based real-time increment correction algorithm in series. Case studies compare multi-stack scheduling strategies under the proposed EMS with the traditional production-oriented strategy. The effectiveness of the extended PF and security dimensions is verified to comprehensively improve the responsiveness to power instructions. Furthermore, we outline five representative cluster-level scheduling strategies aligned with different load scenarios, offering insights for practical industrial implementations. • A general framework of energy management strategy for large-scale power-to-hydrogen (P2H) stations. • The tradeoff between the power factor constraint and the production target in determining multi-stack scheduling strategies. • A two-layer EMS is executed by a model-based hour-ahead robust scheduling and a rule-based real-time increment correction. • Outlining five cluster-level scheduling strategies aligned with various load scenarios of multi-stack P2H stations. [ABSTRACT FROM AUTHOR]

Hybrid green energy system, consisting of photovoltaic (PV), fuel cell and battery, receives wide attention because of its autonomy, flexibility and promising potential in accelerating the development of carbon neutrality in the field of power generation. However, the efficient power dispatching of the hybrid energy system is challenging due to the inevitable uncertainties of the solar energy. To this end, stochastic dynamic programming (SDP) is used in this paper to find the optimal solution to minimize the total fuel consumption during a 72-hour operating cycle, with constraints on the magnitude and rate of the fuel cell and battery operation, in which the stochastic characteristics of the solar power are described by Markov chain. The influence of sampling time and number of states on the solar prediction accuracy is discussed. For comparison, the traditional rule-based algorithm and dynamic programming (DP) algorithms are also utilized to describe and solve the power distribution problem, corresponding to different decision results in terms of how to distribute the energy flow for each time period. Numerical optimization results within the 72-hour period demonstrate that, the SDP has a 20.61% economy and 66.34% battery SOC improvement than that of rule-based algorithm, and in most uncertain cases, the SDP produces superior economic performance than those of both the rule-based algorithm and DP, benefited from the inclusion of the solar power probabilities into the optimization framework. The results of this paper lay a solid foundation for the efficient energy management of the hydrogen and solar hybrid energy system. The stochastic dynamic programming is used in this paper to deal with the uncertainties in solar energy and find the optimal energy scheduling of a hybrid fuel cell/PV/battery system. Numerical optimization results demonstrate that, in most uncertain cases, stochastic dynamic programming produces superior economic performance than those of both the rule-based and dynamic programming algorithm. The results lay a solid foundation for the efficient energy management of the hydrogen and solar hybrid energy system. [Display omitted] [ABSTRACT FROM AUTHOR]

The authors present an automated, rule-based system for converting piano compositions into paintings. Using a color-note association scale presented by Edward Maryon in 1919, which correlates a 12-tone scale with 12 hues of the color circle, the authors present a simple approach for extracting colors associated with each note played in a piano composition. The authors also describe the color extraction and art generation process in detail, as well as the process for creating "moving art," which imitates the progression of a musical piece in real time. They share and discuss artworks generated for four well-known piano compositions. [ABSTRACT FROM AUTHOR]

Background: Adverse drug reactions (ADRs) are estimated to be the fifth cause of hospital death. Up to 50% are potentially preventable and a significant number are recurrent (reADRs). Clinical decision support systems have been used to prevent reADRs using structured reporting concerning the patient's ADR experience, which in current clinical practice is poorly performed. Identifying ADRs directly from free text in electronic health records (EHRs) could circumvent this. Aim: To develop strategies to identify ADRs from free‐text notes in electronic hospital health records. Methods: In stage I, the EHRs of 10 patients were reviewed to establish strategies for identifying ADRs. In stage II, complete EHR histories of 45 patients were reviewed for ADRs and compared to the strategies programmed into a rule‐based model. ADRs were classified using MedDRA and included in the study if the Naranjo causality score was ≥1. Seriousness was assessed using the European Medicine Agency's important medical event list. Results: In stage I, two main search strategies were identified: keywords indicating an ADR and specific prepositions followed by medication names. In stage II, the EHRs contained a median of 7.4 (range 0.01‐18) years of medical history covering over 35 000 notes. A total of 318 unique ADRs were identified of which 63 were potentially serious and 179 (sensitivity 57%) were identified by the rule. The method falsely identified 377 ADRs (positive predictive value 32%). However, it also identified an additional eight ADRs. Conclusion: Two key strategies were developed to identify ADRs from hospital EHRs using free‐text notes. The results appear promising and warrant further study. [ABSTRACT FROM AUTHOR]

Considerable research has demonstrated how effective requirements engineering is critical for the success of software projects. Requirements engineering has been established and recognized as one of the most important aspects of software engineering as of late. It is noteworthy to mention that requirement consistency is a critical factor in project success, and conflicts in requirements lead to waste of cost, time, and effort. A considerable number of research studies have shown the risks and problems caused by working with requirements that are in conflict with other requirements. These risks include running overtime or over budget, which may lead to project failure. At the very least, it would result in the extra expended effort. Various studies have also stated that failure in managing requirement conflicts is one of the main reasons for unsuccessful software projects due to high cost and insufficient time. Many prior research studies have proposed manual techniques to detect conflicts, whereas other research recommends automated approaches based on human analysis. Moreover, there are different resolutions for conflicting requirements. Our previous work proposed a scheme for dealing with this problem using a novel intelligent method to detect conflicts and resolve them. A rule-based system was proposed to identify conflicts in requirements, and a genetic algorithm (GA) was used to resolve conflicts. The objective of this work is to assess and evaluate the implementation of the method of minimizing the number of conflicts in the requirements. The methodology implemented comprises two different stages. The first stage, detecting conflicts using a rule-based system, demonstrated a correct result with 100% accuracy. The evaluation of using the GA to resolve and reduce conflicts in the second stage also displayed a good result and achieved the desired goal as well as the main objective of the research. [ABSTRACT FROM AUTHOR]

Along with the rapidly growing scale of relational database (RDB), how to construct domain-related ontologies from various databases effectively and efficiently has been a bottleneck of the ontology-based integration. The traditional methods for constructing ontology from RDB are mainly based on the manual mapping and transformation, which not only requires a lot of human experience but also easily leads to the semantic loss during the transformation. Ontology learning from RDB is a new paradigm to (semi-)automatically construct ontologies from RDB by borrowing the techniques of machine learning, it provides potential opportunities for integrating heterogeneous data from various data sources efficiently. This paper surveys the recent methods and tools of the ontology learning from RDB, and highlights the potential opportunities and challenges of using ontology learning in semantic information integration. Initially, the previous surveys on the topic of the ontology-based integration and ontology learning were summarized, and then the limitations of previous surveys were identified and analyzed. Furthermore, the methods and techniques of ontology learning from RDB were investigated by classifying into three categories: reverse engineering, mapping, and machine learning. Accordingly, the opportunities and possibility of using ontology learning from RDB in semantic information integration were discussed based on the mapping results between the bottlenecks of ontology-based integration and the features of ontology learning. a This paper is an extension of our prior work [C. Ma and B. Molnár, Use of ontology learning in information system integration: A literature survey, in Intelligent Information and Database Systems, eds. P. Sitek, M. Pietranik, M. Krótkiewicz and C. Srinilta, Communications in Computer and Information Science, Vol. 1178 (Springer, Singapore, 2020), pp. 342–353] [ABSTRACT FROM AUTHOR]

Hyper-Parameter Optimization (HPO) occupies a fundamental role in Deep Learning systems due to the number of hyper-parameters (HPs) to be set. The state-of-the-art of HPO methods are Grid Search, Random Search and Bayesian Optimization. The first two methods try all possible combinations and random combination of the HPs values, respectively. This is performed in a blind manner, without any information for choosing the new set of HPs values. Bayesian Optimization (BO), instead, keeps track of past results and uses them to build a probabilistic model mapping HPs into a probability density of the objective function. Bayesian Optimization builds a surrogate probabilistic model of the objective function, finds the HPs values that perform best on the surrogate model and updates it with new results. In this paper, we improve BO applied to Deep Neural Network (DNN) by adding an analysis of the results of the network on training and validation sets. This analysis is performed by exploiting rule-based programming, and in particular by using Probabilistic Logic Programming. The resulting system, called Symbolic DNN-Tuner, logically evaluates the results obtained from the training and the validation phase and, by applying symbolic tuning rules, fixes the network architecture, and its HPs, therefore improving performance. We also show the effectiveness of the proposed approach, by an experimental evaluation on literature and real-life datasets. [ABSTRACT FROM AUTHOR]

Making autonomous driving a safe, feasible, and better alternative is one of the core problems the world is facing today. The horizon of the applications of AI and deep learning has changed the perspective of the human mind. Initially, what used to be thought of as the subtle impossible task is applicable today, and that too in the feasibly efficient way. Computer vision tasks powered with highly tuned CNNs are outperforming humans in many fields. Introductory implementations of the autonomous vehicle were merely achieved using raw image processing, and hard programmed rule-based logic systems along with machine/deep learning were used as secondary objective handlers. With the autonomous driving method proposed by Nvidia, the usability of CNNs is more adequate, adaptable, and applicable. In this paper, we propose the ensemble implementation of CNN-based regression models for autonomous driving. We have taken simulator generated driving view image dataset along with a mapped file of steering angle in radians. After applying image pre-processing and augmentation, we have used two CNN models along with their ensemble and compared their performance to minimize the risks of unsafe driving. We have compared Nvidia proposed CNN, MobileNet-V2 as regression model and Ensemble-M results for comparison of their respective performance, MSE scores and compute time to process. In result analysis, the MobileNet-V2 model performs better in densely featured roads and the Nvidia model performs better in sparsely featured roads, whereas Ensemble-M normalizes the performance of both models and efficiently results in the least MSE score (0.0201) with the highest computation time utilization making autonomous driving better, safer alternative. [ABSTRACT FROM AUTHOR]

The spread of the Internet of Things (IoT) is demanding new, powerful architectures for handling the huge amounts of data produced by the IoT devices. In many scenarios, many existing isolated solutions applied to IoT devices use a set of rules to detect, report and mitigate malware activities or threats. This paper describes a development environment that allows the programming and debugging of such rule-based multi-agent solutions. The solution consists of the integration of a rule engine into the agent, the use of a specialized, wrapping agent class with a graphical user interface for programming and testing purposes, and a mechanism for the incremental composition of behaviors. Finally, a set of examples and a comparative study were accomplished to test the suitability and validity of the approach. The JADE multi-agent middleware has been used for the practical implementation of the approach. [ABSTRACT FROM AUTHOR]

Mobile Multimodal Interaction aims at exploiting complementary aspects of human communication capacities and new mobile sensors. Recently, most mobile applications are limited to a basic interaction modality, namely touchscreen, which is subject to restricted interaction under certain situations. In this paper, we present On-the-Fly Interaction Editor (OFIE), an application that allows mobile end-users to define and integrate sensor-based unimodal and multimodal input interactions in their already installed applications according to their contexts. OFIE is based on the Event-Condition-Action rules and Programming By Demonstration approach that allows end-users to demonstrate their expected action simply by performing it on the application's interface. We evaluated OFIE through a controlled user study. Our evaluation involves 15 participants distributed on 4 groups based on their programming experience. Each participant was invited to integrate six input interactions (three multimodal inputs). The initial results show that end-users are able to successfully integrate sensor-based input interactions using OFIE. [ABSTRACT FROM AUTHOR]

Reducing energy consumption is a key focus for hybrid electric vehicle (HEV) development. The popular vehicle dynamic model used in many energy management optimization studies does not capture the vehicle dynamics that the in-vehicle measurement system does. However, feedback from the measurement system is what the vehicle controller actually uses to manage energy consumption. Therefore, the optimization solely using the model does not represent what the vehicle controller sees in the vehicle. This paper reports the utility factor-weighted energy consumption using a rule-based strategy under a real-world representative drive cycle. In addition, the vehicle test data was used to perform the optimization approach. By comparing results from both rule-based and optimization-based strategies, the areas for further improving rule-based strategy are discussed. Furthermore, recent development of OBD raises a concern about the increase of energy consumption. This paper investigates the energy consumption increase with extensive OBD usage. [ABSTRACT FROM AUTHOR]

The study aimed to identify the effectiveness of a proposed program in teaching the” Holy Quran recitation rules” based on the functional entrance to develop some skills of Holy Quran recitation Rules for first prep. students, and the sample of the study includes ninety students both males and females who were divided into two groups, a control group and the experimental group by forty five students per each, and the sample of the study was from Mankateen preparatory school joint management samalout education, administration which is under Al-Minia directorate for Education, and the study tools and educational materials were a test in recitation rules for first prep. students, and a suggested programme for recitation rules based on the functional entrance, the teacher's guide, and the student’s guide. And the study reached the effectiveness of the proposed program in developing the skills of recitation rules for first prep. students, where the experimental group students excelled over the control group students in each skill of the six skills of recitation rules which are (Quraan movements – The rules of silent “N” and tanween – The silent “M” rules – The stressed “M” and “N” rules –Legthen rules - Letters oulets). [ABSTRACT FROM AUTHOR]

One of the UN Sustainable Development Goals is the supply of sustainable energy even where no electrical grid is available. The photovoltaic rural electrification programs are the most common systems implemented in remote areas, especially in developing countries. These programs include the systems installation and their maintenance for a given period. Installation costs and even spare parts costs over time are usually well estimated. However, design and cost estimation of the maintenance systems is a difficult task, whose wrong management has often resulted in the failure of these electrification programs. In this work, a methodology for designing maintenance systems and estimating costs is presented. The methodology includes a mixed integer linear programming model and a rule based expert system. The mathematical programming model allows obtaining the optimal size and accurate cost estimation of a maintenance system, based on precise information about the installed systems. This model is calibrated and validated with real running programs and will be used to get an enlarged data set of simulated cases if needed. The rule based expert system is obtained from the data set applying classification and regression methods with general information about the region and program to be run. It can be used for designing programs or for companies making decisions about being involved in a program to be developed. The methodology has been applied to real Morocco programs. [ABSTRACT FROM AUTHOR]

We present a concise source-to-source transformation that introduces justifications for user-defined constraints into the rule-based Constraint Handling Rules (CHR) programming language. There is no need to introduce a new semantics for justifications. This leads to a conservative extension of the language, as we can show the equivalence of rule applications. A scheme of two rules suffices to allow for logical retraction (deletion, removal) of CHR constraints during computation. Without the need to recompute from scratch, these rules remove the constraint and also undo all its consequences. We prove a confluence result concerning the rule scheme. We prove its correctness in general and tighten the results for confluent programs. We give an implementation, show its correctness, present two classical examples of dynamic algorithms, and improve the implementation. The computational overhead of introducing justifications and of performing logical retraction, i.e. the additional time and space needed, is proportional to the derivation length in the original program. This overhead may increase space complexity, but does not change the worst-case time complexity. [ABSTRACT FROM AUTHOR]

We have been coping with rough set-based rule generation and Apriori-based rule generation. We developed a software tool termed "NIS-Apriori." The software tool makes use of the characteristics of both rough sets and the Apriori algorithm. This NIS-Apriori generates certain rules and possible rules based on the possible world semantics, and the mathematical properties of "soundness and completeness" for defined rules are preserved. Some important propositions have been proved for the framework of the NIS-Apriori. We are now applying this environment to several different data sets, and we especially describe three cases of data sets in this paper. This paper newly considers the rule-based functionality for decision making with reasoning, which will recover the black-box problem in recent AI. [ABSTRACT FROM AUTHOR]

Sequencing mixed-model assembly lines is a well researched topic in the literature. However, many methods that have been developed to solve this problem fail to cope with either the large size or the specific characteristics of real-life problems. In this paper, a heuristic is proposed that is derived from Vogel's approximation method for transportation planning. The heuristic is able to handle large and supposedly difficult problem instances. Sophisticated test scenarios considering real-life aspects were generated to evaluate the performance of the heuristic for realistic problem instances. It is shown that the proposed heuristic significantly outperforms priority rule-based methods and requires only reasonable computational effort. [ABSTRACT FROM AUTHOR]

The traditional inventory classification method classifies stock keeping units (SKUs) to three classes based on their annual dollar usage, while in real world problems, other criteria are important as well. In this paper, considering multi-criteria situations, a simple, effective and practical rule-based method is designed and implemented in a real world case, using MATLAB software. The most important characteristic of the proposed method is taking into account the inherent ambiguities that exist in the reasoning process of the system of classification. The methodology and the method proposed here may be easily implemented by inventory managers. The results obtained from the case study in this paper are compared with the analytic hierarchy process (AHP) method. Finally concluding remarks and suggestions for future work are provided. [ABSTRACT FROM AUTHOR]

The technological complexity of modern production facilities and the increasing demands on operation procedures result in new tasks and requirements for automation solutions and operating staff qualification. On the one hand, supervision and control systems must assign tasks which have been carried out by operators - e.g. operative planning of resources, scheduling of maintenance, operation tuning. On the other hand, the operating principles and techniques must become more objective; operating experience and knowledge should be more easily collected, conserved and disseminated. The general objective of this paper is to develop methods and techniques for these issues. The studied approach is based on integrated use of several formalizations of facility operation knowledge - mathematical modelling, data-driven methods, and scenario-oriented supervision and control routines. Here, facility events in the past are classified by means of Data Mining. Cause-and-effect relations between process states and phenomena are expressed by equations. Facility operation routines are modelled in the form of 'if-then' scenarios. The functional chain, which begins with operator knowledge acquisition and moves to knowledge and facility modelling and finally to their integration into a real Supervisory Control and Data Acquisition system, have been implemented and tested for a water treatment and supply plant. [ABSTRACT FROM AUTHOR]

This article comprises of an Expert Enhanced Coloured Stochastic Petri Net (rule base system, or RBS) for modelling and analysing assembly/disassembly systems. RBSs are an Enhanced High-level Petri net extended with Close-World-Assumption (CWA). Traditional Petri nets can be used to model RBSs containing explicitly described knowledge. The main focus was is to facilitate and analyse the process planning activities of assembly/disassembly. The advantages of the new modelling approach were: (1) consideration of the non-desirable events, (2) occurrence of assembly/disassembly tasks with regard to colour of the tokens and utilization of probability concept to determine feasible steps, (3) establishing a relationship among components by means of arc labels, and (4) deeper insight into the assembly/disassembly process using high- and low-level petri nets. [ABSTRACT FROM AUTHOR]

Research and development in Information Technology is increasingly turning to techniques popular in social science fields for the design, testing and validation of new systems. Case studies, in particular, are used as a powerful technique in all areas of system development and research. Manufacturing Planning and Control (MPC) systems are typical of such systems where the problems are no longer predominantly technical. One of the main barriers to the implementation of successful MPC systems is accurate identification of the true user requirements. This paper describes the use of multiple case studies for the development of a rulebased system for the specification of suitable MPC systems in manufacturing companies. The case studies are carried out in an iterative manner to enable the rule-base to be updated and re-tested with each successive cycle. The use of multiple case-study research cycles enables the accuracy and usability of the rulebase to be assessed as the research progresses. The rule-base comprises inputs (company characteristics and management concerns), rules (structured around reasoning) and outputs (recommended MPC system activities). It is shown that it can be expected to be greater than 90% accurate for any small to medium sized enterprise (SME) engaged in batch manufacturing. [ABSTRACT FROM AUTHOR]

Predictive management for energy supply networks using photovoltaics generation (PV) units, heat pump water-heating units (HPUs), and battery units is developed by uniquely combining two-stage stochastic schedule programming and rule-based control to enhance their operating performances, including operating cost reduction under low selling prices of the surplus PV output after a feed-in tariff system and uncertain input conditions. The forecast scenarios of input conditions are generated from the probability distributions at each sampling time. The schedule planning problem is formulated using two-stage stochastic mixed-integer linear programming and solved by inputting the forecast scenarios and the initial operation states of network components. In the operation control, the energy flow rates are modulated according to the actual input conditions under the obtained operation schedule. The forecast scenario generation and stochastic schedule planning are updated using a receding horizon approach. The developed management is applied to an annual operating simulation of a residential energy supply network for a housing complex, consisting of a shared PV unit, four sets of an HPU and thermal storage tank, and shared battery unit. The simulation results reveal that the decrease in the annual operating cost reduction by the developed management from the ideal management based on the previously-known PV output is just 1.57% point. Moreover, at the selling price of the surplus PV output higher than 6 yen/kWh, the developed management has an advantage in the annual operating cost over the charging- and exporting-priority managements. • Developing predictive management for photovoltaic-based energy supply networks. • Employing stochastic schedule planning and operation control in management is novel. • Schedule planning problem is formulated using two-stage stochastic programming. • Operating cost is reduced by 4.5 percent point in developed predictive management. • Developed management is effective at selling power price higher than 6 yen/kWh. [ABSTRACT FROM AUTHOR]

Detecting small sets of relevant patterns from a given data set is a central challenge in data mining. The relevance of a pattern is based on user-provided criteria; typically, all patterns that satisfy certain criteria are considered relevant. Rule-based languages like answer set programming (ASP) seem well suited for specifying such criteria in a form of constraints. Although progress has been made, on the one hand, on solving individual mining problems and, on the other hand, developing generic mining systems, the existing methods focus either on scalability or on generality. In this paper, we make steps toward combining local (frequency, size, and cost) and global (various condensed representations like maximal, closed, and skyline) constraints in a generic and efficient way. We present a hybrid approach for itemset, sequence, and graph mining which exploits dedicated highly optimized mining systems to detect frequent patterns and then filters the results using declarative ASP. To further demonstrate the generic nature of our hybrid framework, we apply it to a problem of approximately tiling a database. Experiments on real-world data sets show the effectiveness of the proposed method and computational gains for itemset, sequence, and graph mining, as well as approximate tiling. Under consideration in Theory and Practice of Logic Programming. [ABSTRACT FROM AUTHOR]

Vessel segmentation as a component of medical image processing is the prerequisite for accurate diagnosis of vascular-related diseases. Manual delineation of blood vessels has been turned out to be time consuming and observer dependent. Therefore, much effort has been dedicated to the automatic or semi-automatic vessel segmentation methods. Previous literatures have reviewed the state of vessel segmentation methods from various perspectives. However, their reviews did not take the modern machine-learning methods especially deep neural networks into account. In this paper, we reviewed the state-of-the-art vessel segmentation methods by dividing them into two categories, rule-based, and machine-learning-based methods. The rule-based methods discriminate vessel structure from background relying on intuitively and exquisitely designed rule sets, while the machine-learning-based methods carry out the segmentation by self-learned rules from the previous experience. Instead of exhaustively listing all vessel segmentation methods, this paper focuses on the well-known blood vessel segmentation methods in recent years, to give readers a glimpse of the current state and future direction of segmentation technique for blood vessels. [ABSTRACT FROM AUTHOR]

Over the last few years, context-aware computing has received a growing amount of attention among the researchers in the IoT and ubiquitous computing community. In principle, context-aware computing transforms a physical environment into a smart space by sensing the surrounding environment and interpreting the situation of the user. This process involves three major steps: context acquisition, context modelling, and context-aware reasoning. Among other approaches, ontology-based context modelling and rule-based context reasoning are widely used techniques to enable semantic interoperability and interpreting user situations. However, implementing rich context-aware applications that perform reasoning on resource-bounded mobile devices is quite challenging. In this paper, we present a context-aware systems development framework for smart spaces, which includes a lightweight efficient rule engine and a wide range of user preferences to reduce the number of rules while inferring personalized contexts. This shows rules can be reduced in order to optimize the inference engine execution speed, and ultimately to reduce total execution time and execution cost. [ABSTRACT FROM AUTHOR]

Highlights • To review free-text clinical text classification approaches from six aspects. • In selected studies, mostly content-based and concept-based features were used. • The datasets used in selected studies were categorized into four distinct types. • Selected studies used either supervised machine learning or rule-based approaches. • Ten open research challenges are presented in clinical text classification domain. Abstract The pervasive use of electronic health databases has increased the accessibility of free-text clinical reports for supplementary use. Several text classification approaches, such as supervised machine learning (SML) or rule-based approaches, have been utilized to obtain beneficial information from free-text clinical reports. In recent years, many researchers have worked in the clinical text classification field and published their results in academic journals. However, to the best of our knowledge, no comprehensive systematic literature review (SLR) has recapitulated the existing primary studies on clinical text classification in the last five years. Thus, the current study aims to present SLR of academic articles on clinical text classification published from January 2013 to January 2018. Accordingly, we intend to maximize the procedural decision analysis in six aspects, namely, types of clinical reports, data sets and their characteristics, pre-processing and sampling techniques, feature engineering, machine learning algorithms, and performance metrics. To achieve our objective, 72 primary studies from 8 bibliographic databases were systematically selected and rigorously reviewed from the perspective of the six aspects. This review identified nine types of clinical reports, four types of data sets (i.e., homogeneous–homogenous, homogenous–heterogeneous, heterogeneous–homogenous, and heterogeneous–heterogeneous), two sampling techniques (i.e., over-sampling and under-sampling), and nine pre-processing techniques. Moreover, this review determined bag of words, bag of phrases, and bag of concepts features when represented by either term frequency or term frequency with inverse document frequency, thereby showing improved classification results. SML-based or rule-based approaches were generally employed to classify the clinical reports. To measure the performance of these classification approaches, we used precision, recall, F-measure, accuracy, AUC, and specificity in binary class problems. In multi-class problems, we primarily used micro or macro-averaging precision, recall, or F-measure. Lastly, open research issues and challenges are presented for future scholars who are interested in clinical text classification. This SLR will definitely be a beneficial resource for researchers engaged in clinical text classification. [ABSTRACT FROM AUTHOR]

Online reviews on tourism attractions provide important references for potential tourists to choose tourism spots. The main goal of this study is conducting sentiment analysis to facilitate users comprehending the large scale of the reviews, based on the comments about Chinese attractions from Japanese tourism website 4Travel. Different statistics- and rule-based methods are used to analyze the sentiment of the reviews. Three groups of novel statistics-based methods combining feature selection functions and the traditional term frequency-inverse document frequency (TF-IDF) method are proposed. We also make seven groups of different rules-based methods. The macro-average and micro-average values for the best classification results of the methods are calculated respectively and the performance of the methods are shown. We compare the statistics-based and rule-based methods separately and compare the overall performance of the two method. According to the results, it is concluded that the combination of feature selection functions and weightings can strongly improve the overall performance. The emotional vocabulary in the field of tourism (EVT), kaomojis, negative and transitional words can notably improve the performance in all of three categories. The rule-based methods outperform the statistics-based ones with a narrow advantage. Two limitations can be addressed: 1) the empirical studies to verify the validity of the proposed methods are only conducted on Japanese languages; and 2) the deep learning technology is not been incorporated in the methods. The results help to elucidate the intrinsic characteristics of the Japanese language and the influence on sentiment analysis. These findings also provide practical usage guidelines within the field of sentiment analysis of Japanese online tourism reviews. Our research is of practicability. Currently, there are no studies that focus on the sentiment analysis of Japanese reviews about Chinese attractions. [ABSTRACT FROM AUTHOR]

The rapid growth of the Internet in the past few years has revealed the limitation of address space in the current Internet Protocol (IP), namely IPv4. Essentially, the increasing demand and consumption of IP addresses have led to the anticipated exhaustion of IPv4 addresses. In order to address this concern, the Internet Protocol version 6 (IPv6) has been developed to provide a sufficient address space. IPv6 is shipped with a new protocol, namely, the neighbour discovery protocol (NDP) which has vulnerabilities that can be used by attackers to launch attacks on IPv6 networks. Such vulnerabilities include the lack of exchange message authentication of NDP. Attacks targeting ICMPv6 protocol display ICMPv6 anomalies. As such, this paper proposes a rule-based technique for detecting ICMPv6 anomalous behaviours that negatively affect the network performance. The effectiveness of this technique is demonstrated by using substantial datasets obtained from the National Advance IPv6 Centre of Excellence (NAv6) laboratory. The experimental results have proved that the proposed technique is capable of detecting ICMPv6 anomalous behaviour s with a detection accuracy rate of 92%. [ABSTRACT FROM AUTHOR]

Decision making in a semistructured environment often involves the use of quantitative, structured analysis along with the qualitative judgment of an expert. Decision support systems and expert systems are often developed to assist in this judgment process. The hybrid information system described in this paper combines a statistical model with a rule-based expert system in order to integrate the quantitative and qualitative aspects of decision making. The GC Advisor hybrid system is designed for use by auditors to assess the ability of the client firm to continue as a going concern. The guidelines for expert system validation given in previous literature are then applied to the validation of GC Advisor. [ABSTRACT FROM AUTHOR]

When learning rule-based categories, sufficient cognitive resources are needed to test hypotheses, maintain the currently active rule in working memory, update rules after feedback, and to select a new rule if necessary. Prior research has demonstrated that conjunctive rules are more complex than unidimensional rules and place greater demands on executive functions like working memory. In our study, event-related potentials (ERPs) were recorded while participants performed a conjunctive rule-based category learning task with trial-by-trial feedback. In line with prior research, correct categorization responses resulted in a larger stimulus-locked late positive complex compared to incorrect responses, possibly indexing the updating of rule information in memory. Incorrect trials elicited a pronounced feedback-locked P300 elicited which suggested a disconnect between perception, and the rule-based strategy. We also examined the differential processing of stimuli that were able to be correctly classified by the suboptimal single-dimensional rule (“easy” stimuli) versus those that could only be correctly classified by the optimal, conjunctive rule (“difficult” stimuli). Among strong learners, a larger, late positive slow wave emerged for difficult compared with easy stimuli, suggesting differential processing of category items even though strong learners performed well on the conjunctive category set. Overall, the findings suggest that ERP combined with computational modelling can be used to better understand the cognitive processes involved in rule-based category learning. [ABSTRACT FROM AUTHOR]

Effective reuse and recycling of end-of-life (EOL) products are essential for improving resource efficiency and protecting environment. Currently, many parts of construction machinery in EOL stage can still be reused directly because they are designed with extreme high strength to meet the bad working conditions, which minimizes the impact on the environment. In this context, a quality evaluation approach for reuse parts is proposed in this paper. Ontology model is built for representing evaluation information with semantic properties and constructing the semantic relevance among the various concepts involved in parts reusing domain, thus achieving the integrating, sharing, and reusing of evaluating parts knowledge. On that basis, analytic hierarchy process (AHP) is put forward to quantify the reusability degree of the parts of EOL construction machinery. Furthermore, combined with ontology, rule-based-reasoning method is utilized to get suggested strategies for reuse parts. In addition, a web-based system is developed to assist manufacturers in managing reuse parts, and a case study is analyzed to demonstrate the proposed quality evaluation approach. [ABSTRACT FROM AUTHOR]

This paper proposes a rule-based voice conversion system for emotion which is capable of converting neutral speech to emotional speech using dimensional space (arousal and valence) to control the degree of emotion on a continuous scale. We propose an inverse three-layered model with acoustic features as output at the top layer, semantic primitives at the middle layer and emotion dimension as input at the bottom layer; an adaptive-based fuzzy inference system acts as connectors to extract the non-linear rules among the three layers. The rules are applied by modifying the acoustic features of neutral speech to create the different types of emotional speech. The prosody-related acoustic features of F0 and power envelope are parameterized using the Fujisaki model and target prediction model separately. Perceptual evaluation results show that the degree of emotion can be perceived well in the dimensional space of valence and arousal. [ABSTRACT FROM AUTHOR]

The volume of data produced has exponentially increased with the digital revolution and it continues to race to the limits of the capacity of our computers and supercomputers. Automatic text summarization is one of efforts to tame the bestial product of our daily data production, which have generated the 90 percent of the data ever produced by humans, in the last two years. In order to understand what a text is about, a summary is needed which is short enough not to compromise the understandability, and comprehensive to include the most important topics of that text. Numerous automatic text summarization software which aimed at achieving this goal use semantic relations, thesauri, and word frequency lists. In this paper, development phases and evaluation results of a software tool called Rule Based Turkish Text Summarizer (RB-TTS) are presented. The average success rate of the RB-TTS is analyzed both quantitatively using ROUGE-N metrics and qualitatively. In the qualitative analysis, five summaries, obtained automatically from texts, are evaluated by 10 Ph.D. students from Dokuz Eylul University Department of Linguistics. The summaries generated by RB-TTS software are compared with the summaries, which were written by the authors of the corresponding texts, and marked as close to them. [ABSTRACT FROM AUTHOR]