Automatic Rule Research Articles

Iterative Scale-Invariant Feature Transform for Remote Sensing Image Registration

Due to significant geometric distortions and illumination differences, developing techniques for high precision and robust multisource remote sensing image registration poses a great challenge. This article presents an iterative image registration approach, called iterative scale-invariant feature transform (ISIFT) for remote sensing images, which extends the traditional scale-invariant feature transform (SIFT)-based registration system to a close-feedback SIFT system that includes a rectification feedback loop to update rectified parameters in an iterative manner. Its key idea uses consistent feature point sets obtained by maximum similarity to calculate new alignment parameters to rectify the current sensed image and the resulting rectified sensed image is then fed back to update and replace the current sensed image as a new sensed image to reimplement SIFT for next iteration. The same process is repeated iteratively until an automatic stopping rule is satisfied. To evaluate the performance of ISIFT, both the simulated and real images are used for experiments for the validation of ISIFT. In addition, several data sets are particularly designed to conduct a comparative study and analysis with existing state-of-the-art methods. Furthermore, experiments with different rotation are also performed to verify the adaptability of ISIFT under different rotation distortions. The experimental results demonstrate that ISIFT improves performance and produces better registration accuracy than traditional SIFT-based methods and existing state-of-the-art methods.

Dimensionally Aware Multi-Objective Genetic Programming for Automatic Crowd Behavior Modeling

One limitation of current data-driven automatic crowd modeling methods is that the models generated have low interpretability, which limits the practical applications of the models. In this article, we propose a new data-driven crowd modeling approach that can generate universal behavior rules with better interpretability. Higher interpretability helps people better understand and analyze the rules. Furthermore, the proposed approach considers both static and dynamic features during modeling to generate a realistic crowd, based on the assumption that humans tend to consider different features with respect to their states. In the proposed method, the automatic behavior rule generation problem is formulated as a symbolic regression problem. Then, the problem is solved by multi-objective genetic programming. On one hand, to improve the interpretability of the behavior rules found, a new mechanism is proposed to guide the algorithm to find concise and dimensionally consistent solutions. On the other hand, decisions made by considering static and dynamic features respectively are combined to improve the generated crowd realism. To validate the effectiveness of the proposed method, three real-world datasets are utilized for training and testing. The simulation results demonstrate that the proposed method is able to find universal behavior rules that are competitive to previous work in accuracy while having better interpretability.

Multi-Agent-Based Urban Vegetation Design.

Urban vegetation is an essential element of the urban city pedestrian walkway. Despite city forest regulations and urban planning best practices, vegetation planning lacks clear comprehension and compatibility with other urban elements surrounding it. Urban planners and academic researchers currently devote vital attention to include most of the urban elements and their impact on the occupants and the environment in the planning stage of urban development. With the advancement in computational design, they have developed various algorithms to generate design alternatives and measure their impact on the environment that meets occupants’ needs and perceptions of their city. In particular, multi-agent-based simulations show great promise in developing rule compliance with urban vegetation design tools. This paper proposed an automatic urban vegetation city rule compliance approach for pedestrian pathway vegetation, leveraging multi-agent system and algorithmic modeling tools. This approach comprises three modules: rule compliance (T-Rule), street vegetation design tool (T-Design), and multi-agent alternative generation (T-Agent). Notably, the scope of the paper is limited to trees, shrubbery, and seating area configurations in the urban pathway context. To validate the developed design tool, a case study was tested, and the vegetation design tool generated the expected results successfully. A questionnaire was conducted to give feedback on the use of the developed tool for enhancing positive experience of the developed tool. It is anticipated that the proposed tool has the potential to aid urban planners in decision-making and develop more practical vegetation planting plans compared with the conventional Two-Dimensional (2D) plans, and give the city occupants the chance to take part in shaping their city by merely selecting from predefined parameters in a user interface to generate their neighborhood pathway vegetation plans. Moreover, this approach can be extended to be embedded in an interactive map where city occupants can shape their neighborhood greenery and give feedback to urban planners for decision-making.

Structured authoring for AR-based communication to enhance efficiency in remote diagnosis for complex equipment

Remote diagnosis procedures are prone to communication errors due to varying levels of experience and knowledge between expert maintainers and technicians. These result in inefficiencies that delay the diagnosis process. The aim of the paper is to develop a Structured-Message Authoring framework for Augmented Reality (AR) Remote Communication (SMAARRC) and to evaluate its ability to enhance the efficiency of remote diagnosis services. The framework proposes a message structure and automatic AR content creation rules for it that enable data capture and sharing within a remote context. Laboratory experiments present an average time reduction of 56% for remote calls while maintaining same quality compared to traditional remote communication methods (phone calls and emails). Remote experts feedback evidence the usability and feasibility of this framework to work in real-life conditions.

A new fuzzy multi-hop clustering protocol with automatic rule tuning for wireless sensor networks

In today’s world, a major challenge is to conserve and make optimal use of energy. This is a critical matter in wireless sensor networks due to their wide application in different areas. More importantly, scant attention has been paid to the use of node energy for certain applications in such networks. This study used the Shuffled Frog Leaping Algorithm (SFLA) to propose a Fuzzy Multi-hop clustering protocol (FMSFLA). The SFLA is used for automated configuration and optimization of the rule-base table in a fuzzy inference system and five adjustable parameters in two phases, i.e. Cluster Head (CH) selection and parent selection, based on application features. The proposed protocol (FMSFLA) considers effective parameters including energy, distance from the base station (BS), the number of neighboring nodes, real node distance from the BS, mean route load, delay, overlap, and the problem of hot spots, to achieve the best application-based performance. The FMSFLA includes rounds, in each round the phases of CH selection, parent selection, cluster formation, and steady state are performed. In the CH selection phase, CHs are selected from candidate nodes based on the fuzzy output and energy threshold (i.e. a control parameter) with respect to the overlap rate of adjacent CHs. In our protocol, the parent selection phase began by determining the levels of CHs in the network. At the end of this phase, the parent of each CH is determined on the basis of the greatest fuzzy output based on application. In the cluster formation phase, the clusters are formed on the basis of the determined CHs. Finally, the information received by CHs is sent through their parents to the BS in the steady state phase. The FMSFLA is evaluated against the LEACH, LEACH-EP, LEACH-FL, ASLPR, SIF, and ERA protocols in terms of the number of alive nodes, received packets, and cluster heads in addition to their appropriate distribution rates and other parameters pertaining to the network lifetime and protocol scalability using three application-oriented scenarios. According to the simulation results, the FMSFLA functioned far better than the other protocols in all scenarios with respect to goals and application features.

Algorithm research of spoken English assessment based on fuzzy measure and speech recognition technology

At present, many speech recognition algorithms are difficult to effectively evaluate the fuzziness of the evaluation algorithm. Based on this, this dissertation uses the speech recognition technology based on fuzzy measure to evaluate the spoken English. In the study the fuzzy measure, based on the traditional algorithm, is used to evaluate the spoken English and different characteristic parameters are extracted to construct the corresponding evaluation model. Simultaneously, the pronunciation is evaluated through automatic learning rules. The English speaking assessment model based on fuzzy measure and speech recognition technology is constructed and validated. The research shows that compared with the traditional algorithms, the spoken language evaluation algorithm based on fuzzy measure and speech recognition technology has the incomparable superiority, and can provide a reference for the follow-up related research.

Automatic fuzzy rules production based on clustering and implication selection

This paper deals with improving the approximation capability of fuzzy systems. Fuzzy negations produced via conical sections are a promising methodology towards better fuzzy implications in fuzzy rules. The linguistic variables and the fuzzy rules are induced automatically following a fuzzy equivalence relation. The uncertainty of linear or nonlinear systems is thus dealt with. In this study, the clustering is optimized without human intervention, but also the best inference mechanism for a particular dataset is prescribed. It has been found that clustering based on fuzzy equivalence relation and fuzzy inference via conical sections leads to remarkably accurate approximations. A fuzzy rule based system with fewer control parameters is proposed. An application on telecom data shows the use of the methodology, its applicability to a real problem and its performance compared to other alternatives in terms of quality.

Institutional Challenges for External Differentiated Integration: The Case of the EEA

This working paper analyses the institutional challenges related to external differentiated integration in the European Economic Area (EEA). It focuses mainly on the formulation of EEA-relevant EU legislation and its incorporation into the EEA Agreement. The paper shows that over the past 25 years various institutional arrangements have been added to the initial institutional framework of the EEA in order to increase and maintain substantive integration. However, the European Union (EU) has been consistent in protecting the autonomy of its decision making which is why the EEA EFTA States have far-reaching access to EU policy making but never the right to vote. The EEA EFTA States therefore insist on separate EEA decision making whenever possible. This has given them a surprisingly large amount of room for manoeuvre for instance, by deliberately delaying the incorporation of politically sensitive acts, and by making EEA-specific adaptations to EU acts. On the other hand, they were also forced to introduce simplified procedures for EEA decision making in order to cope better with the high legislative dynamics of the EU. These procedures give priority to the efficacy of the EEA over the decision-making autonomy of the EEA EFTA States by establishing a more or less automatic rule transfer from the EU to the EEA. Thanks to its far-reaching functional and institutional integration the EEA provides a good example for the analysis of the legal and political feasibility of external differentiated integration. Above all, the results of the empirical analysis demonstrate how difficult it is to reconcile the integration reservations of non-Member States with the principles of the EU in an institutional framework designed to ensure the long-term good functioning of their relations.

A Spectral–Spatial Feedback Close Network System for Hyperspectral Image Classification

This paper presents a new spectral–spatial (SS) approach to hyperspectral image classification (HSIC), called SS feedback close network system (SSFCNS), which has not been explored in the past. Unlike commonly used SS-based methods SSFCNS includes a feedback close network system (FCNS) to obtain spatial information via a selective spatial filter in an iterative manner. More specifically, SSFCNS takes advantage of FCNS which utilizes a particularly selected spatial filter to capture a posteriori spatial information directly from spectral-classified data samples and then feeds back such obtained spatial-filtered image to be combined with the current image cube to create a new image cube that can be used as a new input to re-implement SSFCNS. The process is carried out in such a way that the spatial information obtained from spectral classification results is updated by FCNS iteratively and terminated by a Tanimoto index (TI)-derived automatic stopping rule. To evaluate the performance of SSFCNS several spatial filters (i.e., Gaussian, bilateral, guided, and Gabor filters) are explored for real image experiments. The experimental results demonstrate that SSFCNS performs significantly better in classification accuracy compared to SS-based methods which do not use FCNS.

Extreme pivots: a pivot selection strategy for faster metric search

This manuscript presents the extreme pivots (EP) metric index, a data structure, to speed up exact proximity searching in the metric space model. For the EP, we designed an automatic rule to select the best pivots for a dataset working on limited memory resources. The net effect is that our approach solves queries efficiently with a small memory footprint, and without a prohibitive construction time. In contrast with other related structures, our performance is achieved automatically without dealing directly with the index’s parameters, using optimization techniques over a model of the index. The EP’s model is studied in-depth in this contribution. In practical terms, an interested user only needs to provide the available memory and a sample of the query distribution as parameters. The resulting index is quickly built, and has a good trade-off among memory usage, preprocessing, and search time. We provide an extensive experimental comparison with state-of-the-art searching methods. We also carefully compared the performance of metric indexes in several scenarios, firstly with synthetic data to characterize performance as a function of the intrinsic dimension and the size of the database, and also in different real-world datasets with excellent results.

Automatic Tajweed Rules Recognition using K-Nearest Neighbour (K-NN)

Tajweed refers to a pronunciation rule for Al-Quran recitation in Islam. It acts as guidance for Muslims in reciting the Al-Quran in a correct manner. Yet, Tajweed rules could be complicated as it consists of various types of laws. It could also be confusing, and difficult to remember particularly for the people who have less knowledge in Tajweed rules. Thus, a study on automatic tajweed rules recognition using image processing technique is proposed. The scope of this study is limited to Idgham laws only. Initially, the input image went through the pre-processing process which includes four sub-processes which are greyscale conversion, binary conversion, thinning and flip, and word segmentation. Next, six attributes of shape descriptor which are major axis length, minor axis length, eccentricity, filled area, solidity, and perimeter were extracted from each input image. A technique of k-Nearest Neighbour (k-NN) is employed to recognize the two types of Idgham Laws which are Idgham Maal Ghunnah and Idgham Bila Ghunnah. The performance of the proposed study is evaluated to 180 testing images which returned 84.44% of classification accuracy. The outcome of this study is expected to recognize the Tajweed rules automatically and may assist the user on a proper recitation of Al-Quran.

Towards automatic calibration of neighbourhood influence in cellular automata land-use models

Cellular Automata (CA) land-use models are widely used for understanding processes of land-use change. However, calibration of these models is a knowledge-intensive and time-consuming process. Although calibration of common driving factors such as accessibility (A), or suitability (S) is a relatively straightforward task, calibrating the neighbourhood dynamics (N), which controls the key model behaviour, is often very challenging. Here, building on the SIMLANDER modelling framework, we develop an automatic rule detection (ARD) procedure to automate the calibration of N. To demonstrate the performance of the tool, we simulated 15 years of urban growth in Ahvaz, Iran (2000–2015) using a wide range of different rule-sets. We evaluated calibration goodness-of-fit for each rule-set against a reference map by means of cross-comparison of multiple metrics using a ranking procedure. The ARD procedure can be implemented in two ways: 1) by random sampling of the parameter space, a user-defined number of times, or 2) through a stepwise “grid search” approach for a user-defined number of rule combinations. Both approaches were found to produce successful rule combinations according to the goodness-of-fit metrics applied. Grid search performed slightly better, but at the cost of a fivefold increase in computation time. The ARD approach facilitates model calibration by allowing rapid identification of the optimum ruleset from a wide range of possible parameter settings, while the ranking procedure facilitates comparison of simulations using multiple metrics. The approach we present also helps to improve simulation accuracy with respect to manual calibration methods, and increases understanding of neighbourhood dynamics for the urban area studied. To encourage repeatability and transparency, our approach uses only open data and Free-and-Open Source Software (RStudio environment) and we provide our ARD scripts as supplementary material

Low-Value Proton Pump Inhibitor Prescriptions Among Older Adults at a Large Academic Health System.

Older adults are particularly vulnerable to complications from proton pump inhibitor (PPI) drugs. We sought to characterize the prevalence of potentially low-value PPI prescriptions among older adults to inform a quality improvement (QI) intervention. We created a cohort of patients, aged 65 years or older, receiving primary care at a large academic health system in 2018. We identified patients currently prescribed any PPI using the electronic health record (EHR) medication list (current defined as September 1, 2018). A geriatrician, a gastroenterologist, a QI expert, and two primary care physicians (PCPs) created multidisciplinary PPI appropriateness criteria based on evidenced-based guidelines. Supervised by a gastroenterologist and PCP, two internal medicine residents conducted manual chart reviews in a random sample of 399 patients prescribed PPIs. We considered prescriptions potentially low value if they lacked a guideline-based (1) short-term indication (gastroesophageal reflux disease [GERD]/peptic ulcer disease/Helicobacter pylori gastritis/dyspepsia) or (2) long-term (>8 weeks) indication (severe/refractory GERD/erosive esophagitis/Barrett esophagus/esophageal adenocarcinoma/esophageal stricture/high gastrointestinal bleeding risk/Zollinger-Ellison syndrome). We used the Wilson score method to calculate 95% confidence intervals (CIs) on low-value PPI prescription prevalence. Among 69 352 older adults, 8729 (12.6%) were prescribed a PPI. In the sample of 399 patients prescribed PPIs, 63.9% were female; their mean age was 76.2 years, and they were seen by 169 PCPs. Of the 399 prescriptions, 143 (35.8%; 95% CI = 31.3%-40.7%) were potentially low value-of which 82% began appropriately (eg, GERD) but then continued long term without a guideline-based indication. Among 169 PCPs, 32 (18.9%) contributed to 59.2% of potentially low-value prescriptions. One in eight older adults were prescribed a PPI, and over one-third of prescriptions were potentially low-value. Most often, appropriate short-term prescriptions became potentially low value because they lacked long-term indications. With most potentially low-value prescribing concentrated among a small subset of PCPs, interventions targeting them and/or applying EHR-based automatic stopping rules may protect older adults from harm. J Am Geriatr Soc 67:2600-2604, 2019.

The \u03b4-Machine: Classification Based on Distances Towards Prototypes

We introduce the δ-machine, a statistical learning tool for classification based on (dis)similarities between profiles of the observations to profiles of a representation set consisting of prototypes. In this article, we discuss the properties of the δ-machine, propose an automatic decision rule for deciding on the number of clusters for the K-means method on the predictive perspective, and derive variable importance measures and partial dependence plots for the machine. We performed five simulation studies to investigate the properties of the δ-machine. The first three simulation studies were conducted to investigate selection of prototypes, different (dis)similarity functions, and the definition of representation set. Results indicate that we best use the Lasso to select prototypes, that the Euclidean distance is a good dissimilarity function, and that finding a small representation set of prototypes gives sparse but competitive results. The remaining two simulation studies investigated the performance of the δ-machine with imbalanced classes and with unequal covariance matrices for the two classes. The results obtained show that the δ-machine is robust to class imbalances, and that the four (dis)similarity functions had the same performance regardless of the covariance matrices. We also showed the classification performance of the δ-machine compared with three other classification methods on ten real datasets from UCI database, and discuss two empirical examples in detail.

Transparency and Complexity of Form and Meaning within Words

본고는 단어 차원에서 의미적 투명성, 의미적 복합성, 형태적 투명성, 형태적 복합성을 실제적으로 판정해 낼 수 있는 정의들을 도출해 내고자 하였다. 그 결과는 다음과 같다. 의미적 투명성은 단어 구성 요소의 의미가 형성된 단어의 의미에 그대로 승계되는 성질로서 투명/부분투명/불투명으로 나뉜다. 의미적 복합성은 어떤 한 단어가 내부적으로 형태 분석이 가능하고, 분석된 형태들이 각각 자체의 의미를 가지고 있는 성질로서 복합/단일로 나뉜다. 형태적 투명성은 단어 구성 요소의 형태가 형성된 단어에 그대로 반영되거나, 자동적인 음운론적 규칙에 의하여 변동된 채 반영되는 성질로서 투명/부분투명/불투명으로 나뉜다. 형태적 복합성은 한 단어가 공시적으로 명확하게 두 가지의 형태적 요소를 지니고 있는 성질로서 복합/단일로 나뉜다. 이러한 투명성과 복합성 판단은 언중의 공시적 언어 지식을 바탕으로 이루어진다.This paper aims to define semantic transparency, semantic complexity, morphological transparency and morphological complexity within words. Semantic transparency is categorized into three groups of transparency, partial-transparency and opacity, depending on whether or not a word inherits the meanings of its components. Semantic complexity is divided into two categories of complexity and simplicity, depending on whether or not parts of a word can be analyzed into their own meanings. Morphological transparency is categorized into three groups of transparency, partial-transparency and opacity, depending on whether or not the parts constituting a word remain the same after word formation. In addition, automatic phonological rules are needed to explain morphological transparency. Morphological complexity is divided into two categories of complexity and simplicity, depending on whether or not a word has two or more synchronic parts. Judging the transparency and complexity of a word depends on the native speakers synchronic knowledge of the language. The above four concepts could become fundamental criteria in classifying words.

Template-based AADL automatic code generation

Embedded real-time systems employ a variety of operating system platforms. Consequently, for automatic code generation, considerable redevelopment is needed when the platform changes. This results in major challenges with respect to the automatic code generation process of the architecture analysis and design language (AADL). In this paper, we propose a method of template-based automatic code generation to address this issue. Templates are used as carriers of automatic code generation rules from AADL to the object platform. These templates can be easily modified for different platforms. Automatic code generation for different platforms can be accomplished by formulating the corresponding generation rules and transformation templates. We design a set of code generation templates from AADL to the object platform and develop an automatic code generation tool. Finally, we take a typical Data Processing Unit (DPU) system as a case study to test the tool. It is demonstrated that the auto-generated codes can be compiled and executed successfully on the object platform.

Automatic Rule Generator via FP-Growth for Eye Diseases Diagnosis

The conventional approach in developing a rule-based expert system usually applies a tedious, lengthy and costly knowledge acquisition process. The acquisition process is known as the bottleneck in developing an expert system. Furthermore, manual knowledge acquisition can eventually lead to erroneous in decision-making and function ineffective when designing any expert system. Another dilemma among knowledge engineers are handing conflict of interest or high variance of inter and intrapersonal decisions among domain experts during knowledge elicitation stage. The aim of this research is to improve the acquisition of knowledge level using a data mining technique. This paper investigates the effectiveness of an association rule mining technique in generating new rules for an expert system. In this paper, FP-Growth is the machine learning technique that was used in acquiring rules from the eye disease diagnosis records collected from Sumatera Eye Center (SMEC) Hospital in Pekanbaru, Riau, Indonesia. The developed systems are tested with 17 cases. The ophthalmologists inspected the results from automatic rule generator for eye diseases diagnosis. We found that the introduction of FP-Growth association rules into the eye disease knowledge-based systems, able to produce acceptable and promising eye diagnosing results approximately 88% of average accuracy rate. Based on the test results, we can conclude that Conjunctivitis and Presbyopia disease are the most dominant suffering in Indonesia. In conclusion, FP-growth association rules are very potential and capable of becoming an adequate automatic rules generator, but still has plenty of room for improvement in the context of eye disease diagnosing.

Efficient inference for nonlinear state space models: An automatic sample size selection rule

This paper studies the maximum likelihood estimation of nonlinear state space models. Particle Markov chain Monte Carlo method is introduced to implement the Monte Carlo expectation maximization algorithm for more accurate and robust estimation. Under this framework, an automated sample size selection criterion is constructed via renewal theory. This criterion would increase the sample size when the relative likelihood indicates that the parameters are close to each other. The proposed methodology is applied to the stochastic volatility model and another nonlinear state space model for illustration, where the results show better estimation performance.

Building an ontological knowledgebase for bridge maintenance

The operation stage has the biggest potential value in the bridge life cycle management, and it often critically influences the overall cost of the bridge. As such, changes in the efficiency of the project's operation stage could be of significant benefit to the overall project. However, current approaches in the operation stage often lack the effective support of computer-aided tools. This research presents a holistic method based on an ontology to achieve automatic rule checking and improve the management and communication of knowledge related to bridge maintenance. The developed ontology can also facilitate a smarter decision-making process for bridge management by informing engineers of choices with different considerations. Three approaches; semantic validation, syntactical validation, and case study validation, have been adopted to evaluate this ontology and demonstrate how the developed ontology can be used by engineers when dealing with different issues. The results showed that this approach can create a holistic knowledge base that can integrate various domain knowledge to enable bridge engineers to make more comprehensive decisions rather than a single objective-targeted delivery.

Bee for mining (B4M) – A novel rule discovery method using the Bees algorithm with quality-weight and coverage-weight

This paper proposes a novel tool known as Bee for Mining (B4M) for classification tasks, which enables the Bees Algorithm (BA) to discover rules automatically. In the proposed B4M, two parameters namely quality-weight and coverage-weight have been added to the BA to avoid any ambiguous situations during the prediction phase. The contributions of the proposed B4M algorithm are two-fold: the first novel contribution is in the field of swarm intelligence, using a new version of BA for automatic rule discovery, and the second novel contribution is the formulation of a weight metric based on quailty and coverage of the rules discovered from the dataset to carry out Meta-Pruning and making it suitable for any classification problem in the real world. The proposed algorithm was implemented and tested using five different datasets from University of California, at Irvine (UCI Machine Learning Repository) and was compared with other well-known classification algorithms. The results obtained using the proposed B4M show that it was capable of achieving better classification accuracy and at the same time reduce the number of rules in four out of five UCI datasets. Furthermore, the results show that it was not only effective and more robust, but also more efficient, making it at least as good as other methods such as C5.0, C4.5, Jrip and other evolutionary algorithms, and in some cases even better.