If-then Rules Research Articles

Analysis of an individual‐based influenza epidemic model using random forest metamodels and adaptive sequential sampling

AbstractThis study proposes a three‐step procedure for the analysis of input–response relationships of dynamic models, which enables the analyst to develop a better understanding about the dynamics of the system. The main building block of the procedure is a random forest metamodel capturing the input–output relationships. We utilize an active learning approach as the second step to improve the accuracy of the metamodel. In the last step, we develop a novel way to present the information captured by the metamodel as a set of intelligible IF–THEN rules. For illustration, we use the FluTE model, which is an individual‐based influenza epidemic model. We observe that the number of daily applicable vaccines determines the success of an intervention strategy the most. Another critical observation is that when the daily available vaccines are constrained, nonpharmaceutical strategies should be incorporated to reduce the extent of the outbreak.

A Classification Approach Using Fuzzy Inference System for Non-Proliferative Diabetic Retinopathy

This paper proposes a classification technique using fuzzy inference system (FIS) for non-proliferative diabetic retinopathy (NPDR). The input variables to FIS are the extracted features from the pathologies of NPDR. Abnormalities like exudates and microaneuryms are segmented for feature extraction. The pathological aspects of NPDR leads to fuzzy if-then rules that effectively handles the fuzziness present in some of the features. The role of FIS in NPDR classification replaces the training phase in learning based classification methods. The performance of the proposed fuzzy approach is analyzed for stages of NPDR and diabetic retinopathy classification on various databases. The accuracy of 98.2% is observed for NPDR classification in Messidor database.

Expert System for Diagnosing Osteoarthritis with Fuzzy Tsukamoto Method

Osteoarthritis is a degenerative joint disease involving the cartilage, the lining of the joints, ligaments, and bones, causing pain and stiffness in the joints that suffer from these symptoms. People often ignore pain that occurs when moving the shoulder, plate, knee and hand pain when it has great potential are the symptoms of the disease Osteoarthritis. Expert systems can be used as a system to identify disease Osteoarthritis. With Osteoarthritis disease diagnosis expert system then expected to help people to detect diseases early Osteoarthritis and can consult with a doctor before continuing to a more dangerous stage. In this research using Fuzzy Tsukamoto Algorithm method, which method is an extension of the reasoning Tsukamoto monotonous, every consequent formed IF-Then rules should be presented with a fuzzy set. As a result, output inference of each rule is given explicitly by predicate. Result is obtained by using a weighted average (center average defuzzifier). Symptoms of Osteoarthritis serve as fuzzy values which will then be sorted according to a predetermined membership function. After fuzzy value of the calculation has been obtained, then fuzzy value will be converted into firm value using a weighted average. From these results it can be concluded that the accuracy of the expert system that has been built to have an accuracy of 90% that is 18 of the 20 patients who had been tested using an expert system that has been built

Multimaterial bioprinting—minus the printer: Synthetic bacterial patterning with UV-responsive genetic circuits

In this paper, we argue that synthetic biology can help us employ living systems’ unique capacity for self-construction and biomaterial production toward developing novel architectural fabrication paradigms, in which both the raw material production and its refinement into a target structure can be merged into a single computational process embedded in the living structure itself. To demonstrate, here we introduce bioPheme, a novel biofabrication method for engineering bacteria to build biomaterial(s) of designer’s choice into arbitrary 2D geometries specified via transient UV tracing. To this end, we present the design, construction, and testing of the enabling synthetic DNA circuit, which, once inserted into a bacterial colony, allows the bacteria to execute spatial computation by interacting with one another based on the if-then rules encoded in this circuit. At the heart of this genetic circuit is a pair of UV sensor – actuator, and a pair of cell-to-cell signal transmitter – receptor modules, created with genes extracted from the virus λ Phage and marine bacterium Vibrio fischeri, respectively. These modules are wired together to help designers engineer bacteria to build macro-scale structures with seamlessly integrated biomaterials, thereby bridge the molecular and architectural scales. In this way, a bacterial lawn can be programmed to produce different objects with complementary biomaterial compositions, such as a biomineralized superstructure and an elastic tissue filling in-between. In summary, this paper focuses on how scientists’ increasing ability to harness the innate computational capacity of living cells can help designers create self-constructing structures for architectural biofabrication. Through the discussions in this paper, we aim to initiate a shift in today’s biodesign practices toward a greater appreciation and adoption of bottom-up governance of living structures. We are confident that such a paradigm shift will allow for more efficient and sustainable biofabrication systems in the 4th industrial revolution and beyond.

Fuzzy modeling approach for transient vapor compression and expansion cycle simulation

Abstract Previous mode switching algorithms for heat exchanger moving boundary models in the literature are composed of a set of IF-THEN rules. These representations could lead to numerical challenges due to the inherited discontinuities associated with IF-THEN rules. This paper presents an alternative mode switching methodology which results in a continuous moving boundary heat exchanger model over all possible mode changes. Numerical performance of the proposed method for a heat exchanger has been tested using simulations and sample results are compared with a moving boundary model with switching based on IF-THEN rules and also a finite-volume method. The proposed switching algorithm was implemented within a complete vapor compression cycle model and results were compared with experimental data for a start-up transient.

An Improved IDAF-FIT Clustering Based ASLPP-RR Routing with Secure Data Aggregation in Wireless Sensor Network

In recent years, Wireless Sensor Network (WSN) became a key technology for monitoring and tracking applications in a wide application range. Still, an energy-efficient data gathering protocol has become the most challenging issue. This is because each sensor node in the network is equipped with limited energy resources. To achieve better energy efficiency, better network communication, and minimized delay, clustering is introduced. Therefore, the clustering-based techniques for data gathering play a vital role in terms of energy-saving and increasing the lifetime of the network due to cluster head election and data aggregation. In this proposed methodology, the Integration of Distributed Autonomous Fashion with Fuzzy If-then Rules (IDAF-FIT) algorithm is proposed for clustering, and also the Cluster Head (CH) is elected in the meanwhile. After that, to transmit the packet from source to the destination node by choosing an optimal path, the routing concept is initiated. For this purpose, an Adaptive Source Location Privacy Preservation Technique using Randomized Routes (ASLPP-RR) is presented for routing. Also, Secure Data Aggregation based on Principle Component Analysis (SDA-PCA) algorithm is performed with end-to-end confidentiality and integrity. Finally, the security of confidential data is analyzed properly to obtain a better result than the existing approaches. The overall performance of the proposed methodology when compared with existing is expressed in terms of 20% higher packet delivery ratio, 15% lower packet dropping ratio, 18% higher residual energy, 22% higher network lifetime, and 16% lower energy consumption.

Parameterized simplification logic I: reasoning with implications and classes of closure operators

In this paper, we present a general inference system for reasoning with if-then rules. They are defined using general lattice-theoretic notions and their semantics is defined using particular closure operators parameterized by systems of isotone Galois connections. In this general setting, we introduce a simplification logic, show its sound and complete axiomatization, and deal with related issues. The presented results can be seen as forming parameterized framework for dealing with if-then rules that allows to focus on particular dependencies obtained by choices of parameterizations.

FAST-ODT: A Lightweight Outlier Detection Scheme for Categorical Data Sets

Outlier detection is a key data analysis technique that aims to find unusual data objects in a data set. It has been widely used in varied areas, including communication networks, finance, medicine, environmental studies, etc. Many applications in these areas involve categorical data. For example, the data set used in the application of intrusion detection normally includes a group of captured packets, which tend to have categorical attributes such as “protocol”. Although there are many outlier detection algorithms for applications involving numerical data, only a few existing schemes can handle categorical data. And the schemes designed for categorical data seriously suffer from two problems: low detection precision and high time complexity. In this paper, we present two novel outlier detection algorithms for categorical data sets. First of all, we describe a simple scheme based on entropy, Outlier Detection Tree (ODT). With ODT, a classification tree is constructed to classify the data set into two classes: a normal class and an abnormal class. Thereafter, each data object is identified as an outlier or a normal one using the if-then rules in the tree. Furthermore, we propose an advanced outlier detection algorithm, FAST-ODT, which achieves both high detection accuracy and low time complexity. Our experimental results indicate that FAST-ODT outperforms the existing algorithms in terms of outlier detection precision and computational complexity.

Data-driven smart control of injection molding process

The most widely used cyclic manufacturing process to produce plastic components, injection molding produces large quantities of scrap materials and consumes resources to mitigate the increasing demands for quality products and sophisticated shapes. Such inefficiencies require a smart quality-control system that can bring consistency in the product quality. Continuous monitoring and control of the injection molding are of excessive importance in providing a better understanding of the occurrence of the failures and their correction measures. In the presented paper, a cyber engineering analysis model is developed to illustrate the real injection molding behavior, and multiple experiments are performed to derive the process window for the product with very good quality. To detect the process disturbances, a control boundary with threshold limits of cavity temperature and pressure is established. If-then rule based control algorithm is derived to detect the failures and make the compensatory adjustments to the process parameters. Finally, the proposed method is illustrated with the manufacturing of an automotive product i.e. car door trim module, and its validity is verified. Study results after the introduction of the developed quality control methodology indicate the dramatic reduction in the quality failure rates and the wastages of resources.

Foot Pronation Detection Based on Plantar Pressure Measurement

In the paper, we design a foot pronation detection system based on plantar pressure sensors. The system includes: collecting the pressure sensor signals by reasonably arranging the pressure sensors; collecting the plantar pressure signal value of the test object which has been walking for a period of time; taking the proportional calculation, determining the fuzzy sets, designing the membership function, the fuzzy processing was carried out and the fuzzy rules was established by the IF-THEN rules. Finally the gait phase was deduced according to the fuzzy output signal, and the system function was realized by pronation analysis algorithm. The experimental results show that the system has an important value for sports risk prediction.

Development of rule-based expert system for conceptualisation of poster design

This study discusses development of rule-based expert system (R-ES) as a decision support for poster design conceptualisation. Users of the proposed expert system are novice poster designers while the experts are senior and professional poster designers. Development of R-ES is started by defining type of poster to be designed. Based on professional poster designer’s experiences, 5 types of poster have been proposed, which are advertising, information, movie, event and political poster. A knowledge-based system consists of IF-THEN rules have been developed by the experts to determine poster design concept that are colour combination, poster size, font type and size, expert note, and poster sample. Result of this study is an online expert system for conceptualisation of poster design that could be widely used by novice poster designers without constrained by space and time.

On-The-Fly Syntheziser Programming with Fuzzy Rule Learning.

This manuscript explores fuzzy rule learning for sound synthesizer programming within the performative practice known as live coding. In this practice, sound synthesis algorithms are programmed in real time by means of source code. To facilitate this, one possibility is to automatically create variations out of a few synthesizer presets. However, the need for real-time feedback makes existent synthesizer programmers unfeasible to use. In addition, sometimes presets are created mid-performance and as such no benchmarks exist. Inductive rule learning has shown to be effective for creating real-time variations in such a scenario. However, logical IF-THEN rules do not cover the whole feature space. Here, we present an algorithm that extends IF-THEN rules to hyperrectangles, which are used as the cores of membership functions to create a map of the input space. To generalize the rules, the contradictions are solved by a maximum volume heuristics. The user controls the novelty-consistency balance with respect to the input data using the algorithm parameters. The algorithm was evaluated in live performances and by cross-validation using extrinsic-benchmarks and a dataset collected during user tests. The model’s accuracy achieves state-of-the-art results. This, together with the positive criticism received from live coders that tested our methodology, suggests that this is a promising approach.

An approximate design of the prescribed performance control for uncertain discrete-time nonlinear strict-feedback systems

This paper presents an approximate prescribed performance control for a class of uncertain discrete-time nonlinear strict-feedback systems with full state constraints. The observation of the states is taken with a set of independent random measurement noises. The approximate prescribed performance control is proposed as follows. In the tracking error equations on the adaptive fuzzy backstepping control, the future virtual controls are replaced as the current virtual controls to obtain the actual control in a simple structure. The nonlinear uncertainties included in the systems are approximated as the fuzzy logic systems, and the number of the fuzzy IF–THEN rules is reduced based on the simplified extended single input rule modules. The estimates for the un-measurable states and the adjustable parameters are obtained by using the proposed approximate estimator. The estimation errors are proved to be uniformly ultimately bounded. The effectiveness of the proposed approach is indicated by the simulation experiment of a simple numerical system.

SISTEM PAKAR DIAGNOSA KERUSAKAN MOTOR YAMAHA NMAX MENGGUNAKAN METODE FORWARD CHAINING

The recruitment of new mechanics at Mataram Sakti is no longer through the training process at the head office, but new mechanics are placed at the dealership accompanied by the chief mechanic as a supervisor, with the aim of providing training to new mechanics in order to be able to service or periodically repair Yamaha products especially the latest motorbikes namely Yamaha NMAX, because of the flurry sometimes the mechanical head is not in place so that when the mechanic is experiencing problems it cannot directly ask the mechanical head causing the handling of repairs to be less effective and efficient.
 One way to overcome this is to create a web-based expert system application with a forward chaining method so that the chief mechanic can transfer the knowledge he has into the computer. Forward chaining method is a search technique that starts with known facts and then matches these facts with the IF part of the IF-Then rules, so that conclusions can be drawn. This expert system was built using supporting software including, Macromedia Dreamweaver MX, PHP script language, MySQL database and WAMP server.
 The expert system for diagnosing damage to Yamaha NMAX motorcycles using the forward chaining method can be used as a new mechanical learning media in diagnosing damage to NMAX motorcycles and as a means of chief mechanics transferring their knowledge.

Analysis of Air Pollution Levels in DKI Jakarta Province Using the Mamdani Fuzzy Inference System Method

This study aims to measure the level of air pollution determined by pollutant gases contained in the air. Pollutants that measure air pollution are PM10 (Special Material), SO2 (Sulfur), NO2 (Nitrogen Oxide), CO (Carbon Monoxide, O3 (Ozone), and NO2 (Nitrogen Oxide), which are related to vehicle use and, according to the choice this pollutant threshold, we will discuss the level of air pollution with the fuzzy mamdani inference method. The results of the pollutant threshold study will then be applied to the rules / rules that are applied using the if-then rules and then the input variables are arranged using weighted averages, variable averages weighted will be determined higher into three levels: low, medium and high.Keywords Decision Tree, Feature Selection, Optimization of Lecturer Assistant Performance, Particle Swarm Optimization.

Spare Parts Management for the Repair of Machine Tools Using Fuzzy Logic Approach. (Dept. M. ( Production ) )

Spare parts inventories assist maintenance staff to keep equipment in operating conditions. Thus the level of spares stocked has a direct bearing on machine availability. One of the causes of downtime equipment in the repair process is the lack of necessary spare parts at the time of repair and maintenance actions. The minimization of the spare parts storage cost in enterprises is very important. The models of this theory are built according to the classical scheme of mathematical programming. Construction of such models requires definite assumptions, for example, of orders flows, time distribution laws and others. On the other hand, experienced managers very often make effective administrative decisions on the common sense and practical reasoning level. Therefore, the approach based on fuzzy logic can be considered as a good alternative to the classical inventory control models. In this paper, a fuzzy logic approach is introduced. This approach requires neither complex mathematical models construction no search of optimal solutions on the base of such models. It is based on simple comparison of the demand for the stock of the given brand at the actual time moment with the quantity of the stock available in the warehouse. Depending upon it inventory action is formed consisting in increasing or decreasing corresponding stocks. Expert decisions are considered for developing the fuzzy models, and the approach is based on method of nonlinear dependencies identifications by fuzzy knowledge. The linguistic variables are considered for the membership functions. Simple IF-Then rules are used with expert advices.

A Fuzzy Logic-based Control System for Microwave Ovens

Conventional microwave ovens rely on users for their cooking time. In other words, the user must set the oven’s cooking time manually. This paper aims to design a fuzzy logic-based controller to resolve the above-mentioned issue by determining the cooking time of the microwave oven automatically. The time determined depends on the quantity and type of food. During the fuzzy logic process, we used the Mamdani fuzzy model. This model involves determining the crisp input, fuzzification, rule evaluation, and defuzzification, to obtain the crisp output result. Input real variables used were the type of food and quantity of food, whereas the output variable used was cooking time. A fuzzy logic toolbox on MATLAB software was used to design and simulate the whole system. Considering the IF-THEN rules and functions, we used the value of food as 50, and the type of food as 50 and we obtained the cooking time as 25 minutes. The result showed that Fuzzy models are good at determining cooking time in Microwave ovens and that their cooking time depends on the inputs. Using fuzzy logic in microwave ovens helps to maintain food quality, saves users’ time, and controls the energy used by the oven.

A hyperbox classifier model for identifying secure carbon dioxide reservoirs

Carbon management technologies such as carbon dioxide capture and storage and direct air capture systems will be needed to mitigate climate change in the coming decades. Both of these technologies will depend on the availability of secure geological storage sites that can permanently hold carbon dioxide with minimal risk of leakage. Machine learning tools that can characterize candidate storage sites based on geological data can aid decision-makers in planning carbon management networks. In this work, a mixed integer linear programming model is developed to generate a binary hyperbox classifier for determining the integrity of a candidate storage site. The model is calibrated and validated using literature data on natural carbon dioxide reservoirs, resulting in a set of IF-THEN rules that are readily interpreted by decision-makers. The approach developed here also includes rule simplification features and the capability to account for statistical Type I (false positive) and Type II (false negative) errors. Different sets of rules can be generated using the model based on user-defined number of hyperboxes. The best set of rules can be selected based on a combination of its performance with the validation data and consistency with expert knowledge. Using the case study for identifying secure CO2 reservoirs, the set of rules which resulted in zero false positives using the validation data was generated using three hyperboxes. However, an alternative set of rules which falsely predicted two out of three insecure sites as positive provides simpler rules indicating CO2 density and reservoir depth as the most important criteria.

Guideline-Based Decision Support System for Nursing Homes: A Case Study with the Management of Malnutrition.

Nursing home (NH) residents are known to be at risk of preventable adverse events due to inadequate monitoring or failure to provide necessary treatments. Missed care has been partially explained by nurses' lack of knowledge. We describe a guideline-based decision support system for the management of malnutrition in NHs. Three steps are distinguished: screening, therapeutic management, and follow-up. Clinical practice guidelines have been modeled as decision trees and formalized as IF-THEN rules to be triggered by electronic health records data (e.g., weight, albuminemia). We propose a visualization of recommendations as a dashboard of gauges displaying both current and previous levels of malnutrition to inform on the effect of therapeutic management and facilitate a correct follow-up.

A Path Toward Explainable AI and Autonomous Adaptive Intelligence: Deep Learning, Adaptive Resonance, and Models of Perception, Emotion, and Action.

Biological neural network models whereby brains make minds help to understand autonomous adaptive intelligence. This article summarizes why the dynamics and emergent properties of such models for perception, cognition, emotion, and action are explainable, and thus amenable to being confidently implemented in large-scale applications. Key to their explainability is how these models combine fast activations, or short-term memory (STM) traces, and learned weights, or long-term memory (LTM) traces. Visual and auditory perceptual models have explainable conscious STM representations of visual surfaces and auditory streams in surface-shroud resonances and stream-shroud resonances, respectively. Deep Learning is often used to classify data. However, Deep Learning can experience catastrophic forgetting: At any stage of learning, an unpredictable part of its memory can collapse. Even if it makes some accurate classifications, they are not explainable and thus cannot be used with confidence. Deep Learning shares these problems with the back propagation algorithm, whose computational problems due to non-local weight transport during mismatch learning were described in the 1980s. Deep Learning became popular after very fast computers and huge online databases became available that enabled new applications despite these problems. Adaptive Resonance Theory, or ART, algorithms overcome the computational problems of back propagation and Deep Learning. ART is a self-organizing production system that incrementally learns, using arbitrary combinations of unsupervised and supervised learning and only locally computable quantities, to rapidly classify large non-stationary databases without experiencing catastrophic forgetting. ART classifications and predictions are explainable using the attended critical feature patterns in STM on which they build. The LTM adaptive weights of the fuzzy ARTMAP algorithm induce fuzzy IF-THEN rules that explain what feature combinations predict successful outcomes. ART has been successfully used in multiple large-scale real world applications, including remote sensing, medical database prediction, and social media data clustering. Also explainable are the MOTIVATOR model of reinforcement learning and cognitive-emotional interactions, and the VITE, DIRECT, DIVA, and SOVEREIGN models for reaching, speech production, spatial navigation, and autonomous adaptive intelligence. These biological models exemplify complementary computing, and use local laws for match learning and mismatch learning that avoid the problems of Deep Learning.