Rule-based Framework Research Articles

Reviewing approaches employed in Arabic chatbots

<p>The field of chatbots has witnessed a remarkable evolution in recent years, marked by a transition from simplistic rule-based structures to sophisticated systems employing advanced natural language processing (NLP) techniques. While most languages benefit from NLP support, the majority of chatbot research and development has been conducted in English, leaving a notable scarcity of comparable works in Arabic. This scarcity is attributed to the myriad challenges posed by the linguistically intricate nature of Arabic, encompassing orthographic variations and diverse dialects. This study systematically reviews articles that represent implementations of Arabic chatbots, revealing a discernible shift from rule-based frameworks to the predominant adoption of machine learning (ML) and deep learning (DL) methods. The results highlight the dynamic trajectory of chatbot technology, with a notable emphasis on the pivotal role of DL, as evidenced by a significant peak in 2023. Looking forward, the study anticipates a more sophisticated future for chatbot development, driven by ongoing advancements in artificial intelligence (AI) and NLP, offering valuable insights into the current state of Arabic chatbot research and laying the foundation for continued exploration in this evolving and dynamic field.</p>

Simultaneous sizing and energy management of multi-energy Virtual Power Plants operating in regulated energy markets

This research analyses the case of a Virtual Power Plant (VPP) in regulated electricity markets, trading energy with the consumers and the grid under a Power Purchase Agreement (PPA). The VPP propagates the deployment of solar PVs while balancing its intermittency with a dispatchable power plant, which is assumed in this research to be a CCHP, supplying cooling, heating, and power. The VPP also integrates energy storage systems for a comprehensive assessment. Traditionally, the VPP concept has not been introduced in regulated markets, but it is widely researched in deregulated markets where VPPs trade energy with the electricity grid for profit maximisation. In regulated markets, a special architecture is proposed for a VPP that mediates between residential compounds and electricity grids for profit maximization and energy demand coverage, thus converting the compound into a power generator with minimum dependence on the grid for its energy demand. In the literature on aggregated energy systems in regulated markets, it is usually overlooked to perform detailed energy modelling and optimisation on an hourly level. Only basic rule-based frameworks for energy management are proposed. In this research, it is initially assumed that since the VPP integrates multi-energy components supplying heating, cooling and electricity, optimization of the output of each component for a common profit maximization, is necessary. However, in VPP-related literature, the capacity of each component, which is a main input for energy modelling, is traditionally assumed and not assessed. Therefore, the research aims to explore how to find the optimal capacity configuration of the residential VPP that achieves optimal profit. The paper analyses an iterative exhaustive search framework, integrating the 2-levels of energy optimisation (hourly profit maximisation objective) and capacities optimisation (Life cycle CAPEX & OPEX minimisation). Compared to baseline cases, where only energy optimisation is performed, and capacities are assumed and not assessed in terms of capital investment, the proposed framework achieved a higher annual profit by 3.1 % and a payback period of 11 years. The results also provide comprehensive 3D charts drawing the relations between the achieved profit against capacities configurations, thus allowing high-level decision-making. The results also prove the hypothesis that hourly energy optimisation should not be performed without investment cost assessment and that targeting the minimization of investment costs will indirectly benefit the achieved profit.

A rule-based framework for capturing geometric characteristics in design: A study of façade analysis for acoustic behaviour in urban space

In urban acoustics, the design of built environment substantially impacts the environmental noise of our everyday lives, as the built environment constantly reflects the sounds of human or non-human actors in its vicinity. The effects produced by these reflected sounds significantly depend on the geometric characteristics of the surrounding building façades. Despite their impact, the façade characteristics are often excluded from urban acoustic simulation models. As a result, sound reflection and scattering that are specifically related to building façades remain largely unexplored in noise control at the urban scale. Inspired by computational design tools used for exploring room acoustics, we investigate how a computational approach enables the analysis of geometric characteristics of façades to simulate urban acoustics during early design processes. This paper introduces a rule-based characterisation framework that enables the representation of geometric façade characteristics and their relationships with acoustic constraints in the form of rules. Our first results showed how these rules allowed for capturing and reconstructing façade geometries based on the given acoustic constraints. We believe that this novel approach empowers designers to describe their initial design ideas in a formalism that can be dynamically adapted to various dimensions, such as urban acoustics, and to reconstruct the form throughout the design process.

Developing a residential occupancy schedule generator based on smart thermostat data

Occupancy patterns play a major role in residential buildings’ energy demand. This role is essential to be represented realistically in urban-scale energy simulations with a focus on matching the supply of renewable energy to demand. However, the lack of large-scale datasets that represent the seasonality and dynamic nature of occupancy, especially within the residential sector limited such analysis. Recently, the fast adoption of smart thermostats, featuring passive infrared sensors for motion detection, in residential buildings has allowed for extracting more representative occupancy information for different applications. To this end, this study introduces an open-source Python package to generate large-scale hourly occupancy profiles for residential buildings based on smart thermostat readings. The package takes advantage of the Donate Your Data (DYD) dataset by Ecobee to develop a rule-based framework that addresses the limitations of relying on motion-detection data to represent the whole-building occupancy. The framework was applied to over 8000 Canadian households as a case study. The generated profiles for these buildings are validated by comparing them with residential occupancy profiles generated from the Canadian Time Use Survey (TUS). The results showed that both profiles were statistically similar with a 3 % difference in the aggregated daily occupied hours. Finally, the diversity of the generated profiles before and after the COVID-19 pandemic is investigated to demonstrate the usefulness of the tool. The results proved the potential of the developed package to generate realistic and diverse occupancy schedules for the residential sector.

An Advanced Explainable Belief Rule-Based Framework to Predict the Energy Consumption of Buildings

The prediction of building energy consumption is beneficial to utility companies, users, and facility managers to reduce energy waste. However, due to various drawbacks of prediction algorithms, such as, non-transparent output, ad hoc explanation by post hoc tools, low accuracy, and the inability to deal with data uncertainties, such prediction has limited applicability in this domain. As a result, domain knowledge-based explainability with high accuracy is critical for making energy predictions trustworthy. Motivated by this, we propose an advanced explainable Belief Rule-Based Expert System (eBRBES) with domain knowledge-based explanations for the accurate prediction of energy consumption. We optimize BRBES’s parameters and structure to improve prediction accuracy while dealing with data uncertainties using its inference engine. To predict energy consumption, we take into account floor area, daylight, indoor occupancy, and building heating method. We also describe how a counterfactual output on energy consumption could have been achieved. Furthermore, we propose a novel Belief Rule-Based adaptive Balance Determination (BRBaBD) algorithm for determining the optimal balance between explainability and accuracy. To validate the proposed eBRBES framework, a case study based on Skellefteå, Sweden, is used. BRBaBD results show that our proposed eBRBES framework outperforms state-of-the-art machine learning algorithms in terms of optimal balance between explainability and accuracy by 85.08%.

Personalized recommendations for learning activities in online environments: a modular rule-based approach

Personalization in online learning environments has been extensively studied at various levels, ranging from adaptive hints during task-solving to recommending whole courses. In this study, we focus on recommending learning activities (sequences of homogeneous tasks). We argue that this is an important yet insufficiently explored area, particularly when considering the requirements of large-scale online learning environments used in practice. To address this gap, we propose a modular rule-based framework for recommendations and thoroughly explain the rationale behind the proposal. We also discuss a specific application of the framework.

An Automated Performance Enhancement Approach for Mobile Applications

In the rapidly evolving landscape of mobile applications, the demand for high-quality, performance-driven software is paramount. However, the swift pace of development often leads to the introduction of code smells—bad programming practices that compromise both code quality and application performance. These code smells, if left unaddressed, can result in increased memory consumption, energy consumption, and CPU utilization, ultimately leading to a suboptimal user experience. This paper presents an automated approach for the detection and refactoring of code smells in Android applications, with a focus on improving performance. The proposed approach involves the development of a plugin integrated with Android Studio, which employs static code analysis to identify code smells. The plugin encompasses a customizable rule-based framework that allows for the detection of various code smells unique to Android development. To validate the approach, a comprehensive experiment is conducted. The experiment assesses the effectiveness of the proposed method in detecting code smells and explores the impact of refactoring on application performance. The results showcase that the proposed plugin successfully detects code smells in various open-source Android applications. Moreover, the integration of refactoring recommendations significantly improves the performance of the applications, as demonstrated through memory, energy, and CPU consumption metrics. Comparison with existing tools reveals that the proposed approach offers superior performance in terms of both code smell detection and refactoring. Additionally, the approach bridges the gap left by some existing tools by identifying previously undetected code smells, such as "string concatenation." The presented method not only enhances code quality but also contributes to the overall performance optimization of Android applications. As mobile applications continue to play an increasingly central role in modern life, the importance of maintaining high-quality code that performs optimally cannot be understated. This work provides a valuable contribution towards achieving these goals, offering developers a powerful tool for ensuring that their applications not only meet but exceed user expectations in terms of quality and performance.

Advancements of SMS Spam Detection: A Comprehensive Survey of NLP and ML Techniques

In the digital age, the ubiquity of text messaging has unfortunately paved the way for SMS phishing, or 'smishing,' a deceptive practice where fraudsters dispatch fraudulent messages to extract sensitive information from unsuspecting recipients. This issue is not trivial. It represents a significant threat to both personal privacy and organizational security, leading to potential data breaches and financial repercussions. Against this backdrop, the imperative for advanced detection strategies is undeniable. This survey leverages a systematic review methodology to assess the effectiveness of Natural Language Processing (NLP) and Machine Learning (ML) techniques in the detection of SMS phishing, also known as smishing. By methodically analyzing research spanning various detection strategies, the study illuminates the evolution from basic rule-based frameworks to sophisticated ML algorithms, enriched with NLP for deep analysis. The findings underscore the superior efficacy of combining ML classifiers with NLP, particularly through the deployment of advanced deep learning models like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), which offer unprecedented accuracy in identifying and thwarting complex smishing attacks.The value of this study lies in its comprehensive synthesis of current methodologies and its contribution to the ongoing enhancement of cybersecurity defenses. It serves as a crucial guide for future research directions, emphasizing the necessity of adopting and innovating cutting-edge NLP and ML techniques to stay ahead of evolving digital threats.

Positional faithfulness and nasal assimilation in English

This article analyzes the process of Nasal Assimilation in English.1 The approach to Nasal Assimilation in a standard rule-based framework can be conducted in two ways: by assuming an underlying alveolar nasal or by employing underspecification. The article contributes to the ongoing debate regarding underspecification in phonology and focuses on employing underspecified representations in Optimality Theory. First, it is argued that in such words as, for instance, somber, Nasal Assimilation is best analyzed in terms of positional faithfulness in the form of prevocalic faithfulness. Second, as the analyses show, positional faithfulness does not provide a workable scenario for all the data, and it is necessary to use underspecification to satisfactorily analyze English words which lack the context for positional faithfulness, for example, swamp. Nevertheless, subsequent evaluations demonstrate that in certain phrases, for instance, sing boys, employing underspecification is not sufficient either, and level distinction is necessary. Therefore, the article also offers an argument in favour of levels in Optimality Theory.

A novel approach to assess and improve syntactic interoperability in data integration

Data integration is essential to enrich a database with external information. One effective approach is to match shared identifiers across diverse databases. However, a lack of syntactic interoperability, which refers to the ability to match data based on their syntax, can pose challenges. In this paper, we present a novel method to evaluate and enhance syntactic interoperability, considering associated costs. First, we introduce the linking index and completeness index as generic measures of fine-grained syntactic interoperability. Second, we analyze the data consistency level of the identifiers using a rule-based framework for data quality assessment. Third, we propose a data integration strategy that strikes a balance between fixing data inconsistencies and the resulting benefits, as measured by the linking and completeness indices. The approach is illustrated through two use cases: bibliographic databases and clinical trial registries. The results demonstrate that standardizing identifiers’ representations can significantly improve syntactic interoperability in certain scenarios while in others, the standardization process does not yield improvements, discouraging, hence integration decisions. By conducting a cost–benefit analysis of improving data interoperability, this analysis enables data integrators to make informed decisions regarding the feasibility and advantages of proceeding with data integration.

Discrete separation of patients’ profiles for chronical obstructive pulmonary disease context-aware healthcare efficient systems

According to the Public Health Agency of Canada (PHAC), the symptoms of chronic obstructive pulmonary disease (COPD) are shortness of breath, coughing, and sputum production. Many studies estimate that COPD will become the third-leading cause of death worldwide by 2030 (WHO,2008). Pervasive healthcare systems cover healthcare issues, including chronic diseases; they help patients to manage their own health information and healthcare services at any time and in any place. We developed a COPD healthcare system based on a combination of the parameters of patients. The main goal is to avoid the severe phases of the disease by monitoring them. This combination of risk factors provides in total 600 profiles from data, with 88.5% accuracy. However, many studies have focused on and shown the issues of the effectiveness and accuracy of these systems. The problem is to i apply a new classification model to detect the severe phases of the disease early. Therefore, Instead of working on COPD parameters, we design and validate a profile-based classification model of patients. This model will facilitate the building of a rule-based framework. In addition, the accuracy of our extended COPD system is improved using the classification and separation of patients’ profiles.

A General Rule-Based Framework for Generating Alternatives for Forest Ecosystem Management Decision Support Systems

Linear programming formulations of forest ecosystem management (FEM) problems proposed in the 1960s have been adapted and improved upon over the years. Generating management alternatives for forest planning is a key step in building these models. Global forests are diverse, and a variety of models have been developed to simulate management alternatives. This paper describes iGen, a forest prescription generator that employs a rule-based system (AI-RBS), an AI technique that is often used for expert systems. iGen was designed with the goal of being able to generate management alternatives for virtually any FEM problem. The prescription generator is not designed for, adapted to, focused on—and ideally not limited to—any specific region, landscape, forest condition, projection method, or yield function. Instead, it aims to maximize generality, enabling it to address a broad range of FEM problems. The goal is that practitioners and researchers who do not have and do not want to develop their own alternative generator can use iGen as a prescription generator for their problem instances. For those who choose to develop their own alternative generators, we hope that the concepts and algorithms we propose in this paper will be useful in designing their own systems. iGen’s flexibility can be attributed to three key features. First, users can define the state variable vector for management units according to the available data, models (production functions), and objectives of their problem instance. Second, users also define the types of interventions that can be applied to each type of management unit and create a rule base describing the conditions under which each intervention can be applied. Finally, users specify the equations of motion that determine how the state vector for each management unit will be updated over time, depending on which, if any, interventions are applied. Other than this basic structure, virtually everything in an iGen problem instance is user-defined. iGen uses these key elements to simulate all possible management prescriptions for each management unit and stores the resulting information in a database that is structured to efficiently store the output data from these simulations and to facilitate the generation of optimization models for ultimately determining the Pareto frontier for a given FEM problem. This article introduces iGen, illustrating its concepts, structure, and algorithms through two FEM example problems with contrasting forest management practices: natural regeneration with shelterwood harvests and plantation/coppice. For data and iGen source programs, visit github.com/SilvanaNobre/iGenPaper.

On semi-automated extraction of causal networks from raw text

A rule-based framework, named SCANER (Semi-automated CAusal Network Extraction from Raw text) is presented. SCANER converts raw text into causal networks using a set of natural language processing rules. The raw textual data that contains useful information for informing future decisions and developing strategies in various critical domains must be converted into useful, understandable models. However, building such models manually from raw text is a labor-intensive and time-consuming process and needs to be automated. The automated extraction of causality from raw text, however, has its own set of challenges due to the linguistic complexity and ambiguity of the texts. It can also be argued that for complicated scenarios and critical domains subject matter experts cannot rely solely on such automatically generated models without sound reasoning to support them. This implies the need for a semi-automated human-in-the-loop approach. This research, therefore, is focused on combining the strengths of both manual and automated approaches and on developing a framework for a rule-based semi-automated approach to generate causal networks from raw text. SCANER is evaluated on three collections of raw text from political, food insecurity, and medical domains using F-Score as the evaluation metric. The ground truth for the causal links is generated after incorporating feedback from a group of three human judges. A comparative analysis with Eidos, an open-source causality extraction system, demonstrates the advantages of SCANER in generating dense and accurate causal networks from the raw text.

Application of optimized convolutional neural network to fixture layout in automotive parts

Fixture layout is a complex task that significantly impacts manufacturing costs and requires the expertise of well-trained engineers. While most research approaches to automating the fixture layout process use optimization or rule-based frameworks, this paper presents a novel approach using supervised learning. The proposed framework replicates the 3-2-1 locating principle to layout fixtures for sheet metal designs. This principle ensures the correct fixing of an object by restricting its degrees of freedom. One main novelty of the proposed framework is the use of topographic maps generated from sheet metal design data as input for a convolutional neural network (CNN). These maps are created by projecting the geometry onto a plane and converting the Z coordinate into gray-scale pixel values. The framework is also novel in its ability to reuse knowledge about fixturing to lay out new workpieces and in its integration with a CAD environment as an add-in. The results of the hyperparameter-tuned CNN for regression show high accuracy and fast convergence, demonstrating the usability of the model for industrial applications. The framework was first tested using automotive b-pillar designs and was found to have high accuracy (≈ 100%) in classifying these designs. The proposed framework offers a promising approach for automating the complex task of fixture layout in sheet metal design.

Electronic health record data quality variability across a multistate clinical research network.

Electronic health record (EHR) data have many quality problems that may affect the outcome of research results and decision support systems. Many methods have been used to evaluate EHR data quality. However, there has yet to be a consensus on the best practice. We used a rule-based approach to assess the variability of EHR data quality across multiple healthcare systems. To quantify data quality concerns across healthcare systems in a PCORnet Clinical Research Network, we used a previously tested rule-based framework tailored to the PCORnet Common Data Model to perform data quality assessment at 13 clinical sites across eight states. Results were compared with the current PCORnet data curation process to explore the differences between both methods. Additional analyses of testosterone therapy prescribing were used to explore clinical care variability and quality. The framework detected discrepancies across sites, revealing evident data quality variability between sites. The detailed requirements encoded the rules captured additional data errors with a specificity that aids in remediation of technical errors compared to the current PCORnet data curation process. Other rules designed to detect logical and clinical inconsistencies may also support clinical care variability and quality programs. Rule-based EHR data quality methods quantify significant discrepancies across all sites. Medication and laboratory sources are causes of data errors.

FRBF: A Fuzzy Rule Based Framework for Heart Disease Diagnosis

Heart disease is also known as cardiovascular disease. It is one of the most dangerousand deadly disease in all over the globe. Cardiovascular disease was deemed as amajor illness in old and middle age, but recent trends shown that now cardiovasculardisease is also a deadly disease in young age group due to irregular habit. However,Angiography is one of the way to diagnose heart disease, but it is very expensive andalso has major side effect. The aim of this research paper is to design a fuzzy rulebased framework to diagnosis of the risk level of the heart disease. Our proposedframework used a Mamdani interface system and used UCI machine repositorydataset for heart disease diagnosis. In this proposed study, we have used 10 Inputattribute and one output attribute with 554 rules. Besides, a comparative table is alsopresented, where proposed methodology is better than other methodology. Accordingto the proposed methodology results, that the performance is highly successful and itis a promising tool for identification of a heart disease patient at an early stage. Wehave achieved accuracy, sensitivity rates of 95.2% and 87.04 respectively, on the UCIdataset.

A low temperature preheating strategy with optimized fuzzy controller for lithium-ion batteries

Electric vehicles (EVs) suffer from significant performance loss under low temperatures due to the limited operating temperature ranges of lithium-ion batteries. Warming up the cells before the operation is recommended by manufacturers to recover effective drive for EVs rapidly. In this paper, an optimized internal pulse preheating strategy is proposed to realize the cold start of vehicles without other ground power sources. First, an electro-thermal model of batteries is established, which can dynamically update based on the current state of charge and temperature of cells. Then the internal preheating pulse currents are obtained by using fuzzy logic control with a fixed frequency. The bidirectional pulse amplitudes are decided by the real-time state of charge and temperature in the rule-based framework. Furthermore, an offline genetic algorithm is used to optimize the fuzzy rules with the updated impedance parameters to reduce energy consumption and preheating time. Experiments are conducted with different battery initial states of charge to evaluate the superiority of the proposed strategy. Results show that the battery can achieve a temperature rise from −10 °C to 10 °C in 603 s though the state of charge is at a low level, with the temperature rise above 2 °C/min. Besides, compared with current preheating strategies, the proposed strategy can at least shorten the preheating time by 15% and save the energy loss by 10%.

The ForEx++ based decision tree ensemble approach for robust detection of Parkinson’s disease

The progressive reduction of dopaminergic neurons in the human brain, especially at the substantia nigra is one of the principal causes of Parkinson’s Disease (PD). Voice alteration is one of the earliest symptoms found in PD patients. Therefore, the impaired PD subjects’ acoustic voice signal plays a crucial role in detecting the presence of Parkinson's. This manuscript presents four distinct decision tree ensemble methods of PD detection on a trailblazing ForEx++ rule-based framework. The Systematically Developed Forest (SysFor) and a Penalizing Attributes Decision Forest (ForestPA) ensemble approaches has been used for PD detection. The proposed detection schemes efficiently identify positive subjects using primary voice signal features, viz., baseline, vocal fold, and time–frequency. A novel feature selection scheme termed Feature Ranking to Feature Selection (FRFS) has also been proposed to combine filter and wrapper strategies. The proposed FRFS scheme encompasses Gel’s normality test to rank and selects outstanding features from baseline, time–frequency, and vocal fold feature groups. The SysFor and ForestPA decision forests underneath the ForEx++ rule-based framework on both FRFS feature ranking and subset selection represents Parkinson’s detection approaches, which expedite a better overall impact on segregating PD from control subjects. It has been observed that the ForestPA decision forest in the ForEx++ framework on FRFS ranked features proved to be a robust Parkinson’s detection scheme. The proposed models deliver the highest accuracy of 94.12% and a lowest mean absolute error of 0.25, resulting in an Area Under Curve (AUC) value of 0.97.

Improved Deep Learning-Based Energy Management Strategy for Battery-Supercapacitor Hybrid Electric Vehicle With Adaptive Velocity Prediction

The uncertainties and disturbances in the actual driving conditions of hybrid electric vehicles (HEVs) complicate the design of energy management strategy (EMS). To achieve better EMS performance for a battery-supercapacitor HEV, this paper proposes an improved and adaptive deep learning-based velocity prediction control EMS that can prolong the battery lifetime through efficient utilization of both the battery and supercapacitor. First, feature engineering techniques are used to extract and increase the key features from the historical driving cycle data of known driving conditions. With the extracted features, an improved long short-term memory (LSTM) velocity predictor was developed to predict future driving cycles for a real-time EMS under an unknown driving condition. Second, a real-time EMS based on the rule-based framework optimized with a neural network is proposed to optimize the power allocation online. Simulation results show that the proposed strategy smoothens battery peak power (i.e. prolongs battery life span) by approximately 26.85% on average and increases supercapacitor participation in the EMS, as evidenced by its increased energy throughput. Furthermore, compared with other EMS approaches, the proposed strategy improved the efficiency by significantly reducing total energy losses by approximately 22.25%. These results validate the reliability and robustness of the proposed strategy.

Detection of Health-Related Events and Behaviours from Wearable Sensor Lifestyle Data Using Symbolic Intelligence: A Proof-of-Concept Application in the Care of Multiple Sclerosis.

In this paper, we demonstrate the potential of a knowledge-driven framework to improve the efficiency and effectiveness of care through remote and intelligent assessment. More specifically, we present a rule-based approach to detect health related problems from wearable lifestyle sensor data that add clinical value to take informed decisions on follow-up and intervention. We use OWL 2 ontologies as the underlying knowledge representation formalism for modelling contextual information and high-level concepts and relations among them. The conceptual model of our framework is defined on top of existing modelling standards, such as SOSA and WADM, promoting the creation of interoperable knowledge graphs. On top of the symbolic knowledge graphs, we define a rule-based framework for infusing expert knowledge in the form of SHACL constraints and rules to recognise patterns, anomalies and situations of interest based on the predefined and stored rules and conditions. A dashboard visualizes both sensor data and detected events to facilitate clinical supervision and decision making. Preliminary results on the performance and scalability are presented, while a focus group of clinicians involved in an exploratory research study revealed their preferences and perspectives to shape future clinical research using the framework.