Recent Applications of Explainable AI (XAI): A Systematic Literature Review

This systematic literature review employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to investigate recent applications of explainable AI (XAI) over the past three years. From an initial pool of 664 articles identified through the Web of Science database, 512 peer-reviewed journal articles met the inclusion criteria—namely, being recent, high-quality XAI application articles published in English—and were analyzed in detail. Both qualitative and quantitative statistical techniques were used to analyze the identified articles: qualitatively by summarizing the characteristics of the included studies based on predefined codes, and quantitatively through statistical analysis of the data. These articles were categorized according to their application domains, techniques, and evaluation methods. Health-related applications were particularly prevalent, with a strong focus on cancer diagnosis, COVID-19 management, and medical imaging. Other significant areas of application included environmental and agricultural management, industrial optimization, cybersecurity, finance, transportation, and entertainment. Additionally, emerging applications in law, education, and social care highlight XAI’s expanding impact. The review reveals a predominant use of local explanation methods, particularly SHAP and LIME, with SHAP being favored for its stability and mathematical guarantees. However, a critical gap in the evaluation of XAI results is identified, as most studies rely on anecdotal evidence or expert opinion rather than robust quantitative metrics. This underscores the urgent need for standardized evaluation frameworks to ensure the reliability and effectiveness of XAI applications. Future research should focus on developing comprehensive evaluation standards and improving the interpretability and stability of explanations. These advancements are essential for addressing the diverse demands of various application domains while ensuring trust and transparency in AI systems.

Implementation of a hybrid neural network control technique to a cascaded MLI based SAPF

This paper presents a naïve back propagation (NBP) based i cos ∅ technique implemented to a cascaded multilevel inverter (MLI) based shunt active power filter (SAPF). The recommended control algorithm is applied to extract the fundamental component of load current and to decide the compensating current reference for harmonic elimination. The performance of the SAPF using the proposed NBP-based i cos ∅ technique is compared with another two classical control techniques, such as,i d - i q technique and i cos ∅ technique. The accuracy of the proposed control technique depends on the tuned estimation of active and reactive weights. The performance study of the proposed SAPF with the proposed control technique is investigated under non-linear conditions, with balanced and unbalanced loading conditions. The results reveal that the recommended SAPF is efficient enough to reduce the harmonics from the source current with smooth variation in DC link voltage. The effectiveness of the proposed method is validated by simulation using MATLAB Simulink, and the real-time results are also validated by the experimental setup.

Mapping the Bibliometrics Landscape of AI in Medicine: Methodological Study

BACKGROUND

Artificial intelligence (AI), conceived in the 1950s, has permeated numerous industries, intensifying in tandem with advancements in computing power. Despite the widespread adoption of AI, its integration into medicine trails other sectors. However, medical AI research has experienced substantial growth, attracting considerable attention from researchers and practitioners.

OBJECTIVE

In the absence of an existing framework, this study aims to outline the current landscape of medical AI research and provide insights into its future developments by examining all AI-related studies within PubMed over the past 2 decades. We also propose potential data acquisition and analysis methods, developed using Python (version 3.11) and to be executed in Spyder IDE (version 5.4.3), for future analogous research.

METHODS

Our dual-pronged approach involved (1) retrieving publication metadata related to AI from PubMed (spanning 2000-2022) via Python, including titles, abstracts, authors, journals, country, and publishing years, followed by keyword frequency analysis and (2) classifying relevant topics using latent Dirichlet allocation, an unsupervised machine learning approach, and defining the research scope of AI in medicine. In the absence of a universal medical AI taxonomy, we used an AI dictionary based on the European Commission Joint Research Centre AI Watch report, which emphasizes 8 domains: reasoning, planning, learning, perception, communication, integration and interaction, service, and AI ethics and philosophy.

RESULTS

From 2000 to 2022, a comprehensive analysis of 307,701 AI-related publications from PubMed highlighted a 36-fold increase. The United States emerged as a clear frontrunner, producing 68,502 of these articles. Despite its substantial contribution in terms of volume, China lagged in terms of citation impact. Diving into specific AI domains, as the Joint Research Centre AI Watch report categorized, the learning domain emerged dominant. Our classification analysis meticulously traced the nuanced research trajectories across each domain, revealing the multifaceted and evolving nature of AI's application in the realm of medicine.

CONCLUSIONS

The research topics have evolved as the volume of AI studies increases annually. Machine learning remains central to medical AI research, with deep learning expected to maintain its fundamental role. Empowered by predictive algorithms, pattern recognition, and imaging analysis capabilities, the future of AI research in medicine is anticipated to concentrate on medical diagnosis, robotic intervention, and disease management. Our topic modeling outcomes provide a clear insight into the focus of AI research in medicine over the past decades and lay the groundwork for predicting future directions. The domains that have attracted considerable research attention, primarily the learning domain, will continue to shape the trajectory of AI in medicine. Given the observed growing interest, the domain of AI ethics and philosophy also stands out as a prospective area of increased focus.

A Survey on Artificial Intelligence in Pulmonary Imaging

Over the last decade, deep learning (DL) has contributed a paradigm shift in computer vision and image recognition creating widespread opportunities of using artificial intelligence in research as well as industrial applications. DL has been extensively studied in medical imaging applications, including those related to pulmonary diseases. Chronic obstructive pulmonary disease, asthma, lung cancer, pneumonia, and, more recently, COVID-19 are common lung diseases affecting nearly 7.4% of world population. Pulmonary imaging has been widely investigated toward improving our understanding of disease etiologies and early diagnosis and assessment of disease progression and clinical outcomes. DL has been broadly applied to solve various pulmonary image processing challenges including classification, recognition, registration, and segmentation. This paper presents a survey of pulmonary diseases, roles of imaging in translational and clinical pulmonary research, and applications of different DL architectures and methods in pulmonary imaging with emphasis on DL-based segmentation of major pulmonary anatomies such as lung volumes, lung lobes, pulmonary vessels, and airways as well as thoracic musculoskeletal anatomies related to pulmonary diseases.

The role of artificial intelligence in developing a banking risk index: an application of Adaptive Neural Network-Based Fuzzy Inference System (ANFIS)

Banking risk measurement and management remain one of many challenges for managers and policymakers. This study contributes to the banking literature and practice in two ways by (a) proposing a risk ranking index based on the Mahalanobis Distance (MD) between a multidimensional point representing a bank's risk measures and the corresponding critical ratios set by the banking authorities and (b) determining the relative importance of a bank's risk ratios in affecting its financial standing using an Adaptive Neuro-Fuzzy Inference System. In this study, ten financial ratios representing five risk areas were considered, namely: Capital Adequacy, Credit, Liquidity, Earning Quality, and Operational risk. Data from 45 Gulf banks for the period 2016-2020 was used to develop the model. Our findings indicate that a bank is in a sound risk position at the 99%, 95%, and 90% confidence level if its Mahalanobis distance exceeds 4.82, 4.28, and 4.0, respectively. The maximum distance computed for the banks in this study was 9.31; only five out of the forty-five banks were below the 4.82 and one below the 4.28 and 4.0 thresholds at 3.96. Sensitivity analysis of the risks indicated that the Net Interest Margin is the most significant factor in explaining variations in a bank's risk position, followed by Capital Adequacy Ratio, Common Equity Tier1, and Tier1 Equity in order. The remaining financial ratios: Non-Performing Loans, Equity Leverage, Cost Income Ratio, Loans to Total Assets, and Loans to Deposits have the least influence in the order given; the Provisional Loans Ratio appears to have no influence.

Overall mortality risk analysis for rectal cancer using deep learning-based fuzzy systems

Colorectal cancer is a leading cause of cancer mortality worldwide, with an increasing incidence rate in developing countries. Integration of genetic information with cancer therapy guidance has shown promise in cancer treatment, indicating its potential as an essential tool in translation oncology. However, the high-throughput analysis and variability of genomic data poses a major challenge to conventional analytic approaches. In this study, we propose an advanced analytic approach, named "Fuzzy-based RNNCoxPH," incorporated fuzzy logic, recurrent neural networks (RNNs), and Cox proportional hazards regression (CoxPH) for detecting missense variants associated with high-risk of all-cause mortality in rectum adenocarcinoma. The test data set was downloaded from "Rectum adenocarcinoma, TCGA-READ" the Genomic Data Commons (GDC) portal. In this study, four model-based risk score models were derived using RNN, CoxPH, RNNCoxPH_Addition, and RNNCoxPH_{Multiplication}. The RNNCoxPH_Addition and RNNCoxPH_{Multiplication} models were obtained as the sum and product of the RNN risk degree matrix and the CoxPH risk degree matrix, respectively. Moreover, the fuzzy logic system was used to calculate the survival risk values of missense variants and classified their membership grade to improve the identification of high-risk gene variation locations associated with cancer mortality. The four models were integrated to develop an advanced risk estimation model. There were 20 028 variants associated with survival status, amongst 17 638 variants were associated with survival and 2390 variants associated with mortality. The proposed Fuzzy-based RNNCoxPH model obtained a balanced accuracy of 93.7%, which was significantly higher than that of the other four test methods. In particular, the CoxPH model is commonly used in medical researches and the XGBoost model is famous for its high accuracy in machine learning. The results suggest that the Fuzzy-based RNNCoxPH model exhibits a higher efficacy in identifying and classifying the missense variants related to mortality risk in rectum adenocarcinoma.

Dynamically Generated Hierarchical Neural Networks Designed With the Aid of Multiple Support Vector Regressors and PNN Architecture With Probabilistic Selection

The two issues on dynamically generated hierarchical neural networks such as the sort of basic neurons and how to compose a layer are considered in this article. On the first issue, a variant version of the least-square support vector regression (SVR) is chosen as a basic neuron. Support vector machine (SVM) is a representative classifier which usually shows good classification performance. Along with the SVMs, SVR was introduced to deal with the regression problem. Especially, least-square SVR has the advantages of high learning speed due to the substitution of the inequality constraints by the equality constraint in the formulation of the optimization problem. Based on the least-square SVR, the multiple least-square (MLS) SVR, which is a type of a linear combination of least-square SVRs with fuzzy clustering, is proposed to improve the modeling performance. In addition, a hierarchical neural network, where the MLS SVR is utilized as the generic node instead of the conventional polynomial, is developed. The key issues of hierarchical neural networks, which are generated dynamically layer by layer, are discussed on how to retain the diversity of the nodes located at the same layer according to the increase of the layer. In order to maintain the diversity of the nodes, various selection methods such as truncation selection and roulette wheel selection (RWS) to choose the nodes among candidate nodes are proposed. In addition, in order to reduce the computational overhead to determine all candidates which exhibit all compositions of the input variables, a new implementation method is proposed. From the viewpoint of the diversity of the selected nodes and the computational aspects, it is shown that the proposed method is preferred over the conventional design methodology.

Performance Analysis of Rough Set–Based Hybrid Classification Systems in the Case of Missing Values

The paper presents a performance analysis of a selected few rough set–based classification systems. They are hybrid solutions designed to process information with missing values. Rough set-–based classification systems combine various classification methods, such as support vector machines, k–nearest neighbour, fuzzy systems, and neural networks with the rough set theory. When all input values take the form of real numbers, and they are available, the structure of the classifier returns to a non–rough set version. The performance of the four systems has been analysed based on the classification results obtained for benchmark databases downloaded from the machine learning repository of the University of California at Irvine.

Multi-gene genetic programming to building up fuzzy rule-base in Neo-Fuzzy-Neuron networks

This paper introduces a new approach to build the rule-base on Neo-Fuzzy-Neuron (NFN) Networks. The NFN is a Neuro-Fuzzy network composed by a set of n decoupled zero-order Takagi-Sugeno models, one for each input variable, each one containing m rules. Employing Multi-Gene Genetic Programming (MG-GP) to create and adjust Gaussian membership functions and a Gradient-based method to update the network parameters, the proposed model is dubbed NFN-MG-GP. In the proposed model, each individual of MG-GP represents a complete rule-base of NFN. The rule-base is adjusted by genetic operators (Crossover, Reproduction, Mutation), and the consequent parameters are updated by a predetermined number of Gradient method epochs, every generation. The algorithm uses Elitism to ensure that the best rule-base is not lost between generations. The performance of the NFN-MG-GP is evaluated using instances of time series forecasting and non-linear system identification problems. Computational experiments and comparisons against state-of-the-art alternative models show that the proposed algorithms are efficient and competitive. Furthermore, experimental results show that it is possible to obtain models with good accuracy applying Multi-Gene Genetic Programming to construct the rule-base on NFN Networks.

Fuzzy Classification Methods Based Diagnosis of Parkinson's disease from Speech Test Cases

BACKGROUND

Together with the Alzheimer's disease, Parkinson's disease is considered as one of the two serious known neurodegenerative diseases. Physicians find it hard to predict whether a given patient has already developed or is expected to develop the Parkinson's disease in the future. To overcome this difficulty, it is possible to develop a computing model, which analyzes the data related to a given patient and predicts with acceptable accuracy when he/she is anticipated to develop the Parkinson's disease.

OBJECTIVES

This paper contributes an attractive prediction framework based on some machine learning approaches for distinguishing people with Parkinsonism from healthy individuals.

METHODS

Several fuzzy classifiers such as Inductive Fuzzy Classifier, Fuzzy Rough Classifier and two types of neuro-fuzzy classifiers have been employed.

RESULTS

The fuzzy classifiers utilized in this study have been tested using the "Parkinson Speech Dataset with Multiple Types of Sound Recordings Data Set" of 40 subjects available on the UCI repository.

CONCLUSION

The results achieved show that FURIA, MLP- Bagging - SGD, genfis2 and scg1 performed the best among the fuzzy rough, WEKA, adaptive neuro-fuzzy and neuro-fuzzy classifiers, respectively. The worst performance belongs to nearest neighborhood, IBK, genfis3 and scg3 among the formerly mentioned classifiers. The results reported in this paper are better in comparison to the results reported in Sakar et al., where the same dataset was used, with utilization of different classifiers. This demonstrates the applicability and effectiveness of the fuzzy classifiers used in this study as compared to the non-fuzzy classifiers used by Sakar et al.

One-Dimensional Convolutional Neural Networks with Feature Selection for Highly Concise Rule Extraction from Credit Scoring Datasets with Heterogeneous Attributes

Convolution neural networks (CNNs) have proven effectiveness, but they are not applicable to all datasets, such as those with heterogeneous attributes, which are often used in the finance and banking industries. Such datasets are difficult to classify, and to date, existing high-accuracy classifiers and rule-extraction methods have not been able to achieve sufficiently high classification accuracies or concise classification rules. This study aims to provide a new approach for achieving transparency and conciseness in credit scoring datasets with heterogeneous attributes by using a one-dimensional (1D) fully-connected layer first CNN combined with the Recursive-Rule Extraction (Re-RX) algorithm with a J48graft decision tree (hereafter 1D FCLF-CNN). Based on a comparison between the proposed 1D FCLF-CNN and existing rule extraction methods, our architecture enabled the extraction of the most concise rules (6.2) and achieved the best accuracy (73.10%), i.e., the highest interpretability–priority rule extraction. These results suggest that the 1D FCLF-CNN with Re-RX with J48graft is very effective for extracting highly concise rules for heterogeneous credit scoring datasets. Although it does not completely overcome the accuracy–interpretability dilemma for deep learning, it does appear to resolve this issue for credit scoring datasets with heterogeneous attributes, and thus, could lead to a new era in the financial industry.

Utilizing an Adaptive Neuro-Fuzzy Inference System (ANFIS) for Overcrowding Level Risk Assessment in Railway Stations

The railway network plays a significant role (both economically and socially) in assisting the reduction of urban traffic congestion. It also accelerates the decarbonization in cities, societies and built environments. To ensure the safe and secure operation of stations and capture the real-time risk status, it is imperative to consider a dynamic and smart method for managing risk factors in stations. In this research, a framework to develop an intelligent system for managing risk is suggested. The adaptive neuro-fuzzy inference system (ANFIS) is proposed as a powerful, intelligently selected model to improve risk management and manage uncertainties in risk variables. The objective of this study is twofold. First, we review current methods applied to predict the risk level in the flow. Second, we develop smart risk assessment and management measures (or indicators) to improve our understanding of the safety of railway stations in real-time. Two parameters are selected as input for the risk level relating to overcrowding: the transfer efficiency and retention rate of the platform. This study is the world’s first to establish the hybrid artificial intelligence (AI) model, which has the potency to manage risk uncertainties and learns through artificial neural networks (ANNs) by integrated training processes. The prediction result shows very high accuracy in predicting the risk level performance, and proves the AI model capabilities to learn, to make predictions, and to capture risk level values in real time. Such risk information is extremely critical for decision making processes in managing safety and risks, especially when uncertain disruptions incur (e.g., COVID-19, disasters, etc.). The novel insights stemmed from this study will lead to more effective and efficient risk management for single and clustered railway station facilities towards safer, smarter, and more resilient transportation systems.

Predicting River Flow Using an AI-Based Sequential Adaptive Neuro-Fuzzy Inference System

Artificial intelligence (AI) techniques have been successfully adopted in predictive modeling to capture the nonlinearity of natural systems. The high seasonal variability of rivers in cold weather regions poses a challenge to river flow forecasting, which tends to be complex and data demanding. This study proposes a novel technique to forecast flows that use a single-input sequential adaptive neuro-fuzzy inference system (ANFIS) along the Athabasca River in Alberta, Canada. After estimating the optimal lead time between four hydrometric stations, gauging data measured near the source were used to predict river flow near the mouth, over approximately 1000 km. The performance of this technique was compared to nonsequential and multi-input ANFISs, which use gauging data measured at each of the four hydrometric stations. The results show that a sequential ANFIS can accurately predict river flow (r2 = 0.99, Nash–Sutcliffe = 0.98) with a longer lead time (6 days) by using a single input, compared to nonsequential and multi-input ANFIS (2 days). This method provides accurate predictions over large distances, allowing for flow forecasts over longer periods of time. Therefore, governmental agencies and community planners could utilize this technique to improve flood prevention and planning, operations, maintenance, and the administration of water resource systems.

Controlling wheeled mobile robot considering the effects of uncertainty with neuro-fuzzy cognitive map

In this paper, we present neuro-fuzzy cognitive map (NFCM) to control a non-holonomic wheeled mobile robot, for both the kinematic control and the dynamic control. For this purpose, the rules for updating the parameters of NFCM used in online training have been extracted. Also, the convergence of the presented approach has been confirmed by means of Lyapunov method. To evaluate the strength and robustness of the proposed model, it has been tested in tracking different circular and square paths. Experimental results indicate that despite the presence of disturbances, the changes of system parameters, and the existence of non-holonomic constraints, our robot has been able to follow challenging paths (e.g. square-shape trajectories) successfully.

Fuzzy Broad Learning System: A Novel Neuro-Fuzzy Model for Regression and Classification

A novel neuro-fuzzy model named fuzzy broad learning system (BLS) is proposed by merging the Takagi-Sugeno (TS) fuzzy system into BLS. The fuzzy BLS replaces the feature nodes of BLS with a group of TS fuzzy subsystems, and the input data are processed by each of them. Instead of aggregating the outputs of fuzzy rules produced by every fuzzy subsystem into one value immediately, all of them are sent to the enhancement layer for further nonlinear transformation to preserve the characteristic of inputs. The defuzzification outputs of all fuzzy subsystem and the outputs of enhancement layer are combined together to obtain the model output. The k -means method is employed to determine the centers of Gaussian membership functions in antecedent part and the number of fuzzy rules. The parameters that need to be calculated in a fuzzy BLS are the weights connecting the outputs of enhancement layer to model output and the randomly initialized coefficients of polynomials in consequent part in fuzzy subsystems, which can be calculated analytically. Therefore, fuzzy BLS retains the fast computational nature of BLS. The proposed fuzzy BLS is evaluated by some popular benchmarks for regression and classification, and compared with some state-of-the-art nonfuzzy and neuro-fuzzy approaches. The results indicate that fuzzy BLS outperforms other models involved. Moreover, fuzzy BLS shows advantages over neuro-fuzzy models regarding to the number of fuzzy rules and training time, which can ease the problem of rule explosion to some extent.

User Centered Neuro-Fuzzy Energy Management Through Semantic-Based Optimization

This paper presents a cloud-based building energy management system, underpinned by semantic middleware, that integrates an enhanced sensor network with advanced analytics, accessible through an intuitive Web-based user interface. The proposed solution is described in terms of its three key layers: 1) user interface; 2) intelligence; and 3) interoperability. The system's intelligence is derived from simulation-based optimized rules, historical sensor data mining, and a fuzzy reasoner. The solution enables interoperability through a semantic knowledge base, which also contributes intelligence through reasoning and inference abilities, and which are enhanced through intelligent rules. Finally, building energy performance monitoring is delivered alongside optimized rule suggestions and a negotiation process in a 3-D Web-based interface using WebGL. The solution has been validated in a real pilot building to illustrate the strength of the approach, where it has shown over 25% energy savings. The relevance of this paper in the field is discussed, and it is argued that the proposed solution is mature enough for testing across further buildings.

The Right Direction Needed to Develop White-Box Deep Learning in Radiology, Pathology, and Ophthalmology: A Short Review

The popularity of deep learning (DL) in the machine learning community has been dramatically increasing since 2012. The theoretical foundations of DL are well-rooted in the classical neural network (NN). Rule extraction is not a new concept, but was originally devised for a shallow NN. For about the past 30 years, extensive efforts have been made by many researchers to resolve the "black box" problem of trained shallow NNs using rule extraction technology. A rule extraction technology that is well-balanced between accuracy and interpretability has recently been proposed for shallow NNs as a promising means to address this black box problem. Recently, we have been confronting a "new black box" problem caused by highly complex deep NNs (DNNs) generated by DL. In this paper, we first review four rule extraction approaches to resolve the black box problem of DNNs trained by DL in computer vision. Next, we discuss the fundamental limitations and criticisms of current DL approaches in radiology, pathology, and ophthalmology from the black box point of view. We also review the conversion methods from DNNs to decision trees and point out their limitations. Furthermore, we describe a transparent approach for resolving the black box problem of DNNs trained by a deep belief network. Finally, we provide a brief description to realize the transparency of DNNs generated by a convolutional NN and discuss a practical way to realize the transparency of DL in radiology, pathology, and ophthalmology.

Review of Soft Computing Models in Design and Control of Rotating Electrical Machines

Rotating electrical machines are electromechanical energy converters with a fundamental impact on the production and conversion of energy. Novelty and advancement in the control and high-performance design of these machines are of interest in energy management. Soft computing methods are known as the essential tools that significantly improve the performance of rotating electrical machines in both aspects of control and design. From this perspective, a wide range of energy conversion systems such as generators, high-performance electric engines, and electric vehicles, are highly reliant on the advancement of soft computing techniques used in rotating electrical machines. This article presents the-state-of-the-art of soft computing techniques and their applications, which have greatly influenced the progression of this significant realm of energy. Through a novel taxonomy of systems and applications, the most critical advancements in the field are reviewed for providing an insight into the future of control and design of rotating electrical machines.

Reinforcement Learning-Based Differential Evolution With Cooperative Coevolution for a Compensatory Neuro-Fuzzy Controller

This paper presents the integration of reinforcement learning-based differential evolution (DE) with the cooperative coevolution (R-CCDE) method in a compensatory neuro-fuzzy controller (CNFC). The CNFC model employs compensatory fuzzy operations, which increase the adaptability and effectiveness of the controller. The R-CCDE method was used to determine an adequate control policy for nonlinear system problems. The evolution of a population involved the use of DE with cooperative coevolution to adjust CNFC parameters, and the fitness function of the R-CCDE method is used by a reinforcement signal to determine the controller that can be used to solve the control problem. This paper identified the best performing controller to solve nonlinear system problems. The simulation results of the proposed R-CCDE method were compared with those of various DE methods and the performance of the proposed R-CCDE method was superior to that of the other methods.

Extracting T-S Fuzzy Models Using the Cuckoo Search Algorithm

A new method called cuckoo search (CS) is used to extract and learn the Takagi–Sugeno (T–S) fuzzy model. In the proposed method, the particle or cuckoo of CS is formed by the structure of rules in terms of number and selected rules, the antecedent, and consequent parameters of the T–S fuzzy model. These parameters are learned simultaneously. The optimized T–S fuzzy model is validated by using three examples: the first a nonlinear plant modelling problem, the second a Box–Jenkins nonlinear system identification problem, and the third identification of nonlinear system, comparing the obtained results with other existing results of other methods. The proposed CS method gives an optimal T–S fuzzy model with fewer numbers of rules.

Performance Analysis of Conjugate Gradient Algorithms Applied to the Neuro-Fuzzy Feedback Linearization-Based Adaptive Control Paradigm for Multiple HVDC Links in AC/DC Power System

The existing literature predominantly concentrates on the utilization of the gradient descent algorithm for control systems’ design in power systems for stability enhancement. In this paper, various flavors of the Conjugate Gradient (CG) algorithm have been employed to design the online neuro-fuzzy linearization-based adaptive control strategy for Line Commutated Converters’ (LCC) High Voltage Direct Current (HVDC) links embedded in a multi-machine test power system. The conjugate gradient algorithms are evaluated based on the damping of electro-mechanical oscillatory modes using MATLAB/Simulink. The results validate that all of the conjugate gradient algorithms have outperformed the gradient descent optimization scheme and other conventional and non-conventional control schemes.

Rule Extraction from Training Data Using Neural Network

Data Mining is a powerful technology to help organization to concentrate on most important data by extracting useful information from large database. One of the most commonly used techniques in data mining is Artificial Neural Network due to its high performance in many application domains. Despite many advantages of Artificial Neural Network, one of its main drawbacks is its inherent black box nature which is the main problem of using Artificial Neural Network in data mining. Therefore, this paper proposes a rule extraction algorithm from neural network using classified and misclassified data to convert the black box nature of Artificial Neural Network into a white box. The proposed algorithm is a modification of the existing algorithm, Rule Extraction by Reverse Engineering (RxREN). The proposed algorithm extracts rules from trained neural network for datasets with mixed mode attributes using pedagogical approach. The proposed algorithm uses both classified as well as misclassified data to find out the data ranges of significant attributes in respective classes, which is the innovation of the proposed algorithm. The experimental results clearly show that the performance of the proposed algorithm is superior to existing algorithms.

An Artificial Intelligence Approach for Gears Diagnostics in AUVs

In this paper, an intelligent scheme for detecting incipient defects in spur gears is presented. In fact, the study has been undertaken to determine these defects in a single propeller system of a small-sized unmanned helicopter. It is important to remark that although the study focused on this particular system, the obtained results could be extended to other systems known as AUVs (Autonomous Unmanned Vehicles), where the usage of polymer gears in the vehicle transmission is frequent. Few studies have been carried out on these kinds of gears. In this paper, an experimental platform has been adapted for the study and several samples have been prepared. Moreover, several vibration signals have been measured and their time-frequency characteristics have been taken as inputs to the diagnostic system. In fact, a diagnostic system based on an artificial intelligence strategy has been devised. Furthermore, techniques based on several paradigms of the Artificial Intelligence (Neural Networks, Fuzzy systems and Genetic Algorithms) have been applied altogether in order to design an efficient fault diagnostic system. A hybrid Genetic Neuro-Fuzzy system has been developed, where it is possible, at the final stage of the learning process, to express the fault diagnostic system as a set of fuzzy rules. Several trials have been carried out and satisfactory results have been achieved.

Optimization of the Production of Inactivated Clostridium novyi Type B Vaccine Using Computational Intelligence Techniques

Clostridium novyi causes necrotic hepatitis in sheep and cattle, as well as gas gangrene. The microorganism is strictly anaerobic, fastidious, and difficult to cultivate in industrial scale. C. novyi type B produces alpha and beta toxins, with the alpha toxin being linked to the presence of specific bacteriophages. The main strategy to combat diseases caused by C. novyi is vaccination, employing vaccines produced with toxoids or with toxoids and bacterins. In order to identify culture medium components and concentrations that maximized cell density and alpha toxin production, a neuro-fuzzy algorithm was applied to predict the yields of the fermentation process for production of C. novyi type B, within a global search procedure using the simulated annealing technique. Maximizing cell density and toxin production is a multi-objective optimization problem and could be treated by a Pareto approach. Nevertheless, the approach chosen here was a step-by-step one. The optimum values obtained with this approach were validated in laboratory scale, and the results were used to reload the data matrix for re-parameterization of the neuro-fuzzy model, which was implemented for a final optimization step with regards to the alpha toxin productivity. With this methodology, a threefold increase of alpha toxin could be achieved.