Computational Intelligence Techniques Research Articles

A multi-source data-driven approach for navigation safety integrating computational intelligence and Bayesian networks

Ships often face various risks when sailing at sea, ranging from harsh natural environments to complex traffic conditions. To reduce the impact of these risks on ships and crews, this paper proposes a navigation risk assessment method that integrates computational intelligence (CI) techniques, such as fuzzy logic, with Bayesian networks (BNs) and utility theory. Firstly, a navigation risk assessment system is established using maritime data and expert knowledge, which evaluates risks from a spatial perspective by considering factors such as safeguard and accident conditions across different regions. Secondly, a fuzzy logic-based numerical and expert data transformation method is proposed to derive the prior probabilities of risk factors in BNs. The weighted fuzzy rule base is used to capture the dependencies among the risk factors. Finally, the probability distribution of navigation risk is determined by combining the prior probability and the dependencies, which are converted into risk index values through utility theory. Taking the grid-based navigation risk assessment of the South China Sea as an example, the effectiveness of this method is verified. The results of the study provide theoretical support for navigation risk assessment based on multi-source data and provide a reference for formulate maritime regulatory policies.

Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques

Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques

Tuning PID Controller for Inverted Pendulum Using Whale Optimization Algorithm

Manual tuning of Proportional-Integral-Derivative (PID) controller is time consuming, tedious and generally lead to poor performance. PID controller is a simple and intuitive feedback-based control mechanism being useful to track set points and to reject disturbances. This paper presents a computational Intelligence (CI) technique of Whale Optimization Algorithm (WOA) for tuning the PID controller parameters for inverted pendulum. The inverted pendulum is a benchmark problem in control system design because of its high level of instability and non-linearity. It can mimic the behaviour of open-loop unstable systems such as robot manipulator and missile launcher. The metaheuristic algorithm achieved rise time (0.0913), settling time (1.57), maximum overshot (7.9%) and steady-state error (0.0294). Simulation results demonstrated that the WOA-optimized PID controller can provide an improved closed-loop performance over the Ziegler- Nichols tuned PID controller Parameters. The computational intelligence approach also has superior features, such as easy implementation, stable convergence characteristic and good computational efficiency over the conventional methods of Ziegler- Nichols.

Advanced Machine Learning for Brain Tumor and Alzheimer’s Disease Detection: A Comprehensive Review of Neuroimaging-based Classification Techniques

Alzheimer's disease with progressive neurodegeneration and brain tumors notably characterized by rapid, not limited cell proliferation poses significant health risks unless timely diagnosed and treated. Tumors have a diverse feature and characteristics, added to subtle changes in the brain whose hallmark is Alzheimer's, making accurate segmentation and classification quite challenging. Indeed, while there have been research in the last decade or so that have proven promising results, challenges still linger on. The present work discusses various approaches for image classification and staging of Alzheimer's disease and brain tumors by exploiting techniques in statistical image processing and computational intelligence. This paper includes discussion on morphology of brain tumors along with neuroimaging changes caused by Alzheimer's disease, existing datasets, data augmentation techniques, and methods for component extraction and classification within the DL, TL, and ML framework. Such specific systems have been given the metrics using the datasets; the descriptions of the implementations, however may vary with the case at hand.

Energy-efficient and reliable dual closed-loop DC control system for intelligent electric vehicle charging infrastructure.

This study presents an innovative dual closed-loop DC control system for intelligent electric vehicle (EV) charging infrastructure, designed to address the challenges of high power factor, low harmonic pollution, and high efficiency in EV charging applications. The research implements a three-level Pulse Width Modulation (PWM) rectifier with a diode-clamped topology and Insulated-Gate Bipolar Transistors (IGBTs), achieving a power factor of 0.99, a total harmonic distortion (THD) of 1.12%, and an efficiency of 95% through rigorous simulation. These results surpass those of wireless charging technology and bidirectional DC-DC converters, demonstrating the system's superiority in key performance metrics. The dual closed-loop strategy, integrating a current inner loop and a voltage outer loop, ensures rapid response and high steady-state accuracy, with the PI regulator effectively managing phase coupling for balanced power flow. The voltage outer loop's stability is critical for the system's reliable operation. The study also discusses the challenges in the dynamic variation of midpoint source current and proposes future work to increase the system's switching frequency, improve anti-interference capabilities, and enhance the accuracy of the sampling process. Advanced computational intelligence and optimization techniques are highlighted as essential for tackling the complex challenges of modern EV charging systems. The study contributes to the development of efficient, secure technology for the next generation of wireless networks and power systems, providing a robust empirical basis for the proposed control strategies through MATLAB/Simulink simulations. This research sets a solid foundation for the performance assessment of EV charging systems, offering high-performance, environmentally friendly, and economically viable solutions for sustainable transportation.

Detection of plant root diseases using computational intelligence and advanced image processing techniques

This study presents an advanced Siamese-based Squeeze Googlenet and LeNet-5 (SSGL) model for the early detection of root diseases in plants, which is crucial for agricultural productivity and crop management. The methodology integrates state-of-the-art image processing techniques and Deep Learning (DL) algorithms across several key stages. In the pre-processing phase, techniques like median filtering, histogram equalization, i-CLAHE, and Z-score normalization are applied to enhance image quality and prepare the data for segmentation. The segmentation process utilizes a modified DeepLab V3 model, renowned for its precision in isolating root structures from complex backgrounds, ensuring accurate subsequent analysis. Feature extraction focuses on deriving comprehensive characteristics from segmented root images, including texture features using GLCM, color histograms, geometric metrics like area and perimeter, and shape descriptors such as circularity and rectangularity. A hybrid optimization approach employs the Hybrid Pufferfish-based Coati Optimization (HPCO) algorithm for feature selection, effectively identifying the most relevant features crucial for disease detection. For detection, the SSGL model integrates optimized architectures from SqueezeNet, GoogleNet, and LeNet-5 within a Siamese network framework. This setup enables efficient classification of root images into healthy and diseased categories based on cosine similarity. The proposed SSGL model outperforms other models with the highest accuracy (0.9856), precision (0.9760), sensitivity (0.9764), and F-measure (0.9771), while also achieving the lowest FPR (0.0149) and FNR (0.0109).

DEFECT CHARACTERIZATION OF METALLIC MATERIALS USING SELF-PARAMETERIZED DENSITY-BASED CLUSTERING AND COMPUTATIONAL INTELLIGENCE TECHNIQUES

Rapid growth of manufacturing industries is propelled by transformative technologies such as machine intelligence, autonomous computing and non-destructive testing (NDT). During the manufacturing of wrought products, there is no guarantee that the final product is 100-% flawless. Thus, all final products are subjected to quality checking to identify and eliminate defective products. In industries, most of internal defects are identified using NDT techniques, which fail to precisely characterize the defects. In this paper a novel algorithm, called Self-Parameterized Density-Based Clustering (SPDBC), is proposed for defect characterization. The proposed clustering method uses spatial parameters to identify the size and position of defects by filtering out the noise and other data that correspond to the non-defect area. Using these filtered data, computational intelligence techniques are employed to predict the defect type. SPDBC achieved Jaccard indices of 97.02 % and 98.78 % for identifying the defect size and position, respectively. Gradient boosting regression trees (GBRT) achieved a maximum accuracy of 97.44 % in predicting the defect type. As a result, the proposed approach can assist NDT experts in various sectors to differentiate between problem severities faster and replace defective parts before any major breakdown occurs.

An Intelligent System-Based Strategic Plan for a Humanoid Robot Playing the Game of Dominoes

The application of intelligent systems in humanoid robots provides research and development alternatives, as is the case with human-robot interaction. This paper focuses on the design and implementation of an intelligent system in the NAO robot to plan and execute moves in the board game known as dominoes. This system uses the NAO robot’s vision to determine the distribution of tiles on the board, as well as those available in hand. The appropriate moves are planned using a computational intelligence technique, and a kinematics model executes them. The results show that the vision system has an average error of 5.62%, in addition to 3.37% for the decision-making system and 7.87% for the kinematics of the robot. This leads to the NAO robot being capable of making successful plays through the proposed system, with an average effectiveness of 83.15%.

Impacts of electric vehicle charging stations and DGs on RDS for improving voltage stability using honey badger algorithm

The intelligent computational technique used in this research handles the multi-objective voltage stability optimization (MOVSO) problem in radial distribution systems (RDS). The objectives of the proposed research are to minimize network loss, lower the average voltage deviation index (AVDI), and improve the voltage stability index (VSI) of RDS by taking into account the recently created distributed generators (DGs) and electric vehicle charging stations (EVCSs). To address the MOVSO problem, a novel and innovative honey badger algorithm (HBA) optimization technique is put forth. The two stages of HBA, known as the "digging" and "honey" phases, are responsible for effectively identifying the ideal position and appropriate quantity of EVCSs and DGs. The standard IEEE 33 node test system with different case studies is considered to validate the performance of HBA. The simulation results of improved voltage profile, minimized power loss, AVDI and improved VSI are tabulated. The proposed HBA fine-tunes the ideal position and size of the EVCSs to significantly enhance RDS performance under higher loading circumstances. To demonstrate the efficacy and originality of the suggested HBA, the numerical results are contrasted with those of earlier soft computing techniques.

Integrative Computational Intelligence Techniques for Insomnia and Sleep Stage Recognition from ECG Data

Abstract—Insomnia is a common sleep disorder that can lead to serious health problems, including cardiovascular issues. Early and accurate detection is essential for effective treatment, but traditional diagnostic methods are often costly, time-consuming, and prone to human error. To address these challenges, this paper introduces a novel hybrid artificial intelligence (AI) approach for automatic insomnia detection using electrocardiogram (ECG) signals. The method utilizes heart rate variability (HRV) and power spectral density (PSD) analysis in various classification scenarios, including subject- based classification (normal vs. insomnia), sleep stage-based classification (REM vs. wake), and a combined classification approach using both subject and sleep stage features. Ensemble learning techniques, such as random forest (RF) and decision tree (DT) classifiers, are used in the first two scenarios, while linear discriminant analysis (LDA) is applied in the combined classification. The approach includes ECG signal collection, HRV feature extraction, PSD estimation, and classification. Evaluation using the publicly available PhysioNet dataset shows strong performance across all scenarios, with high sensitivity, specificity, and accuracy. The combined classification scenario, in particular, achieves the highest detection accuracy with LDA. Keywords—HRV Extraction, Sleep Stage, Ensemble, LDA

Advanced Computational Intelligence Techniques for Real-Time Decision-Making in Autonomous Systems

This research explores advanced computational intelligence techniques aimed at enhancing real-time decision-making in autonomous systems. The increasing reliance on autonomous technologies across sectors such as transportation, healthcare, and industrial automation demands robust, adaptive, and reliable decision-making frameworks. This study introduces a novel hybrid model that integrates Reinforcement Learning (RL), Deep Neural Networks (DNN), and Fuzzy Logic to enable autonomous systems to make accurate and timely decisions in complex, dynamic environments. The proposed framework leverages RL for adaptive decision-making, DNNs for pattern recognition and prediction, and Fuzzy Logic for handling uncertainty in system states. Experimental evaluations were conducted using high-fidelity simulations across three scenarios: autonomous vehicle navigation, real-time patient monitoring in healthcare, and robotic process automation. Results indicate a 25% improvement in decision accuracy, a 30% reduction in response time, and enhanced robustness against environmental variability compared to conventional decision-making methods. The findings underscore the effectiveness of computational intelligence in supporting critical decisions in real-time, marking a significant step toward more capable and reliable autonomous systems.

Computational and Human Intelligence Methods for Constructing Practical Risk Prediction Models: An Application to Cardio-Renal Outcomes in Non-Diabetic CKD Patients

The current investigation aimed to develop a novel approach for risk prediction modeling of clinical outcomes in common diseases based on computational and human intelligence techniques with no a priori input on risk factors using real-world individual patient-level data from administrative claims. Bootstrapping multivariable Cox regression and ant colony optimization were employed to develop time-to-first-event risk prediction models of cardio-renal outcomes in patients with non-diabetic chronic kidney disease (CKD) as a demonstration case. A cohort of 504,924 non-diabetic CKD stage 3 or 4 patients enrolled from 2008 to 2018 were identified in the US administrative de-identified claims database, Optum Clinformatics® Data Mart. Initial set of potential risk factors was derived from patient-level data at baseline and included more than 540,000 variables. Risk prediction models of hospitalization for heart failure, worsening of CKD stage from baseline and a renal composite outcome of end-stage kidney disease, kidney failure or need for dialysis in non-diabetic CKD stage 3 or 4 were built. Final model optimization was conducted using human intelligence to combine clinically similar features and build equivalence classes to ensure that risk factors included in the final model were routinely collected and easily interpretable by healthcare providers. Demonstrated validity of our approach in non-diabetic CKD offers opportunities for application in other therapeutic areas, with the potential to improve overall prognosis and decrease the clinical and economic burden of common diseases. The approach enables developing practical prediction models for risk estimation in routine clinical practice.

Prediction model for hardness and tensile strength of graphene reinforced AZ 61 alloy based composite using Metaheuristic Algorithm

It is possible to produce improved material performance through the utilization of computational intelligence approaches such as genetic algorithms optimization technique which are discussed in this paper. The optimization of processes and the development of models that are driven by data are the key uses of these technologies. This article offers a comprehensive introduction of the topic of materials and discusses the ways in which computational intelligence techniques might be utilized to develop new materials. The present study envisages the development of data driven model that enables to derive desirable properties of the said composite; so, in order to secure the optimized subset of requirements (process parameters), a metaheuristic optimization tool is employed. We invoke the use of the Genetic Algorithm (GA) optimizing tool in association with linear regression, so as to achieve the best combination of hardness and tensile strength of AZ61 graphene nanoplate (GNP) composite.

Optimization test function synthesis with generative adversarial networks and adaptive neuro-fuzzy systems

This paper presents an approach to synthesizing optimization test functions that couples generative adversarial networks and adaptive neuro-fuzzy systems. A generative adversarial network produces optimization landscapes from a database of known optimization test functions, and an adaptive neuro-fuzzy system performs regression on the generated landscapes to provide closed-form expressions. These expressions can be implemented as fuzzy basis function expansions. Eight databases of two-dimensional optimization landscapes reported in the literature are used to train the generative network. Exploratory landscape analysis over the generated samples reveals that the network can lead to new optimization landscapes with features of interest. In addition, fuzzy basis function expansions provide the best approximation results when compared against two symbolic regression frameworks over several selected landscapes. Examples are used to illustrate the ability of these functions to model complex surface artifacts such as plateaus. The proposed approach can be used as a mathematical collaboration tool that couples generative artificial and computational intelligence techniques to formulate high-dimensional optimization test problems from two-dimensional synthesized functions.

Enhancing Traffic Control with AI Blockchain and Dynamic Computation Techniques

The rapid urbanization and increasing vehicular density in modern cities have led to significant challenges in traffic management and control. As urban areas continue to expand, the demand for more efficient and intelligent traffic control systems has become increasingly critical. This paper presents a novel approach to enhancing traffic management by integrating Artificial Intelligence (AI), Blockchain technology, and Dynamic Computation Techniques. AI is utilized to analyze and predict traffic patterns, enabling real-time adjustments to traffic signals and flow management. Blockchain provides a secure, transparent, and decentralized platform for data sharing and coordination among various stakeholders, ensuring data integrity and trust. The incorporation of Dynamic Computation Techniques allows for flexible and scalable processing of complex traffic data, facilitating rapid decision-making and adaptation to changing conditions. This multidisciplinary approach not only improves traffic efficiency and reduces congestion but also paves the way for more resilient and sustainable urban transportation systems. The findings highlight the transformative potential of combining AI, Blockchain, and advanced computation methods in the field of traffic control.

Retraction Note: Enhanced decision support system to predict and prevent hypertension using computational intelligence techniques

Retraction Note: Enhanced decision support system to predict and prevent hypertension using computational intelligence techniques

Computational intelligent techniques for predicting optical behavior of different materials

The current research introduces a comparison study of the utilization of artificial neural networks (ANN) and genetic programming (GP) for predicting the optical behavior of different materials. The experimental data for a variety of materials, including semiconductors, insulators, oxides, and halides are extracted and utilized in ANN and GP as inputs. Simulation and prediction processes are carried out based on ANN and GP techniques. The most important aim presented in the current research is to obtain two equations of n as a function of Eg by the two based on ANN and GP models. The first numerical equation is obtained based on the ANN model exhibiting mean squared error (MSE) does not exceed 10−1. The second nonlinear equation is obtained based on the GP model with an acceptable fitness value. The estimated results based on the proposed approaches ANN and GP presented a great match with their targets. It demonstrated that the trained results including simulated and predicted results based on ANN and GP introduce excellent fitting compared with alike results obtained based on the conventional theoretical techniques. The mean absolute percentage error values prove that the ANN model is significantly more accurate than the GP model. Since lower error values suggest better prediction, hence it is clear that ANN performed better than GP. The equation derived by the ANN model is utilized to predict the refractive index for binary and ternary compounds. The values of the refractive index have been predicted for materials for which measurements have been made practically as a test step to ensure the accuracy of the results obtained through the deduced mathematical equations. Then, the application of these equations was generalized to materials that were not measured experimentally. A detailed discussion of the modeling results is introduced and proved that ANN and GP models are effective and successful tools for predicting the refractive index for different types of materials.

A Systematic Review of Computational Intelligence Techniques for Channel Selection in P300-Based Brain Computer Interface Speller

Electroencephalography (EEG)-based P300 speller aids in restoring the communication and control capabilities in patients suffering from motor disabilities. However, the quality and quantity of the data collected from EEG recordings have a substantial influence on the P300 speller’s performance. Hence, selecting the optimum number of recording electrodes, i.e., channels for each user, is a significant difficulty for the P300 speller. There are two fundamental objectives of the channel selection process: (1) to extract the most crucial information from the relevant channels, hence reducing the computing complexity of P300/non-P300 signal processing operation, and (2) to lessen the potential overfitting that could result from using unwanted channels to boost performance. For obtaining the best channel subsets, different channel selection techniques, including manual, filtering, wrapper, and embedded approaches, have been applied by past researchers. This research provides an in-depth examination of recent advancements, status, challenges, and potential solutions related to channel selection strategies in P300 speller systems. Each channel selection technique is thoroughly explored, including detailed comparisons between them. The notable advantages and drawbacks of each method are emphasized along with the discussion on the future direction and scope of work in the field of channel selection in P300 speller. The review underscores that channel selection methods enable the use of a reduced number of channels without compromising classification performance. By eliminating noisy or irrelevant channels, these approaches contribute to enhanced system performance.

Computational intelligence-based classification system for the diagnosis of memory impairment in psychoactive substance users

Computational intelligence techniques have emerged as a promising approach for diagnosing various medical conditions, including memory impairment. Increased abuse of psychoactive drugs poses a global public health burden, as repeated exposure to these substances can cause neurodegeneration, premature aging, and negatively affect memory impairment. Many studies in the literature relied on statistical studies, but they remained inaccurate. Some studies relied on physical data because the time factor was not considered, until Artificial Intelligence (AI) techniques came along that proved their worth in this diagnosis. The variable deep neural network method was used to adapt to the intermediate results and re-process the intermediate in case the result is undesirable. Computational intelligence was used in this study to classify a brain image from MRI or CT scans and to show the effectiveness of the dose ratio on health with treatment time, and to diagnose memory impairment in users of psychoactive substances. Understanding the neurotoxic profiles of psychoactive substances and the underlying pathways is hypothesized to be of great importance in improving the risk assessment and treatment of substance use disorders. The results proved the worth of the proposed method in terms of the accuracy of recognition rate as well as the possibility of diagnosis. It can be concluded that the diagnostic efficiency is increased by increasing the number of hidden layers in the neural network and controlling the weights and variables that control the deep learning algorithm. Thus, we conclude that good classification in this field may save human life or early detection of memory impairment.

A high-performance, parallel, and hierarchically distributed model for coastal run-up events simulation and forecasting

The request for quickly available forecasts of intense weather and marine events impacting coastal areas is gradually increasing. High-performance computing (HPC) and artificial intelligence techniques are crucial in this application. Risk mitigation and coastal management must design scientific workflow appropriately and maintain them continuously updated and operational. Climate change accelerating increase trend of the past decades impacted on sea-level rise, together with broader factors such as geostatic effects and subsidence, reducing the effectiveness of coastal defenses. Due to this, the support tools, such as Early Warning Systems, have become increasingly more valuable because they can process data promptly and provide valuable indications for mitigation proposals. We developed the Shoreline Alert Model (SAM), an operational Python tool that produces simulation scenarios, ‘what-if’ assumptions, and coastal flooding forecasts to fill this gap in our study area. SAM aims to provide decision-makers, scientists, and engineers with new tools to help forecast significant weather-marine events and support related management or emergency responses. SAM aims to fill the gap between the wind-driven wave models, which produce simulations and forecasts of waves of significant height, period, and direction in deep or mid-water, and the run-up local models, which exstimulate marine ingression in the event of intense weather phenomena. It employs a parallelization scheme that allows users to run it on heterogeneous parallel architectures. It produced results approximately 24 times faster than the baseline when using shared memory with distributed memory, processing roughly 20,000 coastal cross-shore profiles along the coastline of the Campania region (Italy). Increasing the performance of this model and, at the same time, honoring the need for relatively modest HPC resources will enable the local manager and policymakers to enforce fast and effective responses to intense weather phenomena.