Computational Intelligence Research Articles

From Waste to Roads: Improving Pavement Performance and Achieving Sustainability with Recycled Steel Slag and Low-Density Polyethylene

The use of waste, recycled, and modified materials is increasingly popular in roadway construction for sustainability and pavement longevity. This research examines the combination of steel slag (SS) and low-density polyethylene (LDPE), commonly used in plastic bags and steel manufacturing by-products, to mitigate environmental pollution. LDPE was tested as a binder modifier in two bitumen grades, 60–70 and 80–100, at concentrations of 3%, 5%, and 7% by weight. SS was used as a replacement for coarse aggregate. The physical properties of both modified and unmodified bitumen grades and SS were analyzed before creating and testing hot-mix asphalt (HMA) samples. The dynamic modulus of these samples was measured at temperatures of 4.4 °C, 21.1 °C, 37.8 °C, and 54.4 °C with frequencies of 0.1 Hz, 0.5 Hz, 1 Hz, 5 Hz, 10 Hz, and 25 Hz. Master curves were developed, and the dynamic modulus data underwent design of experiment (DOE) and computational intelligence (CI) analyses. Using KENPAVE, a mechanistic–empirical tool, the analysis assessed the design life and enhancements in damage ratio for each modifier and grade. The results showed that adding LDPE increases the softening point and penetration grade but decreases ductility due to increased bitumen stiffness, leading to premature fatigue failure at higher LDPE levels. Both 3% LDPE and 3% SS-modified LDPE improved Marshall Stability and dynamic modulus across all temperature and frequency ranges. Specifically, 3% LDPE enhanced stability by 13–16% and 3% SS-LDPE by 30–32%. The KENPAVE results for 3% LDPE showed a design life improvement of 19–25% and a damage ratio reduction of 15–18%. In comparison, 3% SS-LDPE demonstrated a design life improvement of 50–60% and a damage ratio reduction of 25–35%. Overall, this study concludes that 3% LDPE- and 3% SS-LDPE-modified HMA in both bitumen grades 60–70 and 80–100 provide optimal results for improving pavement performance.

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.

Empirical techniques for effort estimation in designing effective ML models

Machine Learning Research often involves the use of diverse libraries, modules, and pseudocodes for data processing, cleaning, filtering, pattern recognition, and computer intelligence. Quantization of Effort Required for the above cumulative processes is rarely discussed in the existing works and The time to reach the desired level of the model's functionality is essential to gauge the environment training for the model training and pre-deployment testing. In this study, we empirically defined the manual-cum-computational effort required for the model development in terms of 2-time factors: time-to-live (time until 1st code modification) and time-for-modification (time between 2 codebase changes) taken together in a mathematical model to compute Effort Factor(quantitative measure of determining effort needed to design ML algorithms). The study is novel in terms of how the effort required to create ML models is calculated with a particular focus on the manual effort direction. The results and the findings obtained can be used for determining the total time needed to synthesize ML models and frameworks in terms of code change cycles and implementation strategies marking a 25% performance increase in the current method above the Standard Pipeline.

Climate friendly MOFs synthesis for drug delivery systems by integrating AI, intelligent manufacturing, and quantum solutions in industry 6.0 sustainable approach.

Since the Industrial Revolution, ecological damage, ecosystem disruption, and climate change acceleration have frequently resulted from human advancement at the price of the environment. Due to the rise in illnesses, Industry 6.0 calls for a renewed dedication to sustainability with latest technologies. Focused research and creative solutions are needed to achieve the UN Sustainable Development Goals (SDGs), especially 3, 9, 13, 14, 15, 17. A promising sustainable technology for enhancing healthcare while reducing environmental effect is Metal Organic Frameworks (MOFs). MOFs are perfect for drug administration because of their high surface areas, adjustable pore sizes, and remarkable drug-loading capacities. They are created by combining advanced artificial intelligence, intelligent manufacturing, and quantum computing. Researchers can create MOFs with functional groups or ligands that bind selectively to target cells or tissues, minimizing off-target effects, thanks to the distinct benefits that families like MIL, HKUST, UiO, and ZIF etc. offer for targeted drug delivery. Combining MOFs with other nanomaterials results in multipurpose systems that can handle challenging biomedical issues. Despite its promise, there are still issues with MOFs' possible toxicity and long-term stability in physiological settings. To advance their medicinal applications, these problems must be resolved. Researchers can increase the usefulness of MOFs in medicine by critically analysing these limitations and putting up creative alternatives. The creation of MOFs especially with advanced technologies (additive manufacturing etc.) for drug delivery is a prime example of how scientific advancement and environmental stewardship may coexist to provide healthcare solutions that are advantageous to both people and the environment.

IEEE Transactions on Emerging Topics in Computational Intelligence Publication Information

IEEE Transactions on Emerging Topics in Computational Intelligence Publication Information

Design for manufacture and assembly (DfMA) for modular buildings: an analytical framework

ABSTRACT Design for Manufacture and Assembly (DfMA) is a proactive strategy aimed at maximizing the potential of modular buildings to address issues, including labor shortages, time overruns, and low productivity. Despite its growing adoption, research on examining existing design practices remains limited. This study therefore aims to 1) develop an analytical framework and 2) uncover underlying modular building design patterns. Drawing inspiration from space syntax analysis, the framework comprises six components: nomenclature system, space identification, spatial relations, module shape, dimensions, and convex break-up. It was then applied to analyze 39 modular building units in Hong Kong. The established framework helps visualize underlying design patterns, e.g. spatial typologies, module shapes and sizes, and standardized spatial configurations. Several design patterns are also identified, i.e. typical space requirements, common module sizes, dimension-coordinated spaces, and the repetitive use of standardized spaces and modules to form units. This innovative framework, along with a discussion on evolving professional practices, offers valuable insights for advancing DfMA and modular construction. Future research is recommended to refine the framework and enhance DfMA by integrating these patterns with expert knowledge and computational intelligence.

Real-Time Data Processing in Cloud Computing: Enterprise Implementation Strategies

This article examines the transformative impact of real-time data access enabled by cloud computing across enterprise organizations, focusing on implementation strategies and architectural patterns. Through detailed analysis of industry-leading case studies, this article explores how cloud-based real-time data processing solutions have revolutionized business operations and customer experiences. This article investigates critical technical components including data streaming architectures, IoT integration, geospatial processing, and predictive analytics implementations. This article demonstrates that successful real-time data processing implementations require careful consideration of infrastructure requirements, scalability patterns, and performance optimization strategies. This article provides insights into common challenges such as handling peak loads, ensuring data consistency, and maintaining system reliability, while also examining emerging trends in edge computing and artificial intelligence integration. This article contributes to the growing body of knowledge on enterprise-scale real-time data processing and offers practical guidance for organizations planning similar implementations.

Transforming Supply Chain Management through Modern B2B Data Integration

This comprehensive article explores the evolution and current state of B2B integration in supply chain management, focusing on implementation challenges, success factors, and future trends. The article examines case studies from industry leaders, including 3M and Advance Auto Parts, demonstrating how modern B2B integration platforms have transformed traditional supply chain operations through automated data exchange, improved visibility, and enhanced collaboration. The article investigates technical and organizational challenges in implementation while providing best practices for successful deployment. The article offers insights into the future direction of B2B integration technologies and their impact on business performance through detailed analysis of cloud computing, API-first approaches, and artificial intelligence applications.

Capacity Planning for High-Traffic Events in Cloud Environments

Cloud capacity planning for high-traffic events has become crucial for modern digital businesses facing unprecedented challenges during seasonal sales, product launches, and viral marketing campaigns. Organizations must implement robust strategies to handle sudden traffic surges while maintaining system stability and user experience. Advanced technologies including artificial intelligence, machine learning, and edge computing enable precise demand forecasting, dynamic resource allocation, and real-time monitoring. These capabilities, combined with automated scaling mechanisms and comprehensive security measures, allow businesses to optimize costs while ensuring consistent performance during peak loads. The integration of cloud-native tools and platforms further enhances operational efficiency through predictive analytics and automated resource management, making it possible for organizations to build resilient systems capable of handling extreme traffic variations while maintaining high availability and customer satisfaction.

Quantum computing-Enhanced AI systems for advanced business intelligence applications

The convergence of quantum computing and artificial intelligence represents a transformative technological paradigm with unprecedented potential for business intelligence applications. This comprehensive review critically examines the revolutionary capabilities of quantum computing-enhanced AI systems in addressing complex computational challenges across multiple business domains. Through systematic analysis of emerging research, implementation frameworks, and interdisciplinary case studies, we investigate how quantum computing's unique computational mechanisms can fundamentally reshape data analysis, strategic decision-making, and predictive modeling. Our comprehensive examination reveals that quantum AI systems demonstrate remarkable potential to reduce computational complexity by up to 90%, enhance predictive accuracy by 60-75%, and provide unprecedented insights across financial, logistical, and strategic business intelligence domains. The research synthesizes evidence from multiple technological domains, highlighting the transformative potential of quantum-enhanced AI in solving previously intractable computational problems. By exploring technological capabilities, implementation challenges, and future research directions, this review provides a critical framework for understanding the emerging intersection of quantum computing and artificial intelligence in advanced business intelligence applications.

Emotion Detection in Speech: A Deep Learning-Driven Approach Leveraging Acoustic Features within Intelligent Computing Systems

As digital image collections grow in size, there is an increasing need for robust image retrieval systems capable of managing large datasets effectively. This work offerings a novel Content-Based Image Retrieval (CBIR) system designed to enhance retrieval accuracy across both general and medical image datasets. The proposed system leverages U-Net for feature extraction, integrated with an improved weight-learning approach to enhance retrieval performance. A Convolutional neural network, U-Net, a network design famous for its picture segmentation ability, is utilized to capture complex, high-level image features. The approach includes an adaptive, query-aware feature weighting mechanism that applies weight re-scaling to parameterized features, assigning optimized weights to top-ranked images. This CBIR system comprises three main components: image pre-processing, U-Net-based feature extraction, and feature re-weighting. During pre-processing, images undergo augmentation and normalization to increase model robustness. The feature re-weighting process evaluates feature importance using cosine similarity, which further improves discriminative power at retrieval. The proposed CBIR system was tested across various image datasets through extensive experiments, with performance measured in terms of recall, precision and F1-score. The results indicate that integrating feature re-weighting with U-Net-based extraction significantly enhances retrieval effectiveness. This work represents a step forward in developing adaptive image retrieval systems that better respond to diverse retrieval scenarios.

Principles and Applications of Two-Dimensional Semiconductor Material Devices for Reconfigurable Electronics

With the advances in edge computing and artificial intelligence, the demands of multifunctional electronics with large area efficiency are increased. As the scaling down of the conventional transistor is restricted by physical limits, reconfigurable electronics are developed to promote the functional integration of integrated circuits. Reconfigurable electronics refer to electronics with switchable functionalities, including reconfigurable logic operation functionalities and reconfigurable responses to electrical or optical signals. Reconfigurable electronics integrate data-processing capabilities with reduced size. Two-dimensional (2D) semiconductor materials exhibit excellent modulation capabilities through electrical and optical signals, and structural designs of 2D material devices achieve versatile and switchable functionalities. 2D semiconductors have great potential to develop advanced reconfigurable electronics. Recent years witnessed the rapid development of 2D material devices for reconfigurable electronics. This work focuses on the working principles of 2D material devices used for reconfigurable electronics, discusses applications of 2D-material-based reconfigurable electronics in logic operation and artificial intelligence, and further provides a future outlook for the development of reconfigurable electronics based on 2D material devices.

Heterogeneous Packaging Technologies for Chiplet and Memory Integration

To meet the High-Performance Computing (HPC) and Artificial Intelligence (AI) market demands of ever higher performance, lower power consumption, wider memory bandwidth with reduced latency, the interconnects connecting D2D in advanced packages are getting ever smaller with tighter bump pitch. Hybrid Copper Bonding (HCB), which can provide direct Cu-Cu connection, is replacing solder-based micro bump Thermal Compressive Bonding (TCB) for die stacking, when the bump pitch shrinks down to less than 20µm. While the interconnects are getting smaller and denser, the overall package size is getting bigger, because more chiplets and High Bandwidth Memory (HBM) need to be assembled on the same package to meet the high-performance requirements. Innovative memory integration solutions, for example memory to logic die 3D stacking, photonic HBM integration, and remote optical HBM connection, are being developed to tackle the issue alternatively. This paper presents a chiplet based heterogeneous integration platform, an advanced custom HBM option, and a menu of advanced packaging offering, which are recently built and delivered by Samsung. including Integrated Stack Capacitor (ISC), Custom HBM, Re-Distribution Layer (RDL) based Fan Out Wafer Level Packaging (FOWLP), Fan Out Panel level packaging (FOPLP), interposer and Si bridge based 2.5 D package architectures, such as I-CubeS, I-CubeR, and I-CubeE, as well as TCB and HCB based 3D IC packaging.

The AI and Quantum Era: Transforming Project Management Practices

Project management is changing drastically due to the integration of artificial intelligence (AI) and quantum computing (QC), redefining traditional methods. This study explores Quantum AI (QAI) and AI-driven solutions to tackle enduring issues, including resource inefficiencies, schedule delays, and budget overruns. These technologies significantly enhance project outcomes by leveraging predictive analytics, dynamic scheduling, and high-dimensional optimization. A comparative analysis of prominent case studies, including the Crossrail Project, East Side Access, and the Montreal Olympics, highlights the superior performance of AI and QAI techniques compared to conventional methods. The study shows that QAI can cut delays by 60%, optimize resource allocation with 83% efficiency, and eliminate cost overruns by up to 40% using Monte Carlo simulations and Failure Mode Effects Analysis. These results demonstrate that quantum artificial intelligence is a ground-breaking tool for handling intricate, interconnected project settings. Additionally, this study emphasizes how QAI is scalable and applicable across industries, especially in fields that need real-time optimization and high-dimensional data processing. The proposed hybrid quantum-classical paradigm provides practical solutions and sets a benchmark for efficiency, scalability, and risk mitigation in project management.

Dwie metody przetwarzania informacji w głębokich sieciach neurono- wych a właściwości systemów inteligencji. Próba porównania i testowania

The rapid development of AI technology in recent years has resulted, among other consequences, in renewal and dominance of connectionistic way of description of cognitive activities of both humans and computational machines. This approach results in new possibilities to compare the performance of digital AI-type computational artefacts with information processing systems of biological and evolutionary origin. The aim of this paper is to show how consequences of this approach towards the problem of computational intelligence look like. The second goal of presented research is to test the thesis of the possible superiority of systems described as immortal computing type over systems presented as mortal computing type.

Decoding Pain: A Comprehensive Review of Computational Intelligence Methods in Electroencephalography-Based Brain–Computer Interfaces

Objective pain evaluation is crucial for determining appropriate treatment strategies in clinical settings. Studies have demonstrated the potential of using brain–computer interface (BCI) technology for pain classification and detection. Collating knowledge and insights from prior studies, this review explores the extensive work on pain detection based on electroencephalography (EEG) signals. It presents the findings, methodologies, and advancements reported in 20 peer-reviewed articles that utilize machine learning and deep learning (DL) approaches for EEG-based pain detection. We analyze various ML and DL techniques, support vector machines, random forests, k-nearest neighbors, and convolution neural network recurrent neural networks and transformers, and their effectiveness in decoding pain neural signals. The motivation for combining AI with BCI technology lies in the potential for significant advancements in the real-time responsiveness and adaptability of these systems. We reveal that DL techniques effectively analyze EEG signals and recognize pain-related patterns. Moreover, we discuss advancements and challenges associated with EEG-based pain detection, focusing on BCI applications in clinical settings and functional requirements for effective pain classification systems. By evaluating the current research landscape, we identify gaps and opportunities for future research to provide valuable insights for researchers and practitioners.

Enhancing seismic risk assessment through probabilistic analysis of liquefaction potential index: a computational intelligence approach

ABSTRACT This study proposes a novel computational intelligence approach for enhancing seismic risk assessment through probabilistic analysis of the liquefaction potential index (LPI). The methodology leverages a hybridised model that combines backpropagation neural networks (BcNN) with an improved firefly algorithm (IFF) to predict LPI values accurately and efficiently. The BcNN-IFF model was trained and validated using a comprehensive dataset comprising the geotechnical and seismic parameters from various earthquake-prone regions worldwide. Feature importance analysis revealed that total stress (σv’) and peak ground acceleration (amax) were the most influential factors in the LPI prediction. The BcNN-IFF model demonstrated superior performance compared to other hybrid models, achieving 91% accuracy in the training phase and 85% accuracy in the testing phase, with low root mean square error and mean absolute error values. The practical implications of the BcNN-IFF model highlights its potential for reliable liquefaction susceptibility assessments, particularly in resource-constrained environments. Future research directions are outlined, emphasising the need for uncertainty quantification, data augmentation, and computational efficiency enhancements to improve the applicability of the model in real-world scenarios. This study advances state-of-the-art computational modelling and provides a foundation for integrating such tools into geotechnical engineering practices for effective seismic risk assessment and infrastructure resilience.

Choroidal melanoma treatment: a shift towards vision preservation

Background: Choroidal melanoma is the most common primary intraocular malignancy in adults, and is known for its aggressive nature and potential for metastasis. Historically, enucleation was the primary treatment, which resulted in significant morbidity and psychological distress. Recent advances have led to a paradigm shift towards vision-preserving therapies. This review aimed to explore advances in choroidal melanoma treatment and their impact on patient care and quality of life. Methods: For this narrative review, we conducted a literature search of major databases, including PubMed/MEDLINE, Embase, and Scopus, from January 1, 1998, to December 30, 2024. The search strategy employed the following keywords: “choroidal melanoma,” “vision preservation,” “plaque brachytherapy,” “proton beam therapy,” “stereotactic radiosurgery,” “enucleation,” “ocular oncology,” “retinal health,” “visual acuity,” “quality of life,” “computational intelligence,” and “AI (artificial intelligence).” We included English-language studies of any design focusing on choroidal melanoma treatment, particularly treatment involving vision-preserving strategies. Results: Advances in vision-preserving therapies, such as plaque brachytherapy, proton-beam irradiation, and stereotactic radiosurgery, have revolutionized the management of choroidal melanoma. These modalities offer improved patient outcomes by reducing the need for enucleation and preserving visual acuity. Plaque brachytherapy achieves high tumor-control rates with minimal side effects, while proton-beam irradiation provides precise tumor targeting, which is particularly beneficial for large tumors. Stereotactic radiosurgery is effective for smaller tumors, but may result in decreased visual acuity over time. Emerging therapies, such as Bel-Sar (AU-011), show promise in controlling tumor growth while preserving vision. The ability of Bel-Sar to control tumors while preserving vision could provide patients with a more favorable prognosis and improved quality of life. Immunotherapy holds significant promise, particularly with the potential for use of immune checkpoint inhibitors and vaccine therapies. Additionally, artificial intelligence (AI) is becoming increasingly important in the management of choroidal melanoma. Conclusions: The shift from enucleation to vision-preserving therapies has significantly improved outcomes and quality of life for patients with choroidal melanoma. Future research should focus on optimizing current therapies for better visual acuity preservation and on exploring new targeted therapies to enhance tumor control while minimizing side effects. Moreover, studies on AI applications for managing this sight- and life-threatening eye condition could significantly transform treatment outcomes.

ЦИФРЛЫҚ ВАЛЮТАЛАРДЫ МЕМЛЕКЕТТІК РЕТТЕУДІҢ КЕЙБІР АСПЕКТІЛЕРІ

This article examines the implications of the introduction of digital currencies and related technologies. Beginning with an analysis of blockchain, cloud computing, and artificial intelligence, it explores the potential benefits and challenges associated with these innovations in the financial sector and the economy as a whole. The article emphasizes the need to establish a robust regulatory framework for the development of digital currencies and to address issues related to cybersecurity and data privacy. It is noted that through strategic cooperation between government, business, and the technology sector, Kazakhstan has the opportunity to take a leading position in the regional digital economy. By adapting best practices in regulating digital currencies and levereging innovation, Kazakhstan can actively stimulate innovation and ensure economic growth.

Artificial Intelligence, Quantum Computing, Autonomous Operation, Emotional Intelligence: Key Drivers of Industry 6.0 and Sustainabile Development Goals (SDG-8,9,12,17) for Business Sustainability in the Oil and Gas Industry

Objective: The objective of the study investigates the extent to which specified programs and machines are activated and achieve business sustainability through sustainable development goals (SDG-8,9,12,17) in Industry 6.0. This report analyses the current situation from 2013 to 2024 and assesses the influence of Industry 6.0 on the oil and gas sector within the Gulf Cooperation Council (GCC). Theoretical Framework: Digital transformation progresses from Industry 5.0 to Industry 6.0 globally within the oil and gas sector, with only certain regions achieving totally autonomous operation, while the majority are endeavouring to attain such autonomy. The industrial revolution is realized through Industry 6.0, which is accomplished by implementing autonomous operations utilizing robotics, Artificial Intelligence (AI), quantum computing, machine learning (ML), the Industrial Internet of Things (IIoT), blockchain technology, and cloud computing within the oil and gas sector. Based on the study, proposed model proposes with autonomous operation through Industry 6.0 techniques and business sustainability. Method: Researchers have gathered numerous empirical articles, case studies and book chapters to thoroughly investigate the topic and its domains. This study employs a literature review methodology, concentrating mostly on the oil and gas service industries within GCC nations. Results and Discussion: Researchers discovered that the oil and gas service industry encounters difficulties in achieving fully automated procedures devoid of human interaction Industry 6.0 will attain corporate sustainability via total autonomy. The second scenario involves artificial intelligence, quantum computing, and emotional intelligence (EI) enabling Industry 6.0 to attain favourable results. Research Implications: The research study suggests that the implementation of Industry 6.0 in the oil and gas service sector remains mostly at a conceptual stage in most areas. Originality/Value: This study contributes to engineering services in oil and gas industry, entrepreneur’s emotional intelligence and autonomous operation during the defined period were not evaluated and it added value in the engineering service sector to mitigate their issues to have better business sustainability.