Computational Intelligence Tools Research Articles

Digital Pathology Applications for PD-L1 Scoring in Head and Neck Squamous Cell Carcinoma: A Challenging Series.

The assessment of programmed death-ligand 1 (PD-L1) combined positive scoring (CPS) in head and neck squamous cell carcinoma (HNSCC) is challenged by pre-analytical and inter-observer variabilities. An educational program to compare the diagnostic performances between local pathologists and a board of pathologists on 11 challenging cases from different Italian pathology centers stained with PD-L1 immunohistochemistry on a digital pathology platform is reported. A laboratory-developed test (LDT) using both 22C3 (Dako) and SP263 (Ventana) clones on Dako or Ventana platforms was compared with the companion diagnostic (CDx) Dako 22C3 pharm Dx assay. A computational approach was performed to assess possible correlations between stain features and pathologists' visual assessments. Technical discordances were noted in five cases (LDT vs. CDx, 45%), due to an abnormal nuclear/cytoplasmic diaminobenzidine (DAB) stain in LDT (n = 2, 18%) and due to variation in terms of intensity, dirty background, and DAB droplets (n = 3, 27%). Interpretative discordances were noted in six cases (LDT vs. CDx, 54%). CPS remained unchanged, increased, or decreased from LDT to CDx in three (27%) cases, two (18%) cases, and one (9%) case, respectively, around relevant cutoffs (1 and 20, k = 0.63). Differences noted in DAB intensity/distribution using computational pathology partly explained the LDT vs. CDx differences in two cases (18%). Digital pathology may help in PD-L1 scoring, serving as a second opinion consultation platform in challenging cases. Computational and artificial intelligence tools will improve clinical decision-making and patient outcomes.

Hardenability modelling and the performance of computational intelligence tools in research on structural alloy steels

x

Cognitive modeling for understanding interactions between people and decision support tools in complex and uncertain environments: A study protocol.

Recent advances in Computational Intelligence Tools and the escalating need for decision-making in the face of complex and uncertain phenomena like pandemics, climate change, and geopolitics necessitate understanding the interaction between these tools and human behavior. It is crucial to efficiently utilize the decision-makers cognitive resources in addressing specific problems. The main goal of this present protocol is to describe the effect that CITs (Computational Intelligence Tools) have on decisions made during complex and uncertain situations. It is an exploratory study with a mixed methodology. Solomon's group experiment design includes a narrative analysis of cognitive features such as integrative complexity (IC), cognitive flexibility (CF), and fluid intelligence (FI). Additionally, measures of neural activity (NA), physiological measures (PM), and eye-tracking data (ET) will be collected during the experimental session to examine the marginal impact of these processes on decision outcomes (DO) and their relation to CIT capabilities. To achieve this objective, 120 undergraduate and graduate students involved in decision-making will participate as subjects. The approximate duration of the study will be 2 years. Strict adherence to the relevant ethical considerations will be maintained during the performance of the experimental tasks. The study will provide valuable information on CITs' effect on decision-making under complex and uncertain contexts. This will help to better understand the link between technology and human behavior, which has important implications. CIT designers can use future results and at the same time, it will be possible to understand cognitive, behavioral, physiological processes, and even the subjective assessment of individuals when they use technological tools to solve a problem.

Performance diagnostics of gas turbines operating under transient conditions based on dynamic engine model and artificial neural networks

Gas turbine engines are machines of high complexity and non-linearity. Interpreting the vast amount of data from a gas turbine and converting them into customer value requires the combination of domain knowledge and modern computational intelligence tools. Reaching to an accurate and reliable diagnosis of gas turbines is a process that is becoming increasingly complex. The engines are now expected to operate in more dynamic conditions to compensate for the intermittent nature of renewables. Transient operating conditions will accelerate the deterioration of gas turbine components which motivates the development of new methods and tools to cope with such type of information. In this paper, we propose a novel performance diagnostic method for gas turbines that combines a dynamic engine model with artificial neural networks (ANN). An engine model of a two shaft gas turbine has been developed in MATLAB/Simulink and used by a family of ANNs to detect the degradation of the engine operating under transient conditions, when all of its components are experiencing degradation. The conducted case studies consider various degradation scenarios. The advantage of the proposed method is that it deals effectively with both fixed and time-evolving degradation. Furthermore, in cases where there is limited amount of data for training ANNs the model can fill this gap by simulating plethora of scenarios that can potentially extend the applicability of ANNs to gas turbine diagnostics. The proposed method could be used as a tool for supporting the operation and maintenance activities of gas turbines.

Computational-Intelligence-Based Spectrum-Sharing Scheme for NOMA-Based Cognitive Radio Networks

The integration of non-orthogonal multiple access (NOMA) technology and cognitive radio networks (CRNs) promises to enhance the spectrum utilization efficiency of 5G and beyond-5G (B5G) mobile communication systems. In this article, a NOMA-based spectrum-sharing scheme is proposed for dual-hop CRNs in which a primary transmitter separated by a long distance from the primary receiver communicates via NOMA-based CRN. In this scenario, we mathematically formulate a constrained optimization problem to maximize the sum rate of all secondary users (SUs) while maintaining the total transmit power of the system. Inspired by the effectiveness of computational intelligence (CI) tools in solving non-linear optimization problems, this article proposes three CI-based solutions to the given problem aiming to guarantee quality of service (QoS) for all users. In addition, an enhanced version of the classic artificial bee colony (ABC) algorithm, referred to here as the enhanced-artificial-bee-colony (EABC)-based power allocation scheme, is proposed to overcome the limitations of classic ABC. The comparison of different CI approaches illustrates that the minimum power required by the secondary NOMA relay to satisfy the primary rate threshold of 5 bit/s/Hz is 20 mW for EABC, while ABC, PSO and GA achieve the same target at 23 mW, 27 mW and 32 mW, respectively. Thus, EABC reduces power consumption by 13.95% compared to ABC, while 29.78% and 46.15% power-saving is achieved compared to PSO and GA, respectively.

A Step Forward to Formalize Tailored to Problem Specificity Mathematical Transforms

Linear functional analysis historically founded by Fourier and Legendre played a significant role to provide a unified vision of mathematical transformations between vector spaces. The possibility of extending this approach is explored when basis of vector spaces is built Tailored to the Problem Specificity (TPS) and not from the convenience or effectiveness of mathematical calculations. Standardized mathematical transformations, such as Fourier or polynomial transforms, could be extended toward TPS methods, on a basis, which properly encodes specific knowledge about a problem. Transition between methods is illustrated by comparing what happens in conventional Fourier transform with what happened during the development of Jewett Transform, reported in previous articles. The proper use of computational intelligence tools to perform Jewett Transform allowed complexity algorithm optimization, which encourages the search for a general TPS methodology.

Barnacles Mating Optimizer with Deep Transfer Learning Enabled Biomedical Malaria Parasite Detection and Classification.

Biomedical engineering involves ideologies and problem-solving methods of engineering to biology and medicine. Malaria is a life-threatening illness, which has gained significant attention among researchers. Since the manual diagnosis of malaria in a clinical setting is tedious, automated tools based on computational intelligence (CI) tools have gained considerable interest. Though earlier studies were focused on the handcrafted features, the diagnostic accuracy can be boosted through deep learning (DL) methods. This study introduces a new Barnacles Mating Optimizer with Deep Transfer Learning Enabled Biomedical Malaria Parasite Detection and Classification (BMODTL-BMPC) model. The presented BMODTL-BMPC model involves the design of intelligent models for the recognition and classification of malaria parasites. Initially, the Gaussian filtering (GF) approach is employed to eradicate noise in blood smear images. Then, Graph cuts (GC) segmentation technique is applied to determine the affected regions in the blood smear images. Moreover, the barnacles mating optimizer (BMO) algorithm with the NasNetLarge model is employed for the feature extraction process. Furthermore, the extreme learning machine (ELM) classification model is employed for the identification and classification of malaria parasites. To assure the enhanced outcomes of the BMODTL-BMPC technique, a wide-ranging experimentation analysis is performed using a benchmark dataset. The experimental results show that the BMODTL-BMPC technique outperforms other recent approaches.

Modeling asphalt pavement condition using artificial neural networks

Pavement maintenance and rehabilitation (M&R) decision-making is an important component of pavement management systems. Timely maintenance of extensive pavement network is mandatory to ensure a safe and comfortable ride to the road users. Accurate and reliable prediction of current pavement condition is a valuable input for taking sound maintenance decisions and selecting appropriate rehabilitation or repair alternatives. Maintenance or repair decisions are usually not based on structural parameters due to certain limitations regarding the collection of structural data. Due to its absence pavement may demand substantial rehabilitation in future, which could have otherwise required only preventive maintenance.Therefore, in the present study, structural performance models are developed using the tools of computational intelligence. Artificial neural networks have been used to develop various structural condition prediction models for asphalt pavements using a variety of input data pertaining to structural, functional and environmental parameters, collected from actual field testing. The reliable correlations developed in this study are expected to popularize the implications of structural adequacy factors in pavement M&R decision-making and ease the work of transportation agencies in obtaining structural condition data. The neural network models are flexible with the addition/modification of data and work well even with the limited data.

Spatio-Temporal Fusion and Machine Vision Algorithms, Metaverse-based Industrial Services, and Computational Intelligence and Operational Modeling Tools in Simulated 3D Extended Reality Environments

Spatio-Temporal Fusion and Machine Vision Algorithms, Metaverse-based Industrial Services, and Computational Intelligence and Operational Modeling Tools in Simulated 3D Extended Reality Environments

Using Optimisation Meta-Heuristics for the Roughness Estimation Problem in River Flow Analysis

Climate change threats make it difficult to perform reliable and quick predictions on floods forecasting. This gives rise to the need of having advanced methods, e.g., computational intelligence tools, to improve upon the results from flooding events simulations and, in turn, design best practices for riverbed maintenance. In this context, being able to accurately estimate the roughness coefficient, also known as Manning’s n coefficient, plays an important role when computational models are employed. In this piece of research, we propose an optimal approach for the estimation of ‘n’. First, an objective function is designed for measuring the quality of ‘candidate’ Manning’s coefficients relative to specif cross-sections of a river. Second, such function is optimised to return coefficients having the highest quality as possible. Five well-known meta-heuristic algorithms are employed to achieve this goal, these being a classic Evolution Strategy, a Differential Evolution algorithm, the popular Covariance Matrix Adaptation Evolution Strategy, a classic Particle Swarm Optimisation and a Bayesian Optimisation framework. We report results on two real-world case studies based on the Italian rivers ‘Paglia’ and ‘Aniene’. A comparative analysis between the employed optimisation algorithms is performed and discussed both empirically and statistically. From the hydrodynamic point of view, the experimental results are satisfactory and produced within significantly less computational time in comparison to classic methods. This shows the suitability of the proposed approach for optimal estimation of the roughness coefficient and, in turn, for designing optimised hydrological models.

MinStab: Stable Network Evolution Rule Mining for System Changeability Analysis

Growing number of evolving systems creates demand for system evolution analytics with modern computational intelligence algorithms and tools. In this paper, we introduce new measures of stability and changeability for system evolution analysis over time. We proposed a Stable Network Evolution Rule Mining and a Changeability Metric for an evolving system. For this, we use two different characteristics of Network Evolution Rules (NERs). First, given a network of a system state S <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> , we call an NER interesting in S <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> if its support and confidence exceed given thresholds (minimum support and minimum confidence). Second, given a set of networks for a set of states (SS), we define the stability of an NER to be the percentage of states in SS in which the rule is interesting. We call an NER stable in SS if its stability exceeds a given threshold named as minimum stability (minStab). Based on this, we developed an intelligent tool, which is used for experiments on evolving systems. We applied our approach to a number of real-world systems including: software system, natural language system, retail market system, and IMDb system. It results Stable NERs and Changeability Metric value for each evolving system.

Computational Intelligence for Studying Sustainability Challenges: Tools and Methods for Dealing With Deep Uncertainty and Complexity.

The study of sustainability challenges requires the consideration of multiple coupled systems that are often complex and deeply uncertain. As a result, traditional analytical methods offer limited insights with respect to how to best address such challenges. By analyzing the case of global climate change mitigation, this paper shows that the combination of high-performance computing, mathematical modeling, and computational intelligence tools, such as optimization and clustering algorithms, leads to richer analytical insights. The paper concludes by proposing an analytical hierarchy of computational tools that can be applied to other sustainability challenges.

Classification of soil aggregates: A novel approach based on deep learning

Having a powerful tool and the knowledge to classify soil aggregates, one of the most important factors in evaluating the performance of tillage implements, will result in quick and accurate classification of soil aggregates. By considering them as virtual sieve, a large part of the energy and workforce used in this sector can be reduced. In this regard, computational intelligence tools can play an important and optimal role in the evaluation of tillage quality and its real-time employment. The objective of the present study was to introduce a method known as deep learning to classify aggregates of any size in specific classes. Accordingly, stereo-pair images were used to provide multiple images simultaneously and the proper nutrition of the network. Since stereo-pair images are not dependent on changes in ambient light, imaging was done under conditions of the field with no lighting system. To train the deep models, the images of each lens were separated from each other and entered into the network. Without the extraction of the required features that is done manually in most image and vision-processing algorithms, the presented deep model began to learn to observe and could extract the required features from the lowest level to highly complex features automatically. Among the variety of neural network algorithms in deep learning, a convolutional neural network (CNN) was used in this study for its unique properties in working on images. To train the CNN, VggNet16, ResNet50, and Inception-v4 architects were used. Classification accuracy of these networks was above 95 %, but the highest accuracy achieved with ResNet50 (98.72 %). This accuracy, which was significantly different from previous studies, indicated the good performance of the deep learning method in the classification of aggregates. The results of the current study showed that the estimation of mean weight diameter (MWD) of aggregates without limitations in size and with great precision is completely practical and achievable.

Review on methodological and normative advances in assessment and estimation of wind energy

In this study, we present a review of articles that address the state of the art in wind energy from different perspectives, specifically focusing on the criteria used for wind energy assessment and wind turbine standards, along with an overview of the technologies necessary to make reliable Wind Power-Grid penetration more efficient. Wind power dynamics are also considered from the perspective of their intermittency and the nature of wind speed variability in order to establish appropriate sampling times for measurements and monitoring. The literature discussed is representative of the technological and methodological advances dedicated to the development, adaptation and application of statistical, computational, numerical and artificial intelligence tools for an assessment of wind energy and wind power forecasting. These applications and methodologies commonly use data registers measured in very short, short, medium and long-term measurement campaigns. Finally, literature on wind power social, environmental and economic policies and trends in costs-capacity-addition and their impact are reviewed from a global perspective. In light of today’s concerns with global warming, it is essential that wind energy interact steadily on the grid with experienced operators and high automatic-control technology worldwide.

Construction duration predictive model based on factorial analysis and fuzzy logic

Abstract Setting the building construction duration for vertical residential works is made still in the study phase of economic and financial feasibility of the project and, in most cases, in an empirical way, increasing the uncertainties and the risks to fulfill the set deadline. However, there are computational intelligence tools that can contribute to reduce the degree of uncertainty. This study aimed to investigate the use of a hybrid system to estimate the deadline for vertical residential building works from design and production characteristics using factorial analysis and Fuzzy Systems. To this end, we used information of a database from the SEURB and in some buildings construction companies in Belém, a city located in the State of Pará, northern of Brazil. For the training and construction of the Fuzzy Forecast Model, data from 71 projects were used and 16 others residential buildings were used for its validation. The results showed a significant level of assertiveness, with 75% accuracy considering a range, whose upper and lower limits were calculated from MAPE and MASE. The model presented a prediction performance superior to other models already consecrated in the literature.

Computational Intelligence Tools to Study Molecular Interactions for Drug Design

Traditional drug designing and discovery is a long and slow process that takes nearly 15 years to release a new drug into the market. Computational Aided Drug Designing process is a promising approach that stimulates the traditional drug developing process by using different computational intelligence tools, those speeding up the drug designing and discovery process. Molecular interactions studies play a crucial role in CADD shows the affinity and bonding of drug and target are significant in drug designing. The drug and target interactions predicted by computational intelligence tools called Molecular Docking softwares. Docking tools find the best orientation and conformation of a ligand on the target molecule with a lower binding free energy to form a stable complex. Those tools also predict the interaction between protein-protein, protein-DNA, and drug-DNA respectively. Virtual screening is a docking process that screen and identifies the drug-like compounds from a large compound database like ZINC and PubChem by giving score through a scoring function build in them. This paper provides a comprehensive overview of molecular interaction tools their significance in drug development. Computational Aided Drug Designing is a broad, growing approach to fasten and minimizing the traditional drug designing process.

A Panoramic Survey on Grasping Research Trends and Topics

Grasping and object manipulation is a key element of intelligent behavior. Many innovative cyberphysical systems involve some kind of object grasp and manipulation, to the extent that grasping has been recognized as a critical technology for the next generation industrial systems. In this survey, we aim to draw a broad landscape of applications and current research trends and topics relating to grasping techniques and tools. Applications range from biomedical and surgical to industrial warehouse pick and place tasks, covering a wide range of spatial scales, from micro to macro scales. The resources involved and research lines under development include the latest computational intelligence tools as well as the research on new materials and devices for sensing and actuation.

Computational intelligence for prediction of biological effects of drugs absorption in lungs

Lungs are recently extensively examined as a route for delivering drugs (active pharmaceutical ingredients, API) into the bloodstream mainly due to the possibility of noninvasive administration of macromolecules, such as proteins and peptides. Absorption mechanisms of chemical compounds in lungs are still not fully understood, what makes pulmonary formulation composition development challenging. The manuscript presents development of an empirical model capable of predicting the excipients’ influence on the absorption of the drug in lungs. Due to complexity of the problem and not fully understood mechanisms of absorption, computational intelligence tools were applied. As a result, a mathematical formula was established and analyzed. The normalized root-mean-squared error (NRMSE) and R2 of the model were 4.57%, and 0.83, respectively. The presented approach is beneficial both practically by developing \textit{in sillico} predictive model and theoretically by gaining knowledge about the influence of API and excipient structure on absorption in lungs.

Combination of G72 Genetic Variation and G72 Protein Level to Detect Schizophrenia: Machine Learning Approaches.

The D-amino acid oxidase activator (DAOA, also known as G72) gene is a strong schizophrenia susceptibility gene. Higher G72 protein levels have been implicated in patients with schizophrenia. The current study aimed to differentiate patients with schizophrenia from healthy individuals using G72 single nucleotide polymorphisms (SNPs) and G72 protein levels by leveraging computational artificial intelligence and machine learning tools. A total of 149 subjects with 89 patients with schizophrenia and 60 healthy controls were recruited. Two G72 genotypes (including rs1421292 and rs2391191) and G72 protein levels were measured with the peripheral blood. We utilized three machine learning algorithms (including logistic regression, naive Bayes, and C4.5 decision tree) to build the optimal predictive model for distinguishing schizophrenia patients from healthy controls. The naive Bayes model using two factors, including G72 rs1421292 and G72 protein, appeared to be the best model for disease susceptibility (sensitivity = 0.7969, specificity = 0.9372, area under the receiver operating characteristic curve (AUC) = 0.9356). However, a model integrating G72 rs1421292 only slightly increased the discriminative power than a model with G72 protein alone (sensitivity = 0.7941, specificity = 0.9503, AUC = 0.9324). Among the three models with G72 protein alone, the naive Bayes with G72 protein alone had the best specificity (0.9503), while logistic regression with G72 protein alone was the most sensitive (0.8765). The findings remained similar after adjusting for age and gender. This study suggests that G72 protein alone, without incorporating the two G72 SNPs, may have been suitable enough to identify schizophrenia patients. We also recommend applying both naive Bayes and logistic regression models for the best specificity and sensitivity, respectively. Larger-scale studies are warranted to confirm the findings.

Carrier optimization of pulmonary powder systems with using computational intelligence tools

Efficient delivery of drug particles to the respiratory tract determines therapeutic efficiency of pulmonary drugs. Only particles with an aerodynamic diameter (dae) below five micrometers (μm) deposit in deep lungs. However fine particles, because of their cohesive nature, frequently cause difficulties related to the manufacturing process and stability of the product. This study is focused on the optimization of carriers for pulmonary drug delivery systems with the use of empirical models. Advanced computational intelligence tools were applied to produce a mathematical formula able to predict fine particle fraction (FPF) for a particular formulation. FPF is a mass percentage of drug particles with an aerodynamic diameter below 5 μm. The best model was characterized by normalized root mean squared error (NRMSE) below 8% and R2 = 0.85. The goal of the in silico optimization was to find the possible directions of carrier modification in order to maximize FPF. Obtained results were applied to the laboratory experiments and resulted in the two new formulations with bovine serum albumin (BSA) as a model drug. Experimental results confirmed the model predictions, and the formulation composed of the carrier with higher bulk density and surface skewness resulted in greater FPF value. The presented work is an example of computational intelligence tools implementation and particles surface assessment based on SEM images in design of the decision support systems for the development of pulmonary powder formulations.